Deep Generative Convolutional Neural Network based Wind Turbines Condition Monitoring

Condition monitoring of wind turbines (WTs) has attracted attention due to fast development of WTs. The inherent intermittence of wind energy and being located in remote area makes it difficult to design proper fault diagnosing method for WTs. To address this issue, we proposed a two block deep learning based method in this paper, which encapsulates two feature extraction and classification in an end-toend architecture. In the designed method, we used generative adversarial network (GAN) as the feature extraction block and convolutional neural network (CNN) as the fault classifier block. The simulations are fulfilled based on real-data from a 3 MGW WT in Ireland, which is obtained from supervisory control and data acquisition system (SCADA). The results demonstrate that the proposed method is a proper alternative for fault classification of WTs. To show the superiority of the proposed method, the results are compared with the results of applying support vector machine (SVM) and feed-forward neural network (FFNN).