Fault prediction model in wind turbines using deep learning structure with enhanced optimisation algorithm

Abstract

Digital Twin (DT) is used for lifetime monitoring of the drive train and can be a costly option. This proposal adopts the predictive modelling of wind turbines by digital twins by deep learning strategies. Initially, the data is acquired from publicly available wind turbine datasets. Next, the deep features and statistical features are extracted, and the autoencoder is adapted to get the deep features. Then, the Enhanced Marine Predators Algorithm (EMPA) is to select the optimal weighted fused features, where the EMPA would tune the weights used for fusion and the features selection. Finally, the predictive modelling is done via a newly recommended Adaptive Deep Temporal Convolution Network with an Attention Mechanism (ADTCN-AM). It is tuned for precise outcomes with the help of EMPA for forecasting the wind speed and predicting the generated power. The comparative performance analysis of the recently used wind prediction system model shows better efficient results.