Identification of Health Status Stages of Wind Turbine High Speed Shaft Bearing with Deep Learning

Yıl 2024, ERKEN GÖRÜNÜM, 1 - 1

Gonca Öcalan , İbrahim Türkoğlu

https://doi.org/10.2339/politeknik.1388385

Öz

Mechanical components in wind turbines with an unstable operating environment under variable weather conditions are at a very high risk of wear. This situation brings about sudden unexpected stops of components and high maintenance costs. It is of great importance to plan appropriate maintenance times in order to ensure continuity in energy production, prevent unexpected unplanned downtime and minimize maintenance costs. Therefore, before a component failure occurs, the health status must be carefully monitored and maintenance periods must be planned according to the wear and tear process. In this paper, in order to evaluate the health status of a real wind turbine high-speed shaft bearing, the healthy, degradation and fault stages of the bearing are identified by a deep learning based classification model. In the proposed study, vibration data obtained from a real wind turbine high-speed shaft have been used. The study basically consists of the steps of extracting the features of the vibration data, selecting the features that will effectively reveal the health process of the bearing, obtaining the health index by integrating the selected features, and classifying the health index into stages with the LSTM deep learning model. In the study where four different health stages are defined, an accuracy of 99% has been obtained on the test data.

Anahtar Kelimeler

wind turbine, vibration, deep learning, classification of health status

Rüzgâr Türbini Yüksek Hızlı Şaft Rulmanının Sağlık Durumu Aşamalarının Derin Öğrenme İle Belirlenmesi

Öz

Değişken hava koşulları altında kararsız çalışma ortamına sahip rüzgâr türbinlerinde, mekanik bileşenler oldukça yüksek yıpranma riski altındadır. Bu durum, bileşenlerde ani beklenmedik duruşları ve yüksek bakım maliyetlerini beraberinde getirmektedir. Enerji üretiminde sürekliliği sağlamak, beklenmeyen plansız duruşların önüne geçmek ve bakım maliyetlerini en aza indirgemek amacıyla uygun bakım zamanlarının planlanması oldukça büyük öneme sahiptir. Bundan dolayı bileşende arıza meydana gelmeden önce sağlık durumunun dikkatli bir şekilde takip edilmesi ve bakım periyotlarının yıpranma sürecine göre planlanması gerekir. Bu makalede, gerçek bir rüzgâr türbini yüksek hızlı şaft rulmanının sağlık durumunun değerlendirilmesi amacıyla, rulmanın sağlıklı, bozulma ve arızalanma aşamaları derin öğrenme tabanlı sınıflandırma modeli ile belirlenmektedir. Önerilen çalışmada gerçek bir rüzgâr türbini yüksek hızlı şaftından elde edilen titreşim verileri kullanılmaktadır. Bu çalışma, temel olarak titreşim verilerine ait özelliklerinin çıkarılması, rulmanın sağlık sürecini etkin bir şekilde ortaya çıkaracak özelliklerin seçilmesi, seçilen özelliklerin bütünleştirilerek sağlık indeksinin elde edilmesi ve sağlık indeksinin aşamalara bölünerek Uzun Kısa Süreli Bellek (Long Short Term Memory – LSTM) derin öğrenme modeli ile sınıflandırılması adımlarından oluşmaktadır. Dört farklı sağlık aşamasının belirlendiği çalışmada test verileri üzerinde %99 oranında doğruluk değeri elde edilmiştir.

Anahtar Kelimeler

rüzgâr türbini, titreşim, derin öğrenme, sağlık durumunun sınıflandırılması

Etik Beyan

Bu makalenin yazar(lar)ı çalışmalarında kullandıkları materyal ve yöntemlerin etik kurul izni ve/veya yasal-özel bir izin gerektirmediğini beyan ederler.

