Article Open Access

Hybrid CNN-LSTM Model for Predictive Maintenance of Wind Turbine Systems

Qi Jiang

Abstract


Predictive maintenance enhances the reliability and efficiency of wind turbine systems through its role in managing these wind energy systems, which represent the most commonly used renewable resource worldwide. This research develops a combined Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework to refine fault detection as well as maintenance tactics using Supervisory Control and Data Acquisition (SCADA) measurements. Through its spatial pattern extraction ability, CNN operates on multivariate sensor data, while LSTM maintains temporal dependencies to recognise complex time-dependent degradation patterns. The proposed Hybrid CNN-LSTM model achieved outstanding predictive maintenance performance for wind turbines with an accuracy of 96.5%, precision of 96%, and recall of 95.5%. It outperformed CNN (accuracy: 91%), LSTM (89.5%), and Random Forest (83.5%) in all key metrics. The model also achieved the highest F1-score (96%) and AUC (0.96), proving its reliability in real-time fault detection. Verification of the methodology involves testing it on real SCADA data from two wind farm sites over two years, where it proves capable of spotting abnormal operations at early stages. Secure wind energy operations, along with efficient cost reduction, become feasible through the use of this solution, which reduces unexpected equipment failures while minimising downtime events.


Keywords


Predictive Maintenance, Wind Turbine Systems, CNN-LSTM Model, SCADA Data, Anomaly Detection

References


A. Nasser and H. AL-Khazraji, “A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance,” Int. J. Electr. Comput. Eng., vol. 12, no. 1, pp. 721–730, 2022, doi: 10.11591/ijece.v12i1.pp721-730.

C. Walker, C. Rothon, K. Aslansefat, Y. Papadopoulos, and N. Dethlefs, “A deep learning framework for wind turbine repair action prediction using alarm sequences and long short-term memory algorithms,” arXiv:2207.09457, 2022, doi: 10.48550/arXiv.2207.09457.

R. Rahim, “Quantum computing in communication engineering: Potential and practical implementation,” Prog. Electron. Commun. Eng., vol. 1, no. 1, pp. 26–31, 2024, doi: 10.31838/PECE/01.01.05.

E. Tefera, F. Martínez-Álvarez, and J. M. Cecilia, “A new hybrid CNN-LSTM for wind power forecasting in Ethiopia,” in Advances in Computational Intelligence, I. Rojas, G. Joya, and A. Catala, Eds. Cham, Switzerland: Springer, 2023, pp. 209–218, doi: 10.1007/978-3-031-40725-3_18.

G. Muthukumar and J. Philip, “CNN-LSTM hybrid deep learning model for remaining useful life estimation,” arXiv:2412.15998, 2024, doi: 10.48550/arXiv.2412.15998.

J. Backhus et al., “Equipment health assessment: Time series analysis for wind turbine performance,” arXiv:2403.00975, 2024, doi: 10.48550/arXiv.2403.00975.

J. Zhang, Z. Zhao, J. Yan, and P. Cheng, “Ultra-short-term wind power forecasting based on CGAN-CNN-LSTM model supported by LiDAR,” Sensors, vol. 23, no. 9, p. 4369, 2023, doi: 10.3390/s23094369.

R. Rahim, “Adaptive algorithms for power management in battery-powered embedded systems,” SCCTS J. Embedded Syst. Des. Appl., vol. 1, no. 1, pp. 25–30, 2024, doi: 10.31838/ESA/01.01.05.

K. Abdelli, H. Griesser, and S. Pachnicke, “A hybrid CNN-LSTM approach for laser remaining useful life prediction,” arXiv:2203.12415, 2022, doi: 10.48550/arXiv.2203.12415.

S. Al-Said, O. Findik, and B. Assanova, “Enhancing predictive maintenance in manufacturing: A CNN-LSTM hybrid approach for reliable component failure prediction,” in Technology-Driven Business Innovation, 2024, pp. 137–153, doi: 10.1007/978-3-031-51997-0_11.

Y. Zhou et al., “Automatic remaining useful life estimation framework with embedded convolutional LSTM as the backbone,” arXiv:2008.03961, 2020, doi: 10.48550/arXiv.2008.03961.

