Most studies on distributed flexible job shop scheduling problem (DFJSP) assume that both processing time and transmission time are crisp values. However, due to the complexity of the factory processing environment, the processing information is uncertain. Therefore, we consider the uncertainty of processing environment, and for the first time propose a multiobjective distributed fuzzy flexible job shop scheduling problem with transfer (MO-DFFJSPT). To solve the MO-DFFJSPT, a hybrid decomposition variable neighborhood memetic algorithm (HDVMA) is proposed with the objectives of minimizing the makespan, maximum factory load, and total workload. In the proposed HDVMA, the well-designed encoding/decoding method and four initialization rules are used to generate the initial population, and several effective evolutionary operators are designed to update populations. Additionally, a weight vector is introduced to design high quality individual selection rules and acceptance criteria. Then, three excellent local search operators are designed for variable neighborhood search (VNS) to enhance its exploitation capability. Finally, a Taguchi experiment is designed to adjust the important parameters. Fifteen benchmarks are constructed, and the HDVMA is compared with four other famous algorithms on three metrics. The experimental results show that HDVMA is superior to the other four algorithms in terms of convergence and uniformity of non-dominated solution set distribution.
21 November 2025 in Transportation Research Part E: Logistics and Transportation Review
This paper introduces an adaptive multi-objective evolutionary algorithm (MBEA) with a memory mechanism to solve the resolution of the fuzzy flexible job shop scheduling problem. The algorithm aims to minimize both the maximum completion time and energy consumption. In contrast to the conventional polling local search approach, the algorithm employs a technique of dynamically choosing local search strategies. This enhances the overall optimization capacity and quality of solutions, while also reducing the search duration. This work presents a memory-based strategy as a solution to the issue commonly observed in traditional MOEA/D, where potential high-quality solutions are often lost during the iteration process. The proposed strategy aims to store solutions with promising properties, thereby enhancing the convergence speed of the algorithm and mitigating the risk of the algorithm getting stuck in local optimization. A comprehensive strategy is proposed that incorporates five initialization rules to ensure the generation of a high-quality initial population. This strategy is further enhanced by implementing an elite archiving strategy to effectively cover the Pareto frontiers. Extensive experimentation was carried out on 23 datasets of varying sizes. The results of the experiments indicate that the enhanced algorithm exhibits notably superior performance compared to the other five widely recognized evolutionary algorithms. This research outcome not only introduces a novel and efficient approach for addressing the fuzzy flexible job shop scheduling issue but also holds significant practical value and provides guidance for scheduling decisions in real-world industrial production scenarios.