A modified tabu search strategy for multiple-response grinding process optimisation

Abstract

Multiple-response grinding process is usually too complex to optimise, requiring a large number of interacting process variables and responses. Experimentation techniques, such as factorial design, fractional factorial design and Response Surface Methodology (RSM) that may be used for this process are too difficult to implement for production lines involving grinding and other necessary operations. For grinding process involving continuous variable, non-linear and multiple-response optimisation problem, the potential of Tabu Search (TS) strategy needs to be explored either in its original form or its variant. In this paper, integrating Artificial Neural Network (ANN) and composite desirability function with a Modified Tabu Search (MTS) strategy, based on Mahalanobis multivariate distance approach to identify tabu move, with scatter search intensification scheme is proposed for the above-mentioned problem. Computational results show that MTS provides better consistency in terms of sample mean and standard deviation of composite desirability measures than that of real-coded GA.