Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques

Carroll, J. Douglas; Koukoura, Sofia; McDonald, Alasdair; Charalambous, Anastasis; Weiss, Sholom M.; McArthur, S.D.J.

doi:10.1002/we.2290

Cited by 83 publications

(46 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Oil particle counting [6] and operation data analysis (especially temperatures, as, for example, in [7][8][9][10][11]) are widely used techniques for condition monitoring: they are more easily interpretable, but the drawback is that they furnish a later stage and more uncertain fault diagnosis, with respect to sub-component vibration spectra analysis. This remark is supported quantitatively in the work [12], where large amounts of labeled wind turbine supervisory control and data acquisition (SCADA) and vibration data have been processed, and the conclusion is that operation data can be used for reliably diagnosing a failure approximately one month before it occurs, while high frequency vibration data can be used to extend the accurate prediction capability to five to six months before failure. Furthermore, using operation data analysis, the fault diagnosis can successfully be performed through Artificial Intelligence techniques approximately 75% of the time, while, using vibration data, this percentage rises to 100%.…”

Section: Introductionmentioning

confidence: 87%

“…In [19], a critical analysis of the synchrosqueezing transform for the representation of non-stationary signals is proposed: for this aim, the synchrosqueezing transform is improved using iterative generalized demodulation and the proposed method is validated using both numerically simulated and experimental vibration signals of wind turbines planetary gearboxes. Finally, for comprehensive and recent reviews about wind turbine drive-train condition monitoring techniques, refer to [12,20,21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

et al. 2020

View full text Add to dashboard Cite

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind turbine had recently recovered from a planetary bearing fault, and one wind turbine was undergoing a high speed shaft bearing fault. The healthy wind turbines are selected as references and the damaged and recovered are selected as targets: vibration measurements are processed through a multivariate Novelty Detection algorithm in the feature space, with the objective of distinguishing the target wind turbines with respect to the reference ones. The application of this algorithm is justified by univariate statistical tests on the selected time-domain features and by a visual inspection of the data set via Principal Component Analysis. Finally, a novelty index based on the Mahalanobis distance is used to detect the anomalous conditions at the damaged wind turbine. The main result of the study is that the statistical novelty of the damaged wind turbine data set arises clearly, and this supports that the proposed measurement and processing methods are promising for wind turbine condition monitoring.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Defect identification challenges resulting from the lower speed of the MB may be partially mitigated by recording longer sampling periods of vibration data. For example, a ten second data acquisition period has been found to be less successful in detecting low speed bearing defects than for high speed bearing/gear tooth defects (Carroll et al, 2019). This suggests that one cause of reduced detection rates for faults in low speed bearings may therefore be due to insufficient sampling periods.…”

Section: Fault Diagnosis and Prognosismentioning

confidence: 99%

A review of wind turbine main-bearings: design, operation, modelling, damage mechanisms and fault detection

Hart¹,

Clarke²,

Nicholas³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a review of existing theory and practice relating to main-bearings for wind turbines. The mainbearing performs the critical role of supporting the turbine rotor, with replacements typically requiring its complete removal. The operational conditions and loading for wind turbine main-bearings deviate significantly from those of more conventional power plants and other bearings present in the wind turbine power-train, i.e. those in the gearbox and generator. This work seeks to thoroughly document current main-bearing theory in order to allow for appraisal of existing design and analysis practices, while also seeking to form a solid foundation for future research in this area. The most common main-bearing setups are presented along with standards for bearing selection and rating. Typical loads generated by a wind turbine rotor, and subsequently reacted at the main-bearing, are discussed. This is followed by the related tribological theories of lubrication, wear and associated failure mechanisms. Finally, existing techniques for bearing modeling, fault diagnosis and prognosis relevant to the main-bearing are presented.

show abstract

“…Yang et al [15] proposed a prediction model based on the double-layer convolutional neural network (CNN) to predict the remaining useful life of the bearing. Carrol et al [16] used ANN, support vector machine (SVM), and logistic regression to predict the remaining life of a gearbox and found that the ANN method has the highest prediction accuracy. Li et al [17] established a RUL prediction model for lithium batteries based on Elman neural network and verified the feasibility of the model in prediction.…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Prediction of Rolling Bearings Using Electrostatic Monitoring Based on Two-Stage Information Fusion Stochastic Filtering

Zhang

Wang

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The accurate prediction of the remaining useful life (RUL) of rolling bearings is of great significance for a rational formulation of maintenance strategies and the reduction of maintenance costs. According to the two-stage nonlinear degradation characteristics of rolling bearing operation, this paper proposes a prognosis model based on modified stochastic filtering. First, multiple features reextracted from the time domain, frequency domain, and complexity angles, and the baseline Gaussian mixture model (GMM) is established using the normal operating data after spectral regression. The Bayesian-inferred distance (BID) is used as a quantitative indicator to reflect the bearing performance degradation degree. Then, taking multiparameter fusion results as input, the relationship between BID and remaining life is established by the two-stage stochastic filtering model to realize online dynamic remaining useful life prediction. The method in this paper overcomes the difficulty of accurately defining the failure threshold of rolling bearing. At the same time, it reduces the computational burden, avoiding the need of calculating the joint probability distribution for high-dimensional data. Finally, the proposed method has been verified experimentally to have high precision and engineering application value.

show abstract

Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques

Cited by 83 publications

References 24 publications

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

A review of wind turbine main-bearings: design, operation, modelling, damage mechanisms and fault detection

Remaining Useful Life Prediction of Rolling Bearings Using Electrostatic Monitoring Based on Two-Stage Information Fusion Stochastic Filtering

Contact Info

Product

Resources

About