Parameter design optimization via neural network and genetic algorithm

Abstract

Among the many extensive industrial applications which parameter design optimization problems have found include product development, process design and operational condition settings. The parameter design optimization problems are complex owing to that nonlinear relationships and interactions may occur among parameters. To resolve such problems, engineers commonly employ the Taguchi method. However, the Taguchi method has some limitations in practice. Therefore, in this work, we present a novel means of improving the effectiveness of the optimization of parameter design. The proposed approach employs the neural network and generic algorithm, and consists of two phases. Phase 1 formulates a fitness function for a problem by a neural network method to predict the value of the response for a given parameter setting. Phase 2 applies a genetic algorithm to search for the optimal parameter combination. A numerical example demonstrates the effectiveness of the proposed approach. Significance: This work provides an efficient approach to optimize the parameter design problems, which is relatively simple and is fairly easy for engineers to apply to diverse industrial applications.