面向工程机械的数字孪生与PHM融合技术综述
A Review on the Integration of Digital Twin and PHM for Construction Machinery
摘要: 针对工程机械在恶劣多变工况下传统故障预测与健康管理(PHM)面临动态适应性差、故障样本稀缺、机理解释困难及闭环决策弱等瓶颈，本文系统综述数字孪生与PHM的深度融合进展，梳理面向工程机械的DT-PHM通用参考架构，并分析其向“云–边–端”协同、微服务解耦、多维物理映射的演进趋势；同时以机理与数据深度融合为主线，剖析了基于实时数据的孪生模型动态修正、虚实协同故障诊断、物理内嵌机器学习寿命预测以及面向维修决策的健康评估与策略优化四类代表性前沿方法，为工程机械从被动维护向全局最优预测性维护转型提供理论支撑与工程指南。
Abstract: Aiming at the bottlenecks of traditional Prognostics and Health Management (PHM) for construction machinery under harsh and variable operating conditions, including poor dynamic adaptability, scarce fault samples, difficulties in mechanism interpretability, and inadequate closed-loop decision-making, this paper systematically reviews the progress of deep integration between digital twin (DT) and PHM. A general reference architecture of DT-PHM for construction machinery is proposed, and its evolution trends toward cloud-edge-end collaboration, microservice decoupling, and multi-dimensional physical mapping are summarized. Taking the deep integration of mechanism and data as the main thread, this paper further analyzes four representative cutting-edge approaches: dynamic correction of twin models based on real-time data, virtual-physical collaborative fault diagnosis, physics-embedded machine-learning-based remaining-useful-life prediction, as well as health assessment and strategy optimization for maintenance decision-making. This research provides theoretical support and engineering guidance for the transformation of construction machinery from reactive maintenance to globally optimal predictive maintenance.
文章引用：葛韩越, 王海涛, 张蕉蕉, 江琦. 面向工程机械的数字孪生与PHM融合技术综述[J]. 机械工程与技术, 2026, 15(5): 558-565. https://doi.org/10.12677/met.2026.155053

