A5079002529- Machine Fault Diagnosis Techniques
- Anomaly Detection Techniques and Applications
- Fault Detection and Control Systems
- Additive Manufacturing and 3D Printing Technologies
- Photopolymerization techniques and applications
- Energy Load and Power Forecasting
- Power System Reliability and Maintenance
Wuhan University
2023
In view of the wide application wind power, it is critically essential to develop solutions high fault rate and long mean time repair (MTTR). Multisensor fusion methods have been widely applied in condition monitoring anomaly detection industrial installation. Aimed at turbine (WT) driveline, a new method utilizing deep residual LSTM network with attention model (ResLSTM-AM) proposed this article. First, data from multisensor systems, such as supervisory control acquisition (SCADA), are...
Condition monitoring of wind turbines (WT) is a crucial task to ensure efficient and safe operations. This paper proposes novel model, interactive spatio-temporal network (IST-Net), extract features from supervisory control data acquisition (SCADA) effectively. The proposed model utilizes an learning structure that combines uniform refine long short-term memory (URLSTM) convolutional neural (CNN) features. Firstly, the SCADA preprocessed by utilizing missing values filling, feature...
Aimed at identifying the health state of wind turbines (WTs) accurately by using comprehensive spatio and temporal information from supervisory control data acquisition (SCADA) data, a novel anomaly-detection method called decomposed sequence interactive network (DSI-Net) is proposed in this paper. Firstly, DSI-Net model trained preprocessed healthy state. Subsequences trend seasonality are obtained DSI-Net, which can dig out underlying features both dimensions through learning process....