International Journal of Computer Engineering and Applications, Volume IV, Issue II/III, Oct.13 www.ijcea.com ISSN 2321-3469 STEEL FAULTS DIAGNOSIS USING PREDICTIVE ANALYSIS Sanjay Jain 1 , Chandreshekhar Azad 2 , Vijay Kumar Jha 3 1 Director, MICA Educational Company, Opposite Ranchi Club Gate, Ranchi 2 Research Scholar, Department of IT, Birla Institute of Technology, Mesra (Ranchi) 3 Associate Professor, Department of IT, Birla Institute of Technology, Mesra (Ranchi) ABSTRACT: In the steel industry, specifically alloy steel, creating different defected product can impose a high cost for steel product manufacturer. One common fault in producing low carbon steel grades is Pits & Blister defect. To remove this drawback, we need to grind the surface of the steel product. Grinding cause waste of time and involved cost of the production will be increased. Incidence of defects analysis is related to numerous factors including material analysis, production processes etc. In this study we created data mining based model to predict this fault. Data mining methods used in this predictive analysis are decision tree, multilayer perceptron neural network and logistic regression after that we use genetic algorithm for optimization. We then compared the efficiency and accuracy of these models and select the appropriate model. In this study, data mining is used to perform Predictive Analysis, to create decision tree and neural network. For the experiment Steel Plates Faults Data Set is taken from UCI repository. The model trained using the decision tree, provide the higher accuracy. Keywords: Data mining, Decision Tree, Multilayer Perceptron Neural Network, Logistic Regression. [1] INTRODUCTION A fault may be defined as an unacceptable difference of at least one characteristic property or attribute of a system from acceptable usual typical performance. Therefore, fault diagnosis is the description of the kind, size, location and time of discover of a fault. The main purpose of any fault diagnosis system is to determine the location and occurrence time of possible faults on the basis of accessible data and knowledge about the performance of diagnosed processes. Manual fault diagnosis system is the traditional way where an expert with electronic meter tries to obtain some information about relevant operational equipment, check the maintenance manual and then diagnosed the probable causes of a particular fault. However, intelligent fault diagnosis techniques can provide quick and correct systems that help Sanjay Jain, Chandreshekhar Azad and Vijay Kumar Jha 69