Author name cluster

Qianwang Deng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2026 Journal Article

A knowledge-based memetic algorithm for integrated scheduling of equipment operation and spare parts manufacturing in distributed assembly flexible job shops

Wenxiang Jiang
Qianwang Deng
Qiang Luo
Jingxing Zhang
Jicong Zhou

Under the development context of Industry 4. 0, researches on the integration of equipment operation and maintenance (O&M) activities with spare parts manufacturing have garnered increasing attention. Meanwhile, new challenges emerge in spare parts manufacturing due to the increasing complexity of equipment. However, existing integrated scheduling studies have been simplified in the spare parts manufacturing, making it difficult to cope with actual spare parts replacement scenarios of complex equipment. To address this gap, this paper investigates an integrated scheduling problem (ISP-PAO) that includes distributed flexible production, flexible assembly, and operational strategies of complex equipment. We formalize the ISP-PAO through a mathematical model with dual objectives of minimizing total energy consumption and maximizing operational utility. Furthermore, several problem-specific knowledge properties are systematically analyzed and proved, and a knowledge-based memetic algorithm (KBMA) is further proposed to solve the problem. To strengthen optimization capability, the algorithm incorporates four initialization strategies, five knowledge-based local search operators and an energy-aware pareto front refinement strategy. Extensive experiments validate the effectiveness of proposed components, and comparative studies comprehensively evaluate the superiority and robustness of the KBMA, demonstrating its exceptional performance in addressing the ISP-PAO.

Details DOI

EAAI Journal 2025 Journal Article

Deep reinforcement learning for dynamic scheduling in distributed heterogeneous flexible job shop with integrated inventory allocation and product delivery

Liuran Lu
Qianwang Deng
Yangyang Hu
Qiang Luo
Shuocheng Gao
Jingxing Zhang

Traditional scheduling primarily emphasizes machine flexibility and is conducted in static environments. However, in practical production environments, customer orders can be supplied either through direct production or from warehouse inventory, with order delivery depending on logistics vehicles scheduling. Furthermore, to ensure product quality, inspection procedures must be conducted prior to delivery, and unqualified products must be reworked. Therefore, this study investigates a dynamic distributed heterogeneous flexible job shop scheduling problem (DDHFJSP-IAT) that incorporates inventory allocation, quality inspection, and product delivery. First, a mixed-integer linear programming (MILP) model is formulated to simultaneously minimize total costs and total delay penalty. Second, an Improved Rescheduling Method (IRSM) is proposed to address the challenges associated with product inspection and rework. Third, a dual-population memetic algorithm based on the Double Deep Q-Network (D2QDMA) is proposed to solve the DDHFJSP-IAT. This algorithm incorporates a six-layer chromosome encoding scheme, twelve neighborhood search operators based on the problem characteristics, and a cost-saving strategy. The Double Deep Q-Network (DDQN) is employed to dynamically select the most appropriate neighborhood search operators, and 65 normalized state features are extracted to construct the state space. Finally, extensive experiments are conducted utilizing 46 newly formulated benchmark instances. The results confirm the consistency between the MILP model and the D2QDMA, demonstrating that the D2QDMA outperforms five well-known comparison algorithms over 75 % of the instances regarding diversity, convergence, and uniformity, thereby validating its effectiveness and superiority in solving the DDHFJSP-IAT.

Details DOI

EAAI Journal 2023 Journal Article

Optimal production scheduling with multi-round information interaction for demander-dominated decentralized scheduling problem

Like Zhang
Qianwang Deng
Xiaoyu Wen
Yan Zhao
Guiliang Gong

Demander-dominated market scenarios are becoming increasingly common owing to the emergence of alternative service providers and competitive market environment. However, these scenarios have not been considered in previous studies pertaining to decentralized scheduling problems. Thus, service providers cannot formulate optimal production scheduling schemes for such scenarios. In this study, we investigate a demander-dominated decentralized scheduling problem in which the demander can adopt the private-strategic behavior of transferring partial orders towards its alternative service providers. The aim of this study is to provide guidance to service providers for developing high-quality production scheduling solutions under asymmetric information. First, we design a multi-round information interaction mechanism with a learning strategy to realize information interaction. Subsequently, a metaheuristic algorithm termed MAM is developed based on the multi-round information interaction mechanism to solve the proposed problem. A problem-dependent initialization method and a solution generation method integrating the learning strategy are developed to improve the search efficiency. Experimental results indicate the usefulness of the initialization method and learning strategy. Based on a comparison with two well-established adapted algorithms, the effectiveness of the proposed algorithm is confirmed, particularly for instances with loose due dates. Furthermore, we analyze the effect of MAM on both the service provider and the demander by comparing it with traditional centralized approaches. Statistical results show that the proposed algorithm yields high-quality solutions for the service provider and that maintaining the confidentiality of private information is conducive to the demander, particularly when the due dates are tight.

Details DOI

EAAI Journal 2021 Journal Article

Energy-efficient production scheduling through machine on/off control during preventive maintenance

Guiliang Gong
Raymond Chiong
Qianwang Deng
Wenwu Han
Like Zhang
Dan Huang

This paper studies an important extension of energy-efficient production scheduling research, where machine on/off control and machine maintenance are considered simultaneously. The inspiration of this extension is that a machine must be turned off if it needs to be maintained, and an already-turned-off machine can be maintained without needing to be restarted. We therefore formulate an energy-efficient production scheduling problem with machine maintenance through machine on/off control, aiming to optimise three objectives – the makespan, total number of machine restarts, and energy consumption – at the same time. Four rules are designed to set the machine on/off criteria, maintenance periods and predefined maintenance windows, based on solutions of the job shop scheduling problem (JSP) as a test case. Three heuristics are proposed to insert the maintenance activities into the solutions and move their maintenance-operation blocks to optimise the objectives. The effectiveness of the first rule and the moving of maintenance-operation blocks have been proven mathematically. Our proposed heuristics, unlike traditional heuristic algorithms, are expected to be applicable and effective even if we change the objectives and constraints, require minimal computational time (only a few seconds) to optimise a scheduling solution, and can solve different types of scheduling problems without needing any modification. Experiments undertaken indicate promising performance of the proposed heuristics based on 182 JSP benchmark instances.

Details DOI