复杂产品总装拉动式多车间协同调度的集成式遗传规划算法

doi:10.3901/JME.260226

摘要/Abstract

摘要： 复杂产品制造当前面临生产规模增加、定制化程度上升与生产周期缩短等发展趋势，亟需探索更高效的调度方法以提升生产效率与支撑发展需求。然而，复杂产品制造常见的总装拉动式生产模式需要多个车间协同生产，具有规模大、资源多、逻辑复杂等特征，现有多车间调度模型与方法难以满足算法优化与响应能力要求。为此，通过考虑车间内部约束与耦合约束，构建一种复杂产品总装拉动式多车间协同调度模型。在此基础上，通过考虑不同车间特性，提出一种基于小生境的多优先级规则集合协同集成式遗传规划算法，以通过生成多个调度规则集合构成更有效的调度策略。此外，构建一种基于互补性的规则集合更新机制来提升生成规则集合有效性，并设计一种多车间次序解码策略以获取完整的多车间调度方案。基于实际场景分析，采用PSPLIB标准数据集构建该问题的数据集，通过与当前最新的遗传规划算法和现有优先级规则对比，并结合消融试验，验证所提算法的优越性。

关键词: 总装拉动, 多车间协同调度, 遗传规划, 集成学习, 优先级规则

Abstract: The complex products is experiencing trends of increasing production scale, higher levels of customization, and shorter production cycles, requiring more efficient scheduling techniques to enhance production efficiency and meet future development needs. However, the final assembly pull production mode for complex products requires the collaboration of multiple workshops. Its characteristics, including large scale, abundant resources, and complex process logic, result in existing multi-workshop scheduling models and methods being inadequate to meet the demands in terms of solution quality and response speed. To address this issue, a multi-workshop collaborative scheduling model for complex product with final assembly pull is constructed, considering both internal constraints and coupling constraints across workshops. Based on this model and considering the characteristics of different workshops, a niche-based ensemble genetic programming with multiple priority rule sets is proposed to construct a more effective scheduling strategy by generating multiple scheduling priority rule sets. Additionally, a complementary priority rule set update mechanism is constructed to enhance the effectiveness of the generated priority rule sets, and a multi-workshop sequencing decoding mechanism is designed to obtain a complete multi-workshop scheduling solution. Through an analysis of real-world scenarios, a dataset based on the PSPLIB standard is constructed, and a comparative study with the latest genetic programming and manually designed priority rules, along with ablation experiments, is conducted to thoroughly validate the advantages of the proposed algorithm.

Key words: assembly pull, multi-workshop collaborative scheduling, genetic programming, ensemble learning, priority rule

中图分类号:

TP182

李继伟, 张剑, 任晓羽, 陈浩杰. 复杂产品总装拉动式多车间协同调度的集成式遗传规划算法[J]. 机械工程学报, 2026, 62(5): 37-48.

LI Jiwei, ZHANG Jian, REN Xiaoyu, CHEN Haojie. Ensemble Genetic Programming for Complex Products Multi-workshop Collaborative Scheduling Problem with Final Assembly Pull[J]. Journal of Mechanical Engineering, 2026, 62(5): 37-48.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260226

