Using a fuzzy scheduling system for solving a dynamic job shop problem

This paper is concerned with the dynamic job shop scheduling problem with objective to minimize total weighted tardiness. A fuzzy system approach is proposed to dynamically guide the selection of dispatching rules for different problem instances by learning from fuzzy rules and previous solutions. Several experiments are designed and conducted in different scenarios to evaluate the effectiveness of the fuzzy scheduling system against traditional dispatching rules. Preliminary experimental results indicate that the fuzzy scheduling system is efficient and effective.