Leveraging Digital Twins and AI for Enhanced Gearbox Condition Monitoring in Wind Turbines: A Review
Source abstract
Abstract
Wind power plays a significant role in sustainable energy production, but the reliability of wind turbines depends heavily on the integrity of their gearboxes. Gearbox failures can lead to significant downtime and operational disruption. In this context, this paper provides an overview of the evolution of gearbox monitoring techniques, culminating in the emergence of digital twin (DT) technology. We explore the application of DT technology to gearbox condition monitoring, focusing on two critical components: bearings and gears. This includes a comprehensive review of methodologies involving model-based approaches and data-driven techniques using signal processing (SP) and artificial intelligence (AI) algorithms. We address the challenges of “learning with minimal knowledge” and propose a framework for the effective application of DT technology. Finally, we discuss future research directions and potential contributions to advancing the field of gearbox condition monitoring through the continued development and implementation of DT-based solutions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gear and Bearing Dynamics Analysis · Machine Fault Diagnosis Techniques · Advanced machining processes and optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mechanical Structures Laboratory, Ecole Militaire Polytechnique, Algiers 16046, Algeria
LabISEN, ISEN Yncrea Ouest, 29200 Brest, France
Institut de Recherche Dupuy de Lôme (UMR CNRS 6027), University of Brest, 29238 Brest, France
Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China
References (100+)
Show source-provided references
1. Overcoming Catch-22 for rare earth metals in green transition: Solutions in electrical machine manufacturing10.1016/j.rser.2024.114917 ↗
2. Analysis of hybrid offshore renewable energy sources for power generation: A literature review of hybrid solar, wind, and waves energy systems10.1016/j.dibe.2024.100497 ↗
3. Digital Twin of Wind Turbine Surface Damage Detection Based on Deep Learning-Aided Drone Inspection10.1016/j.renene.2024.122332 ↗
4. Backwell, B., Emerson Clarke, E., Fang, R., Fiestas, J., Gitobu, N., Khinda, R., Ladwa, A., Lathigara, W., Liang, W., and Global Wind Report 2023 (2023, November 06). Technical Report, Global Wind Energy Council. Available online: https://sawea.org.za/sites/default/files/content-files/Market%20Reports/GWEC-2023_interactive.pdf.
5. De Kooning, J.D., Stockman, K., De Maeyer, J., Jarquin-Laguna, A., and Vandevelde, L. (2021). Digital twins for wind energy conversion systems: A literature review of potential modelling techniques focused on model fidelity and computational load. Processes, 9.10.3390/pr9122224 ↗
6. Material wear and fatigue in wind turbine systems10.1016/j.wear.2013.01.060 ↗
7. Llopis-Albert, C., Rubio, F., Devece, C., and García-Hurtado, D. (2024). Digital twin-based approach for a multi-objective optimal design of wind turbine gearboxes. Mathematics, 12.10.20944/preprints202403.1774.v1 ↗
8. Vrba, J., Cejnek, M., Steinbach, J., and Krbcova, Z. (2021). A machine learning approach for gearbox system fault diagnosis. Entropy, 23.10.3390/e23091130 ↗
9. Berghout, T., and Benbouzid, M. (2024). UBO-EREX: Uncertainty Bayesian-Optimized Extreme Recurrent EXpansion for Degradation Assessment of Wind Turbine Bearings. Electronics, 13.10.3390/electronics13122419 ↗
10. National Academies of Sciences, Engineering, and Medicine (2023). Foundational Research Gaps and Future Directions for Digital Twins, National Academies of Sciences, Engineering, and Medicine.
