Qatar Essay Example | Topics and Well Written Essays - 1500 words - 1

Qatar - Essay Example Qatar is a little peninsula that is on the western shore of the Arabian Gulf and it covers approximately 4,247 square miles (6,286 square kilometers). Qatar is just 160 kilometers north into the Persian Gulf from Saudi Arabia. It is located between latitudes 24Â ° and 27Â ° N, and longitudes 50Â ° and 52Â ° E. Qatar mostly consist of low and barren plain that is covered with sand. To the southeast lies the Khor al Adaid (‘Inland Sea’), which is a region of rolling sand dunes surrounding Persian Gulf’s inlet? The landmass creates a rectangle that is described by the local folklore as resembling right hand’s palm that is extended in a prayer. The neighboring nations include Iran to the northeast. Bahrain to the northwest, Saudi Arabia and the United Arab Emirates to the south. Both Qatar and Bahrain claim the Hawar Islands located west of Qatar and it is uninhabited. Just recently, only few semi-permanent seasonal encampments have been found in the interi or desert. Resources of water that are near the coast together with opportunities for pearl diving, fishing, and seagoing trade have facilitated larger, and additional permanent settlements. The patterns of these settlements have contributed to the social differences between Hadar and Bedouin. Qatar’s climate can be described as subtropical dry, hot desert climate that has low annual rainfall. During the summer the temperatures are extremely high and there is a big difference between maximum and minimum temperatures, more so in the inland areas. The Persian Gulf slightly influences the coastal areas and have lower maximum, however, it has higher minimum temperatures and the moisture percentage in the air are higher. Summer ‘June – September’ is extremely hot with low rainfall. Daily maximum temperatures are able to easily reach 40Â °C or more. Winter is cooler with irregular rainfall.

Identifying Clusters in High Dimensional Data

Identifying Clusters in High Dimensional Data â€Å"Ask those who remember, are mindful if you do not know).† (Holy Quran, 6:43) Removal Of Redundant Dimensions To Find Clusters In N-Dimensional Data Using Subspace Clustering Abstract The data mining has emerged as a powerful tool to extract knowledge from huge databases. Researchers have introduced several machine learning algorithms to explore the databases to discover information, hidden patterns, and rules from the data which were not known at the data recording time. Due to the remarkable developments in the storage capacities, processing and powerful algorithmic tools, practitioners are developing new and improved algorithms and techniques in several areas of data mining to discover the rules and relationship among the attributes in simple and complex higher dimensional databases. Furthermore data mining has its implementation in large variety of areas ranging from banking to marketing, engineering to bioinformatics and from investment to risk analysis and fraud detection. Practitioners are analyzing and implementing the techniques of artificial neural networks for classification and regression problems because of accuracy, efficiency. The aim of his short r esearch project is to develop a way of identifying the clusters in high dimensional data as well as redundant dimensions which can create a noise in identifying the clusters in high dimensional data. Techniques used in this project utilizes the strength of the projections of the data points along the dimensions to identify the intensity of projection along each dimension in order to find cluster and redundant dimension in high dimensional data. 1 Introduction In numerous scientific settings, engineering processes, and business applications ranging from experimental sensor data and process control data to telecommunication traffic observation and financial transaction monitoring, huge amounts of high-dimensional measurement data are produced and stored. Whereas sensor equipments as well as big storage devices are getting cheaper day by day, data analysis tools and techniques wrap behind. Clustering methods are common solutions to unsupervised learning problems where neither any expert knowledge nor some helpful annotation for the data is available. In general, clustering groups the data objects in a way that similar objects get together in clusters whereas objects from different clusters are of high dissimilarity. However it is observed that clustering disclose almost no structure even it is known there must be groups of similar objects. In many cases, the reason is that the cluster structure is stimulated by some subsets of the spaces dim ensions only, and the many additional dimensions contribute nothing other than making noise in the data that hinder the discovery of the clusters within that data. As a solution to this problem, clustering algorithms are applied to the relevant subspaces only. Immediately, the new question is how to determine the relevant subspaces among the dimensions of the full space. Being faced with the power set of the set of dimensions a brute force trial of all subsets is infeasible due to their exponential number with respect to the original dimensionality. In high dimensional data, as dimensions are increasing, the visualization and representation of the data becomes more difficult and sometimes increase in the dimensions can create a bottleneck. More dimensions mean more visualization or representation problems in the data. As the dimensions are increased, the data within those dimensions seems dispersing towards the corners / dimensions. Subspace clustering solves this problem by identifying both problems in parallel. It solves the problem of relevant subspaces which can be marked as redundant in high dimensional data. It also solves the problem of finding the cluster structures within that dataset which become apparent in these subspaces. Subspace clustering is an extension to the traditional clustering which automatically finds the clusters present in the subspace of high dimensional data space that allows better clustering the data points than the original space and it works even when the curse of dimensionality occurs. The most o f the clustering algorithms have been designed to discover clusters in full dimensional space so they are not effective in identifying the clusters that exists within subspace of the original data space. The most of the clustering algorithms produces clustering results based on the order in which the input records were processed [2]. Subspace clustering can identify the different cluster within subspaces which exists in the huge amount of sales data and through it we can find which of the different attributes are related. This can be useful in promoting the sales and in planning the inventory levels of different products. It can be used for finding the subspace clusters in spatial databases and some useful decisions can be taken based on the subspace clusters identified [2]. The technique used here for indentifying the redundant dimensions which are creating noise in the data in order to identifying the clusters consist of drawing or plotting the data points in all dimensions. At second step the projection of all data points along each dimension are plotted. At the third step the unions of projections along each dimension are plotted using all possible combinations among all no. of dimensions and finally the union of all projection along all dimensions and analyzed, it will show the contribution of each dimension in indentifying the cluster which will be represented by the weight of projection. If any of the given dimension is contributing very less in order to building the weight of projection, that dimension can be considered as redundant, which means this dimension is not so important to identify the clusters in given data. The details of this strategy will be covered in later chapters. 2 Data Mining 2.1 What is Data Mining? Data mining is the process of analyzing data from different perspective and summarizing it for getting useful information. The information can be used for many useful purposes like increasing revenue, cuts costs etc. The data mining process also finds the hidden knowledge and relationship within the data which was not known while data recording. Describing the data is the first step in data mining, followed by summarizing its attributes (like standard deviation mean etc). After that data is reviewed using visual tools like charts and graphs and then meaningful relations are determined. In the data mining process, the steps of collecting, exploring and selecting the right data are critically important. User can analyze data from different dimensions categorize and summarize it. Data mining finds the correlation or patterns amongst the fields in large databases. Data mining has a great potential to help companies to focus on their important information in their data warehouse. It can predict the future trends and behaviors and allows the business to make more proactive and knowledge driven decisions. It can answer the business questions that were traditionally much time consuming to resolve. It scours databases for hidden patterns for finding predictive information that experts may miss it might lies beyond their expectations. Data mining is normally used to transform the data into information or knowledge. It is commonly used in wide range of profiting practices such as marketing, fraud detection and scientific discovery. Many companies already collect and refine their data. Data mining techniques can be implemented on existing platforms for enhance the value of information resources. Data mining tools can analyze massive databases to deliver answers to the questions. Some other terms contains similar meaning from data mining such as â€Å"Knowledge mining† or â€Å"Knowledge Extraction† or â€Å"Pattern Analysis†. Data mining can also be treated as a Knowledge Discovery from Data (KDD). Some people simply mean the data mining as an essential step in Knowledge discovery from a large data. The process of knowledge discovery from data contains following steps. * Data cleaning (removing the noise and inconsistent data) * Data Integration (combining multiple data sources) * Data selection (retrieving the data relevant to analysis task from database) * Data Transformation (transforming the data into appropriate forms for mining by performing summary or aggregation operations) * Data mining (applying the intelligent methods in order to extract data patterns) * Pattern evaluation (identifying the truly interesting patterns representing knowledge based on some measures) * Knowledge representation (representing knowledge techniques that are used to present the mined knowledge to the user) 2.2 Data Data can be any type of facts, or text, or image or number which can be processed by computer. Todays organizations are accumulating large and growing amounts of data in different formats and in different databases. It can include operational or transactional data which includes costs, sales, inventory, payroll and accounting. It can also include nonoperational data such as industry sales and forecast data. It can also include the meta data which is, data about the data itself, such as logical database design and data dictionary definitions. 2.3 Information The information can be retrieved from the data via patterns, associations or relationship may exist in the data. For example the retail point of sale transaction data can be analyzed to yield information about the products which are being sold and when. 2.4 Knowledge Knowledge can be retrieved from information via historical patterns and the future trends. For example the analysis on retail supermarket sales data in promotional efforts point of view can provide the knowledge buying behavior of customer. Hence items which are at most risk for promotional efforts can be determined by manufacturer easily. 2.5 Data warehouse The advancement in data capture, processing power, data transmission and storage technologies are enabling the industry to integrate their various databases into data warehouse. The process of centralizing and retrieving the data is called data warehousing. Data warehousing is new term but concept is a bit old. Data warehouse is storage of massive amount of data in electronic form. Data warehousing is used to represent an ideal way of maintaining a central repository for all organizational data. Purpose of data warehouse is to maximize the user access and analysis. The data from different data sources are extracted, transformed and then loaded into data warehouse. Users / clients can generate different types of reports and can do business analysis by accessing the data warehouse. Data mining is primarily used today by companies with a strong consumer focus retail, financial, communication, and marketing organizations. It allows these organizations to evaluate associations between certain internal external factors. The product positioning, price or staff skills can be example of internal factors. The external factor examples can be economic indicators, customer demographics and competition. It also allows them to calculate the impact on sales, corporate profits and customer satisfaction. Furthermore it allows them to summarize the information to look detailed transactional data. Given databases of sufficient size and quality, data mining technology can generate new business opportunities by its capabilities. Data mining usually automates the procedure of searching predictive information in huge databases. Questions that traditionally required extensive hands-on analysis can now be answered directly from the data very quickly. The targeted marketing can be an example of predictive problem. Data mining utilizes data on previous promotional mailings in order to recognize the targets most probably to increase return on investment as maximum as possible in future mailings. Tools used in data mining traverses through huge databases and discover previously unseen patterns in single step. Analysis on retail sales data to recognize apparently unrelated products which are usually purchased together can be an example of it. The more pattern discovery problems can include identifying fraudulent credit card transactions and identifying irregular data that could symbolize data entry input errors. When data mining tools are used on parallel processing systems of high performance, they are able to analy ze huge databases in very less amount of time. Faster or quick processing means that users can automatically experience with more details to recognize the complex data. High speed and quick response makes it actually possible for users to examine huge amounts of data. Huge databases, in turn, give improved and better predictions. 