Convolutional Neural Networks using the SMOTE Algorithm and Features Fusion for Wind Turbine Fault Prediction

Abstract

This research introduces an innovative method using Convolutional Neural Networks (CNNs) to identify mass imbalances in wind turbine rotors through a feature fusion strategy. To address the issue of class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied. A detailed simulation was carried out using a 1.5 MW three-bladed Wind Turbine model, employing tools such as Turbsim, FAST, and Matlab Simulink, to collect rotor speed data under different wind conditions. Mass imbalances were simulated by modifying blade density in the software. The fusion architecture combines feature extraction with Power Spectral Density analysis, improving the CNNs ability to work across both frequency and time domains. The effectiveness of this approach was confirmed through a comparative analysis with 9 classifiers and 4 different dataset combinations, demonstrating its capability in detecting mass imbalances.