11. Online condition monitoring of floating wind turbines drivetrain by means of digital twin10.1016/j.ymssp.2021.108087 ↗
12. Pujana, A., Esteras, M., Perea, E., Maqueda, E., and Calvez, P. (2023). Hybrid-model-based digital twin of the drivetrain of a wind turbine and its application for failure synthetic data generation. Energies, 16.10.3390/en16020861 ↗
13. Physic-based vs data-based digital twins for bush bearing wear diagnostic10.1016/j.wear.2023.204888 ↗
14. Digital twin based virtual sensor for online fatigue damage monitoring in offshore wind turbine drivetrains10.1115/1.4055551 ↗
15. Research on digital twin driven rolling bearing model-data fusion life prediction method10.1109/ACCESS.2023.3277040 ↗
16. A Review of machine learning techniques for wind turbine’s fault detection, diagnosis, and prognosis10.1080/15435075.2023.2217901 ↗
17. An explainable predictive maintenance strategy for multi-fault diagnosis of rotating machines using multi-sensor data fusion10.1016/j.dajour.2024.100425 ↗
18. Rotating machine bearing health prognosis using a data driven approach based on KS-density and BiLSTM10.1049/smt2.12215 ↗
19. Li, J., Wang, S., Yang, J., Zhang, H., and Zhao, H. (2023). A digital twin-based state monitoring method of gear test bench. Appl. Sci., 13.10.3390/app13053291 ↗
20. Hu, Y., Taha, O.W., and Yang, K. (2024). Fault Detection in Active Magnetic Bearings Using Digital Twin Technology. Appl. Sci., 14.10.3390/app14041384 ↗
21. A transferable diagnosis method with incipient fault detection for a digital twin of wind turbine10.1016/j.dte.2024.100001 ↗
22. Digital twin-assisted interpretable transfer learning: A novel wavelet-based framework for intelligent fault diagnostics from simulated domain to real industrial domain10.1016/j.aei.2024.102681 ↗
23. Digital twin-based gearbox fault diagnosis using variational mode decomposition and dynamic vibration modeling10.1016/j.measurement.2025.116669 ↗
24. Graphics-based modular digital twin software framework for production lines10.1016/j.cie.2024.110308 ↗
25. How will the digital twin shape the future of industry 5.0?10.1016/j.technovation.2024.103025 ↗
26. Da Rocha, H., Pereira, J., Abrishambaf, R., and Espirito Santo, A. (2022). An interoperable digital twin with the IEEE 1451 standards. Sensors, 22.10.3390/s22197590 ↗
27. Lindner, M., Bank, L., Schilp, J., and Weigold, M. (2023). Digital twins in manufacturing: A RAMI 4.0 compliant concept. Sci, 5.10.3390/sci5040040 ↗
28. (2016). Standard for an Architectural Framework for the Internet of Things (IOT) (Standard No. IEEE-P2413).
29. (2021). Automation Systems and Integration–Digital Twin Framework for Manufacturing—Part 1: Overview and General Principles (Standard No. ISO 23247-1:2021).
30. (2012). Industrial Automation Systems and Integration—COLLADA Digital Asset Schema Specification for 3D Visualization of Industrial Data (Standard No. ISO/PAS 17506:2012).
31. An overview of information technology standardization activities related to additive manufacturing10.1007/s40964-019-00087-5 ↗
32. (2019). Information Technology—Cloud Computing—Guidance for Policy Development (Standard No. ISO/IEC TR 22678:2019). Available online: https://www.iso.org/standard/73642.html.