2.6 Descriptive and Predictive Data Mining Descriptive data mining aims to find patterns in the data that provide some information about what the data contains. It describes patterns in existing data, and is generally used to create meaningful subgroups such as demographic clusters. For example descriptions are in the form of Summaries and visualization, Clustering and Link Analysis. Predictive Data Mining is used to forecast explicit values, based on patterns determined from known results. For example, in the database having records of clients who have already answered to a specific offer, a model can be made that predicts which prospects are most probable to answer to the same offer. It is usually applied to recognize data mining projects with the goal to identify a statistical or neural network model or set of models that can be used to predict some response of interest. For example, a credit card company may want to engage in predictive data mining, to derive a (trained) model or set of models that can quickly identify tr ansactions which have a high probability of being fraudulent. Other types of data mining projects may be more exploratory in nature (e.g. to determine the cluster or divisions of customers), in which case drill-down descriptive and tentative methods need to be applied. Predictive data mining is goad oriented. It can be decomposed into following major tasks. * Data Preparation * Data Reduction * Data Modeling and Prediction * Case and Solution Analysis 2.7 Text Mining The Text Mining is sometimes also called Text Data Mining which is more or less equal to Text Analytics. Text mining is the process of extracting/deriving high quality information from the text. High quality information is typically derived from deriving the patterns and trends through means such as statistical pattern learning. It usually involves the process of structuring the input text (usually parsing, along with the addition of some derived linguistic features and the removal of others, and subsequent insertion into a database), deriving patterns within the structured data, and finally evaluation and interpretation of the output. The High Quality in text mining usually refers to some combination of relevance, novelty, and interestingness. The text categorization, concept/entity extraction, text clustering, sentiment analysis, production of rough taxonomies, entity relation modeling, document summarization can be included as text mining tasks. Text Mining is also known as the discovery by computer of new, previously unknown information, by automatically extracting information from different written resources. Linking together of the extracted information is the key element to create new facts or new hypotheses to be examined further by more conventional ways of experimentation. In text mining, the goal is to discover unknown information, something that no one yet knows and so could not have yet written down. The difference between ordinary data mining and text mining is that, in text mining the patterns are retrieved from natural language text instead of from structured databases of facts. Databases are designed and developed for programs to execute automatically; text is written for people to read. Most of the researchers think that it will need a full fledge simulation of how the brain works before that programs that read the way people do could be written. 2.8 Web Mining Web Mining is the technique which is used to extract and discover the information from web documents and services automatically. The interest of various research communities, tremendous growth of information resources on Web and recent interest in e-commerce has made this area of research very huge. Web mining can be usually decomposed into subtasks. * Resource finding: fetching intended web documents. * Information selection and pre-processing: selecting and preprocessing specific information from fetched web resources automatically. * Generalization: automatically discovers general patterns at individual and across multiple website * Analysis: validation and explanation of mined patterns. Web Mining can be mainly categorized into three areas of interest based on which part of Web needs to be mined: Web Content Mining, Web Structure Mining and Web Usage Mining. Web Contents Mining describes the discovery of useful information from the web contents, data and documents [10]. In past the internet consisted of only different types of services and data resources. But today most of the data is available over the internet; even digital libraries are also available on Web. The web contents consist of several types of data including text, image, audio, video, metadata as well as hyperlinks. Most of the companies are trying to transform their business and services into electronic form and putting it on Web. As a result, the databases of the companies which were previously residing on legacy systems are now accessible over the Web. Thus the employees, business partners and even end clients are able to access the companys databases over the Web. Users are accessing the application s over the web via their web interfaces due to which the most of the companies are trying to transform their business over the web, because internet is capable of making connection to any other computer anywhere in the world [11]. Some of the web contents are hidden and hence cannot be indexed. The dynamically generated data from the results of queries residing in the database or private data can fall in this area. Unstructured data such as free text or semi structured data such as HTML and fully structured data such as data in the tables or database generated web pages can be considered in this category. However unstructured text is mostly found in the web contents. The work on Web content mining is mostly done from 2 point of views, one is IR and other is DB point of view. â€Å"From IR view, web content mining assists and improves the information finding or filtering to the user. From DB view web content mining models the data on the web and integrates them so that the more soph isticated queries other than keywords could be performed. [10]. In Web Structure Mining, we are more concerned with the structure of hyperlinks within the web itself which can be called as inter document structure [10]. It is closely related to the web usage mining [14]. Pattern detection and graphs mining are essentially related to the web structure mining. Link analysis technique can be used to determine the patterns in the graph. The search engines like Google usually uses the web structure mining. For example, the links are mined and one can then determine the web pages that point to a particular web page. When a string is searched, a webpage having most number of links pointed to it may become first in the list. Thats why web pages are listed based on rank which is calculated by the rank of web pages pointed to it [14]. Based on web structural data, web structure mining can be divided into two categories. The first kind of web structure mining interacts with extracting patterns from the hyperlinks in the web. A hyperlink is a structural comp onent that links or connects the web page to a different web page or different location. The other kind of the web structure mining interacts with the document structure, which is using the tree-like structure to analyze and describe the HTML or XML tags within the web pages. With continuous growth of e-commerce, web services and web applications, the volume of clickstream and user data collected by web based organizations in their daily operations has increased. The organizations can analyze such data to determine the life time value of clients, design cross marketing strategies etc. [13]. The Web usage mining interacts with data generated by users clickstream. â€Å"The web usage data includes web server access logs, proxy server logs, browser logs, user profile, registration data, user sessions, transactions, cookies, user queries, bookmark data, mouse clicks and scrolls and any other data as a result of interaction† [10]. So the web usage mining is the most important task of the web mining [12]. Weblog databases can provide rich information about the web dynamics. In web usage mining, web log records are mined to discover the user access patterns through which the potential customers can be identified, quality of internet services can be enhanc ed and web server performance can be improved. Many techniques can be developed for implementation of web usage mining but it is important to know that success of such applications depends upon what and how much valid and reliable knowledge can be discovered the log data. Most often, the web logs are cleaned, condensed and transformed before extraction of any useful and significant information from weblog. Web mining can be performed on web log records to find associations patterns, sequential patterns and trend of web accessing. The overall Web usage mining process can be divided into three inter-dependent stages: data collection and pre-processing, pattern discovery, and pattern analysis [13]. In the data collection preprocessing stage, the raw data is collected, cleaned and transformed into a set of user transactions which represents the activities of each user during visits to the web site. In the pattern discovery stage, statistical, database, and machine learning operations a re performed to retrieve hidden patterns representing the typical behavior of users, as well as summary of statistics on Web resources, sessions, and users. 3 Classification 3.1 What is Classification? As the quantity and the variety increases in the available data, it needs some robust, efficient and versatile data categorization technique for exploration [16]. Classification is a method of categorizing class labels to patterns. It is actually a data mining methodology used to predict group membership for data instances. For example, one may want to use classification to guess whether the weather on a specific day would be â€Å"sunny†, â€Å"cloudy† or â€Å"rainy†. The data mining techniques which are used to differentiate similar kind of data objects / points from other are called clustering. It actually uses attribute values found in the data of one class to distinguish it from other types or classes. The data classification majorly concerns with the treatment of the large datasets. In classification we build a model by analyzing the existing data, describing the characteristics of various classes of data. We can use this model to predict the class/type of new data. Classification is a supervised machine learning procedure in which individual items are placed in a group based on quantitative information on one or more characteristics in the items. Decision Trees and Bayesian Networks are the examples of classification methods. One type of classification is Clustering. This is process of finding the similar data objects / points within the given dataset. This similarity can be in the meaning of distance measures or on any other parameter, depending upon the need and the given data. Classification is an ancient term as well as a modern one since classification of animals, plants and other physical objects is still valid today. Classification is a way of thinking about things rather than a study of things itself so it draws its theory and application from complete range of human experiences and thoughts [18]. From a bigger picture, classification can include medical patients based on disease, a set of images containing red rose from an image database, a set of documents describing â€Å"classification† from a document/text database, equipment malfunction based on cause and loan applicants based on their likelihood of payment etc. For example in later case, the problem is to predict a new applicants loans eligibility given old data about customers. There are many techniques which are used for data categorization / classification. The most common are Decision tree classifier and Bayesian classifiers. 