Towards a knowledge-based scheduling system for semiconductor testing

This paper describes our efforts towards the development of a knowledge-based scheduling system for the scheduling of semiconductor testing operations. Semiconductor testing is the final phase of a four-phase semiconductor manufacturing process. The scheduling problem is a static deterministic version of what we call the workstation scheduling problem (WS). WS can be characterized as a generalized job shop problem with both parallel workstation clusters and batch processors; it requires sequencing and routeing decisions on discrete (i.e. nonbatch) and batch workstations. The proposed system consists of two distinct components: a knowledge base developed using a frame-based knowledge representation scheme, and a solution strategy based on filtered beam search. The scheduling mechanism and the associated knowledge representation scheme have been implemented on a Sun Sparc station 1+ using the programming language Common Lisp. We report on our experience to date with the system on three dimensions: computational experience, decision support capability, and knowledge management. Further research directions are suggested.