A Data-Driven Adaptive Scheduling Framework for Vehicle Maintenance Using Deep Reinforcement Learning
Downloads
This paper proposes a data-driven adaptive scheduling method based on the Deep Deterministic Policy Gradient (DDPG) algorithm to address the challenges that traditional vehicle dynamic maintenance scheduling methods struggle to cope with real-time, complex and resource optimization issues. A mathematical model of vehicle dynamic maintenance scheduling is constructed, defining the state space, action space and reward function. Then, the DDPG reinforcement learning framework is used to optimize strategies through the Actor-Critic structure. Contrastive experiments are also carried out in a simulation environment to evaluate the algorithm's performance. The results indicate that the DDPG algorithm achieves an average maintenance response time of 23.4 minutes, approximately 34% shorter than the genetic algorithm. Its resource utilization reaches 88.7%, over 13% higher than traditional methods. Moreover, the maintenance satisfaction score is 4.6 out of 5. The findings show that the algorithm has remarkable advantages in multi-objective scheduling optimization and provides feasible paths and technical support for the intelligence of vehicle dynamic maintenance systems.
Downloads
[1] Ma, X., Li, X., Zhang, J., Ma, Z., Jiang, Q., Liu, X., & Ma, J. (2025). Repairing Backdoor Model with Dynamic Gradient Clipping for Intelligent Vehicles. IEEE Transactions on Dependable and Secure Computing, 22(1), 804–818. doi:10.1109/TDSC.2024.3419040.
[2] Mayo, S. A., Shi, X., & Hu, Q. (2023). Computational fluid dynamic study on design and modification of underwater remotely operated vehicle. Journal of Physics: Conference Series, 2591(1), 012022. doi:10.1088/1742-6596/2591/1/012022.
[3] Luo, Q., Xu, Z., Zhang, Y., Igene, M., Bataineh, T., Soltanirad, M., Jimee, K., & Liu, H. (2025). Vehicle Trajectory Repair Under Full Occlusion and Limited Datapoints with Roadside LiDAR. Sensors, 25(4), 1114. doi:10.3390/s25041114.
[4] Eddy, C. W., Castanier, M. P., & Wagner, J. R. (2024). Predictive Maintenance of a Ground Vehicle Using Digital Twin Technology. SAE Technical Papers, 2024(4), 12. doi:10.4271/2024-01-2867.
[5] Fan, G., & Jiang, Z. (2023). Approach for Scheduling Automatic Guided Vehicles Considering Equipment Failure and Power Management. Journal of Marine Science and Application, 22(3), 624–635. doi:10.1007/s11804-023-00357-3.
[6] Zhang, F., Xu, G., Li, Z., & Li, M. (2023). Vehicle-bridge Interaction Analysis and Maximum Allowable Speed of a Deployable Emergency Repair Beam. KSCE Journal of Civil Engineering, 27(10), 4332–4351. doi:10.1007/s12205-023-1735-z.
[7] Liu, Y., Zuo, X., Ai, G., & Zhao, X. (2023). A construction-and-repair based method for vehicle scheduling of bus line with branch lines. Computers and Industrial Engineering, 178. doi:10.1016/j.cie.2023.109103.
[8] Fang, J., Chen, R., Chen, J., Xu, J., & Wang, P. (2023). A multi-objective optimisation method of rail combination profile in high-speed turnout switch panel. Vehicle System Dynamics, 61(1), 336–355. doi:10.1080/00423114.2022.2052327.
[9] Kuyu, Y. Ç., & Vatansever, F. (2024). A hybrid approach of ALNS with alternative initialization and acceptance mechanisms for capacitated vehicle routing problems. Cluster Computing, 27(10), 13583–13606. doi:10.1007/s10586-024-04643-9.
[10] Wang, Y., Lin, C., Zhao, B., Gong, B., & Liu, H. (2024). Trajectory-based vehicle emission evaluation for signalized intersection using roadside LiDAR data. Journal of Cleaner Production, 440, 140971. doi:10.1016/j.jclepro.2024.140971.