3.2 Types of Classification There are two types of classification. One is supervised classification and other is unsupervised classification. Supervised learning is a machine learning technique for discovering a function from training data. The training data contains the pairs of input objects, and their desired outputs. The output of the function can be a continuous value which can be called regression, or can predict a class label of the input object which can be called as classification. The task of the supervised learner is to predict the value of the function for any valid input object after having seen a number of training examples (i.e. pairs of input and target output). To achieve this goal, the learner needs to simplify from the presented data to hidden situations in a meaningful way. The unsupervised learning is a class of problems in machine learning in which it is needed to seek to determine how the data are organized. It is distinguished from supervised learning in that the learner is given only unknown examples. Unsupervised learning is nearly related to the problem of density estimation in statistics. However unsupervised learning also covers many other techniques that are used to summarize and explain key features of the data. One form of unsupervised learning is clustering which will be covered in next chapter. Blind source partition based on Independent Component Analysis is another example. Neural network models, adaptive resonance theory and the self organizing maps are most commonly used unsupervised learning algorithms. There are many techniques for the implementation of supervised classification. We will be discussing two of them which are most commonly used which are Decision Trees classifiers and Naà ¯ve Bayesian Classifiers. 3.2.1 Decision Trees Classifier There are many alternatives to represent classifiers. The decision tree is probably the most widely used approach for this purpose. It is one of the most widely used supervised learning methods used for data exploration. It is easy to use and can be represented in if-then-else statements/rules and can work well in noisy data as well [16]. Tree like graph or decisions models and their possible consequences including resource costs, chance event, outcomes, and utilities are used in decision trees. Decision trees are most commonly used in specifically in decision analysis, operations research, to help in identifying a strategy most probably to reach a target. In machine learning and data mining, a decision trees are used as predictive model; means a planning from observations calculations about an item to the conclusions about its target value. More descriptive names for such tree models are classification tree or regression tree. In these tree structures, leaves are representing class ifications and branches are representing conjunctions of features those lead to classifications. The machine learning technique for inducing a decision tree from data is called decision tree learning, or decision trees. Decision trees are simple but powerful form of multiple variable analyses [15]. Classification is done by tree like structures that have different test criteria for a variable at each of the nodes. New leaves are generated based on the results of the tests at the nodes. Decision Tree is a supervised learning system in which classification rules are constructed from the decision tree. Decision trees are produced by algorithms which identify various ways splitting data set into branch like segment. Decision tree try to find out a strong relationship between input and target values within the dataset [15]. In tasks classification, decision trees normally visualize that what steps should be taken to reach on classification. Every decision tree starts with a parent node called root node which is considered to be the parent of every other node. Each node in the tree calculates an attribute in the data and decides which path it should follow. Typically the decision test is comparison of a value against some constant. Classification with the help of decision tree is done by traversing from the root node up to a leaf node. Decision trees are able to represent and classify the diverse types of data. The simplest form of data is numerical data which is most familiar too. Organizing nominal data is also required many times in many situations. Nominal quantities are normally represented via discrete set of symbols. For example weather condition can be described in either nominal fashion or numeric. Quantification can be done about temperature by saying that it is eleven degrees Celsius or fifty two degrees Fahrenheit. The cool, mild, cold, warm or hot terminologies can also be sued. The former is a type of numeric data while and the latter is an example of nominal data. More precisely, the example of cool, mild, cold, warm and hot is a special type of nominal data, expressed as ordinal data. Ordinal data usually has an implicit assumption of ordered relationships among the values. In the weather example, purely nominal description like rainy, overcast and sunny can also be added. These values have no relationships or distance measures among each other. Decision Trees are those types of trees where each node is a question, each branch is an answer to a question, and each leaf is a result. Here is an example of Decision tree. Roughly, the idea is based upon the number of stock items; we have to make different decisions. If we dont have much, you buy at any cost. If you have a lot of items then you only buy if it is inexpensive. Now if stock items are less than 10 then buy all if unit price is less than 10 otherwise buy only 10 items. Now if we have 10 to 40 items in the stock then check unit price. If unit price is less than 5 £ then buy only 5 items otherwise no need to buy anything expensive since stock is good already. Now if we have more than 40 items in the stock, then buy 5 if and only if price is less than 2 £ otherwise no need to buy too expensive items. So in this way decision trees help us to make a decision at each level. Here is another example of decision tree, representing the risk factor associated with the rash driving. The root node at the top of the tree structure is showing the feature that is split first for highest discrimination. The internal nodes are showing decision rules on one or more attributes while leaf nodes are class labels. A person having age less than 20 has very high risk while a person having age greater than 30 has a very low risk. A middle category; a person having age greater than 20 but less than 30 depend upon another attribute which is car type. If car type is of sports then there is again high risk involved while if family car is used then there is low risk involved. In the field of sciences engineering and in the applied areas including business intelligence and data mining, many useful features are being introduced as the result of evolution of decision trees. * With the help of transformation in decision trees, the volume of data can be reduced into more compact form that preserves the major characteristic Identifying Clusters in High Dimensional Data Identifying Clusters in High Dimensional Data â€Å"Ask those who remember, are mindful if you do not know).† (Holy Quran, 6:43) Removal Of Redundant Dimensions To Find Clusters In N-Dimensional Data Using Subspace Clustering Abstract The data mining has emerged as a powerful tool to extract knowledge from huge databases. Researchers have introduced several machine learning algorithms to explore the databases to discover information, hidden patterns, and rules from the data which were not known at the data recording time. Due to the remarkable developments in the storage capacities, processing and powerful algorithmic tools, practitioners are developing new and improved algorithms and techniques in several areas of data mining to discover the rules and relationship among the attributes in simple and complex higher dimensional databases. Furthermore data mining has its implementation in large variety of areas ranging from banking to marketing, engineering to bioinformatics and from investment to risk analysis and fraud detection. Practitioners are analyzing and implementing the techniques of artificial neural networks for classification and regression problems because of accuracy, efficiency. The aim of his short r esearch project is to develop a way of identifying the clusters in high dimensional data as well as redundant dimensions which can create a noise in identifying the clusters in high dimensional data. Techniques used in this project utilizes the strength of the projections of the data points along the dimensions to identify the intensity of projection along each dimension in order to find cluster and redundant dimension in high dimensional data. 1 Introduction In numerous scientific settings, engineering processes, and business applications ranging from experimental sensor data and process control data to telecommunication traffic observation and financial transaction monitoring, huge amounts of high-dimensional measurement data are produced and stored. Whereas sensor equipments as well as big storage devices are getting cheaper day by day, data analysis tools and techniques wrap behind. Clustering methods are common solutions to unsupervised learning problems where neither any expert knowledge nor some helpful annotation for the data is available. In general, clustering groups the data objects in a way that similar objects get together in clusters whereas objects from different clusters are of high dissimilarity. However it is observed that clustering disclose almost no structure even it is known there must be groups of similar objects. In many cases, the reason is that the cluster structure is stimulated by some subsets of the spaces dim ensions only, and the many additional dimensions contribute nothing other than making noise in the data that hinder the discovery of the clusters within that data. As a solution to this problem, clustering algorithms are applied to the relevant subspaces only. Immediately, the new question is how to determine the relevant subspaces among the dimensions of the full space. Being faced with the power set of the set of dimensions a brute force trial of all subsets is infeasible due to their exponential number with respect to the original dimensionality. In high dimensional data, as dimensions are increasing, the visualization and representation of the data becomes more difficult and sometimes increase in the dimensions can create a bottleneck. More dimensions mean more visualization or representation problems in the data. As the dimensions are increased, the data within those dimensions seems dispersing towards the corners / dimensions. Subspace clustering solves this problem by identifying both problems in parallel. It solves the problem of relevant subspaces which can be marked as redundant in high dimensional data. It also solves the problem of finding the cluster structures within that dataset which become apparent in these subspaces. Subspace clustering is an extension to the traditional clustering which automatically finds the clusters present in the subspace of high dimensional data space that allows better clustering the data points than the original space and it works even when the curse of dimensionality occurs. The most o f the clustering algorithms have been designed to discover clusters in full dimensional space so they are not effective in identifying the clusters that exists within subspace of the original data space. The most of the clustering algorithms produces clustering results based on the order in which the input records were processed [2]. Subspace clustering can identify the different cluster within subspaces which exists in the huge amount of sales data and through it we can find which of the different attributes are related. This can be useful in promoting the sales and in planning the inventory levels of different products. It can be used for finding the subspace clusters in spatial databases and some useful decisions can be taken based on the subspace clusters identified [2]. The technique used here for indentifying the redundant dimensions which are creating noise in the data in order to identifying the clusters consist of drawing or plotting the data points in all dimensions. At second step the projection of all data points along each dimension are plotted. At the third step the unions of projections along each dimension are plotted using all possible combinations among all no. of dimensions and finally the union of all projection along all dimensions and analyzed, it will show the contribution of each dimension in indentifying the cluster which will be represented by the weight of projection. If any of the given dimension is contributing very less in order to building the weight of projection, that dimension can be considered as redundant, which means this dimension is not so important to identify the clusters in given data. The details of this strategy will be covered in later chapters. 