A microcomputer expert system for advising on stocks in spare parts inventory systems

This paper describes the development and application of a logistic expert system for advising on the stocks of spare parts in inventory systems. The expert system designed, called SPARTA, is efficient and simple microcomputer application software and uses a standard programming environment and PC Plus as AI tool. SPARTA is a rule-based expert system consisting of a knowledge base and an inference engine. It combines causal knowledge and surface knowledge which allows a condensed design of the knowledge base. SPARTA’s domain of expertise is restricted to the items for which the exponential distribution of times between failures can be assumed. SPARTA’s output includes: (1) the list of recommended stocks, (2) the effectiveness of investment in spares, and (3) suggestions concerning further investment in spare parts.