Classifying tensile strength of HSLA steel: an investigation through neural networks using Mahalanobis Distance. (3rd December 2009)

• Record Type: Journal Article
• Authors: Das, Prasun; Datta, Shubhabrata; Bhattacharyay, Bidyut Kr.
• Is Part Of: International journal of mechatronics and manufacturing systems. Volume 3:Number 1/2(2010)
• Page Start: 97
• Page End: 115
• Publication Date: 2009-12-03
• Subjects: HSLA -- high strength low alloy steel -- thermomechanical processing -- classification -- dimension reduction -- MTS -- Mahalanobis Taguchi system -- artificial neural networks -- ANNs -- Taguchi methods -- tensile strength -- sensitivity analysis -- variable selection; Mechatronics -- Periodicals; 629.89
• Languages: English
• ISSNs: 1753-1039

Abstract

This paper addresses a comparative approach of classification of Thermomechanically Controlled Processed (TMCP) High Strength Low Alloy (HSLA) steels based on Mahalanobis-Taguchi System (MTS) principles and ensemble neural networks, including sensitivity analysis for variable selection. Later, a hybrid approach is developed, depending on the ability of Mahalanobis Distance (MD) in capturing the correlation structure of a multi-dimensional system, both for the Multi-Layered Perceptron (MLP) and for Radial Basis Function (RBF) networks. The results are found to be quite consistent in describing the role of input parameters for effective classification of such steel.