A NN-based expert system for the forging design of steering knuckles

Basic architecture, knowledge express and reasoning mode of the NN-based (neural network based) expert system are studied in this paper. The design theories, experience knowledge of the forging process and artificial intelligence technology are unified to develop the FDesign-SK (Expert system for the forging design of the steering knuckle) software. The experiential knowledge extracted from kinds of forging samples of steering knuckles is stored in this system. The framework of the system is modularization, which makes the interface operate easily. FDesign-SK is a system of opening design and good self-training function. Therefore, the training samples could be expanded to improve forecast accuracy and stability of the system. The forging design of steering knuckles assisted with FDesign-SK could shorten development period, lower cost and reduce workload of the designer.