A JOB-SPLITTING HEURISTIC FOR LOT-SIZE SCHEDULING IN MULTISTAGE, MULTIPRODUCT PRODUCTION PROCESSES

This paper focuses primarily on cyclic scheduling in multi-stage, multi-product production. Cyclic schedules are generalizations of common cycle schedules (CCSP) in which the cycle time for each product is required to be an integer multiple (not necessarily one as in the CCSP) of the base cycle time. Solution procedures which have been reported in literature for this problem ignore in-process inventory and are limited to single-stage and/or single-product production processes. After reviewing the literature, this paper presents an efficient heuristic procedure which generates near-optimal cyclic schedules for the multi-product, multi-stage flow shop production environment under deterministic and stationary conditions. This procedure accounts for all inventory costs including in-process inventory and idle time. The proposed solution is then compared to the optimal CCSP solution developed by El-Najdawi and Kleindorfer and, as expected, performed significantly better than the traditional CCSP approach. Compared to other heuristics studied in the literature, this procedure appears to be more useful as a computable and cost-efficient approach for practical size applications.