2 Data Mining 2.1 What is Data Mining? Data mining is the process of analyzing data from different perspective and summarizing it for getting useful information. The information can be used for many useful purposes like increasing revenue, cuts costs etc. The data mining process also finds the hidden knowledge and relationship within the data which was not known while data recording. Describing the data is the first step in data mining, followed by summarizing its attributes (like standard deviation mean etc). After that data is reviewed using visual tools like charts and graphs and then meaningful relations are determined. In the data mining process, the steps of collecting, exploring and selecting the right data are critically important. User can analyze data from different dimensions categorize and summarize it. Data mining finds the correlation or patterns amongst the fields in large databases. Data mining has a great potential to help companies to focus on their important information in their data warehouse. It can predict the future trends and behaviors and allows the business to make more proactive and knowledge driven decisions. It can answer the business questions that were traditionally much time consuming to resolve. It scours databases for hidden patterns for finding predictive information that experts may miss it might lies beyond their expectations. Data mining is normally used to transform the data into information or knowledge. It is commonly used in wide range of profiting practices such as marketing, fraud detection and scientific discovery. Many companies already collect and refine their data. Data mining techniques can be implemented on existing platforms for enhance the value of information resources. Data mining tools can analyze massive databases to deliver answers to the questions. Some other terms contains similar meaning from data mining such as â€Å"Knowledge mining† or â€Å"Knowledge Extraction† or â€Å"Pattern Analysis†. Data mining can also be treated as a Knowledge Discovery from Data (KDD). Some people simply mean the data mining as an essential step in Knowledge discovery from a large data. The process of knowledge discovery from data contains following steps. * Data cleaning (removing the noise and inconsistent data) * Data Integration (combining multiple data sources) * Data selection (retrieving the data relevant to analysis task from database) * Data Transformation (transforming the data into appropriate forms for mining by performing summary or aggregation operations) * Data mining (applying the intelligent methods in order to extract data patterns) * Pattern evaluation (identifying the truly interesting patterns representing knowledge based on some measures) * Knowledge representation (representing knowledge techniques that are used to present the mined knowledge to the user) 2.2 Data Data can be any type of facts, or text, or image or number which can be processed by computer. Todays organizations are accumulating large and growing amounts of data in different formats and in different databases. It can include operational or transactional data which includes costs, sales, inventory, payroll and accounting. It can also include nonoperational data such as industry sales and forecast data. It can also include the meta data which is, data about the data itself, such as logical database design and data dictionary definitions. 2.3 Information The information can be retrieved from the data via patterns, associations or relationship may exist in the data. For example the retail point of sale transaction data can be analyzed to yield information about the products which are being sold and when. 2.4 Knowledge Knowledge can be retrieved from information via historical patterns and the future trends. For example the analysis on retail supermarket sales data in promotional efforts point of view can provide the knowledge buying behavior of customer. Hence items which are at most risk for promotional efforts can be determined by manufacturer easily. 2.5 Data warehouse The advancement in data capture, processing power, data transmission and storage technologies are enabling the industry to integrate their various databases into data warehouse. The process of centralizing and retrieving the data is called data warehousing. Data warehousing is new term but concept is a bit old. Data warehouse is storage of massive amount of data in electronic form. Data warehousing is used to represent an ideal way of maintaining a central repository for all organizational data. Purpose of data warehouse is to maximize the user access and analysis. The data from different data sources are extracted, transformed and then loaded into data warehouse. Users / clients can generate different types of reports and can do business analysis by accessing the data warehouse. Data mining is primarily used today by companies with a strong consumer focus retail, financial, communication, and marketing organizations. It allows these organizations to evaluate associations between certain internal external factors. The product positioning, price or staff skills can be example of internal factors. The external factor examples can be economic indicators, customer demographics and competition. It also allows them to calculate the impact on sales, corporate profits and customer satisfaction. Furthermore it allows them to summarize the information to look detailed transactional data. Given databases of sufficient size and quality, data mining technology can generate new business opportunities by its capabilities. Data mining usually automates the procedure of searching predictive information in huge databases. Questions that traditionally required extensive hands-on analysis can now be answered directly from the data very quickly. The targeted marketing can be an example of predictive problem. Data mining utilizes data on previous promotional mailings in order to recognize the targets most probably to increase return on investment as maximum as possible in future mailings. Tools used in data mining traverses through huge databases and discover previously unseen patterns in single step. Analysis on retail sales data to recognize apparently unrelated products which are usually purchased together can be an example of it. The more pattern discovery problems can include identifying fraudulent credit card transactions and identifying irregular data that could symbolize data entry input errors. When data mining tools are used on parallel processing systems of high performance, they are able to analy ze huge databases in very less amount of time. Faster or quick processing means that users can automatically experience with more details to recognize the complex data. High speed and quick response makes it actually possible for users to examine huge amounts of data. Huge databases, in turn, give improved and better predictions. 2.6 Descriptive and Predictive Data Mining Descriptive data mining aims to find patterns in the data that provide some information about what the data contains. It describes patterns in existing data, and is generally used to create meaningful subgroups such as demographic clusters. For example descriptions are in the form of Summaries and visualization, Clustering and Link Analysis. Predictive Data Mining is used to forecast explicit values, based on patterns determined from known results. For example, in the database having records of clients who have already answered to a specific offer, a model can be made that predicts which prospects are most probable to answer to the same offer. It is usually applied to recognize data mining projects with the goal to identify a statistical or neural network model or set of models that can be used to predict some response of interest. For example, a credit card company may want to engage in predictive data mining, to derive a (trained) model or set of models that can quickly identify tr ansactions which have a high probability of being fraudulent. Other types of data mining projects may be more exploratory in nature (e.g. to determine the cluster or divisions of customers), in which case drill-down descriptive and tentative methods need to be applied. Predictive data mining is goad oriented. It can be decomposed into following major tasks. * Data Preparation * Data Reduction * Data Modeling and Prediction * Case and Solution Analysis 2.7 Text Mining The Text Mining is sometimes also called Text Data Mining which is more or less equal to Text Analytics. Text mining is the process of extracting/deriving high quality information from the text. High quality information is typically derived from deriving the patterns and trends through means such as statistical pattern learning. It usually involves the process of structuring the input text (usually parsing, along with the addition of some derived linguistic features and the removal of others, and subsequent insertion into a database), deriving patterns within the structured data, and finally evaluation and interpretation of the output. The High Quality in text mining usually refers to some combination of relevance, novelty, and interestingness. The text categorization, concept/entity extraction, text clustering, sentiment analysis, production of rough taxonomies, entity relation modeling, document summarization can be included as text mining tasks. Text Mining is also known as the discovery by computer of new, previously unknown information, by automatically extracting information from different written resources. Linking together of the extracted information is the key element to create new facts or new hypotheses to be examined further by more conventional ways of experimentation. In text mining, the goal is to discover unknown information, something that no one yet knows and so could not have yet written down. The difference between ordinary data mining and text mining is that, in text mining the patterns are retrieved from natural language text instead of from structured databases of facts. Databases are designed and developed for programs to execute automatically; text is written for people to read. Most of the researchers think that it will need a full fledge simulation of how the brain works before that programs that read the way people do could be written. 2.8 Web Mining Web Mining is the technique which is used to extract and discover the information from web documents and services automatically. The interest of various research communities, tremendous growth of information resources on Web and recent interest in e-commerce has made this area of research very huge. Web mining can be usually decomposed into subtasks. * Resource finding: fetching intended web documents. * Information selection and pre-processing: selecting and preprocessing specific information from fetched web resources automatically. * Generalization: automatically discovers general patterns at individual and across multiple website * Analysis: validation and explanation of mined patterns. Web Mining can be mainly categorized into three areas of interest based on which part of Web needs to be mined: Web Content Mining, Web Structure Mining and Web Usage Mining. Web Contents Mining describes the discovery of useful information from the web contents, data and documents [10]. In past the internet consisted of only different types of services and data resources. But today most of the data is available over the internet; even digital libraries are also available on Web. The web contents consist of several types of data including text, image, audio, video, metadata as well as hyperlinks. Most of the companies are trying to transform their business and services into electronic form and putting it on Web. As a result, the databases of the companies which were previously residing on legacy systems are now accessible over the Web. Thus the employees, business partners and even end clients are able to access the companys databases over the Web. Users are accessing the application s over the web via their web interfaces due to which the most of the companies are trying to transform their business over the web, because internet is capable of making connection to any other computer anywhere in the world [11]. Some of the web contents are hidden and hence cannot be indexed. The dynamically generated data from the results of queries residing in the database or private data can fall in this area. Unstructured data such as free text or semi structured data such as HTML and fully structured data such as data in the tables or database generated web pages can be considered in this category. However unstructured text is mostly found in the web contents. The work on Web content mining is mostly done from 2 point of views, one is IR and other is DB point of view. â€Å"From IR view, web content mining assists and improves the information finding or filtering to the user. From DB view web content mining models the data on the web and integrates them so that the more soph isticated queries other than keywords could be performed. [10]. In Web Structure Mining, we are more concerned with the structure of hyperlinks within the web itself which can be called as inter document structure [10]. It is closely related to the web usage mining [14]. Pattern detection and graphs mining are essentially related to the web structure mining. Link analysis technique can be used to determine the patterns in the graph. The search engines like Google usually uses the web structure mining. For example, the links are mined and one can then determine the web pages that point to a particular web page. When a string is searched, a webpage having most number of links pointed to it may become first in the list. Thats why web pages are listed based on rank which is calculated by the rank of web pages pointed to it [14]. Based on web structural data, web structure mining can be divided into two categories. The first kind of web structure mining interacts with extracting patterns from the hyperlinks in the web. A hyperlink is a structural comp onent that links or connects the web page to