Z. Wang, X. Li, N. Li, and L. Shu, “An AI-driven approach to wind turbine bearing fault diagnosis from acoustic signals,” arXiv:2403.09030, 2024, doi: 10.48550/arXiv.2403.09030.

T. M. S. Kumar, “Low-power communication protocols for IoT-driven wireless sensor networks,” J. Wireless Sensor Netw. IoT, vol. 1, no. 1, pp. 37–43, 2024, doi: 10.31838/WSNIOT/01.01.06.

Z. Lin and X. Liu, “Wind power forecasting of an offshore wind turbine based on high-frequency SCADA data and deep learning neural network,” Energy, vol. 201, p. 117693, 2020, doi: 10.1016/j.energy.2020.117693.

M. Khan, T. Liu, and F. Ullah, “A new hybrid approach to forecast wind power for large scale wind turbine data using deep learning with TensorFlow framework and principal component analysis,” Energies, vol. 12, no. 12, p. 2229, 2019, doi: 10.3390/en12122229.

A. H. Abdel-Aty, K. S. Nisar, W. R. Alharbi, S. Owyed, and M. H. Alsharif, “Boosting wind turbine performance with advanced smart power prediction: Employing a hybrid ARMA-LSTM technique,” Alexandria Eng. J., vol. 96, pp. 58–71, 2024, doi: 10.3390/en14010125.

I. Delgado and M. Fahim, “Wind turbine data analysis and LSTM-based prediction in SCADA system,” Energies, vol. 14, no. 1, p. 125, 2020, doi: 10.1007/s10462-022-10217-9.

S. Garg and R. Krishnamurthi, “A survey of long short-term memory and its associated models in sustainable wind energy predictive analytics,” Artif. Intell. Rev., vol. 56, suppl. 1, pp. 1149–1198, 2023, doi: 10.1080/03772063.2022.2121222.

T. Anushalini and B. Sri Revathi, “Role of machine learning algorithms for wind power generation prediction in renewable energy management,” IETE J. Res., vol. 70, no. 4, pp. 4319–4332, 2024, doi: 10.1080/03772063.2022.2121222.

D. Wang, X. Cui, and D. Niu, “Wind power forecasting based on LSTM improved by EMD-PCA-RF,” Sustainability, vol. 14, no. 12, p. 7307, 2022, doi: 10.3390/su14127307.

L. Qi, Q. Zhang, Y. Xie, J. Zhang, and J. Ke, “Research on wind turbine fault detection based on CNN-LSTM,” Energies, vol. 17, no. 17, p. 4497, 2024, doi: 10.3390/en17174497.

K. Ariunaa, U. Tudevdagva, and M. Hussai, “The need for chemical sustainability in advancing sustainable chemistry,” Innov. Rev. Eng. Sci., vol. 2, no. 2, pp. 33–40, 2025, doi: 10.31838/INES/02.02.05.

S. S. Shah, D. Tang, and S. C. Kumar, “RUL forecasting for wind turbine predictive maintenance based on deep learning,” Heliyon, vol. 10, no. 20, 2024, doi: 10.1016/j.heliyon.2024.e39268.

F. Zhang, Y. Zhu, C. Zhang, P. Yu, and Q. Li, “Abnormality detection method for wind turbine bearings based on CNN-LSTM,” Energies, vol. 16, no. 7, p. 3291, 2023, doi: 10.3390/en16073291.

H. Dhungana, “A machine learning approach for wind turbine power forecasting for maintenance planning,” Energy Informatics, vol. 8, no. 1, p. 2, 2025, doi: 10.1186/s42162-024-00459-4.

P. Xin, X. Zhang, C. Yuan, and C. Li, “Fault diagnosis of wind turbine based on CNN-LSTM parallel network model,” Acad. J. Eng. Technol. Sci., vol. 6, no. 12, pp. 115–121, 2023, doi: 10.25236/AJETS.2023.061218.

P. A. Buestán-Andrade, M. Santos, J. E. Sierra-García, and J. P. Pazmiño-Piedra, “Comparison of LSTM, GRU and transformer neural network architecture for prediction of wind turbine variables,” in Int. Conf. Soft Comput. Models Ind. Environ. Appl., Cham, Switzerland: Springer, 2023, pp. 334–343, doi: 10.1007/978-3-031-44064-8_31.