Destekleyen Kurum

TUBİTAK – BİDEB 2211/C Yurtiçi Öncelikli Alanlar Doktora Burs Programı

Kaynakça

• [1] Çoban O., Kılınç N.Ş., "Yenilenebilir Enerji Tüketimi ve Karbon Emisyonu İlişkisi: Türkiye Örneği", Sos. Bilim. Enstitüsü Derg., 38: 195–208, (2015).
• [2] Xuejun W., Yunpeng G., Hexu Y., Hongjuan L., Yanqing T., Bin L., "Research on Fault Diagnosis of Gearbox Bearing of Wind Turbine Generator Set Based on DNN-1.5 MW", 2021 3rd World Symp. Artif. Intell., 92–97, (2021).
• [3] Zhang G., Li Y., Jiang W., Shu L., "A fault diagnosis method for wind turbines with limited labeled data based on balanced joint adaptive network", Neurocomputing, 481: 133–153, (2022).
• [4] Liang P., Deng C., Yuan X., Zhang L., "A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox", ISA Trans., 135: 462–475, (2023).
• [5] Wu Y., Tang B., Deng L., Li Q., "Distillation-enhanced fast neural architecture search method for edge-side fault diagnosis of wind turbine gearboxes", Expert Syst. Appl., 208: 118049, (2022).
• [6] Li Q., Tang B., Deng L., Xiong P., Zhao M., "Cross-Attribute adaptation networks: Distilling transferable features from multiple sampling-frequency source domains for fault diagnosis of wind turbine gearboxes", Measurement, 200: 111570, (2022).
• [7] Xu Z., Li C., Yang Y., "Fault diagnosis of rolling bearings using an Improved Multi-Scale Convolutional Neural Network with Feature Attention mechanism", ISA Trans., 110: 379–393, (2021).
• [8] Tang Z., Wang M., Ouyang T., Che F., "A wind turbine bearing fault diagnosis method based on fused depth features in time–frequency domain", Energy Reports, 8: 12727–12739, (2022).
• [9] Praveen H.M., Sabareesh G.R., Inturi V., Jaikanth A., "Component level signal segmentation method for multi-component fault detection in a wind turbine gearbox", Measurement, 195: 111180, (2022).
• [10] Kaycı B., Demir B.E., Demir F., "Deep Learning Based Fault Detection and Diagnosis in Photovoltaic System Using Thermal Images Acquired by UAV", Politek. Derg., 27: 91–99, (2024).
• [11] Öcalan G., Türkoğlu İ., "Dönen Makinelerde Ham Titreşim İşaretleri ve Derin Öğrenme Kullanılarak Arıza Teşhisi", 2021 Akıllı Sist. Yenilikler ve Uygulamaları Konf., 1–7, (2021).
• [12] Kaya K., Ünsal A., "Yapay Sinir Ağlarıyla Asenkron Motor Çoklu Arızalarının Tespiti ve Sınıflandırılması", Politek. Derg., 25: 1687–1699, (2022).
• [13] Ben Ali J., Fnaiech N., Saidi L., Chebel-Morello B., Fnaiech F., "Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals", Appl. Acoust., 89: 16–27, (2015).
• [14] Ben Ali J., Saidi L., Mouelhi A., Chebel-Morello B., Fnaiech F., "Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations", Eng. Appl. Artif. Intell., 42: 67–81, (2015).
• [15] Yan M., Wang X., Wang B., Chang M., Muhammad I., "Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model", ISA Trans., 98: 471–482, (2020).
• [16] Dong S., Wu W., He K., Mou X., "Rolling bearing performance degradation assessment based on improved convolutional neural network with anti-interference", Measurement, 151: 107219, (2020).
• [17] Chan Y.L., Shuai H.H., "Explainable Health State Prediction for Social IoTs through Multi-Channel Attention", 2021 IEEE Glob. Commun. Conf., 1–6, (2021).
• [18] Ben Ali J., 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", Appl. Acoust., 132: 167–181, (2018).
