A hybrid neural network and genetic algorithm approach to the determination of initial process parameters for injection moulding

Determination of the initial process parameters for injection moulding is a highly skilled task and is based on a skilled operator's "know-how" and in tuitive sense acquired through long-term experience rather than on a theore tical and analytical approach. In the face of global competition, the curre nt trial-and-error practice is inadequate. In this paper, a hybrid neural n etwork and genetic algorithm approach is described to determine a set of in itial process parameters for injection moulding. A hybrid neural network an d genetic algorithm system for the determination of initial process paramet er settings for injection moulding based on the proposed approach was devel oped and validated. The preliminary validation test of the system has indic ated that the system can determine a set of initial process parameters for injection moulding quickly, from which good quality moulded parts can be pr oduced without relying on experienced moulding personnel.