a different web page or different location. The other kind of the web structure mining interacts with the document structure, which is using the tree-like structure to analyze and describe the HTML or XML tags within the web pages. With continuous growth of e-commerce, web services and web applications, the volume of clickstream and user data collected by web based organizations in their daily operations has increased. The organizations can analyze such data to determine the life time value of clients, design cross marketing strategies etc. [13]. The Web usage mining interacts with data generated by users clickstream. â€Å"The web usage data includes web server access logs, proxy server logs, browser logs, user profile, registration data, user sessions, transactions, cookies, user queries, bookmark data, mouse clicks and scrolls and any other data as a result of interaction† [10]. So the web usage mining is the most important task of the web mining [12]. Weblog databases can provide rich information about the web dynamics. In web usage mining, web log records are mined to discover the user access patterns through which the potential customers can be identified, quality of internet services can be enhanc ed and web server performance can be improved. Many techniques can be developed for implementation of web usage mining but it is important to know that success of such applications depends upon what and how much valid and reliable knowledge can be discovered the log data. Most often, the web logs are cleaned, condensed and transformed before extraction of any useful and significant information from weblog. Web mining can be performed on web log records to find associations patterns, sequential patterns and trend of web accessing. The overall Web usage mining process can be divided into three inter-dependent stages: data collection and pre-processing, pattern discovery, and pattern analysis [13]. In the data collection preprocessing stage, the raw data is collected, cleaned and transformed into a set of user transactions which represents the activities of each user during visits to the web site. In the pattern discovery stage, statistical, database, and machine learning operations a re performed to retrieve hidden patterns representing the typical behavior of users, as well as summary of statistics on Web resources, sessions, and users. 3 Classification 3.1 What is Classification? As the quantity and the variety increases in the available data, it needs some robust, efficient and versatile data categorization technique for exploration [16]. Classification is a method of categorizing class labels to patterns. It is actually a data mining methodology used to predict group membership for data instances. For example, one may want to use classification to guess whether the weather on a specific day would be â€Å"sunny†, â€Å"cloudy† or â€Å"rainy†. The data mining techniques which are used to differentiate similar kind of data objects / points from other are called clustering. It actually uses attribute values found in the data of one class to distinguish it from other types or classes. The data classification majorly concerns with the treatment of the large datasets. In classification we build a model by analyzing the existing data, describing the characteristics of various classes of data. We can use this model to predict the class/type of new data. Classification is a supervised machine learning procedure in which individual items are placed in a group based on quantitative information on one or more characteristics in the items. Decision Trees and Bayesian Networks are the examples of classification methods. One type of classification is Clustering. This is process of finding the similar data objects / points within the given dataset. This similarity can be in the meaning of distance measures or on any other parameter, depending upon the need and the given data. Classification is an ancient term as well as a modern one since classification of animals, plants and other physical objects is still valid today. Classification is a way of thinking about things rather than a study of things itself so it draws its theory and application from complete range of human experiences and thoughts [18]. From a bigger picture, classification can include medical patients based on disease, a set of images containing red rose from an image database, a set of documents describing â€Å"classification† from a document/text database, equipment malfunction based on cause and loan applicants based on their likelihood of payment etc. For example in later case, the problem is to predict a new applicants loans eligibility given old data about customers. There are many techniques which are used for data categorization / classification. The most common are Decision tree classifier and Bayesian classifiers. 3.2 Types of Classification There are two types of classification. One is supervised classification and other is unsupervised classification. Supervised learning is a machine learning technique for discovering a function from training data. The training data contains the pairs of input objects, and their desired outputs. The output of the function can be a continuous value which can be called regression, or can predict a class label of the input object which can be called as classification. The task of the supervised learner is to predict the value of the function for any valid input object after having seen a number of training examples (i.e. pairs of input and target output). To achieve this goal, the learner needs to simplify from the presented data to hidden situations in a meaningful way. The unsupervised learning is a class of problems in machine learning in which it is needed to seek to determine how the data are organized. It is distinguished from supervised learning in that the learner is given only unknown examples. Unsupervised learning is nearly related to the problem of density estimation in statistics. However unsupervised learning also covers many other techniques that are used to summarize and explain key features of the data. One form of unsupervised learning is clustering which will be covered in next chapter. Blind source partition based on Independent Component Analysis is another example. Neural network models, adaptive resonance theory and the self organizing maps are most commonly used unsupervised learning algorithms. There are many techniques for the implementation of supervised classification. We will be discussing two of them which are most commonly used which are Decision Trees classifiers and Naà ¯ve Bayesian Classifiers. 3.2.1 Decision Trees Classifier There are many alternatives to represent classifiers. The decision tree is probably the most widely used approach for this purpose. It is one of the most widely used supervised learning methods used for data exploration. It is easy to use and can be represented in if-then-else statements/rules and can work well in noisy data as well [16]. Tree like graph or decisions models and their possible consequences including resource costs, chance event, outcomes, and utilities are used in decision trees. Decision trees are most commonly used in specifically in decision analysis, operations research, to help in identifying a strategy most probably to reach a target. In machine learning and data mining, a decision trees are used as predictive model; means a planning from observations calculations about an item to the conclusions about its target value. More descriptive names for such tree models are classification tree or regression tree. In these tree structures, leaves are representing class ifications and branches are representing conjunctions of features those lead to classifications. The machine learning technique for inducing a decision tree from data is called decision tree learning, or decision trees. Decision trees are simple but powerful form of multiple variable analyses [15]. Classification is done by tree like structures that have different test criteria for a variable at each of the nodes. New leaves are generated based on the results of the tests at the nodes. Decision Tree is a supervised learning system in which classification rules are constructed from the decision tree. Decision trees are produced by algorithms which identify various ways splitting data set into branch like segment. Decision tree try to find out a strong relationship between input and target values within the dataset [15]. In tasks classification, decision trees normally visualize that what steps should be taken to reach on classification. Every decision tree starts with a parent node called root node which is considered to be the parent of every other node. Each node in the tree calculates an attribute in the data and decides which path it should follow. Typically the decision test is comparison of a value against some constant. Classification with the help of decision tree is done by traversing from the root node up to a leaf node. Decision trees are able to represent and classify the diverse types of data. The simplest form of data is numerical data which is most familiar too. Organizing nominal data is also required many times in many situations. Nominal quantities are normally represented via discrete set of symbols. For example weather condition can be described in either nominal fashion or numeric. Quantification can be done about temperature by saying that it is eleven degrees Celsius or fifty two degrees Fahrenheit. The cool, mild, cold, warm or hot terminologies can also be sued. The former is a type of numeric data while and the latter is an example of nominal data. More precisely, the example of cool, mild, cold, warm and hot is a special type of nominal data, expressed as ordinal data. Ordinal data usually has an implicit assumption of ordered relationships among the values. In the weather example, purely nominal description like rainy, overcast and sunny can also be added. These values have no relationships or distance measures among each other. Decision Trees are those types of trees where each node is a question, each branch is an answer to a question, and each leaf is a result. Here is an example of Decision tree. Roughly, the idea is based upon the number of stock items; we have to make different decisions. If we dont have much, you buy at any cost. If you have a lot of items then you only buy if it is inexpensive. Now if stock items are less than 10 then buy all if unit price is less than 10 otherwise buy only 10 items. Now if we have 10 to 40 items in the stock then check unit price. If unit price is less than 5 £ then buy only 5 items otherwise no need to buy anything expensive since stock is good already. Now if we have more than 40 items in the stock, then buy 5 if and only if price is less than 2 £ otherwise no need to buy too expensive items. So in this way decision trees help us to make a decision at each level. Here is another example of decision tree, representing the risk factor associated with the rash driving. The root node at the top of the tree structure is showing the feature that is split first for highest discrimination. The internal nodes are showing decision rules on one or more attributes while leaf nodes are class labels. A person having age less than 20 has very high risk while a person having age greater than 30 has a very low risk. A middle category; a person having age greater than 20 but less than 30 depend upon another attribute which is car type. If car type is of sports then there is again high risk involved while if family car is used then there is low risk involved. In the field of sciences engineering and in the applied areas including business intelligence and data mining, many useful features are being introduced as the result of evolution of decision trees. * With the help of transformation in decision trees, the volume of data can be reduced into more compact form that preserves the major characteristic

Leadership in Thoughts from the Tao-te-Ching and The Qualities of a Pri

Leadership in Thoughts from the Tao-te-Ching and The Qualities of a Prince Lao-Tzu’s â€Å"Thoughts from the Tao-te Ching† and Machiavelli’s â€Å"The Qualities of a Prince† both have the ultimate goal of making better leaders. The tactics that each writer chooses to present as a guide for the leader are almost opposite of each other. Today’s American government would benefit from a combination of the two extreme ideas. Lao-Tzu’s laissez-faire attitude towards the economy, as well as his small scale, home defense military is appealing to a liberal person. Machiavelli’s attitude towards miserliness and lower taxes, while being always prepared for war, would appeal to a conservative person. The writers are in agreement on some issues, such as taxes, but other ideas, such as government involvement in the everyday lives of citizens are completely opposed to one another. Lao-Tzu believes in moderation and small government. He states that a leader should stay within his country and govern his people only. He stresses that when the maser governs, the people should hardly be aware that he exists. A leader who is loved is better than one who is feared. The worst is one who is despised (22). Lao-Tzu also believes that war is not necessary when all follow the Tao. He states that â€Å"violence, even well intentioned, always rebounds upon itself;† therefore, if you have a neutral position, you will not be harmed (24). He believes that people are inherently good and not greedy. Man’s greed...

