Title :
Wind turbine anomaly detection using normal behavior models based on SCADA data
Author :
Peng Sun ; Jian Li ; Yonglong Yan ; Xiao Lei ; Xiaomeng Zhang
Author_Institution :
Dept. of High Voltage & Insulation Eng., Chongqing Univ., Chongqing, China
Abstract :
This paper presents an approach for anomaly detection in wind turbines (WTs) using normal behavior models (NBMs) based on supervisory control and data acquisition (SCADA) data. A genetic algorithm combined with partial least squares regression (GAPLS) is used for input parameter selection to reduce the redundant parameters for anomaly detection in WTs. The NBMs for 14 temperature parameters of SCADA system are developed by using back propagation neural networks (BPNNs). The proposed method is verified by a case of a 1.5MW WT fault. Results show that the NBM has a low prediction error under normally operation condition and a high prediction error prior to the fault. The prediction error can be used as an effective indicator for anomaly detection in WTs.
Keywords :
SCADA systems; backpropagation; genetic algorithms; least squares approximations; power system faults; wind turbines; BPNN; GAPLS; NBM; SCADA data; back propagation neural networks; genetic algorithm; input parameter selection; normal behavior model; partial least squares regression; power 1.5 MW; prediction error; supervisory control and data acquisition data; wind turbine anomaly detection; Accuracy; Condition monitoring; Data models; Generators; SCADA systems; Temperature distribution; Wind turbines; Anomaly detection; SCADA data; normal behavior models; wind turbine;
Conference_Titel :
High Voltage Engineering and Application (ICHVE), 2014 International Conference on
Conference_Location :
Poznan
DOI :
10.1109/ICHVE.2014.7035504