http://www.cjmenet.com.cn/CN/Y2026/V62/I5/37

参考文献

[1] ILDIRIM M，OZOY F N，OZPOLAT A，et al. Comparative analysis of competition power in high technology and low technology intensive manufactures[J]. International Journal of Innovation and Economic Development，2017，3(4):41-52.
[2] 任杉，王晋，赵欣，等. 复杂产品智能设计与主动运维“双馈式”制造服务方法体系[J]. 机械工程学报，2024，60(6):127-136. REN Shan，WANG Jin，ZHAO Xin，et al. Intelligent design and proactive operation and maintenance "dual-feedback" manufacturing service method system[J]. Journal of Mechanical Engineering，2024，60(6):127-136.
[3] 朱海华，付泰然，李霏，等. 基于数字孪生的复杂产品装配物料过程齐套时间预测[J]. 机械工程学报，2025，61(8):384-398. ZHU Haihua，FU Tairan，LI Fei，et al. Prediction of material process synchronization time for complex product assembly based on digital twin[J]. Journal of Mechanical Engineering，2025，61(8):384-398.
[4] LIN C，WEI H，ZHENGXIN Z，et al. Manufacturing resource management and control for production site of complex products[J]. Transactions of Nanjing University of Aeronautics & Astronautics，2024，41(6):806-818.
[5] 孙甜. 拉动式造船涂装生产计划研究[J]. 船舶物资与市场，2024，32(1):61-63. SUN Tian. Research on pull shipbuilding coating production planning[J]. Shipbuilding Materials and Market，2024，32(1):61-63.
[6] LU C，GAO L，YI J，et al. Energy-efficient scheduling of distributed flow shop with heterogeneous factories:A real-world case from automobile industry in China[J]. IEEE Transactions on Industrial Informatics，2020，17(10):6687-6696.
[7] NADERI B，RUIZ R. The distributed permutation flow shop scheduling problem[J]. Computers & Operations Research，2010，37(4):754-768.
[8] SHAO W S，SHAO Z S，PI D C. Modeling and multi-neighborhood iterated greedy algorithm for distributed hybrid flow shop scheduling problem[J]. Knowledge-based Systems，2020，194:105527.
[9] JIA H Z，FUH J Y，NEE A Y，et al. Web-based multi-functional scheduling system for a distributed manufacturing environment[J]. Concurrent Engineering，2002，10(1):27-39.
[10] CHAN F T，CHUNG S H，CHAN P L Y. Application of genetic algorithms with dominant genes in a distributed scheduling problem in flexible manufacturing systems[J]. International Journal of Production Research，2006，44(3):523-543.
[11] 方子丞，李新宇，高亮. 带负载均衡的混合算法求解分布式异构作业车间调度问题[J]. 控制理论与应用，2024(6):977-989. FANG Zicheng，LI Xinyu，GAO Liang. Hybrid algorithm with load balancing for solving distributed heterogeneous job shop scheduling problem[J]. Control Theory and Applications，2024(6):977-989.
[12] QIAO L，ZHANG Z，HUANG Z. A scheduling algorithm for multi-workshop production based on BOM and process route[J]. Applied Sciences，2021，11(11):5078.
[13] 李修琳，鲁建厦，柴国钟，等. 基于混合遗传算法的混流混合车间协同调度问题[J]. 中国机械工程，2012，23(8):935-940. LI Xiulin，LU Jianxia，CHAI Guozhong，et al. Collaborative scheduling problem of mixed-flow hybrid workshop based on hybrid genetic algorithm[J]. China Mechanical Engineering，2012，23(8):935-940.
[14] 廖不凡，雷琦，吴文烈，等. 基于混合教学优化算法的多车间协作综合调度[J]. 中国机械工程，2020，31(16):1940-1949. LIAO Bufan，LEI Qi，WU Wenlie，et al. Multi-shop collaborative integrated scheduling based on hybrid teaching optimization algorithm[J]. China Mechanical Engineering，2020，31(16):1940-1949.
[15] 王艳红，尹涛，谭园园，等. 基于规则与Q学习的作业车间动态调度算法[J]. 计算机集成制造系统，2024，30(10):3535-3546. WANG Yanhong，YIN Tao，TAN Yuanyuan，et al. A dynamic scheduling algorithm for job shop based on rules and Q-learning[J]. Computer Integrated Manufacturing Systems，2024，30(10):3535-3546.
[16] SHAN S，HU Z，LIU Z，et al. An adaptive genetic algorithm for demand-driven and resource-constrained project scheduling in aircraft assembly[J]. Information Technology and Management，2017，18:41-53.
[17] ZHANG F，MEI Y，NGUYEN S，et al. Survey on genetic programming and machine learning techniques for heuristic design in job shop scheduling[J]. IEEE Transactions on Evolutionary Computation，2023，28(1):147-167.
[18] SU X，CUI R，LI C，et al. A heuristic solution framework for the resource-constrained multi-aircraft scheduling problem with transfer of resources and aircraft[J]. Expert Systems with Applications，2023，228:120430.
