Wind Turbine Fault Diagnosis with Generative- Temporal Convolutional Neural Network

Condition monitoring of wind turbines (WTs) is gained attention due to the fast development of WTs. The inherent intermittency of wind energy and locating in remote areas of WTs makes designing proper fault diagnosing method too difficult. To address this issue, we propose a two block deep learning based method in this paper, which encapsulates two feature extraction and classification in end-to-end architecture. In the designed method, we use the generative adversarial network (GAN) as a feature extraction block and temporal convolutional neural network (TCNN) as fault classifier block. The proposed structure can make benefits from the leverage GAN and TCNN and the simulation results based on real data from a 3 MGW WT in Ireland, which is obtained from supervisory control and data acquisition system (SCADA) demonstrated that it is a great alternative for WTs’ fault classification. To show the superiority of the proposed method, the results are compared with the support vector machine (SVM) and the feed-forward neural network (FFNN).