Anomaly detection for wind turbines based on the reconstruction of condition parameters using stacked denoising autoencoders. (March 2020)

• Record Type: Journal Article
• Authors: Chen, Junsheng; Li, Jian; Chen, Weigen; Wang, Youyuan; Jiang, Tianyan
• Is Part Of: Renewable energy. Volume 147(2020)Part 1
• Page Start: 1469
• Page End: 1480
• Publication Date: 2020-03
• Subjects: Wind turbine -- SCADA data -- Anomaly detection -- Stacked denoising antoencoders -- Moving window -- Multiple noise levels; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2019.09.041
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: This paper proposes an approach for detecting anomalies in a wind turbine (WT) based on multivariate analysis. Firstly, the stacked denoising autoencoders (SDAE) model with moving window and multiple noise levels is developed to reconstruct the normal operating data. The correlations among multivariable and temporal dependency inherent in each variable can be captured simultaneously with moving window processing. Both the coarse-grained and fine-grained features of input data can be learned by training with multiple noise levels. Then, the monitoring indicator is derived from the reconstruction error. The threshold value of monitoring indicator is determined by statistical analysis of the values of the monitoring indicator during normal operation. To identify the most relevant parameter related to the detected anomaly in WT, the contribution degree to which each parameter contributes to the exceedance of the threshold is calculated. Finally, the abnormal level is quantified according to the overlap between test behavior distribution and baseline condition to provide supports for operation and maintenance planning of WT. Demonstration on real SCADA data collected from a wind farm in Eastern China shows that the proposed method is effective for the anomaly detection and early warning of an actual WT. Highlights: A novel approach for detecting anomaly in wind turbine is presented. Moving window processing is adopted to incorporate the temporal dependence. Multiple noise levels training is proposed to improve the detection performance. The abnormal level of a wind turbine is quantitatively assessed.