Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. (March 2018)

• Record Type: Journal Article
• Authors: Ben Ali, Jaouher; Saidi, Lotfi; Harrath, Salma; Bechhoefer, Eric; Benbouzid, Mohamed
• Is Part Of: Applied acoustics. Volume 132(2018)
• Page Start: 167
• Page End: 181
• Publication Date: 2018-03
• Subjects: ART2 -- Feature extraction -- Fault diagnosis -- High speed shaft bearing -- Wind turbines; AGWN Additive Gaussian White Noise -- ANN Artificial Neural Network -- ART2 Adaptive Resonance Theory 2 -- D degraded state -- EEMD Ensemble Empirical Mode Decomposition -- EMD Empirical Mode -- EWMA exponential weighted moving average -- F failure state -- H healthy state -- HSSB high-speed shaft bearing -- IMF intrinsic mode function -- MDVD Multi-Dimensional Variational Decomposition -- SK Spectral Kurtosis -- STFT Short-Time Fourier Transform -- SVM Support Vector Machines -- VMD Variational Mode Decomposition -- WTG wind turbine generator; Acoustical engineering -- Periodicals; Periodicals; 620.2
• DOI: 10.1016/j.apacoust.2017.11.021
• Languages: English
• ISSNs: 0003-682X

Abstract

Highlights: Investigation of three domains for feature extraction. Classify online the extracted features using the ART2 neural network. A new ART2 offline step is proposed using Randall bearing vibration model. The proposed method defines accurately and online the severity of the fault without human intervention. A validation using real WTG vibration signals under real experimental conditions shows the importance of the proposed method. Abstract: As a critical component, failures of high-speed shaft bearing in wind turbines cause the unplanned stoppage of electrical energy production. Investigations related to naturally progressed defects of high-speed shaft bearings are relatively scarce and the online assessment in damage severities is rarely available in the literature. In this sense, this paper presents a new online vibration-based diagnosis method for wind turbine high-speed bearing monitoring. The adaptive resonance theory 2 (ART2) is proposed for an unsupervised classification of the extracted features. The Randall model is adapted considering the geometry of the tested bearing to train the ART2 in the offline step. In fact, the time domain, the frequency domain, and the time-frequency domain are investigated for a better bearing fault characterization. Indeed, the use of real measured data from a wind turbine drivetrain proves that the proposed data-driven approach is suitable for wind turbine bearings online condition monitoring even under real experimental conditions. This method reveals a better generalization capability compared to previous works even with noisy measurements.