33. Cindrić, I., Jurčević, M., and Hadjina, T. (2025). Mapping of Industrial IoT to IEC 62443 Standards. Sensors, 25.10.3390/s25030728 ↗
34. A review of the technology standards for enabling digital twin: [version 2; peer review: 2 approved]
35. Digital twin model of gas turbine and its application in warning of performance fault10.1016/j.cja.2022.07.021 ↗
36. Kanaga Priya, P., and Reethika, A. (2024). A review of digital twin applications in various sectors. Transforming Industry Using Digital Twin Technology, Springer.10.1007/978-3-031-58523-4_12 ↗
37. Bofill, J., Abisado, M., Villaverde, J., and Sampedro, G.A. (2023). Exploring Digital Twin-Based Fault Monitoring: Challenges and Opportunities. Sensors, 23.10.20944/preprints202306.0841.v1 ↗
38. Nickpasand, M., Gaspar, H.M., and Energy, S.G.R. (2023, January 20–23). Digital Twin for Agile Manufacturing: Challenges from the Offshore Wind Turbine Industry. Proceedings of the ECMS, Florence, Italy.10.7148/2023-0442 ↗
39. Technologies Used by General Electric to Create Digital Twins for Energy Industry10.1007/s10749-024-01839-2 ↗
40. Digital twin enabled domain adversarial graph networks for bearing fault diagnosis10.1109/TICPS.2023.3298879 ↗
41. Fu, C., Gao, C., and Zhang, W. (2023). A Digital-Twin Framework for Predicting the Remaining Useful Life of Piezoelectric Vibration Sensors with Sensitivity Degradation Modeling. Sensors, 23.10.3390/s23198173 ↗
42. Yao, H., Zhang, X., Guo, Q., Miao, Y., and Guan, S. (2024). Fault diagnosis method for oil-immersed transformers integrated digital twin model. Sci. Rep., 14.10.1038/s41598-024-71107-w ↗
43. Wind turbine vibration management: An integrated analysis of existing solutions, products, and Open-source developments10.1016/j.egyr.2024.03.014 ↗
44. FEM and ANN approaches to wind turbine gearbox monitoring and diagnosis: A mini review10.1007/s40860-022-00183-4 ↗
45. Zhu, X., Shi, W., Huang, Z., and Shi, L. (2025). Geometry-Based Synchrosqueezing S-Transform with Shifted Instantaneous Frequency Estimator Applied to Gearbox Fault Diagnosis. Sensors, 25.10.3390/s25020540 ↗
46. Peng, H., Zhang, H., Shangguan, L., and Fan, Y. (2022). Review of tribological failure analysis and lubrication technology research of wind power bearings. Polymers, 14.10.3390/polym14153041 ↗
47. (2004). Rolling Bearings—Damages and Failures—Terms Characteristics and Causes (Standard No. ISO 15243).
48. Bearings faults and limits in wind turbine generators10.1016/j.rineng.2024.101891 ↗
49. Incremental learning with multi-fidelity information fusion for digital twin-driven bearing fault diagnosis10.1016/j.engappai.2024.108212 ↗
50. Ruan, D., Chen, Y., Gühmann, C., Yan, J., and Li, Z. (2022). Dynamics modeling of bearing with defect in Modelica and application in direct transfer learning from simulation to test bench for bearing fault diagnosis. Electronics, 11.10.3390/electronics11040622 ↗
51. Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing10.1016/j.ress.2023.109186 ↗
52. Liu, X., Huang, H., and Xiang, J. (2020). A personalized diagnosis method to detect faults in a bearing based on acceleration sensors and an FEM simulation driving support vector machine. Sensors, 20.10.3390/s20020420 ↗
53. Rapid deployment of digital twin for life prediction of rolling bearings10.1007/s10489-025-06536-9 ↗
54. Cyclostationarity blind deconvolution via eigenvector screening and its applications to the condition monitoring of rotating machinery10.1016/j.ymssp.2024.111782 ↗
55. Garrett, H., and Long, D.G. (2025). Frequency-Constrained QR: Signal and Image Reconstruction. Remote Sens., 17.10.3390/rs17030464 ↗
