The development of a consultation expert system for metal materials processing and manufacturing

In this paper, a research work on the development of a consultation expert system for metal materials processing and manufacturing (ESMMPM) is presented, which can be run under Chinese DOS and programmed by PROLOG and C. A three–dimensional domain framework consisting of surface processing technologies, failure types, and machine components is proposed, from which the expert knowledge can be acquired. A method of combining predicate logic with production rules is applied to represent knowledge. A hybrid inference strategy is employed in which backward inference computation is used as a major tool, and forward inference as an auxiliary one. The knowledge base can be easily updated, deleted and added to in operation. The development of a cold forming tools subsystem has been completed, and the further development work based on neural networks and genetic algorithms is continuing.