DE SCHEDULING PREVENTIVE MAINTENANCE WITHIN A QUEUE TIME FOR MAXIMUM THROUGHPUT IN SEMICONDUCTOR MANUFACTURING

We address the PM-QT problem, of scheduling preventive maintenance (PM) activities on tools within queue time (QT) restrictions, such that the overall throughput is maximized and the QT restrictions are not violated. Despite the increased occurrences of QT in semiconductor manufacturing, this problem has not been explicitly addressed. We formulate this problem as a mixed integer linear program (MILP) and propose a cross-entropy (CE) heuristic approach for its efficient solution. We show that the CE solutions are indeed efficient in runtime reductions with almost no compromise of the solution's quality (less than 1% difference between MILP and CE solutions for large scale problems).