Intelligent Process Planning Using a Machine Learning Approach

Abstract

Abstract This paper presents a framework for integrating the paradigm of case-base reasoning with the knowledge based approach in intelligent process planning. The proposed case based system uses process planning cases to represent the process planning knowledge and possesses self-learning capability in the sense that it develops its knowledge from the past and the new planning experiences. It therefore can overcome some weakness in the knowledge-based expert systems. The proposed framework combines the strength of both the case base reasoning and knowledge based reasoning approaches. The case based system contains four major elements: retriever, modifier, simulator and repairer . A feature based representation scheme is used to represent and index process planning cases in the system's memory. The retriever uses a similarity metric to retrieve an old case which is the most similar case, among all old ones, to the new case. The modifier is then activated to adapt the process plan of the retrieved case to fit the needs for the new case. The simulator is used to verify the feasibility of the modified plan. If the modified plan is proven to be infeasible, the repairer will be used to repair the failed plan. The knowledge based system is used as a complementary unit to assist the case based system in the framework. In this paper, rotational parts are used to show how the four elements in the case based system integrated with the knowledge based system can be used to support learning capability in automated process planning.