Work Roll Consumption

Reduction in Work Roll Consumption of Skin Pass Mill Using six sigma-A case study A Thesis Submitted to the Ranchi University in partial fulfilment of the requirement for the award of the degree Of Master of Science Engg. In PRODUCTION MANAGEMENT By CHANDRA PRAKASH ROLL NO: 20/M/PM/2002 Under the guidance of Mr K. D. P. Singh Lecturer Department of Mechanical Engineering [pic] MECHANICAL ENGINEERING DEPARTMENT NATIONAL INSTITUTE OF TECHNOLOGY, JAMSHEDPUR September -2008 MECHANICAL ENGINEERING DEPARTMENT NATIONAL INSTITUTE OF TECHNOLOGY, JAMSHEDPUR RANCHI UNIVERSITY CANDIDATE’S DECLARATION I here certify that the work which is being presented in this thesis entitled â€Å"Reduction in Work Roll Consumption of Skin Pass Mill using six sigma-A case study† in partial fulfilments for the award of degree of Master of Science Engg. In Production Management, & Submitted in the Department of Mechanical Engineering NIT, JAMSHEDPUR is an authentic record of my own work carried out under the Supervision of Mr K. D. P Singh Lecturer, Department of Mechanical Engineering. National Institute of Technology, Jamshedpur. The matter embodied in this thesis has not been submitted by me for the award of any other degree. Signature of candidate This is to certify that above statement made by the candidate is correct to the best of my knowledge. Mr K. D. P Singh Lecturer Mechanical Engineering Department NIT, Jamshedpur Dr J. N. Yadav Professor & HOD Mechanical Engineering Department Signature of internal examiner Signature of external examiner ACKNOWLEDGEMENT First of all I would like to express my gratitude to Mr. C. M. Verma Head, BAF/SPM/ECL Cold Rolling Mill, Tata Steel for allowing me to be a owner of this case study matching to my area of work where I could really apply and develop my technical skills in practical aspect. I am extremely grateful to Mr K. D. P. Singh (Lecturer NIT, JSR), Mr Vivek (Sr Manager, BAF & Six sigma Co-ordinator CRM), and Mr. Dharmendra Kumar (Manager Roll shop) for guiding this case study. They have guided me at every step, clearly explained the objectives, the problems statements, technical concepts and terminology to make my case study a success. They always extended a helping hand and spent their valuable time to explain the problems that ever obstructed my path. Working in Tata Steel has not only been a learning experience on technical aspects but there were many other things, which could only be experienced in organization of such repute. Their work culture, discipline, employee’s devotion towards their job and company are extraordinary. Thanks a lot to all those who helped me directly or indirectly during the completion of this case study and special thanks to the associates of Skin Pass Mill and Roll Shop of cold rolling mill Tata steel. Chandra Prakash ABSTRACT This case study deals in reducing Work Roll consumption of Skin Pass Mill of cold rolling Mill. Cold Rolling is a Process by which hot rolled strip or stock is introduced between rollers and squeezed or compressed to the desired thickness. The quality of work rolls that come into direct contact with the steel product has a direct effect on product quality and mill operation. At the time of taking up this case study, Roll cost was one of the major operational cost element for Skin pass Mill & due to increase in global Roll prices its contribution increases from 15 % of total conversion cost to 22 % of total conversion cost . In the mean time there were some additional problem associated with work roll grinding & operational practices at Skin pass mill which showing variability in the process of Roll grinding & Skin passing. This case study deals in bringing improvement in the work roll consumption of Skin pass Mill by using Six Sigma techniques (Define-Measure-Analyse-Improve & Control). Statistical methods are used to analyse the data and pin point the vital causes impacting the work roll consumption of Skin Pass Mill. Regression analysis & trial plan conducted during finalizing optimal and feasible solution, as this case study deals in improving standard operating practices & reducing variability within the process of roll grinding & skin passing. CONTENTS PAGE NO ABSTRACT 4 CONTENTS 5 LIST OF FIGURES 8 LIST OF TABLES 10 NOMENCLATURE 11 CHAPTER 1 INTRODUCTION AND LITERATURE SURVEY 1. 1 INTRODUCTION 12 1. 2 BASIC OF COLD ROLLING 15 1. 3 SKIN PASS MILL 16 1. 3. 1 OVERVIEW OF SKIN PASS MILL 18 1. 3. 2 PURPOSE OF SKIN PASSING 19 1. 4 ROLLS & THEIR REQUIREMENTS 25 1. 5 ROLL GRINDING PROCESS 31 1. 6 ROLL TEXTURING PRACTICES 35 . 7 SIX SIGMA APPROACH 41 1. 7. 2 SIX SIGMA IMPLEMENTATION 41 1. 8 PROBLEM DEFINITION 44 1. 9 OBJECTIVE OF CASE STUDY 45 CHAPTER 2: ANALYSIS OF THE PROBLEM PAGE NO 2. 1 INTRODUCTION 46 2. 2 BRAIN STORMING 46 2. 3 PARETO ANALYSIS 47 2. 4 INDIVIDUAL AND MOVING RANGE GRAPH 50 2. 5 MOODS MEDIAN TEST 52 2. 6 CAUSE EFFECT DIAGRAM 57 2. 7 OUTCOME OF ANALYSIS 60 CHAPTER – 3 METHODOLOGY TO ACHIEVE OBJECTIVES 3. 1INTRODUCTION 61 3. 2 PREPERATION OF ACTION PLAN 62 . 3 NORMAL GRINDING TRIALS & ACTION 62 3. 4 CRACK GRINDING TRIALS & ACTIONS 63 3. 5 SKIN PANEL ROLL GRINDING 63 3. 6 OPERATOR VARIABILITY 64 3. 7 ROLL CHANGE DUE TO ROLL ROUGHNESS 64 3. 8 SCH EDULING MODIFICATION 65 3. 9 ROUGHNESS PREDICTION MODEL 66 CHAPTER – 4 RESULTS AND DISCUSSIONS PAGE NO 4. 1 INTRODUCTION 68 4. 2 BEFORE AND AFTER COMPARISSION 68 4. 3 DISCUSSION ON RESULTS 71 4. 4 RESULTS 72 4. 5 CONTROL PLAN 73 . 6 SAVINGSCALCULATION 74 CHAPTER – 5 CONCLUSION & FUTURE SCOPE 75 REFERENCES 76 List of Figures Page No 1. 1 Skin Pass Mill & Tandem Cold Mill Photograph 12 1. 2 Line layout of cold rolling mill 14 1. 3 Skin Pass Mill Tata steel 16 1. 4 Tensile test graph before skin Passing 20 1. 5 Tensile test graph after skin Passing 22 1. 6 Luder band 24 1. 7Correlation between Roughness & peak count28 1. 8 Skewness of Surface28 1. 9 Surface measured at EDT m/c Tata steel 29 2. 0 Waviness Roughness & form of surface30 2. Roll Grinding M/c at Cold Rolling Mill 32 2. 2 EDT Vs Shot Blast Roll 37 2. 3 Effect of time & temp on surface texture38 2. 4 Effect of –ve polarity on surface texture38 2. 5 Roll texturing m/c at Cold rolling mill40 2. 6 Work roll consumption trend at skin pass mill 44 2. 7 Pareto chart for SPM Work roll grinding 49 2. 8 X bar & moving range chart for normal grinding 50 2. 9 Box plot for different operator at Roll Shop 54 List of Figures Page No 3. 0 Capability histogram for normal grinding 55 3. 1 Roll tonnage trend at skin pass Mill 56 . 2 Abnormal roll change trend at skin pass mill 57 3. 3 Cause & effect diagram for roll change due to low Ra 58 3. 4 SPM Work roll consumption trend before case study 68 3. 5 SPM Work roll consumption trend before case study 69 3. 6 Capability histogram before case study 69 3. 7 Capability histogram after case study 70 3. 8 Trend of abnormal roll change at skin pass mill 71 List of Tables Page No 1. 1 Roll roughness detail of tandem & skin pass mill 26 1. 2 Roughness Accuracy detail of texturing m/c 27 1. Selection of peripheral speed 31 1. 4 Standard Stock removal specification 33 1. 5 Grit size for different Roll 34 1. 6 Action on Grinding wheel on various condition 34 1. 7 Structure of grinding based upon requirement 35 1. 8 Grinding data for skin pass mill work roll 49 1. 9 Data capturing sheet51 2. 0 Operator variability matrix52 2. 1 Regression test result53 2. 2 Abnormal Roll Change detail at Skin Pass mill56 2. 3 Prioritization matrix for roll change reasons 57 2. 4 Scheduling Example of skin pass mill59 2. Normal Grinding trials & findings62 2. 6 Crack Grinding trials & findings63 2. 7 Modified Scheduling Example 65 2. 8 list of parameter effecting roughness 66 2. 9 Results of case study 72 3. 0 Control Plan for reducing work roll consumption 73 3. 1 Saving of the case study 74 NOMENCLATURE TCM – Tandem Cold Mill SPM – Skin Pass Mill M/c, m/c – Machine EDT – Electro Discharge Texturing Ra – Average Roughness CRM – Cold Rolling Mill IMR – Individual Moving Range TDC – Technical Delivery Condition ECT – Eddy current testing CRMIS: Cold Rolling Mill Information system PLTCM: Pickling line tandem cold Mill YPE: Yield Point Elongation SPM: Skin Pass Mill BAF: Batch Annealing Furnace ECL: Electrolytic Cleaning line RCL: Recoiling line NSC: Nippon Steel Corporation CRCA: Cold Rolled Closed Annealed CHAPTER 1 INTRODUCTION AND LITERATURE SURVEY 1. INTRODUCTION This chapter gives information about cold rolling mill, Skin Pass mill, Roll grinding, and Roll texturing process . It also describes about six sigma tool & its implementation at the end it describes objective of the case study. Cold Rolling is a Process by which hot rolled strip or stock is introduced between rollers and squeezed or compressed to the desired thickness. Amount of strain introduce determines the properties of the finished product. Following are Purpose of Cold Rolling ? Good formability ? Superior surface finish ? Reasonable strength ? Close dimensional tolerance Fig 1. 1 Tandem Cold Mill Tata steel Skin Pass Mill Tata steel Cold Rolling Mill complex has been commissioned at TATA STEEL works in the year 2000. The total output of the Cold Rolling Mill complex consists of 0. 96 mt of cold rolled and annealed products and 0. 5 mtpa (Million Tonne Per Annum) of cold rolled and galvanized products. Hence, the total installed capacity of this unit is approximately 1. 5 million tons per annum. The range of thickness and width of these cold rolled products are 0. 3 to 3. 2 mm and 800 to1560 mm respectively. The primary input material to the cold rolling complex is a hot rolled coil. The cold rolled products are broadly under the categories: ? Annealed coils ? Galvanized coils ? Cold rolled full hard coils. The cold rolled products from the Cold Rolling Mill complex are designed to cater to various market segments such as construction, general Eng. , automobile, white goods, packaging and others. CRM Process flow at Tata Steel Pickling (to remove oxides and scales) Cold rolling in tandem mill to achieve desired thickness Electrolytic cleaning line to clean the surface dirt. Batch annealing furnace for internal stress relieving Skin passing to remove luder bands, develop mechanical properties, Impart desired surface finish; improve flatness, Inspection, finishing, dispatch Sub Section of Cold Rolling Mill ? Pickling Line &Tandem Cold Mill (PL-TCM) ? Batch Annealing Furnace (BAF) ? Electrolytic cleaning Line (ECL) ? Skin Pass Mill (SPM) ? Galvanising Line ? Recoiling Line (RCL) ? Coil Packaging Line (CPL) pic] Fig 1. 2 Line lay out of Cold Rolling Mill Tata steel 1. 2 Basic of Cold Rolling Mill Following are the basic Processes ? The Hot Strip Mill sends the hot rolled coils (thickness 2 to 6 mm width and 800-1560 mm) to the Cold Rolling Mill Complex for processing. ? First the hot rolled coils are passed through the Pickling section containing Hydrochloric acid, in order to cl ean the surface of rust & scales, making them ready for cold rolling. ? The Trimming Section where the edges of pickled hot rolled coils are trimmed( if necessary) ? The coil is then fed into the main mill, viz. Tandem Cold Mill with five mill stands, each having three pairs of rolls in the five stands which bring down the strip thickness in a controlled manner to the desired target value of (0. 3mm to 3. 