[11] Dalhatu, A. A., Saad, A. M., de Azevedo, R. C., & de Tomi, G. (2023). Remotely Operated Vehicle Taxonomy and Emerging Methods of Inspection, Maintenance, and Repair Operations: An Overview and Outlook. Journal of Offshore Mechanics and Arctic Engineering, 145(2). doi:10.1115/1.4055476.
[12] Tsallis, C., Papageorgas, P., Piromalis, D., & Munteanu, R. A. (2025). Application-wise review of Machine Learning-based predictive maintenance: Trends, challenges, and future directions. Applied Sciences, 15(9), 4898. doi:10.3390/app15094898
[13] Wang, W., Wang, X., Fu, J., Lu, Z., Zhou, R., Shao, Y., Wang, J., & Morgenthal, G. (2023). A novel frame-type crashworthy device for protecting bridge piers from vehicle collisions. Structures, 57. doi:10.1016/j.istruc.2023.105313.
[14] Zhang, J., Xu, W., Wang, J., Quan, Z., Su, L., Tan, W., Chen, T., & Liu, S. (2023). Comparative analysis of testing technologies in airfield pavement emergency repair. Journal of Shenzhen University Science and Engineering, 40(6), 693–704. doi:10.3724/SP.J.1249.2023.06696.
[15] Fu, W., Li, J., Liao, Z., & Fu, Y. (2025). A bi-objective optimization approach for scheduling electric ground-handling vehicles in an airport. Complex and Intelligent Systems, 11(4), 1–27. doi:10.1007/s40747-025-01815-x.
[16] Dolatabadi, A., Abdeltawab, H., & Mohamed, Y. A. R. I. (2022). Deep reinforcement learning-based self-scheduling strategy for a CAES-PV system using accurate sky images-based forecasting. IEEE Transactions on Power Systems, 38(2), 1608-1618. doi:10.1109/TPWRS.2022.3177704.
[17] Nian, T., Wang, M., Li, S., Li, P., & Song, J. (2024). Enhancing pavement structural resilience: analyzing the impact of vehicle-induced dynamic loads on RAP-recycled cement-stabilized crushed stone pavements with tip cracks. Materials and Structures/Materiaux et Constructions, 57(7), 1–20. doi:10.1617/s11527-024-02439-2.
[18] Chi, H., Sang, H. Y., Zhang, B., Duan, P., & Zou, W. Q. (2024). BDE-Jaya: A binary discrete enhanced Jaya algorithm for multiple automated guided vehicle-scheduling problem in matrix manufacturing workshop. Swarm and Evolutionary Computation, 89, 101651. doi:10.1016/j.swevo.2024.101651.
[19] Campbell, T. M., & Trudel, G. (2024). Protecting the regenerative environment: selecting the optimal delivery vehicle for cartilage repair—a narrative review. Frontiers in Bioengineering and Biotechnology, 12. doi:10.3389/fbioe.2024.1283752.
[20] Lou, P., Sun, Z., & Su, X. (2023). Temperature effects of ballastless track and dynamic responses of vehicle-track coupling system on tunnel floor with high temperature. Structures, 50, 1391–1402. doi:10.1016/j.istruc.2023.02.103.
[21] Guo, G., Hao, C., & Du, B. (2023). Static and dynamic response characteristics of a ballastless track structure of a high-speed railway bridge with interlayer debonding under temperature loads. Engineering Failure Analysis, 151. doi:10.1016/j.engfailanal.2023.107377.
[22] Toru, E., & Yılmaz, G. (2023). A multi-depot vehicle routing problem with time windows for daily planned maintenance and repair service planning. Pamukkale University Journal of Engineering Sciences, 29(8), 913–919. doi:10.5505/pajes.2023.99569.
[23] Wang, Q., Mao, J., Wen, X., Wallace, S. W., & Deveci, M. (2025). Flight, aircraft, and crew integrated recovery policies for airlines-A deep reinforcement learning approach. Transport Policy, 160, 245-258. doi:10.1016/j.tranpol.2024.11.011.
[24] Sun, Z., Jiao, J., Li, W., Li, Z., & Li, P. (2022). A task scheduling strategy for a power cloud data center based on an improved ant colony algorithm. Power System Protection and Control, 50(2), 95–101. doi:10.19783/j.cnki.pspc.210466.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
