Optimizing Multiple Response Problem Using Artificial Neural Networks and Genetic Algorithm

This paper proposes a new intelligent approach for solving multi-response statistical optimization problems. In most real world optimization problems, we are encountered adjusting process variables to achieve optimal levels of output variables (response variables). Usual optimization methods often begin with estimating the relation function between the response variable and the control variables. Among these techniques, the response surface methodology (RSM) due to its simplicity has attracted the most attention in recent years. However, in some cases the relationship between the response variable and the control factors is so complex; hence a good estimate of the response variable cannot be achieved using polynomial regression models. An alternative approach presented in this study employs artificial neural networks to estimate response functions and genetic algorithm to optimize the process. Furthermore, the proposed approach uses taguchi robust parameter design to overcome the common limitation of the existing multi-response approaches, which typically ignore the dispersion effect of the responses. In order to evaluate the effectiveness of the proposed method, the method has been applied to a numerical example from litterateur and the results were satisfactory.