2 mm). ? This completes the process of cold rolling or rolling at ambient temperatures. ? From here the two-third of the product goes to Electrolytic cleaning line, where generally two process takes place and they are Predegressing and electrolytic cleaning with the help of NaOH, after this the sheet is washed with high pressure steam to remove the bubbles of NaOH from the surface. Then the coil is dried in the hot drier. ? The coil comes to Batch Annealing furnace directly from Electrolytic cleaning line where they are stacked covered and heated in a closed hood in a 100% hydrogen atmosphere. This process improves the mechanical properties of the strip. ? The Skin Pass Mill takes care of the coils annealed in Batch Annealing furnace by passing them through a single stand high-speed mill with two pairs of rolls. The objective is to impart the correct surface texture and to control the mechanical properties as per customer requirement. The coils are properly oiled for rust protection and recoiled in the Recoiling Lines (RCL 1, 2 & 3) for inspecting the surface. ? The remaining one- third part of the production from PLTCM goes to the Galvanising Lines (1 & 2) where coils are again cleaned, rinsed, dried, L-annealed/heated and taken through a Molten zinc bath for a continuous uniform coating of zinc. This zinc coating helps give a sacrificial layer on the cold rol led strip for corrosion protection. The Continuous packaging line takes care of the packing requirement of the coils as per the customer specifications. 1. 3 Skin Pass Mill [pic] Fig 1. 3 Skin Pass Mill Tata steel front view Skin pass mill: Annealed coils are given a small cold reduction (typically around 1-3 %) in the skin pass mill. This operation results in the right surface roughness imparted on the strip surface as per the customer specifications. In addition, a metallurgical defects known as stretcher strains are eliminated, and also the flatness of the strip is improved. The basic operation done in the cold rolling mill is the wet temper rolling as a cold rolling finishing which is the final process in the integrated steel production, where all materials received from the cold rolling process are processed into the final products with required properties through cleaning, heat treatment and then temper rolling. As this process is closely related to user requirement for mechanical properties, surface properties, size etc. many detailed operation standards are required (annealing surface, size change). This process is quickly adaptable to shape correction reprocessing etc. ut there are many operations which require human hands, as compared with cold rolling. As skin passing is the final process of the integrated steel making operation, the information obtained from this process must be completely fed back to the processes on the down stream side of the steel making furnace. This process is located closest to users and achieving in line quality to meet the user requirements must guaranty the quality. The feed back of information to the preceding processes to be reflected in production is very important. The temper rolling operation falls into three types as shown below: Operation using water-soluble rolling oil Operation using oil-soluble rolling oil Operation in with no rolling oil is used (Dry rolling). Each type of rolling operation has both advantages and disadvantages. The type of rolling operation must be selected in due consideration of the ease of temper rolling, the ease of operation and rust preventive at downstream process at customers end. The surface of roll to be used for temper rolling is mat-finished by shot blasting of steel grit or Elector Discharge Texturing (EDT). This finish is widely as it ensures good paint ability. When the working rolls are ground, the roll surface is bright- finished to about Ra (0. 05 µm) by using a grinding wheel of small grain size. The surface roughness of the strip rolled by bright-finished rolls is below Ra(0. 35 µm), which is suitable for prime coating Generally, the surface finish condition of strip in the temper rolling process is controlled in terms of the surface finished of work rolls only. For confirmation of this condition, the roughness and look of sheet surface after temper rolling is Checked at regular intervals. Temper rolling oil used is mainly applied to thick products, using dull-finished work rolls. The majority of rolling oils used for this rolling are sodium nitrite-based oils. The concentration of sodium nitrite is 5 ( 10% oil-soluble temper rolling oils higher rust preventive power to meet required uses have been developed and put into practical use. 1. 3. 1 OVERVIEW OF SKIN PASS MILL Skin pass an overview ? Single stand mill ? 4- High wet skin pass non-reversible mill ? Capacity: 1mtpa ? Line speed: 900mpm ? Thk range: 0. 3-3. 2 mm ? Width range: 900-1580 mm SPM Equipment ? Main drive-3 ? Mill stand rolls-4 ? Auxiliary roll-8 ? Oiling system ? Fume exhaust system ? Hydraulic gap control system ? Elongation control ? Low pressure hydraulic system ? Quick roll changing car ? Auto tempered car ? Back up rolls polishing ? Unique Features of SPM ? Higher productivity. ? High degree of accuracy- elongation control ? Surface cleanliness- wet skin pass ? Eco fr iendly fume exhaust ? Automatic quick work rolls change & pass line 1. 3. 2 PURPOSE OF SKIN PASSING ? Improvement of mechanical properties of material ? Shape correction Adjustment of surface properties (roughness) ? Apply rust preventive oil (optional) ? Improvement of mechanical properties of material ? Elimination of yield point elongation ? Improvement of formability by decreasing the yield point ? Improvement of other mechanical properties The skin passing of material has to be done with optimum parameters such that the purpose of skin passing is met. Ideally the skin passing has to be done in such a way that alternate grains are strained by which we will get 50% strained surface grains and 50% strain free surface grains. Upper yield point Stress Yield point elongation Lower yield point Strain Fig 1. 4 tensile test graphs before skin passing Yield point elongation is a well-known phenomenon in low carbon steel. After the elastic portion of the stress strain curve (a schematic engineering stress-strain curve is shown in the above figure) the load drops at upper yield point. At lower yield point this drop becomes steady, but a continuous series of fluctuation appears in the stress strain curve. This is commonly known as yield point elongation. After this stage, the curve becomes smooth again. Reason: The reason behind this phenomenon is the alternate locking and unlocking of dislocations by the interstitial atoms (C and N) in steel matrix. C and N atoms form interstitial solid solution and these have natural affinity for locking the dislocations. The locked dislocations cannot move freely, which restricts deformation of the material. The deformation of the material is actually caused by movement and multiplication of dislocations. The deformation stops when the dislocations are not free enough to continue their movements, and further application of load in this situation causes crack generation and failure. After cold rolling and annealing, a low carbon steel strip is supposed to undergo a forming operation. However, this forming becomes difficult if the dislocations are pinned down by the interstitial solute atoms. The annealing treatment provides ample opportunity for the dislocations to move freely and sit at the thermodynamically favourable sites, where the solute atoms pin the dislocations and kill their mobility. This is commonly known as Cottrell atmosphere. Now, if the material is subjected to a tensile load, the stress strain curve will show a serration, i. . alternate load drop and load jump, just after the yield point. Load drop indicates that the dislocations are pulled off from the solute atmosphere, coupled with generation of fresh dislocations under the external force, and load jump indicates that the momentarily free dislocations are again encountering with the solute atoms. This actually constitutes the stage of yield point elongation. Due to the pinning effect of the s olute atoms, the dislocation multiplication sources also become active, which generates fresh dislocations. After this stage, when sufficient fresh dislocations are available for continuing deformation, the stress-strain curve becomes smooth again. This yield point elongation (YPE) is absolutely detrimental as far as the formability of the material is concerned. It creates Luder bands or stretcher strain marks, which finally leads to failure of the component. These bands are visible on the strip surface. When a test specimen exhibits YPE during its tensile testing, these bands appear on the specimen surface, starting from middle (where necking starts) and spreading towards the ends, at an angle of approximately 450 to the tensile axis. YPE elongation continues till the entire specimen surface is covered by the Luder band formation, then smooth plastic deformation starts. Here comes the role of skin passing. Since YPE, after batch annealing, cannot be avoided, a skin depth deformation is given to the just annealed steel strip. This skin depth deformation actually overcomes this region of the stress-strain curve. Sufficient number of dislocations is pulled off from the solute (C, N) atmosphere, at the same time fresh dislocations are generated, which is sufficient for facilitating the forming operation at the next stage. If the material, in skin passed (or temper rolled) condition, is subjected to tensile testing, the stress strain curve will not show any YPE and the plastic deformation will take place without a sharp yield point, as shown in the figure below. That is what precisely desired for drawing or deep drawing grade material. If this skin passed material is left unused for a sufficiently long time, or subjected to a brief heat treatment at a low temperature, the YPE reappears once again. The YS value also goes up and ductility of the material drops. This phenomenon is known as strain aging. UTS YS Stress Strain Fig 1. tensile test graphs after skin passing From the discussion made so far, it is clear that the locking of dislocations are related to the two important factors, one is movement of dislocations, the other is movement of interstitial solute atoms. Therefore diffusion has a very important role to play. If the testing is carried out at room temperature, the mobility of dislocations un der the action of external load is more than the mobility of solute atoms. If the similar test is carried out at a higher temperature, the mobility of the solute atoms increases, and movements of dislocation and solute atoms may be comparable. Such a situation would give rise to an interesting phenomenon called dynamic strain aging, where the solute atoms keep on interacting with the dislocations and the entire stress strain curve (after elastic limit) shows serration. Since YPE is directly related to the concentrations of C and N atoms in steel, the extent of deformation (known as temper elongation) to be given at skin pass mill (SPM), which is a critical factor, varies with steel composition. The magnitude of temper elongation should be high for higher C content. For instance, the temper elongation in case of CQ material should be higher than that in case of EDD grade. If the temper elongation is less than the required amount, the material will show stretcher strain marks during forming. If temper elongation is higher than the required amount, the strength of the material will increase. This is not desirable, particularly for the softer grades like IF and EDD, because the strain hardening exponent value is higher for these grades, compared to that for ordinary CQ material. Theoretically speaking, IF or interstitial free deep drawing grade steel should not require any skin passing. The reason is that the C and N concentrations are kept very low in this grade (of the order of 30 ppm). In addition, presence of Ti in this steel promotes the fixing of C and N atoms in form of carbide and carbonitiride precipitates, thereby creating a condition so that the Fe matrix becomes virtually free of interstitial solute atoms. Such a condition favours the easy movement of dislocations without any hindrance, and this steel has been established as the highest formable grade, with maximum deep drawability and ductility. In practice, IF grade steel is subjected to skin passing with a small magnitude of elongation, and, of all grades, it requires minimum temper elongation. The skin pass depends on Yield strength of the material in the following way: Lower the skin pass (roughly less than 0. 