考虑外包混合形式的TOC产品组合优化研究

Multiform Hybrid Decision for TOC Product Mix Optimization with Extending Capacity of Outsourcing Based on Immune Algorithm

首先,根据外包的两种形式(带料外包、不带料外包)研究了外包混合形式下产品组合优化的建模问题,并通过数学证明其有效产出最优。其次,应用免疫算法(IA)对其进行了优化求解,在合理时间内得到大、小规模产品组合决策的最优解或近优解。最后,将本算法与传统TOCh、修订TOCh、整数规划(IP)、禁忌搜索(TS)、遗传算法(GA)等进行了仿真比较,证明了本算法的有效性和实用性。

The theory of constraints （TOC） product mix problems considering the extending capacity of outsourcing that involves determination of the quantity and the identification of each product to make or buy is one of the most fundamental decisions in a manufacturing plant. First, the multiform hybrid decision for TOC product mix optimization with the extending capacity of outsourcing is described and modeled for meeting the customs＇ demands and maximizing system throughput. Furthermore, a theorem is proved, which is that the throughput of product mix optimization synthesizing these two outsourcing forms simultaneously are more outstanding than the others that only consider one form of outsourcing in TOC product mix optimization. Second, an intelligent search approach based on immune algorithm （IA） and TOC （IA_TOC_Ⅱ） is introduced to identify the optimal or near optimal product mix for small or large problem instances under conditions where the original TOC heuristic （TOCh） failed. In the case, the immune response mechanism based the explicit optimizing process of TOCh, combining with immune selection mechanism, immune self adaptive regulation mechanism and vaccination mechanism ensures that the immune evolution always moves forward the direction of optimization in feasible space, and promotes that the proposed IA_TOC_Ⅱ approach achieves the optimal or near optimal solutions for small or large size product mix problems in reasonable times. Comparing the results of the IA-TOC_Ⅱ approach with other published approaches in literatures, including the original TOCh, revised TOCh, integer programming IP, tabu search （TS）, and genetic algorithm （GA）, the simulation tests prove that the IA-TOC_Ⅱ approach outperforms other published approaches. Therefore, the proposed approach is appropriate for adoption by production planners or mangers for the multiform hybrid decision for TOC product mix optimization with the extending capacity of outsourcing in the manufacturing plant.