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). Multi-sensor fusion methods have been widely applied in condition monitoring and anomaly detection of industrial installation. Aimed at the wind turbine driveline, a new method utilizing the deep residual LSTM network with Attention model (ResLSTM-AM) is proposed in this paper. Firstly, data from multi-sensor fusion systems like supervisory control and data acquisition (SCADA) is preprocessed by quartile data cleaning and corresponding selection using the calculation of maximal information coefficient (MIC) to enhance its reliability. Secondly, we establish the neural network by the deep residual network (ResNet), long short-term memory network (LSTM), and attention mechanism (AM) for time series forecasting of wind turbines. 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. Additionally, the attention mechanism after a LSTM layer amplifies the influence of vital data. The model gets validated based on historical SCADA data from actual wind turbines containing healthy conditions and anomaly conditions, showing 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.

Data imbalances present a serious problem for intelligent fault diagnosis. They can lead to reduced diagnostic precision, which can jeopardize equipment reliability and safety. Based on that, this paper proposes a novel fault diagnosis method combining the denoising diffusion implicit model (DDIM) with a new convolutional neural network framework. First, the Gramian angular difference field (GADF) is used to generate 2D images, which are then augmented using DDIM. Next, by utilizing the weight-sharing properties of a convolutional neural network and the self-attention mechanism along with the global data processing capabilities of Transformers, a TransNet model is constructed. The augmented data are input into the model for training to establish a fault diagnosis framework. Finally, the method is validated and analyzed using the CWRU bearing dataset and the Nanchang Railway Bureau dataset. The results show that the proposed method achieves over 99% recognition accuracy on the two datasets. Meanwhile, the proposed model provides better generalization performance and recognition accuracy than existing fault diagnosis methods.

Condition monitoring of wind turbines (WT) is a crucial task to ensure efficient and safe operations. This paper proposes a novel model, interactive spatio-temporal network (IST-Net), to extract features from supervisory control and data acquisition (SCADA) data effectively. The proposed model utilizes an interactive learning structure that combines uniform refine long and short-term memory network (URLSTM) and convolutional neural network (CNN) to extract spatio-temporal features. Firstly, the SCADA data is preprocessed by utilizing the missing values filling, the feature selection, and the normalization. Secondly, an IST-Net model is trained by the data of healthy state. The IST-Net can extract spatio-temporal information to represent the operation status of WT by the interactive learning process of two isometric sequences split from the original sequence. Finally, the trained model receives online data and calculated the residual between true value and predicted value. The root mean squared error (RMSE) of the residual is calculated as the monitoring indicator, and the exponentially weighted moving average (EWMA) control chart is utilized for threshold determination. Experimental results reveal that the proposed model has better capability in precise anomaly detection compared to existing methods.