6 %), the material will have the tendency to show Bauschinger’s effect. Higher the skin passing (above 1. 5%) the material will be over strained. That’s the reason why the skin passing for a given YS, has to be done with the optimum reduction such that the material does not get into either of the problems stated above. Also percentage reduction increases with increasing YS to get the optimum properties. Parameters on which Skin pass Load depends: Grain Size: Higher the ASTM grain size number (finer the grain), higher is the skin pass load. Speed: Increasing the speed of skin pass mill will require higher load for the same reduction Diameter of work roll: Larger the diameter of the work rolls, higher is the roll force required to remove stretcher strain. Roughness of the strip from Tandem Cold Mill: The incoming coil has got some roughness values because of the final finishing in stand number (5) of tandem Cold Mill. Many times to high roughness of the incoming strip to Skin Pass Mill and the requirement of Average roughness values on the surface in the ranger of 0. -1. 2 microns for most applications, the peaks are knocked off during skin passing which is detrimental from forming and image clarity point of view. The best practice for this should be keeping as low roughness as possible on the strip surface after tandem cold mill (of course sticker formation during annealing in Batch annealing furnace has to be kept in mind), a nd imparting higher roughness on the work rolls in the skin pass mill. 1. 3. 3 THEORY OF SKIN PASSING When the annealed mild steel sheet is preformed, surface markings, called stretcher strains markings, appear on deformed parts. Stretcher strains are also called as Luder bands. The formation of these markings can be prevented by Skin passing the sheet by giving the sheet elongation of 1-2 % before Performing. LUDER BAND OR STRECHER STRAIN This band is formed with an angle of about 45 deg – 50 deg with respect to the tensile axis the markings formed between Upper and lower are called as â€Å"Luder Lines† or â€Å"Stretcher Strains† as shown in fig 1. 6 Tensile load Luder band Tensile load Fig 1. 6 Luder band 1. 4 Rolls & their requirement for Cold Rolling The performance characteristics of rolls used in cold rolling mill, both in Tandem Cold Mill(TCM) and Skin Pass Mill, are critical to mill productivity and to the quality and acceptance of the cold rolled products. With the rapid change in roll technology, roll management in cold rolling has become an area of utmost importance. The increasing requirements of critical surface finish and texture of flat rolled product has necessitated application of the state of art technology in roll preparation and roll inspection. Rolls also represent a significant investment and input to a value analysis of cost per ton rolled. The quality of work rolls that come into direct contact with the steel product has a direct effect on product quality and mill operation. A forged steel with a chromium content of 5 mass% has been conventionally used to meet the requirement of metallurgical structure homogeneity and high hardness for work rolls in cold rolling. Rolls having improved performance are strongly demanded. 1. 4. 1 Requirement from textured Rolls: 1. 4. 1. 1 Surface finish: Surface roughness is imparted to Work Rolls which are used in 5th stand of Tandem cold mill and to the work rolls of Skin Pass Mill. The primary requirement of surface roughness for tandem mill rolls is to prevent stickers in the next process i. e. batch annealing. The surface roughness on Skin pass mill is guided by the requirement of surface roughness on Cold rolled strip which is based on its end use. Ra is the universally recognized and most used international parameter of roughness. It is the arithmetic mean of the departures of the profile from the mean line. Ra = 1/L {y (x)}dx For a typical application of auto grade the Ra value in strip ranges from 0. 8 to 1. 2 micron. The final roughness on SPM roll is decided based on the transfer ratio of roughness from roll to strip (ranges from 45-60% based on mill parameters). A typical transfer plot and the values of roughness is shown in table 1. 1 Table 1. 1 Roll Roughness detail of Tandem cold mill & skin pass mill Work Roll |Tandem Cold MILL Work Rolls |Skin Pass Mill Work Rolls | |Average roughness |PPC |Average roughness |PPC | |3. |75 |3 |120 | |4. 0 |70 |3. 0 |96, 118 | |4. 5 |65 |3. 5 |80 | |5. 0 |60 |4. 0 |70 | The distribution of surface roughness over the roll body is also of importance to ensure consistency of surface roughness over the strip widths produced in a campaign. The ROLLTEX Electro discharge texturing process of Sarclad machine produces a texture to the capability as mentioned in table 1. 2. Roughness Definition: Roughness is defined as the finer irregularities of the surface texture that usually result from the inherent action of some production process such as machining or wear. Roughness features are typically in the sub micron range. Continuously recurring, irregular depressions and elevations on the surface of the coil are known as roughness. Rough coil surface is usually caused by severe roll groove wears surface roughness can also be caused due to corrosion if the rod is stored for lengthy periods in damp or corrosive atmospheres. The degree of roughness can be determined by microscopic examination or with Ra meter. Surface roughness has two main attributes: Roughness height or depth, and Lateral dimension. Roughness heights of the structure on polishing or machining surface are frequently measured as a root mean square roughness. The units of roughness are angstroms or nanometres for smoothers surface ‘lim' and micrometers â€Å" µm† for rougher surface. Lateral dimensions frequently and called surface spatial wave lengths are measured in micrometers. A rough surface is usually described in terms of its deviation from a smooth reference surface. Some conventional methods for surface measurement are optical microscope, scanning electron microscope and transmission electron microscope. These can be used to produce topographic maps of surfaces. Today laser scattering technique has become more common. Ra value: Average/mean height of surface peaks and troughs over a reference length indicates an overall profile of the sheet surface, dullness or brightness. Roughness is imparted to the rolls by Electro discharge texturing method Table 1. 2 Roughness accuracy detail of texturing m/c |Sno |Range of roughness value |Accuracy of surface produced (Ra) |Accuracy of surface produced (PPC-peaks per | | | | |centimetre) | |1 |0. to 6. 0 micron Ra |+/- 4 % of mean Ra |+/- 4 % of mean PPC | |2 |6. 1 to 10. 0 micron Ra |+/- 5 % of mean Ra |+/- 5 % of mean PPC | |3 |>10. 1 micron Ra |+/- 6 % of mean Ra |+/- 6 % of mean PPC | 1. 4. 1. 2 Peak Count: It is the measurement of number of peaks in the specified length over a particular bandwidth (normally 1 micron). A profile peak is the highest part of the profile between an upwards and downwards crossing of the mean line. The exposed auto body panels typically require 100 ppi on the Cold rolled sheet. The transfer ratio of peak counts from roll to the strip ranges between 60-70%, based on again the rolling conditions. Figure 1. 7 shows the correlation between the roughness of the surface & the peak counts. Fig 1. 7 Correlation between roughness & peak counts Stability of the surface profile: The textured roll is required to give a consistent transfer of roughness and peak count on the strip while rolling. During rolling the surface experiences wear of the peaks and the roll is Fig 1. 8 Skewness of surface discarded after a certain tonnage, determined based on the cut-off point of surface requirement on the strip. To assess this requirement of surface stability, metrology experts and certain European instrument manufacturers have devised surface texture height parameters, which can be analysed by a Data Processing Module (DPM), supplied separately by the surface finish tester manufacturers. Out of various parameters used in this analysis, the most commonly used is Rsk (Skewness) and tp % (known as bearing ratio). Rsk is the measure of the symmetry of the amplitude distribution curve about the mean line. As shown in figure 1. 8 if Rsk is negative the surface peaks are higher, which is prone to a large drop in surface finish during the initial rolling. Based on the practical experience of cold rollers over the world, a slight positive value is preferred. A typical surface plot after texturing a surface to roughness value of 2. 93 micron in Sarclad EDT machine and measured by DPM is shown in Figure 1. 9 Fig 1. 9 Surface measurements done on Tata EDT-Skin Pass Mill roll. The Bearing ratio (tp%) is a measure of the length of bearing surface (expressed as a % of the assessment length), where the profile peaks have been cut off at a line which runs parallel to the mean line of the profile. The line defining the bearing surface can be set at a selected depth below the highest peak or at a selected distance above or below the mean line of the profile. When this line is set to the depth of the largest profile valley, the tp is 100% because the entire profile is above the bearing line. By plotting the tp value against depth below the highest profile peak between the 0% and 100 % limits, the bearing ratio (known as Abott- Firestone curve) curve is obtained. Figure 1. 9 shows the bearing ratio curve against a particular value of Rsk. 1. 4. 1. 3Waviness: Most surface profile results from the combined effects of roughness, waviness and form as shown in figure 2 Waviness parameters are produced by passing the data of the surface measurement through a low pass filter, so that longer wavelengths than the cut-off are included. The waviness, Wa is calculated from the resulting profile. Fig 2 Waviness, Roughness and Form of a surface Wavelengths in the roughness category < 800 micron are covered or filtered out by painting, in the end application of the CR strip. Wavelengths >800 micron defined as â€Å"Waviness† remain or are enhanced after painting and contribute to poor Distinctness of image or image clarity. If Wa is held below 0. 6 micron, irrespective of the Ra, then those wavelengths >800 micron have only a marginally adverse effect on Distinctness of image. Samples of sheet produced by tandem/ temper mill rolls textured by the Rolltex EDT process consistently show levels of Wa