参考文献

[1] 李思雨, 程中华, 刘子昌, 等. 故障预测与健康管理系统研究与应用现状分析[J]. 火炮发射与控制学报, 2023, 44(6): 99-105.
[2] Grieves, M. and Vickers, J. (2017) Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems. In: Kahlen, F.J., Flumerfelt, S. and Alves, A., Eds., Transdisciplinary Perspectives on Complex Systems, Springer International Publishing, 85-113.
https://doi.org/10.1007/978-3-319-38756-7_4
[3] 储振航, 肖飞, 郭建国, 等. 数字孪生视角下的空天装备数字化[J]. 航空兵器, 2024, 31(3): 1-13.
[4] 石健, 刘冬, 王少萍. 基于数字孪生的机电液系统PHM关键技术综述[J]. 机械工程学报, 2024, 60(4): 66-81.
[5] 陶飞, 刘蔚然, 张萌, 胡天亮, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
[6] 王田, 李雨婷, 王文华. 就地计算、云边协同: 传感云与边缘计算的一体化框架(特邀) [J]. 计算机工程, 2026, 52(2): 7-12.
[7] 顾毅, 王峰, 谭杭波, 郑锦泉, 等. 一种基于云边协同的盾构机故障监测诊断方法与系统[P]. 中国专利, CN117786392B. 2024-05-17.
[8] Tao, F., Zhang, M., Liu, Y. and Nee, A.Y.C. (2018) Digital Twin Driven Prognostics and Health Management for Complex Equipment. CIRP Annals, 67, 169-172.
https://doi.org/10.1016/j.cirp.2018.04.055
[9] Wang, Y., Zhang, Z., Yang, Y., Xue, C., Zhang, W., Wang, L., et al. (2024) MKDC: A Lightweight Method for Cloud-Edge Collaborative Fault Diagnosis Model. IEEE Sensors Journal, 24, 32607-32618.
https://doi.org/10.1109/jsen.2024.3447064
[10] Zhidchenko, V., Startcev, E. and Handroos, H. (2022) Reference Architecture for Running Computationally Intensive Physics-Based Digital Twins of Heavy Equipment in a Heterogeneous Execution Environment. IEEE Access, 10, 54164-54184.
https://doi.org/10.1109/access.2022.3176645
[11] Stadtmann, F., Rasheed, A., Kvamsdal, T., Johannessen, K.A., San, O., Kölle, K., et al. (2023) Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions. IEEE Access, 11, 110762-110795.
https://doi.org/10.1109/access.2023.3321320
[12] Gupta, A., Schultes, P., Ha, T.W., et al. (2025) Transforming the BMW Connected Vehicle Backend with Karpenter.
https://aws.amazon.com/cn/blogs/industries/transforming-the-bmw-connected-vehicle-backend-with-karpenter/
[13] Kapteyn, M.G., Pretorius, J.V.R. and Willcox, K.E. (2021) A Probabilistic Graphical Model Foundation for Enabling Predictive Digital Twins at Scale. Nature Computational Science, 1, 337-347.
https://doi.org/10.1038/s43588-021-00069-0
[14] Yu, J., Wang, S., Wang, L. and Sun, Y. (2023) Gearbox Fault Diagnosis Based on a Fusion Model of Virtual Physical Model and Data-Driven Method. Mechanical Systems and Signal Processing, 188, Article 109980.
https://doi.org/10.1016/j.ymssp.2022.109980
[15] Ritto, T.G. and Rochinha, F.A. (2021) Digital Twin, Physics-Based Model, and Machine Learning Applied to Damage Detection in Structures. Mechanical Systems and Signal Processing, 155, Article 107614.
https://doi.org/10.1016/j.ymssp.2021.107614
[16] Booyse, W., Wilke, D.N. and Heyns, S. (2020) Deep Digital Twins for Detection, Diagnostics and Prognostics. Mechanical Systems and Signal Processing, 140, Article 106612.
https://doi.org/10.1016/j.ymssp.2019.106612
[17] Xu, Y., Jiang, Q., Li, S., Zhao, Z., Sun, B. and Huang, G.Q. (2024) Digital Twin-Driven Discriminative Graph Learning Networks for Cross-Domain Bearing Fault Recognition. Computers & Industrial Engineering, 193, Article 110292.
https://doi.org/10.1016/j.cie.2024.110292
[18] Wang, Q., Zhang, X., Lu, J., Xiao, G., Ren, Y. and Li, W. (2025) Digital Twin-Driven Physically Constrained Generative Adversarial Network for Industrial Boiler Fault Diagnosis. IEEE Transactions on Instrumentation and Measurement, 74, 1-15.
https://doi.org/10.1109/tim.2025.3558806
[19] Arias Chao, M., Kulkarni, C., Goebel, K. and Fink, O. (2022) Fusing Physics-Based and Deep Learning Models for Prognostics. Reliability Engineering & System Safety, 217, Article 107961.
https://doi.org/10.1016/j.ress.2021.107961
[20] Chen, Z., Dai, Y. and Liu, Y. (2024) Crack Propagation Simulation and Overload Fatigue Life Prediction via Enhanced Physics-Informed Neural Networks. International Journal of Fatigue, 186, Article 108382.
https://doi.org/10.1016/j.ijfatigue.2024.108382
[21] Lu, W., Wang, Y., Zhang, M. and Gu, J. (2024) Physics Guided Neural Network: Remaining Useful Life Prediction of Rolling Bearings Using Long Short-Term Memory Network through Dynamic Weighting of Degradation Process. Engineering Applications of Artificial Intelligence, 127, Article 107350.
https://doi.org/10.1016/j.engappai.2023.107350
[22] Aivaliotis, P., Georgoulias, K. and Chryssolouris, G. (2019) The Use of Digital Twin for Predictive Maintenance in Manufacturing. International Journal of Computer Integrated Manufacturing, 32, 1067-1080.
https://doi.org/10.1080/0951192x.2019.1686173
[23] Liu, S., Dai, W., Lv, S., Yuan, C. and Sun, Y. (2025) Maintenance Decision Methodology Integrating Twin Data with Reinforcement Learning. The International Journal of Advanced Manufacturing Technology, 138, 5705-5719.
https://doi.org/10.1007/s00170-025-15850-y
[24] Do, P., Nguyen, V., Voisin, A., Iung, B. and Neto, W.A.F. (2024) Multi-Agent Deep Reinforcement Learning-Based Maintenance Optimization for Multi-Dependent Component Systems. Expert Systems with Applications, 245, Article 123144.
https://doi.org/10.1016/j.eswa.2024.123144

为你推荐