Wind Turbine Main Bearing Fault Prognosis Based Solely on SCADA Data

Encalada-Dávila, Ángel; Puruncajas, Bryan; Tutivén, Christian; Vidal, Yolanda

doi:10.3390/s21062228

Cited by 49 publications

(41 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of the normality model is that it is capable to cope with the various operational and environmental conditions that the WT will face, see [18]. Thus, the train and test datasets include data from all working conditions: different wind speed regions and their associated regions of operation of the WT (start up, maximize power, and limit wind power to avoid exceeding the safe electrical and mechanical loads), different year seasons, curtailment, etc.…”

Section: Train and Test Setsmentioning

confidence: 99%

See 1 more Smart Citation

Improved Ensemble Learning for Wind Turbine Main Bearing Fault Diagnosis

Beretta

Vidal

Sepúlveda³

et al. 2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The goal of this paper is to develop, implement, and validate a methodology for wind turbines’ main bearing fault prediction based on an ensemble of an artificial neural network (normality model designed at turbine level) and an isolation forest (anomaly detection model designed at wind park level) algorithms trained only on SCADA data. The normal behavior and the anomalous samples of the wind turbines are identified and several interpretable indicators are proposed based on the predictions of these algorithms, to provide the wind park operators with understandable information with enough time to plan operations ahead and avoid unexpected costs. The stated methodology is validated in a real underproduction wind park composed by 18 wind turbines.

show abstract

Section: Train and Test Setsmentioning

confidence: 99%

“…In this work, a normality model at WT level is selected, based in [18], where the target variable is selected to be the closest sensor to the component under study. In particular, as the main bearing is the component to be monitored, the main shaft temperature is used as target variable.…”

Section: Introductionmentioning

confidence: 99%

Improved Ensemble Learning for Wind Turbine Main Bearing Fault Diagnosis

Beretta

Vidal

Sepúlveda³

et al. 2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this case, an AE is trained to rebuild the input at the output, using only healthy data. Here is where the normality model [23] works, since by contrast, if a faulty sample is entered, the AE will not rebuild the input well, thus, the residual error will help to detect a fault since it will be used as an indicator.…”

Section: A Autoenconder Architecture For Mfdmmentioning

confidence: 99%

“…Thus, based on these errors a fault detection threshold, t F D , [23] is computed, which defines when the samples are considered as faulty or healthy. To calculate the t F D , the mean and standard deviation are used.…”

Section: Fault Detection Metric Based On Prediction Errorsmentioning

confidence: 99%

Wind Turbine Multi-Fault Detection based on SCADA Data via an AutoEncoder

Encalada-Dávila¹,

Tutivén²,

Puruncajas³

et al. 2021

REPQJ

View full text Add to dashboard Cite

Nowadays, wind turbine fault detection strategies are settled as a meaningful pipeline to achieve required levels of efficiency, availability, and reliability, considering there is an increasing installation of this kind of machinery, both in onshore and offshore configuration. In this work, it has been applied a strategy that makes use of SCADA data with an increased sampling rate. The employed wind turbine in this study is based on an advanced benchmark, established by the National Renewable Energy Laboratory (NREL) of USA. Different types of faults on several actuators and sensed by certain installed sensors have been studied. The proposed strategy is based on a normality model by means of an autoencoder. As of this, faulty data are used for testing from which prediction errors were computed to detect if those raise a fault alert according to a defined metric which establishes a threshold on which a wind turbine works securely. The obtained results determine that the proposed strategy is successful since the model detects the considered three types of faults. Finally, even when prediction errors are small, the model is able to detect the faults without problems.

show abstract

“…Wind turbine faults emerge endlessly due to changeful working conditions and exposure to the sun, rain, sandstorms, and other severe weather factors throughout the year [5]. As a result, faults such as turbine gearbox faults [6], main bearing faults [7], and generator faults [8] lead to wind turbine maintenance downtime. Wind turbine maintenance is difficult and expensive due to high-altitude maintenance operations, which results in the need for considerable manpower and material resources, and can incur huge economic losses.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Method for Wind Turbine Gearboxes Based on IWOA-RF

Tang

Liang

et al. 2021

Energies

View full text Add to dashboard Cite

A fault diagnosis method for wind turbine gearboxes based on undersampling, XGBoost feature selection, and improved whale optimization-random forest (IWOA-RF) was proposed for the problem of high false negative and false positive rates in wind turbine gearboxes. Normal samples of raw data were subjected to undersampling first, and various features and data labels in the raw data were provided with importance analysis by XGBoost feature selection to select features with higher label correlation. Two parameters of random forest algorithm were optimized via the whale optimization algorithm to create a fitness function with the false negative rate (FNR) and false positive rate (FPR) as evaluation indexes. Then, the minimum fitness function value within the given scope of parameters was found. The WOA was controlled by the hyper-parameter α to optimize the step size. This article uses the variant form of the sigmoid function to alter the change trend of the WOA hyper-parameter α from a linear decline to a rapid decline first and then a slow decline to allow the WOA to be optimized. In the initial stage, a larger step size and step size change rate can make the model progress to the optimization target faster, while in the later stage of optimization, a smaller step size and step size change rate allows the model to more accurately find the minimum value of the fitness function. Finally, two hyper-parameters, corresponding to the minimum fitness function value, were substituted into a random forest algorithm for model training. The results showed that the method proposed in this paper can significantly reduce the false negative and false positive rates compared with other optimization classification methods.

show abstract

Wind Turbine Main Bearing Fault Prognosis Based Solely on SCADA Data

Cited by 49 publications

References 39 publications

Improved Ensemble Learning for Wind Turbine Main Bearing Fault Diagnosis

Improved Ensemble Learning for Wind Turbine Main Bearing Fault Diagnosis

Wind Turbine Multi-Fault Detection based on SCADA Data via an AutoEncoder

Fault Diagnosis Method for Wind Turbine Gearboxes Based on IWOA-RF

Contact Info

Product

Resources

About