Development of a Case-Based Reasoning expert system for the disturbance management in automated guided vehicle systems

Abstract

Automated guided vehicle systems (AGVS) are an essential part of modern intralogistics. So far, the major part of the design cycle (implementation and operation) of an AGVS demands human expertise. Especially, the manually executed management of occurring disturbances leads to high maintenance costs since it often requires the consultation of experts. Therefore, the following paper discusses the development of a Case-Based Reasoning (CBR) expert system for assisting the disturbance management in AGVS. The development is sectioned into three major parts: (1) generation of the case-base, (2) development of the algorithms for case retrieval, case adaptation and retaining new cases and (3) the validation of the expert system. The generation of the case-base and the training data for the expert system is done by simulating the real production layout of a German white good manufacturer using the simulation environment Visual Components. The solutions for the simulated disturbances as well as the adaptation algorithms are based on knowledge extracted from system experts.