• [19] Özkat E.C., "Makine Öğrenmesi Metodolojisi Kullanılarak Yüksek Hızlı Rulmanlarda Sağlık Göstergesinin Belirlenmesi", Eur. J. Sci. Technol., 176–183, (2021).
• [20] Mian T., Choudhary A., Fatima S., "An efficient diagnosis approach for bearing faults using sound quality metrics", Appl. Acoust., 195: 108839, (2022).
• [21] Xie F., Wang G., Shang J., Liu H., Xiao Q., Xie S., "Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion", Sensors, 23: 4921, (2023).
• [22] Choudhary A., Mian T., Fatima S., "Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images", Measurement, 176: 109196, (2021).
• [23] Barzegaran M., Mazloomzadeh A., Mohammed O.A., "Fault Diagnosis of the Asynchronous Machines Through Magnetic Signature Analysis Using Finite-Element Method and Neural Networks", IEEE Trans. Energy Convers., 28: 1064–1071, (2013).
• [24] Ottewill J.R., Ruszczyk A., Broda D., "Monitoring tooth profile faults in epicyclic gearboxes using synchronously averaged motor currents: Mathematical modeling and experimental validation", Mech. Syst. Signal Process., 84: 78–99, (2017).
• [25] Soave E., D’Elia G., Dalpiaz G., "Prognostics of rotating machines through generalized Gaussian hidden Markov models", Mech. Syst. Signal Process., 185: 109767, (2023).
• [26] Zhu H., Huang Z., Lu B., Zhou C., "Bearing remaining useful life prediction of fatigue degradation process based on dynamic feature construction", Int. J. Fatigue, 164: 107169, (2022).
• [27] Du X., Jia W., Yu P., Shi Y., Cheng S., "A remaining useful life prediction method based on time–frequency images of the mechanical vibration signals", Measurement, 202: 111782, (2022).
• [28] Li J., Mao W., Yang B., Meng Z., Tong K., Yu S., "RUL prediction of rolling bearings across working conditions based on multi-scale convolutional parallel memory domain adaptation network", Reliab. Eng. Syst. Saf., 243: 109854, (2024).
• [29] Jia X., Ji D.Y., Minami T., Lee J., "Data Quality and Usability Assessment Methodology for Prognostics and Health Management: A Systematic Framework", IFAC-PapersOnLine, 55: 55–60, (2022).
• [30] J. Lee, H. Qiu, G. Yu, J. Lin and R.T.S., "IMS Bearing Data Set", https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/, (2007).
• [31] Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Morello, B., Zerhouni, N. V.C., "PRONOSTIA Bearing Data Set", https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/, (2012).
• [32] Eric Bechhoefer, "Wind Turbine High Speed Bearing Prognosis Data", https://github.com/mathworks/WindTurbineHighSpeedBearingPrognosis-Data/, (2020).
• [33] Kobenko V.Y., Frolov S.O., "Monitoring of the Wind Turbine Bearing Condition Using Identification Measurement Technology", 2022 Dyn. Syst. Mech. Mach., 1–6, (2022).
• [34] HBK, "Measuring Vibration: The Complete Guide", https://www.bksv.com/en/knowledge/blog/vibration/measuring-vibration., (2022).
• [35] Mohd Ghazali M.H., Rahiman W., "Vibration Analysis for Machine Monitoring and Diagnosis: A Systematic Review", Shock Vib., 2021: 1–25, (2021).
• [36] Pelioğlu Ö.M., "Dişlilerdeki Hatanın Titreşim Analizi Yoluyla Belirlenmesi", Gazi Üniversitesi Fen Bilim. Enstitüsü, Yüksek Lisans Tezi, (2019).
• [37] Sun B., Liu X., "Bearing early fault detection and degradation tracking based on support tensor data description with feature tensor", Appl. Acoust., 188: 108530, (2022).
