Condition Monitoring and Fault Detection of Wind Turbine Driveline With the Implementation of Deep Residual Long Short-Term Memory Network
Yuwei He, Jiayang Liu, Shijing Wu, Xiaosun Wang
Abstract
In view of the wide application of wind power, it is critically essential to develop solutions to the high fault rate and the long mean time to repair (MTTR). Multisensor fusion methods have been widely applied in condition monitoring and anomaly detection of industrial installation. Aimed at the wind turbine (WT) driveline, a new method utilizing the deep residual LSTM network with attention model (ResLSTM-AM) is proposed in this article. First, data from multisensor fusion systems, such as supervisory control and data acquisition (SCADA), are preprocessed by quartile data cleaning and corresponding selection using the calculation of maximal information coefficient (MIC) to enhance its reliability. Second, we establish the neural network by the deep residual network (ResNet), long short-term memory (LSTM) network, and attention mechanism (AM) for time-series forecasting of WTs. The newly added residual connecting architecture in LSTM layers ensures a higher learning rate in feature extraction and provides a more flexible data flow both in forward and backward signals. In addition, the AM after an LSTM layer amplifies the influence of vital data. The model gets validated based on historical SCADA data from actual WTs containing healthy conditions and anomaly conditions, showing that ResNet contributes more. Based on the root-mean-square error (RMSE), the alarming threshold is calculated by an exponential weighted moving average (EWMA). For two chosen variables, the proposed method is confirmed to be efficient and reliable with the accuracy of 0.9945 and 0.9880 in the results of trials and comparisons with other existing models.