Multi-response grinding process functional approximation and its influence on solution quality of a modified tabu search

Abstract

In this paper, the solution quality of a modified tabu search (MTS) strategy for a constrained, two- stage, multi-response, and continuous variable grinding process optimization problem is studied for varied degree of process functional approximations. Multivariate regression (MR) and artificial neural network (ANN) is selected, and found to be suitable for process functional approximation or modelling at each stage of grinding. Integrating these functional approximations or process models (MR or ANN- based) with desirability functions, near-optimal solutions (expressed in terms of mean and standard deviation of a single primary objective measure or a composite desirability at the final stage) is determined using MTS strategy. The computational run results show that MTS is efficient and suitable to determine near optimal acceptable solutions for varied degree of functional approximation for the two-stage constrained optimization problem. However, the results also indicate that MTS provide inferior or sub-optimal solutions for higher order nonlinear approximation (based on ANN models) as compared to MR-based classical linear models.