Fault Diagnosis Based on Interpretable Convolutional Temporal-spatial Attention Network for Offshore Wind Turbines  

作　　者：Xiangjing Su Chao Deng Yanhao Shan Farhad Shahnia Yang Fu Zhaoyang Dong 

机构地区：[1]the Engineering Research Center of Offshore Wind Technology Ministry of Education,Shanghai University of Electric Power,Shanghai 200090,China [2]the Offshore Wind Power Research Institute,Shanghai University of Electric Power,Shanghai 200090,China [3]the Yantai Power Supply Company,State Grid Shandong Electric Power Co.,Ltd.,Yantai 264001,China [4]the School of Engineering and Energy,Murdoch University,Perth WA 6150,Australia [5]the School of Electrical and Electronic Engineering,Nan yang Technological University,Singapore 639798,Singapore

出　　处：《Journal of Modern Power Systems and Clean Energy》2024年第5期1459-1471,共13页现代电力系统与清洁能源学报（英文）

摘　　要：Fault diagnosis(FD)for offshore wind turbines(WTs)are instrumental to their operation and maintenance(O&M).To improve the FD effect in the very early stage,a condition monitoring based sample set mining method from supervisory control and data acquisition(SCADA)time-series data is proposed.Then,based on the convolutional neural network(CNN)and attention mechanism,an interpretable convolutional temporal-spatial attention network(CTSAN)model is proposed.The proposed CTSAN model can extract deep temporal-spatial features from SCADA time-series data sequentially by:(1)a convolution feature extraction module to extract features based on time intervals;(2)a spatial attention module to extract spatial features considering the weights of different features;and(3)a temporal attention module to extract temporal features considering the weights of intervals.The proposed CTSAN model has the superiority of interpretability by exposing the deep temporal-spatial features extracted in a human-understandable form of the temporal-spatial attention weights.The effectiveness and superiority of the proposed CTSAN model are verified by real offshore wind farms in China.

关 键 词：Offshore wind turbine(WT) GEARBOX fault diagnosis(FD) attention mechanism INTERPRETABILITY temporal-spatial feature 

分 类 号：TM315[电气工程—电机] TP277[自动化与计算机技术—检测技术与自动化装置]