Wind Fleet Generator Fault Detection via SCADA Alarms and Autoencoders

Premature failures caused by excessive wear are responsible for a large fraction of the maintenance costs of wind turbines. Therefore, it is crucial to be able to identify the propagation of these failures as early as possible. To this end, a novel condition monitoring method is proposed that uses statistical data analysis techniques and machine learning to construct a multivariate anomaly detection framework, based on high-frequency temperature SCADA data from wind turbines. This framework contains several steps. First, there is a preprocessing step in which relevant wind turbine states are extracted from the data. These states are the operating conditions and whether or not the turbine exhibits transient behavior. The second step entails anomaly detection on the temperature time series data. Fleet information is used to filter out exogenous (environmental) factors. Furthermore, multiple models are combined to get more stable and robust anomaly detections. By combining them the weaknesses of the individual models are alleviated resulting in a better overall performance. A limitation of machine learning-based anomaly detection on temperature data is the requirement that at least one year of “healthy” (meaning without anomalies) training data is available to account for seasonal effects. The lack of verified “healthy” data spread out evenly over the seasons generally means that the anomaly detection accuracy is severely compromised for the unrepresented seasons. This research uses smart retraining to reduce this limitation. Statistical techniques that leverage the information of the fleet are used to extract “healthy” data from at least one year, but preferably multiple years, of unverified data. This can then be used as training data for the machine learning-based models. To validate the pipeline, temperature and failure data of a real operational wind farm is used. Although the methodology is general in its scope, the validation case focusses specifically on generator bearing failures.

show abstract

“…The use of fleet information is not new, e.g. Beretta et al, (2020), Hendrickx et al (2020). The latter is most similar to our work.…”

Section: Gcwt Olse)supporting

confidence: 77%

“…This has great advantages when the amount of healthy data is limited. Beretta, Cárdenas, Koch and Cusidó (2020) detect generator faults using a combination of an autoencoder and alarm log data of several fleets of wind turbines. They find that combining the two methods increases the performance drastically.…”

Section: Related Workmentioning

confidence: 99%

Condition monitoring of wind turbines using machine learning based anomaly detection and statistical techniques for the extraction of 'healthy data'

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Where * defines element-wise multiplication between vectors, the information flow from the present cell state c t is controlled by the output gate O t to the current output, described by (15).…”

Section: B: Xgboost Regression Model and Hyperparameter Optimizationmentioning

confidence: 99%

“…The sensors forming the SCADA system are in the main components of the wind turbine; the data is usually sampled at a frequency of 10-min. This sampling interval makes it easy for data transfer and storage in a database for ultimate retrieval [15]. SCADA Systems on a WT typically record wind parameters like wind speed and wind deviations; performance parameters like power output, rotor speed, blade pitch angle; vibration parameters like tower acceleration and drive train acceleration; temperature parameters like bearing temperature and gearbox temperature.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Predictive Maintenance of Wind Turbine Based on SCADA Data

Udo

Muhammad²

2021

IEEE Access

View full text Add to dashboard Cite

Rystad Energy's analysis shows that installed offshore wind capacity will rise to 27.5 GW in 2026 from 10.5 GW in 2020. This report indicates that increasingly complex maintenance needs must be met for wind turbines(WTs). IRENA report shows that offshore wind operation and maintenance (OM) costs typically constitute 16-25% of the cost of electricity for offshore wind farms deployed in the G20 countries. Data collection and analytics, predictive maintenance, and production output optimisation of WTs must be explored to increase operational reliability and reduce maintenance costs of WTs. Predictive maintenance in wind turbines can be achieved by analysing data obtained by sensors already equipped with the WT. This network of sensors forms part of a Supervisory Control and Data Acquisition (SCADA) system. We developed a method for monitoring and detecting anomalies in the WT critical components, such as the gearbox and the generator. The proposed approach is based on the historical SCADA data that is common in most wind farms. We developed models using extreme gradient boosting (XGBoost) and Long Short-Term Memory (LSTM) to build the characteristics behaviour of critical WT components, and Statistical Process Control (SPC) was used to evaluate its anomalous behaviour. The proposed method was tested on two real case studies regarding six different WT to determine its effectiveness and applicability.

show abstract

“…This goal can, e.g., be pursued by physical models [31] or neural networks [32]. Alternative approaches based on anomaly detection and fusion of multiple indicators and alarm logs, addressing generator and main bearing failures, have been proposed in [33,34]. When located in a wind farm, also adjacent turbines can serve as a reference value [31].…”

Section: Previous Workmentioning

confidence: 99%

Quantification of the Information Loss Resulting from Temporal Aggregation of Wind Turbine Operating Data

et al. 2021

Self Cite

View full text Add to dashboard Cite

SCADA operating data are more and more used across the wind energy domain, both as a basis for power output prediction and turbine health status monitoring. Current industry practice to work with this data is by aggregating the signals at coarse resolution of typically 10-min averages, in order to reduce data transmission and storage costs. However, aggregation, i.e., downsampling, induces an inevitable loss of information and is one of the main causes of skepticism towards the use of SCADA operating data to model complex systems such as wind turbines. This research aims to quantify the amount of information that is lost due to this downsampling of SCADA operating data and characterize it with respect to the external factors that might influence it. The issue of information loss is framed by three key questions addressing effects on the local and global scale as well as the influence of external conditions. Moreover, recommendations both for wind farm operators and researchers are provided with the aim to improve the information content. We present a methodology to determine the ideal signal resolution that minimized storage footprint, while guaranteeing high quality of the signal. Data related to the wind, electrical signals, and temperatures of the gearbox resulted as the critical signals that are largely affected by an information loss upon aggregation and turned out to be best recorded and stored at high resolutions. All analyses were carried out using more than one year of 1 Hz SCADA data of onshore wind farm counting 12 turbines located in the UK.

show abstract

Wind Fleet Generator Fault Detection via SCADA Alarms and Autoencoders

Cited by 19 publications

References 23 publications

Condition monitoring of wind turbines using machine learning based anomaly detection and statistical techniques for the extraction of 'healthy data'

Condition monitoring of wind turbines using machine learning based anomaly detection and statistical techniques for the extraction of 'healthy data'

Data-Driven Predictive Maintenance of Wind Turbine Based on SCADA Data

Quantification of the Information Loss Resulting from Temporal Aggregation of Wind Turbine Operating Data

Contact Info

Product

Resources

About