Title: Application of ANN in Six Sigma DMADV and its comparison with regression analysis in view of a case study in a leading steel industry
Authors: A.M. Kuthe, B.D. Tharakan
Addresses: Department of Mechanical Engineering, Visvesvaraya National Institute of Technology (VNIT), Nagpur, India. ' M.P. Christian College of Engineering & Technology (MPCCET), Kailash Nagar, Near Industrial Estate, Bhilai, Distt. Durg, Chhattisgarh 490026, India
Abstract: Six Sigma as a problem-solving approach has traditionally been used in fields such as business, engineering and production processes. The core of the Six Sigma methodologies is data-driven and it is a systematic approach to problem solving, with focus on customer impact. Artificial Neural Network with its predictive capacity can be a useful key tool in augmenting the effectiveness of application for DMADV. Feed-forward back propagation neural networks can be used for evolving computational models, which correlates highly complex process interdependencies for its better analysis, design and verification.
Keywords: design for six sigma; DFSS; DMADV; artificial neural networks; ANNs; feedforward back propagation networks; manufacturing processes; steel plates; oxygen blown converters; continuous cast; casting; MSE; mean square error; computational modelling; process improvement; regression analysis.
International Journal of Six Sigma and Competitive Advantage, 2009 Vol.5 No.1, pp.59 - 74
Published online: 30 Mar 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article