A review of the application of oil analysis in condition monitoring and life prediction of wind turbine gearboxes

2021 ◽  
Vol 63 (5) ◽  
pp. 289-301
Author(s):  
Yu Bie ◽  
Xihao Liu ◽  
Tao Xu ◽  
Zhengfei Zhu ◽  
Zhixiong Li
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Lubricating Oil ◽  
Measurement Technology ◽  
Oil Analysis ◽  
Testing Methods ◽  
Oil Viscosity ◽  
Diagnosis And Prognosis

Condition maintenance of wind turbine gearboxes is important because of their high failure probability and the difficulties associated with their maintenance. Diagnosis and prognosis are the two main aspects of condition maintenance. This paper summarises the development of fault diagnosis and life prediction methods for wind power gearboxes. Fault diagnosis methods include single-method analyses such as vibration analysis, acoustic emission (AE) analysis and oil analysis, as well as multi-information testing methods. Oil analysis can be used to monitor early wear and the wear evolution process, providing direct data for the remaining useful life (RUL) prediction of the gearbox and the lubricant. Though wind turbine gearbox RUL prediction has received more attention among these diagnoses, there is still only limited literature available regarding this. Measurement of the lubricating oil condition is one of the most often applied methods for diagnosis and prognosis and within this the oil viscosity is an important parameter. Viscosity estimation has wide application prospects in oil analysis and the tendency is to apply online testing methods. Oil viscosity can be more accurately measured by considering thermal effects, which can be studied using numerical and experimental methods. This viscosity measurement has been increasingly applied in oil analysis, with viscosity sensors. This review focuses on the application of online oil testing and measurement technology in the fault diagnosis and RUL prediction of wind turbine gearboxes. Challenging problems are identified and possible solutions are suggested in this review.

Hybrid method for remaining useful life prediction in wind turbine systems

2018 ◽  
Vol 116 ◽  
pp. 173-187 ◽  
Author(s):  
M.A. Djeziri ◽  
S. Benmoussa ◽  
R. Sanchez
Keyword(s):  
Wind Turbine ◽  
Hybrid Method ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Useful Life

scholarly journals PCA based health indicator for remaining useful life prediction of wind turbine gearbox

2019 ◽  
Vol 29 ◽  
pp. 31-36
Author(s):  
Sabareesh G R ◽  
Hemanth Mithun Praveen ◽  
Divya Shah ◽  
Krishna Dutt Pandey ◽  
Vamsi I
Keyword(s):  
Wind Turbine ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Health Indicator ◽  
Wind Turbine Gearbox ◽  
Useful Life

Parameter estimation and remaining useful life prediction of lubricating oil with HMM

Wear ◽  
2017 ◽  
Vol 376-377 ◽  
pp. 1227-1233 ◽  
Author(s):  
Ying Du ◽  
Tonghai Wu ◽  
Viliam Makis
Keyword(s):  
Parameter Estimation ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Lubricating Oil ◽  
Useful Life

scholarly journals Remaining Useful Life Prediction and Fault Diagnosis of Rolling Bearings Based on Short-Time Fourier Transform and Convolutional Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Shuang Zhou ◽  
Maohua Xiao ◽  
Petr Bartos ◽  
Martin Filip ◽  
Guosheng Geng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Fault Identification ◽  
Rolling Bearings ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Useful Life ◽  
Short Time

Rolling bearings play a pivotal role in rotating machinery. The remaining useful life prediction and fault diagnosis of bearings are crucial to condition-based maintenance. However, traditional data-driven methods usually require manual extraction of features, which needs rich signal processing theory as support and is difficult to control the efficiency. In this study, a bearing remaining life prediction and fault diagnosis method based on short-time Fourier transform (STFT) and convolutional neural network (CNN) has been proposed. First, the STFT was adopted to construct time-frequency maps of the unprocessed original vibration signals that can ensure the true and effective recovery of the fault characteristics in vibration signals. Then, the training time-frequency maps were used as an input of the CNN to train the network model. Finally, the time-frequency maps of testing signals were inputted into the network model to complete the life prediction or fault identification of rolling bearings. The rolling bearing life-cycle datasets from the Intelligent Management System were applied to verify the proposed life prediction method, showing that its accuracy reaches 99.45%, and the prediction effect is good. Multiple sets of validation experiments were conducted to verify the proposed fault diagnosis method with the open datasets from Case Western Reserve University. Results show that the proposed method can effectively identify the fault classification and the accuracy can reach 95.83%. The comparison with the fault diagnosis classification effects of backpropagation (BP) neural network, particle swarm optimization-BP, and genetic algorithm-BP further proves its superiority. The proposed method in this paper is proved to have strong ability of adaptive feature extraction, life prediction, and fault identification.

Sign in / Sign up

Export Citation Format

Share Document