56. Husung, S., Koch, Y., Welzbacher, P., Kraus, B., Roehnert, F., Faheem, F., and Kirchner, E. (2023). Systemic conception of the data acquisition of Digital Twin solutions for use case-oriented development and its application to a gearbox. Systems, 11.10.3390/systems11050227 ↗
57. Mathematic modeling of vibration transmission path with discontinuous contact interfaces for gear dynamics in the gear-shaft-bearing-housing system10.1016/j.measurement.2023.114054 ↗
58. New intelligent gear fault diagnosis method based on Autogram and radial basis function neural network10.1177/1687814020916593 ↗
59. Temirkhan, M., Tariq, H.B., Kaloudis, K., Kalligeros, C., Spitas, V., and Spitas, C. (2022). Parametric quasi-static study of the effect of misalignments on the path of contact, transmission error, and contact pressure of crowned spur and helical gear teeth using a novel rapidly convergent method. Appl. Sci., 12.10.3390/app121910067 ↗
60. A computationally robust solution to the contact problem of two rotating gear surfaces in space10.1007/s11012-023-01738-2 ↗
61. An interpretable multiplication-convolution network for equipment intelligent edge diagnosis10.1109/TSMC.2023.3346398 ↗
62. Dynamic modeling and vibration analysis for fault diagnosis of rotate vector reducers10.1016/j.ymssp.2024.111965 ↗
63. Study on bifurcation characteristics of multi-clearance bending torsional coupling gear transmission based on EHL10.1177/1687814020937500 ↗
64. Digital twin-driven intelligent assessment of gear surface degradation10.1016/j.ymssp.2022.109896 ↗
65. Gearbox bearing fault simulation using a finite element model reduction technique10.1088/1742-6596/364/1/012082 ↗
66. Zhang, Q., Wu, Z., An, B., Sun, R., and Cui, Y. (2025). Digital Twin-Based Technical Research on Comprehensive Gear Fault Diagnosis and Structural Performance Evaluation. Sensors, 25.10.3390/s25092775 ↗
67. Wei, P., Li, C., Jiang, Z., and Wang, D. (2024). Real-time digital twin of ship structure deformation field based on the inverse finite element method. J. Mar. Sci. Eng., 12.10.20944/preprints202401.0399.v1 ↗
68. El Amli, A., El Yousfi, B., Soualhi, A., and Guillet, F. (2025). A Novel Hybrid FEM–Dynamic Modeling Approach for Enhanced Vibration Diagnostics in a Two-Stage Spur Gearbox. Energies, 18.10.3390/en18092176 ↗
69. Liu, W., Han, B., Zheng, A., and Zheng, Z. (2024). Fault Diagnosis for Reducers Based on a Digital Twin. Sensors, 24.10.3390/s24082575 ↗
70. Wang, Y., Sun, W., Liu, L., Wang, B., Bao, S., and Jiang, R. (2023). Fault diagnosis of wind turbine planetary gear based on a digital twin. Appl. Sci., 13.10.3390/app13084776 ↗
71. An efficient fault diagnosis framework for digital twins using optimized machine learning models in smart industrial control systems10.1007/s44196-023-00241-6 ↗
72. Wind turbine fault detection and identification using a two-tier machine learning framework
73. A combined short time fourier transform and image classification transformer model for rolling element bearings fault diagnosis in electric motors10.3390/make3010011 ↗
74. State-of-the-art review and synthesis: A requirement-based roadmap for standardized predictive maintenance automation using digital twin technologies10.1016/j.aei.2024.102800 ↗
75. Rashid, H., Habbouche, H., Amirat, Y., Mamoune, A., Titah-Benbouzid, H., and Benbouzid, M. (2024). B-FLOWS: Biofouling Focused Learning and Observation for Wide-Area Surveillance in Tidal Stream Turbines. J. Mar. Sci. Eng., 12.10.3390/jmse12101828 ↗
76. Zhang, W., Liu, Y., Zhang, S., Long, T., and Liang, J. (2021). Error fusion of hybrid neural networks for mechanical condition dynamic prediction. Sensors, 21.10.3390/s21124043 ↗
