Knowledge-based System for Taguchi’s Robust Design Model

This paper presents a model of generic knowledge-based system for the selection of optimal process parameters in multiresponse processes, that consists of three modules which (1) use expert system, designed for selecting an inner and an outer orthogonal array, to design the experimental plan, (2) use Taguchi’s quality loss function and multivariate statistical methods to adequately present responses, uncorrelate and synthesise them into a single process performance measure, (3) use neural networks to construct the response function model and genetic algorithm to optimise parameter design. The model is given in a form of an hybrid intelligent system for the process design, optimisation, modelling and/or simulation. Two case studies are presented to illustrate the effectiveness of the proposed model in comparison to several commonly used approaches from the literature.