32 research outputs found
An intelligent data mining technique for product quality improvement
No full textAdvances in data mining have provided techniques for automatically discovering underlying knowledge and extracting useful information from large volumes of data. Data mining offers tools for quick discovery of relationships, patterns and knowledge in large complex databases. Application of data mining to manufacturing is relatively limited mainly because of complexity of manufacturing data. Growing self organizing map (GSOM) algorithm has been proven to be an efficient algorithm to analyze unsupervised DNA data. However, it produced unsatisfactory clustering when used on some large manufacturing data. In this paper a data mining methodology has been proposed using a GSOM tool which was developed using a modified GSOM algorithm. The proposed method is used to generate clusters for good and faulty products from a manufacturing dataset. The clustering quality (CQ) measure proposed in the paper is used to evaluate the performance of the cluster maps. The paper also proposed an automatic identification of variables to find the most probable causative factor(s) that discriminate between good and faulty product by quickly examining the historical manufacturing data. The proposed method offers the manufacturers to smoothen the production flow and improve the quality of the products. Simulation results on small and large manufacturing data show the effectiveness of the proposed method
Case-based reasoning for adaptive aluminum extrusion die design together with parameters by neural networks
No full textGlobal Product Development 2011, Part 13, 491-496, DOI: 10.1007/978-3-642-15973-2_50 ISBN 978-3-642-15972-5International audienceNowadays Aluminum extrusion die design is a critical task forimproving productivity which involves with quality, time and cost. Case-Based Reasoning (CBR) method has been successfully applied to support the die design process in order to design a new die by tackling previous problems together with their solutions to match with a new similar problem. Such solutions are selected and modified to solve the present problem. However, the applications of the CBR areuseful onlyretrievingprevious features whereas the critical parameters are missing. In additions, the experience learning to such parameters are limited. This chapter proposes Artificial Neural Network(ANN) to associate the CBR in order to learning previous parameters and predict to the new die design according to theprimitive die modification. The most satisfactory is to accommodate the optimal parameters of extrusion processes
Prediction of the process capability for compression rubber part forming in the automotive supply chain
No full textPurpose: The paper proposes predicting production process capability for the compression rubber part in automotive supply chain management. Delivery of parts to tier 1 and OEM on time is the most important part of supply chain management, together with the delivery of on-quality and on-cost control to maintain the competitiveness of the supply chain. There are many suppliers to produce many automotive parts for tier 1. Therefore, the simulation approach properly predicts and prevents the process from getting into trouble during the actual production time. Production process quality control is critical to ensure that the good quality of the parts purchased can be delivered on time. Rubber parts are used widely in automotive, motorcycles, trucks, and other types of vehicles, with small sizes but in huge quantities to support general OEM brands and specific parts. The rubber part manufacturing process is complex and uncertain with compression moulding and rubber curing conditions. Therefore, good conditions can predict the production process's capability to commission and deliver on schedule. Design/methodology/approach: A neuro-fuzzy system is adopted and developed to deal with the uncertain process capability under multi-criteria decision-making. Findings: The methodology development can be used in the actual rubber part manufacturing supply chain environment and can predict uncertain problems that might occur in the subcontractor factories. Research limitations/implications: The prediction of the production process capability of the rubber part supply chain might be more effective on the real-time monitoring control system and can be tracking location part progress for further planning both success or rescheduling. Practical implications: The platform can be applied to audit and test the actual industrial supply chain, and problem and research questions are brought about from the real supply chain in the local country. Originality/value: The methodology development was originally created for the particular supply chain in rubber automotive parts that can replace the existing system to obtain a more efficient performance evaluation process
