Fault Detection in Wind Turbine Using Time-Domain Vibration Features and LOOCV-Tuned Neural Networks

Articles in Press

Document Type : Research Paper

Authors
Abdulhamid Hamdan Al-Hinai
Karu Clement Varaprasad
Viswanadhan Vinod Kumar
Department of Mechanical and Mechatronic Engineering, Sohar University, Sohar, Oman
10.22055/jacm.2025.48637.5384
Abstract
This study proposes a novel, hardware-efficient condition monitoring approach for wind turbines using only time-domain vibration features and Leave-One-Out Cross-Validation with Artificial Neural Networks. Vibration data were collected from a lab-scale Wind Turbine Simulator under four conditions: healthy, bearing fault, blade crack, and blade imbalance, using sensors mounted on three orthogonal axes and acquired via NI 9234 DAQ. Statistical features like RMS, peak acceleration, crest factor, and shock pulse count were extracted and used to train a feedforward Artificial Neural Network. The horizontal-east axis provides the most diagnostic data and the model achieved 83.3% Leave-One-Out Cross-Validation accuracy with perfect recall for healthy and blade crack cases. This efficient approach enables scalable, real-time fault classification for intelligent wind energy systems.
Keywords
Artificial Neural Network
Fault Classification
Shock Pulse Detection
Time-Domain Vibration Analysis
Wind Turbine Condition Monitoring
Subjects

Publisher’s Note Shahid Chamran University of Ahvaz remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

