A two-stage anomaly decomposition scheme based on multi-variable correlation extraction for wind turbine fault detection and identification. (1st September 2022)

• Record Type: Journal Article
• Authors: Wang, Anqi; Pei, Yan; Qian, Zheng; Zareipour, Hamidreza; Jing, Bo; An, Jiayi
• Is Part Of: Applied energy. Volume 321(2022)
• Publication Date: 2022-09-01
• Subjects: Wind turbines -- Condition monitoring -- Fault identification -- Anomaly cause -- Multi-variable correlation extraction -- Hotelling's method; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2022.119373
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: Underlying causes of anomaly are identified for wind turbines. The Co-NBM method is proposed for WT fault detection based on SCADA data. Fault locations could be identified by the first-stage decomposition. Underlying causes of the anomalies are determined by the second-stage decomposition. Abstract: Effective condition monitoring is critical to improve the reliability and reduce unplanned downtime of wind turbines (WTs). Supervisory control and data acquisition (SCADA) data with the advantages of easy access and low cost, has been widely used in wind turbine condition monitoring (WTCM). While the existing literature based on SCADA data for WTCM provides whether the condition is normal or abnormal, few have attempted to identify the underlying causes of the anomaly. In this paper, a two-stage anomaly decomposition scheme based on the multi-variable correlation extraction is proposed for WT fault detection and anomaly causes identification. Firstly, a normal behavior model (NBM) based on the multi-variable correlation extraction (Co-NBM) is proposed for WT fault detection using only SCADA data. A network based on the multi-head self-attention mechanism is designed to extract correlation among the variables. It can effectively provide early warning and reduce false alarms rate by exploring the multi-variable correlations. Furthermore, a two-stage anomaly decomposition scheme based on the Hotelling's T 2 method is proposed for WT fault identification. It is capable of effectively identifying the fault locations and anomaly causes based on the defined two-stage abnormal factors. Compared with auto-encoder (AE) and LSTM-attention methods, the proposed method could achieve better performance in fault detection and reduce the false alarm rate. Moreover, the proposed method could also provide the underlying cause of the anomaly, which is useful for the decision making of WT maintenance.