Abstract & Overview
Process parameters have direct influence on the flow behavior of melt and final part quality for injection molding, and the relationship between part quality and process conditions is very complex. So how to build the relationship model and get optimum process conditions is the key to improving part quality. Shrinkage is one of several important indexes determining the quality of injection molded parts, and non-uniform volumetric shrinkage in the cavity is an indication of potential warpage. A combination method of artificial neural network and hybrid genetic algorithm is proposed in this paper to optimize the process parameters and improve part quality. This ANN-HGA method is applied in an industrial product, and the volumetric shrinkage variation in the part is selected as quality index to optimize the process parameters. The results show that volumetric shrinkage variation in the part is minimized under the optimum process and the results are satisfied.