Multi-pass expert control system - a control/scheduling structure for flexible manufacturing cells

Abstract Expert systems are currently being touted as a means to resolve manufacturing scheduling problems. Unfortunately, the expert systems developed to date are neither generic nor are they responsive enough to be used for on-line system control. In this paper, a control structure is outline which takes advantage of both expert system technology and discrete event stimulation. The simulation is used as a prediction mechanism to evaluate several possible control alternatives provided by the expert system. A performance measure is obtained from the simulation for each of the suggested alternatives. A control effector is then employed to affect the physical control of the cell based on the measured. This performance measure is worth a great deal of domain-specific knowledge that otherwise would have to be included in the expert system knowledge base. The integration of the expert control system, the simulation, and the control effectorsform a system called a multipass expert control system (MPECS). MPECS is designed for the control and scheduling of flexible manufacturing cells. Experiments to evaluate the performance of MPECS have yielded advantages of between 2.3% to 29.3% compared to single-pass, single-rule priority dispatching and multipass, multirule dispatching procedures.