77. Benbouzid, M. (2021). Signal Processing for Fault Detection and Diagnosis in Electric Machines and Systems, Institution of Engineering & Technology.10.1049/PBPO153E ↗
78. Wear monitoring based on vibration measurement during machining: An application of FDM and EMD10.1016/j.measen.2024.101051 ↗
79. Nasiri, A., Rahideh, A., Agah, G.R., and Kia, S.H. (2024). Ball-Bearing Fault Detection of Squirrel-Cage Induction Motors Based on Single-Phase Stator Current Using Wavelet Packet Decomposition and Statistical Features. IEEE Trans. Energy Convers., early access.10.1109/TEC.2024.3461753 ↗
80. Habbouche, H., Benkedjouh, T., Amirat, Y., and Benbouzid, M. (2025). A Wavelet Transform-Based Transfer Learning Approach for Enhanced Shaft Misalignment Diagnosis in Rotating Machinery. Electronics, 14.10.3390/electronics14020341 ↗
81. Xia, J., Huang, R., Liao, Y., Li, J., Chen, Z., and Li, W. (2023). Digital twin-assisted gearbox dynamic model updating toward fault diagnosis. Front. Mech. Eng., 18.10.1007/s11465-023-0748-0 ↗
82. Gearbox fault diagnosis based on a fusion model of virtual physical model and data-driven method10.1016/j.ymssp.2022.109980 ↗
83. Matania, O., Bechhoefer, E., and Bortman, J. (2023). Digital Twin of a Gear Root Crack Prognosis. Sensors, 23.10.3390/s23249883 ↗
84. Zhu, D., Li, Z., and Hu, N. (2022). Multi-body dynamics modeling and analysis of planetary gearbox combination failure based on digital twin. Appl. Sci., 12.10.3390/app122312290 ↗
85. Digital twin-enabled entropy regularized wavelet attention domain adaptation network for gearboxes fault diagnosis without fault data10.1016/j.aei.2024.103055 ↗
86. Lifting wavelet-informed hierarchical domain adaptation network: An interpretable digital twin-driven gearbox fault diagnosis method10.1016/j.ress.2024.110660 ↗
87. Digital twin-assisted fault diagnosis framework for rolling bearings under imbalanced data10.1016/j.asoc.2024.112528 ↗
88. Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samples10.1016/j.knosys.2024.111641 ↗
89. A Model-Data Combination Driven Digital Twin Model for Few Samples Fault Diagnosis of Rolling Bearings10.1088/1361-6501/ad50f3 ↗
90. Bearing crack diagnosis using a smooth sliding digital twin to overcome fluctuations arising in unknown conditions10.3390/app12136770 ↗
91. Applications of artificial neural network based battery management systems: A literature review10.1016/j.rser.2023.114262 ↗
92. A literature review of fault diagnosis based on ensemble learning10.1016/j.engappai.2023.107357 ↗
93. Exploring Feature Selection With Limited Labels: A Comprehensive Survey of Semi-Supervised and Unsupervised Approaches10.1109/TKDE.2024.3397878 ↗
94. The meta-defect-detection system for gear pitting based on digital twin10.1016/j.aei.2023.102003 ↗
95. Digital twin-driven discriminative graph learning networks for cross-domain bearing fault recognition10.1016/j.cie.2024.110292 ↗
96. Digital twin-assisted enhanced meta-transfer learning for rolling bearing fault diagnosis10.1016/j.ymssp.2023.110490 ↗
97. Digital twin-driven graph domain adaptation neural network for remaining useful life prediction of rolling bearing10.1016/j.ress.2024.109991 ↗
98. Prediction of bearing remaining useful life based on a two-stage updated digital twin10.1016/j.aei.2025.103123 ↗
99. Digital twin-assisted dual transfer: A novel information-model adaptation method for rolling bearing fault diagnosis10.1016/j.inffus.2024.102271 ↗
100. Zhang, C., Qin, F., Zhao, W., Li, J., and Liu, T. (2023). Research on rolling bearing fault diagnosis based on digital twin data and improved ConvNext. Sensors, 23.10.3390/s23115334 ↗