Fault prognosis of wind turbine generator using SCADA data

Zhao, Yingying; Li, Dongsheng; Dong, Ao; Lin, Jiajia; Kang, Dahai; Shang, Li

doi:10.1109/naps.2016.7747914

Cited by 20 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance degradation of wind turbines lasted for about 44 days until a fault occurred, and similar phenomenon is observed on other wind turbines [21]. Therefore, we use predictions at M = 30, M = 40, M = 50, and M = 60 days ahead as baselines to predict a fault, respectively.…”

Section: Prediction Performancementioning

confidence: 58%

“…More specifically, the features that allow us to analyze generator faults fall into the first, second, and third categories in Section 4.1.1 [21]. Table 5 summarizes the selected features and potential correlations for generator fault prediction and diagnosis purposes.…”

Section: Feature Selectionmentioning

confidence: 99%

“…wind speed (1) miscorrelation of wind speed and generator active power indicates a fault in wind turbines [21]; (2) miscorrelation between generator speed and generator active power indicates a fault in generator [10]; (3) miscorrelation between generator speed and generator reactive power suggests an electrical fault in the generator [10]; (4) anomalous temperature changes caused by heat transfer can be helpful for figuring out the trajectory of a generator fault [9]; (5) shaft torque calculated in Equation 1 reflects the generator's load [2], and it can be used as an indicator for a generator fault.…”

Section: Scada Features Reasons For Wind Turbine Generator Fault Predmentioning

confidence: 99%

“…As discussed in the earlier work [21], there exists a pure intuition that most of the generators function most of the time healthily, and faults rarely occur. For the top three components output from the process of data-preprocessing, the largest and densest cluster exists.…”

Section: Prediction Modelmentioning

confidence: 99%

“…The continuous unhealthy state can indicate a developing or developed fault. Thus, the anomaly operation index (AOI(t)) is proposed to measure a wind turbine's performance over a period of historical time t [21]. AOI(t) is defined as Equation 3, which reflects the proportion of unhealthy instances to all instances during a time period of t.…”

Section: Prediction Modelmentioning

confidence: 99%

See 4 more Smart Citations

Fault Prediction and Diagnosis of Wind Turbine Generators Using SCADA Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

Abstract:The fast-growing wind power industry faces the challenge of reducing operation and maintenance (O&M) costs for wind power plants. Predictive maintenance is essential to improve wind turbine reliability and prolong operation time, thereby reducing the O&M cost for wind power plants. This study presents a solution for predictive maintenance of wind turbine generators. The proposed solution can: (1) predict the remaining useful life (RUL) of wind turbine generators before a fault occurs and (2) diagnose the state of the wind turbine generator when the fault occurs. Moreover, the proposed solution implies low-deployment costs because it relies solely on the information collected from the widely available supervisory control and data acquisition (SCADA) system. Extra sensing hardware is needless. The proposed solution has been deployed and evaluated in two real-world wind power plants located in China. The experimental study demonstrates that the RUL of the generators can be predicted 18 days ahead with about an 80% prediction accuracy. When faults occur, the specific type of generator fault can be diagnosed with an accuracy of 94%.

show abstract

Section: Prediction Performancementioning

confidence: 58%

Section: Feature Selectionmentioning

confidence: 99%