[1] Al-Hinai, A. H., Varaprasad, K. C., Kumar, V. V., Comprehensive review of vibration-based analysis for wind turbine condition monitoring, Mechanical Engineering for Society and Industry, 4(3), 2024, 570–605.
[2] Swadi, M., Kadhim, D. J., Salem, M., Tuaimah, F. M., Majeed, A. S., Alrubaie, A. J., Investigating and predicting the role of photovoltaic, wind and hydrogen energies in sustainable global energy evolution, Global Energy Interconnection, 7(4), 2024, 429–445. 
[3] Chen, R., Qin, D., Liu, C., Dynamic modelling and dynamic characteristics of wind turbine transmission gearbox-generator system electromechanical-rigid-flexible coupling, Alexandria Engineering Journal, 65, 2022, 307–325. 
[4] Ozturkoglu, O., Ozcelik, O., Günel, S., Effects of operational and environmental conditions on estimated dynamic characteristics of a large in-service wind turbine, Journal of Vibration Engineering and Technologies, 12, 2024, 803–824.
[5] Li, Y., Zhu, C., Chen, X., Tan, J., Fatigue Reliability analysis of wind turbine drivetrain considering strength degradation and load sharing using survival signature and FTA, Energies, 13(8), 2020, 2108. 
[6] Chang, C. C. W., Ding, T. J., Han, W., Chai, C. C., Bhuiyan, M. A. S., Choon-Yian, H., Song, T. C., Recent advancements in condition monitoring systems for wind turbines: A review, Energy Reports, 9, 2023, 22–27. 
[7] Tritschler, N., Dugenske, A., Kurfess, T., An automated Edge Computing-Based condition health monitoring system: with an application on rolling element bearings, Journal of Manufacturing Science and Engineering, 143(7), 2021, 071006. 
[8] Kumar, V., Dhami, S., Goyal, D., Intelligent Condition Monitoring Techniques for Early fault diagnosis of rotating Machines – a review, Journal of University of Shanghai for Science and Technology, 23(8), 2021, 549–566. 
[9] Chavan, N. P., Kale, M. S., Deshmukh, S. P., Thakar, C. M., A review on development and trend of condition monitoring and fault diagnosis, ECS Transactions, 107(1), 2022, 17863–17870. 
[10] Surucu, O., Gadsden, S. A., Yawney, J., Condition Monitoring using Machine Learning: A Review of Theory, Applications and Recent Advances, Expert Systems with Applications, 221, 2023, 119738. 
[11] Cakir, M., Guvenc, M. A., Mistikoglu, S., The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system, Computers and Industrial Engineering, 151, 2020, 106948. 
[12] Al-Hinai, A. H., Varaprasad, K. C., Kumar, V. V., Performance optimization of a horizontal axis wind turbine simulator under the effects of blade’s pitch angle variation, Research on Engineering Structures and Materials, 11(5), 2025, 2331-2349.
[13] Narasinh, V., Mital, P., Chakravortty, N., Mittal, S., Kumar, A. V., Venkatraman, C., Kulkarni, N., Thakur, I., Analysing and Forecasting Degradation in Wind Turbines under Transient Operating Conditions through Vibration Analysis, E3S Web of Conferences, 572, 2024, 01006. 
[14] Patil, H., Patel, D., Diagnosis of localized defects in floating bush bearings through time-frequency domain analysis, Maintenance Reliability and Condition Monitoring, 3(2), 2023, 27–44. 
[15] Charan, K. S., An Auto-Encoder based TinyML approach for Real-Time anomaly detection, SAE International Journal of Advances and Current Practices in Mobility, 5(4), 2022, 1496–1501. 
[16] Aasi, A., Tabatabaei, R., Aasi, E., Jafari, S. M., Experimental investigation on time-domain features in the diagnosis of rolling element bearings by acoustic emission, Journal of Vibration and Control, 28(19–20), 2021, 2585–2595. 
[17] Hasan, M. J., Rashid, M., Nasir, A. F. A., Abdullah, M. A., Razman, M. A. M., Musa, R. M., Majeed, A. P. P. A., Gearbox Fault Diagnostics: an examination on the efficacy of different feature extraction techniques, Advances in Intelligent Systems and Computing, 2021, 399–406. 
[18] Parziale, M., Lomazzi, L., Giglio, M., Cadini, F., Vibration‐based structural health monitoring exploiting a combination of convolutional neural networks and autoencoders for temperature effects neutralization, Structural Control and Health Monitoring, 29(11), 2022, 3076. 
[19] Kulevome, D. K. B., Wang, H., Wang, X., Deep Neural Network based Classification of Rolling Element Bearings and Health Degradation Through Comprehensive Vibration Signal Analysis, Journal of Systems Engineering and Electronics, 33(1), 2022, 233–246. 
[20] Moghadam, A., Kakhki, F., Comparative Study of Decision Tree Models for Bearing Fault Detection and Classification, In: Tareq Ahram, Waldemar Karwowski, Pepetto Di Bucchianico, Redha Taiar, Luca Casarotto and Pietro Costa (eds) Intelligent Human Systems Integration (IHSI 2022): Integrating People and Intelligent Systems, AHFE (2022) International Conference, Vol. 22, AHFE International, USA, 2022.
[21] Al-Saad, M., Al-Mosallam, M., Alsahlani, A. A. M., Best Time Domain features for early detection of faults in rotary machines using RAT and ANN, Journal of Vibration Engineering and Technologies, 11(3), 2022, 1137–1149. 
[22] Alzghoul, A., Jarndal, A., Alsyouf, I., Bingamil, A. A., Ali, M. A., AlBaiti, S., On the Usefulness of Pre-processing Methods in Rotating ‎Machines Faults Classification using Artificial Neural Network, Journal of Applied and Computational Mechanics, 7(1), 2021, 254-261.
[23] Rangel-Rodriguez, A. H., Machorro-Lopez, J. M., Granados-Lieberman, D., De Santiago-Perez, J. J., Amezquita-Sanchez, J. P., Valtierra-Rodriguez, M., Detection of Cracks in Low-Power Wind Turbines Using Vibration Signal Analysis with Empirical Mode Decomposition and Convolutional Neural Networks, AI, 6(8), 2025, 179. 
[24] Bougoffa, M., Benmoussa, S., Djeziri, M., Contaret, T., Wind turbine blades fault diagnosis based on vibration signals utilizing convolutional neural network, International Conference on Decision Aid Sciences and Applications (DASA), 2024, 1–5. 
[25] Ali, W., El-Thalji, I., Giljarhus, K. E. T., Delimitis, A., Classification Analytics for wind turbine blade faults: Integrated Signal analysis and Machine learning approach, Energies, 17(23), 2024, 5856.
[26] Meyer, A., Vibration fault diagnosis in wind turbines based on automated feature learning, Energies, 15(4), 2022, 1514.
Journal of Applied and Computational Mechanics

Articles in Press, Corrected Proof
Available Online from 27 November 2025