• [38] Shi M., Ding C., Que H., Wu C., Shi J., Shen C., Huang W., Zhu Z., "Multilayer-graph-embedded extreme learning machine for performance degradation prognosis of bearing", Measurement, 207: 112299, (2023).
• [39] Sim J., Min J., Kim S., Lee S.W., Choi J.H., "Construction of bearing health indicator under time-varying operating conditions based on Isolation Forest", Eng. Appl. Artif. Intell., 126: 107058, (2023).
• [40] Kim S., An D., Choi J.H., "Diagnostics 101: A Tutorial for Fault Diagnostics of Rolling Element Bearing Using Envelope Analysis in MATLAB", Appl. Sci., 10: 7302, (2020).
• [41] Lyakhov P.A., Kialdze M.R., Kaplun D.I., Voznesensky A.S., "Removal of Ocular Artifacts from the Electroencephalogram Signal Flow using Median Filtering", 2021 Int. Conf. Autom. Informatics, 97–100, (2021).
• [42] Zhao Z., Chen N.Z., "An exponential smoothing multi-head graph attention network (ESMGAT) method for damage zone localization on wind turbine blades", Compos. Struct., 342: 118224, (2024).
• [43] Shi J., Zhong J., Zhang Y., Xiao B., Xiao L., Zheng Y., "A dual attention LSTM lightweight model based on exponential smoothing for remaining useful life prediction", Reliab. Eng. Syst. Saf., 243: 109821, (2024).
• [44] Wang D.F., Feng L.X., "Fuzzy Asynchronous Fault Detection for Markov Jump Systems With Packet Loss Compensation and Partially Unknown Transition Probabilities", 2023 IEEE 2nd Ind. Electron. Soc. Annu. On-Line Conf., 1–6, (2023).
• [45] Wikipedia, "Exponential Smoothing", https://en.wikipedia.org/wiki/Exponential_smoothing, (2023).
• [46] Cheng Y., Hu K., Wu J., Zhu H., Lee C.K.M., "A deep learning-based two-stage prognostic approach for remaining useful life of rolling bearing", Appl. Intell., 52: 5880–5895, (2022).
• [47] Baptista M.L., Goebel K., Henriques E.M.P., "Relation between prognostics predictor evaluation metrics and local interpretability SHAP values", Artif. Intell., 306: 103667, (2022).
• [48] Liang Z., Gao J., Jiang H., Gao X., Gao Z., Wang R., "A Degradation Degree Considered Method for Remaining Useful Life Prediction Based on Similarity", Comput. Sci. Eng., 21: 50–64, (2019).
• [49] Hou Z., Wang H., Yue Y., Xiong M., Zhang W., "A novel framework based on two-stage multi-view feature optimization and improved support vector data description for aeroengine bearing early fault detection", Reliab. Eng. Syst. Saf., 245: 110027, (2024).
• [50] Shang Y., Sun F., Fang Q., Chen B., "Heliyon A novel fault diagnosis strategy for LED lamps via light output time-frequency characteristics analysis and machine learning", Heliyon, 9: e19737, (2023).
• [51] Peng S., Liao H., Liu Y., Ouyang W., Li C., He S., "State Monitoring and Fault Detection of GIS Isolation Disconnector Based on Spearman Rank Correlation Coefficient", 2023 3rd Int. Conf. Electr. Eng. Control Sci., 1270–1273, (2023).
• [52] Wang Z., Zhao W., Li Y., Dong L., Wang J., Du W., Jiang X., "Adaptive staged RUL prediction of rolling bearing", Measurement, 222: 113478, (2023).
• [53] Chen Y., Liu Z., Zhang Y., Zheng X., Xie J., "Degradation-trend-dependent Remaining Useful Life Prediction for Bearing with BiLSTM and Attention Mechanism", 2021 IEEE 10th Data Driven Control Learn. Syst. Conf., 1177–1182, (2021).
