Principal Component Analysis in Grey Based Taguchi Method for Optimization of Multiple Surface Quality Characteristics of 6061-T4 Aluminum in CNC End Milling

Abstract

The present study highlights a multi‐objective optimization problem by applying Principal Component Analysis (PCA) coupled with grey based Taguchi method through a case study in CNC end milling of 6061‐T4 Aluminum. The study aimed at evaluating the best process environment which could simultaneously satisfy multiple requirements of surface quality. In view of the fact, that traditional Taguchi method cannot solve a multi‐objective optimization problem; to overcome this limitation, grey relation theory has been coupled with Taguchi method. Furthermore, to follow the basic assumption of Taguchi method i.e. quality attributes should be uncorrelated or independent; which is not always satisfied in practical situation. To overcome this shortcoming the study applied Principal Component analysis to eliminate response correlation and to evaluate independent or uncorrelated quality indices called Principal Components which were aggregated to compute an overall quality index denoted as overall grey relational grade which was optimized (minimized) finally. The study combined PCA and grey based Taguchi method for predicting optimal setting. Optimal result was verified through confirmatory test.