Anomaly Detection of Wind Turbine Gearbox Based on Digital Twin Drive
Zeng Xiangjun, Yang Ming, Yang Xianglong, Yifan Bo, Feng Chen, Yu Zhou
Abstract
Anomaly detection for wind turbines (WTs) can improve their operational reliability and reduce their operation and maintenance costs. In this paper, a new WT anomaly detection method based on digital twin drive is proposed, which combines the advantages of data-driven methods and model simulation technology. It can use actual WT SCADA data to guide the construction of simulation models. Meanwhile, the simulation analysis results can also be used to verify whether the actual data analysis results are credible. Compared with a single data analysis method or a single model simulation analysis method, the proposed method can improve the reliability of anomaly detection results through the interaction of actual WT data analysis and the virtual simulation model analysis. The proposed method is verified by a WT with gearbox failure, and the data analysis result is consistent with the simulation result, proving the effectiveness of the method.