• [54] Laha S.K., "Enhancement of fault diagnosis of rolling element bearing using maximum kurtosis fast nonlocal means denoising", Measurement, 100: 157–163, (2017).
• [55] Al-Raheem K.F., Abdul-Karem W., "Rolling bearing fault diagnostics using artificial neural networks based on Laplace wavelet analysis", Int. J. Eng. Sci. Technol., 2: 278–290, (2011).
• [56] Moshrefzadeh A., "Condition monitoring and intelligent diagnosis of rolling element bearings under constant/variable load and speed conditions", Mech. Syst. Signal Process., 149: 107153, (2021).
• [57] Qiu H., Niu Y., Shang J., Gao L., Xu D., "A piecewise method for bearing remaining useful life estimation using temporal convolutional networks", J. Manuf. Syst., 68: 227–241, (2023).
• [58] Ding W., Li J., Mao W., Meng Z., Shen Z., "Rolling bearing remaining useful life prediction based on dilated causal convolutional DenseNet and an exponential model", Reliab. Eng. Syst. Saf., 232: 109072, (2023).
• [59] Wikipedia, "Temel bileşen analizi", https://tr.wikipedia.org/wiki/Temel_bileşen_analizi, (2023).
• [60] Shilaskar S., Saitwal P., Raundal P., Rathi M., "LSTM Sequence to Sequence Model for Dynamic Title Generation", 2024 Int. Conf. Inven. Comput. Technol., 2083–2087, (2024).
• [61] Zhang Y., "Research on Text Classification Method Based on LSTM Neural Network Model", 2021 IEEE Asia-Pacific Conf. Image Process. Electron. Comput., 1019–1022, (2021).
• [62] Rajyagor B., Rakholia R., "Isolated Gujarati Handwritten Character Recognition (HCR) using Deep Learning (LSTM)", 2021 Fourth Int. Conf. Electr. Comput. Commun. Technol., 1–6, (2021).
• [63] Adeel A., Gogate M., Hussain A., Whitmer W.M., "Lip-Reading Driven Deep Learning Approach for Speech Enhancement", IEEE Trans. Emerg. Top. Comput. Intell., 5: 481–490, (2021).
• [64] Balcı S., Akkaya M., "Regression Model Extractions of a T-Equivalent Circuit Modelling for Medium-Length Transmission Line Based-on the Parametric Simulation Approach", J. Polytech., 0900: (2024).
• [65] Karaca H., Tekerek A., "Enhancing Cybersecurity against Ransomware Attacks Using LSTM Deep Learning Method: A Case Study on Android Devices", J. Polytech., 0900: 1–1, (2024).
• [66] Cai W., Zhang W., Hu X., Liu Y., "A hybrid information model based on long short-term memory network for tool condition monitoring", J. Intell. Manuf., 31: 1497–1510, (2020).
• [67] Zhou H., Cheng L., Teng L., Sun H., "Bearing Fault Diagnosis Based on RF-PCA-LSTM Model", 2021 2nd Inf. Commun. Technol. Conf., 278–282, (2021).
• [68] Li W., Wang L., Lu P., Hua L., "Bearing Fault Diagnosis Research Based on Empirical Mode Decomposition and Deep Learning", 2020 35th Youth Acad. Annu. Conf. Chinese Assoc. Autom., 32–37, (2020).
• [69] Kumar S., Ganga D., "Classification of Rolling Bearing Fault Based on Long Short Term Memory Neural Network", 2023 2nd Int. Conf. Innov. Technol., 1–5, (2023).
• [70] Chen Q., Ma X., Yan B., Yanyan W., Huang G., "Remaining useful life prediction of bearings with two-stage LSTM", 2022 5th Int. Symp. Auton. Syst., 1–6, (2022).
• [71] Yang Y., Yang X., Sun Y., Zhang G., "Residual Life Prediction of Rolling Bearing Based on LSTM Neural Networks", 2024 IEEE 4th Int. Conf. Electron. Technol. Commun. Inf., 288–295, (2024).
• [72] Sokolova M., Lapalme G., "A systematic analysis of performance measures for classification tasks", Inf. Process. Manag., 45: 427–437, (2009).