A knowledge-base self-learning system

Expert systems in general require long development periods and are subject to knowledge obsolescence. This is particularly true in the case of assembly, where large sets of data and heuristics are inevitable. This paper employs a limited set of expert knowledge and develops a Knowledge-Base Self-Learning (KBSL) system to generate new knowledge. The system has two functions, Prstly to evaluate sequences and prioritise for further evaluation by Reinforcement Learning (RL), and secondly, to self generate new knowledge. This new knowledge is then available to combine with existing knowledge for evaluating and prioritising product sequences. A key contribution of this self-learning technique, is establishing new knowledge, and adding this to the knowledge-base for application to new assembly sequence evaluations. One outcome of this approach is the requirement for complete knowledge is less onerous. However, a tradeoff between initial depth of knowledge coded and expert system performance must be considered. The method developed here was intended as a component in a hybrid system.