Warpage optimization of fiber-reinforced composite injection molding by combining back propagation neural network and genetic algorithm

Warpage is an important index in measuring part quality in the short fiber-reinforced composite injection molding process. In addition to process parameters, fiber parameters have an important influence on part warpage. In this study, the objective function is a minimum problem of the warpage. The design parameters include fiber aspect ratio, fiber content, injection time, melt temperature, mold temperature, and holding pressure. The combined back propagation neural network (BPNN) and genetic algorithm (GA) approach is proposed to optimize the fiber-reinforced composite injection molding process. On the basis of orthogonal experiment design, Moldflow software is applied in the short fiber-reinforced composite injection molding process. The importance of various parameters on the influence of warpage is researched by the range analysis method. Thereafter, a back propagation neural network model is developed on the basis of the simulation results to map the complex nonlinear relationship between design parameters and warpage. The GA is interfaced with this predictive model to improve the warpage significantly by optimizing the design parameters. A case study of a part is presented. The optimum values of design parameters are determined to minimize the warpage. Results show that the combined BPNN/GA approach is an effective method for the warpage optimization of fiber-reinforced composite injection molding.