[19] CHEN H，LI X，GAO L. A surrogate-assisted dual-tree genetic programming framework for dynamic resource constrained multi-project scheduling problem[J]. International Journal of Production Research，2024，62(16):5631-5653.
[20] NGUYEN S，MEI Y，XUE B，et al. A hybrid genetic programming algorithm for automated design of dispatching rules[J]. Evolutionary Computation，2019，27(3):467-496.
[21] FRIEDLANDER A，NESHATIAN K，ZHANG M. Meta-learning and feature ranking using genetic programming for classification:Variable terminal weighting[C]//2011 IEEE Congress of Evolutionary Computation. New Orleans:IEEE，2011，941-948.
[22] MEI Y，ZHANG M，NGUYEN S. Feature selection in evolving job shop dispatching rules with genetic programming[C]//Proceedings of the Genetic and Evolutionary Computation Conference 2016. Denver:ACM，2016，365-372.
[23] SITAHONG A，YUAN Y，MA J，et al. Effective and interpretable rule mining for dynamic job-shop scheduling via improved gene expression programming with feature selection[J]. Applied Sciences，2023，13(11):6631.
[24] LI X，ZHAO Q，TANG H，et al. Flexible job shop composite dispatching rule mining approach based on an improved genetic programming algorithm[J]. Tsinghua Science and Technology，2024，29(5):1390-1408.
[25] CHEN H，LI X，GAO L. A guided genetic programming with attribute node activation encoding for resource constrained project scheduling problem[J]. Swarm and Evolutionary Computation，2023，83:101418.
[26] HU M，CHEN Z，XIA Y，et al. Rules mining-based gene expression programming for the multi-skill resource constrained project scheduling problem[J]. CMES- Computer Modeling in Engineering & Sciences，2023，136(3):2815-2840.
[27] HILDEBRANDT T，BRANKE J. On using surrogates with genetic programming[J]. Evolutionary Computation，2015，23(3):343-367.
[28] LUO J，VANHOUCKE M，COELHO J. Automated design of priority rules for resource-constrained project scheduling problem using surrogate-assisted genetic programming[J]. Swarm and Evolutionary Computation，2023，81:101339.
[29] PARK J，MEI Y，NGUYEN S，et al. An investigation of ensemble combination schemes for genetic programming based hyper-heuristic approaches to dynamic job shop scheduling[J]. Applied Soft Computing，2018，63:72-86.
[30] ĐUMIĆ M，JAKOBOVIĆ D. Ensembles of priority rules for resource constrained project scheduling problem[J]. Applied Soft Computing，2021，110:107606.
[31] CHEN H，DING G，QIN S，et al. A hyper-heuristic based ensemble genetic programming approach for stochastic resource constrained project scheduling problem[J]. Expert Systems with Applications，2021，167:114174.
[32] PÉTROWSKI A. A clearing procedure as a niching method for genetic algorithms[C]//Proceedings of IEEE International Conference on Evolutionary Computation. Nagoya:IEEE，1996，798-803.
[33] GUO W，VANHOUCKE M，COELHO J，et al. Automatic detection of the best performing priority rule for the resource-constrained project scheduling problem[J]. Expert Systems with Applications，2021，167:114116.
[34] CHAND S，HUYNH Q，SINGH H，et al. On the use of genetic programming to evolve priority rules for resource constrained project scheduling problems[J]. Information Sciences，2018，432:146-163.
[35] KOZA J R G P. Genetic programming:On the programming of computers by means of natural selection [M]. America:The MIT Press，1992.
[36] BROOKS G H. An algorithm for finding optimal or near optimal solutions to the production scheduling problem[J]. The Journal of Industrial Engineering，1969，16(1):34-40.
[37] CHEN H J，ZHANG J，LI R，et al. A two-stage genetic programming framework for stochastic resource constrained multi-project scheduling problem under new project insertions[J]. Applied Soft Computing，2022，124:109087.
[38] SPRECHER A，KOLISCH R. PSPLIB—a project scheduling problem library[J]. European Journal of Operational Research，1996，96:205-216.
[39] 陈浩杰，丁国富，张剑，等. 求解资源受限多项目调度的改进遗传规划算法[J]. 中国机械工程，2021，32(10):1213-1221. CHEN Haojie，DING Guofu，ZHANG Jian，et al. Improved genetic programming algorithm for resource-constrained multi-project scheduling[J]. China Mechanical Engineering，2021，32(10):1213-1221.