A Synergistic Approach of Desirability Functions and Metaheuristic Strategy to Solve Multiple Response Optimization Problems

Abstract

Ensuring quality of a product is rarely based on observations of a single quality characteristic. Generally, it is based on observations of family of properties, so‐called ‘multiple responses’. These multiple responses are often interacting and are measured in variety of units. Due to presence of interaction(s), overall optimal conditions for all the responses rarely result from isolated optimal condition of individual response. Conventional optimization techniques, such as design of experiment, linear and nonlinear programmings are generally recommended for single response optimization problems. Applying any of these techniques for multiple response optimization problem may lead to unnecessary simplification of the real problem with several restrictive model assumptions. In addition, engineering judgements or subjective ways of decision making may play an important role to apply some of these conventional techniques. In this context, a synergistic approach of desirability functions and metaheuristic technique is a viable alternative to handle multiple response optimization problems. Metaheuristics, such as simulated annealing (SA) and particle swarm optimization (PSO), have shown immense success to solve various discrete and continuous single response optimization problems. Instigated by those successful applications, this chapter assesses the potential of a Nelder‐Mead simplex‐based SA (SIMSA) and PSO to resolve varied multiple response optimization problems. The computational results clearly indicate the superiority of PSO over SIMSA for the selected problems.