Recurrent neural network optimization for wind turbine condition prognosis

• Autorzy: Kerboua Adlen , Kelaiaia Ridha

Identyfikatory

DOI

10.29354/diag/151608

• Języki publikacji: EN

Abstrakty

EN

This research focuses on employing Recurrent Neural Networks (RNN) to prognosis a wind turbine operation’s health from collected vibration time series data, by using several memory cell variations, including Long Short Time Memory (LSTM), Bilateral LSTM (BiLSTM), and Gated Recurrent Unit (GRU), which are integrated into various architectures. We tune the training hyperparameters as well as the adapted depth and recurrent cell number of the proposed networks to obtain the most accurate predictions. Tuning those parameters is a hard task and depends widely on the experience of the designer. This can be resolved by integrating the training process in a Bayesian optimization loop where the loss is considered as the objective function to minimize. The obtained results show the effectiveness of the proposed method, which generates more accurate recurrent models with a more accurate prognosis of the operating state of the wind turbine than those generated using trivial training parameters.

Słowa kluczowe

EN

forecasting; recurrent network; optimization; hyperparameters; loss

PL

prognozowanie; optymalizacja; sieci rekurencyjne; strata

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2022
• Tom: Vol. 23, No. 3
• Strony: art. no. 2022301
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Kerboua Adlen

• Faculty of Technology, Université 20 août 1955-Skikda, Algeria

• https://orcid.org/0000-0003-3078-462X

autor

Kelaiaia Ridha

• LGMM Laboratory, Faculty of Technology, Université 20 Août 1955-Skikda, Algeria

Bibliografia

• 1. Lipinski D, Majewski M. System for monitoring and optimization of micro- and nano-machining processes using intelligent voice and visual communication. In Lecture Notes in Computer Science; Springer: Berlin, Germany, 2013;8206:16-23.
• 2. Majewski M, Kacalak W. Smart control of lifting devices using patterns and antipatterns. Advances in intelligent systems and computing. In Artificial Intelligence. Trends in Intelligent Systems; Springer: Cham, Switzerland, 2017;573:486-493. https://doi.org/10.1007/978-3-319-57261-1_48.
• 3. Ganga D, Ramachandran V. Adaptive prediction model for effective electrical machine maintenance. Journal of Quality in Maintenance Engineering 2020; 26(1):166-180. https://doi.org/10.1108/JQME-12- 2017-0087.
• 4. Demidova L, Marchev D. Development of the forecasting model for the complex technical systems' failures time during the proactive maintenance using the recurrent neural networks' technology. 2nd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA). 2020:370-374. https://doi.org/10.1109/SUMMA50634.2020.928078 1.
• 5. Cherif H, Benakcha A, Laib I, Chehaidia S, Menacer A, Soudan B, Olabi A-G. Early detection and localization of stator inter-turn faults based on discrete wavelet energy ratio and neural networks in induction motor. Energy. 2020;212:118684. https://doi.org/10.1016/j.energy.2020.118684.
• 6. Rosato A, Araneo R, Andreotti A, Succetti F, Panella M. 2-D Convolutional Deep Neural Network for the Multivariate Prediction of Photovoltaic Time Series. Energies. 2021;14:2392. https://doi.org/10.3390/en14092392.
• 7. Azzouzi M, Diarra R, Popescu D. Fault diagnosis of sensors, actuators and wind turbine system. Diagnostyka. 2018;19(4):3-10. https://doi.org/10.29354/diag/93846.
• 8. Tarek K, Abdelaziz L, Zoubir C, Kais K, Karim N. Optimized multi layer perceptron artificial neural network based fault diagnosis of induction motor using vibration signals. Diagnostyka. 2021;22(1):65-74. https://doi.org/10.29354/diag/133091.
• 9. Mana M, Piccioni E, Terzi L. Wind turbine fault diagnosis through temperature analysis: an Artificial Neural Network approach. Diagnostyka. 2017;18(1): 9-16.
• 10. Sajid H, Hossam AG. Vibration analysis and time series prediction for wind turbine gearbox prognostics. International Journal of Prognostics and Health Management; Special Issue on Wind Turbine PHM. 2013;4(3). https://doi.org/10.36001/ijphm.2013.v4i3.2144.
• 11. Mao W, He J, Tang J, Li Y. Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network. Advances in Mechanical Engineering 2018; 10(12). https://doi.org/10.1177/1687814018817184.
• 12. Liu, ZH., Meng, XD., Wei, HL, Chen L, Lu BL, Wang ZH, Chen L. A Regularized LSTM method for predicting remaining useful life of rolling bearings. Int. J. Autom. Comput. 2021;18:581-593. https://doi.org/10.1007/s11633-020-1276-6.
• 13. Xie Y, Zhao J, Qiang B, Mi L, Tang C, Li L. Attention mechanism-based CNN-LSTM model for wind turbine fault prediction using SSN ontology annotation. Wireless Communications and Mobile Computing. 2021:627588. https://doi.org/10.1155/2021/6627588.
• 14. Khorram A, Khalooei M, Rezghi M. End-to-end CNN + LSTM deep learning approach for bearing fault diagnosis. Applied Intellifence 2021;51:736-751. https://doi.org/10.1007/s10489-020-01859-1.
• 15. Baskar P-K, Kaluvan H. Long short-term memory (LSTM) recurrent neural network (RNN) based traffic forecasting for intelligent transportation. AIP Conference Proceedings 2022;2435:020039. https://doi.org/10.1063/5.0083590.
• 16. Pascanu R, Mikolov T, Bengio Y. On the difficulty of training recurrent neural networks. International conference on machine learning PMLR 2013:1310-1318.
• 17. Bechhoefer E, Van Hecke B, He D. Processing for improved spectral analysis. Annual Conference of the Prognostics and Health Management Society 2013.
• 18. Jaouher B, Saidi L, Harrath S, Bechhoefer E, Benbouzid M. Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. Applied Acoustics 2017;133:167-181. https://doi.org/10.1016/j.apacoust.2017.11.021.
• 19. Brownlee J. How to scale data for long short-term memory networks in Python. 2017. https://machinelearningmastery.com/how-to-scaledata-for-long-short-term-memory-networks-inpython/.
• 20. Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997;9(8):1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
• 21. Kerboua A, Metatla A, Kelaiaia R, Batouche M. Realtime safety monitoring in the induction motor using deep hierarchic long short-term memory. Int J Adv Manuf Technol. 2018;99:2245–2255. https://doi.org/10.1007/s00170-018-2607-4.
• 22. Schuster M, Paliwal K. Bidirectional recurrent neural networks. IEEE transactions on Signal Processing. 1997;45(11):2673-2681. https://doi.org/10.1109/78.650093.
• 23. Cho K, Van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv. 2014. https://doi.org/10.48550/arXiv.1406.1078.
• 24. Wang S, Wang X, Wang S, Wang D. Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting. International Journal of Electrical Power & Energy Systems. 2019;109(2):470-479. https://doi.org/10.1016/j.ijepes.2019.02.022.
• 25. He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision. 2015; 1026-1034. https://doi.org/10.48550/arXiv.1502.01852.
• 26. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A Simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 2014;\ 15:1929-1958.
• 27. Kingma D-P, Jimmy B. Adam: A method for stochastic optimization. arXiv 2014:1412.6980. https://doi.org/10.5555/2627435.2670313.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).