M. Kavitha, “Enhancing security and privacy in reconfigurable computing: Challenges and methods,” SCCTS Trans. Reconfigurable Comput., vol. 1, no. 1, pp. 16–20, 2024, doi: 10.31838/RCC/01.01.04.

Ö. A. Karaman, “Prediction of wind power with machine learning models,” Appl. Sci., vol. 13, no. 20, p. 11455, 2023, doi: 10.3390/app132011455.

A. Lawal, S. Rehman, L. M. Alhems, and M. M. Alam, “Wind speed prediction using hybrid 1D CNN and BLSTM network,” IEEE Access, vol. 9, pp. 156672–156679, 2021, doi: 10.1109/ACCESS.2021.3129812.

F. Shahid, A. Zameer, A. Mehmood, and M. A. Z. Raja, “A novel WaveNets long short term memory paradigm for wind power prediction,” Appl. Energy, vol. 269, p. 115098, 2020, doi: 10.1016/j.apenergy.2020.115098.

J. Wang, Y. Qian, L. Zhang, K. Wang, and H. Zhang, “A novel wind power forecasting system integrating time series refining, nonlinear multi-objective optimized deep learning and linear error correction,” Energy Convers. Manag., vol. 299, p. 117818, 2024, doi: 10.1016/j.enconman.2024.117818.

F. Shahid, A. Zameer, and M. Muneeb, “A novel genetic LSTM model for wind power forecast,” Energy, vol. 223, p. 120069, 2021, doi: 10.1016/j.energy.2021.120069.

Z. Zhao et al., “Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features,” Eng. Appl. Artif. Intell., vol. 121, p. 105982, 2023, doi: 10.1016/j.engappai.2023.105982.

L. Xiang, J. Liu, X. Yang, A. Hu, and H. Su, “Ultra-short term wind power prediction applying a novel model named SATCN-LSTM,” Energy Convers. Manag., vol. 252, p. 115036, 2022, doi: 10.1016/j.enconman.2021.115036.

M. Kavitha, “Energy-efficient algorithms for machine learning on embedded systems,” J. Integr. VLSI, Embedded Comput. Technol., vol. 1, no. 1, pp. 16–20, 2024, doi: 10.31838/JIVCT/01.01.04.

A. Kisvari, Z. Lin, and X. Liu, “Wind power forecasting – A data-driven method along with gated recurrent neural network,” Renew. Energy, vol. 163, pp. 1895–1909, 2021, doi: 10.1016/j.renene.2020.10.099.

E. T. Habtemariam, K. Kekeba, M. Martínez-Ballesteros, and F. Martínez-Álvarez, “A Bayesian optimization-based LSTM model for wind power forecasting in the Adama district, Ethiopia,” Energies, vol. 16, no. 5, p. 2317, 2023, doi: 10.3390/en16052317.

O. Abedinia et al., “Wind power forecasting enhancement utilizing adaptive quantile function and CNN-LSTM: A probabilistic approach,” IEEE Trans. Ind. Appl., vol. 60, no. 3, pp. 4446–4457, 2024, doi: 10.1109/TIA.2024.3350945.

S. M. Malakouti et al., “Advanced techniques for wind energy production forecasting: Leveraging multi-layer perceptron + Bayesian optimization, ensemble learning, and CNN-LSTM models,” Case Stud. Chem. Environ. Eng., vol. 10, p. 100881, 2024, doi: 10.1016/j.cscee.2024.100881.

C. Xie, X. Yang, T. Chen, Q. Fang, J. Wang, and Y. Shen, “Short-term wind power prediction framework using numerical weather predictions and residual convolutional long short-term memory attention network,” Eng. Appl. Artif. Intell., vol. 133, p. 108543, 2024, doi: 10.1016/j.engappai.2023.108543.




DOI: https://doi.org/10.52088/ijesty.v5i4.1679

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Qi Jiang

International Journal of Engineering, Science, and Information Technology (IJESTY) eISSN 2775-2674