AdaBoost-inspired co-evolution differential evolution for reconfigurable flexible job shop scheduling considering order splitting

Abstract

With the increasing demand for personalized and diversified products, manufacturing industries are in urgent need of taking measures to reduce the differences among products and enhance flexibility and reconfigurability so as to accommodate these personalized and diversified products. Consequently, this research focuses on the reconfigurable flexible job shop scheduling problem with order splitting taken into consideration. A mixed-integer linear programming model is proposed with the aim of minimizing tardiness costs, reconfiguration costs and energy costs. To solve this problem efficiently, a co-evolution differential evolution algorithm is developed, which is enhanced by an AdaBoost-inspired multiple mutation strategies ensemble mechanism (AMMSE), an AdaBoost-inspired adaptive crossover mechanism (AAC), rule-based initialization, and variable neighborhood search. Among them, AMMSE can effectively ensemble the advantages of different mutation strategies by adaptively selecting a proper number of chromosomes to train mutation strategies with different performance weights. AAC can adaptively control the crossover rate of each gene by evaluating the average importance score of each gene based on the performance weight distribution of chromosomes. Experimental results demonstrate that combining the above improvements can significantly boost the performance of the differential evolution algorithm. As a result, the enhanced algorithm outperforms other state-of-the-art algorithms by a large margin. By using the enhanced algorithm to solve the studied problem, nearly 1.1 times of production costs can be saved.