Fault diagnosis of small sample wind turbine blade in ice-covered and damage condition based on ResNet50-SVM and transfer learning

Abstract

Wind turbine blade failures, such as icing and damage, risk safety and efficiency, but limited fault data hinders diagnosis. This study proposes a hybrid framework combining ResNet50-SVM and transfer learning for small-sample fault diagnosis. A coupled simulation model first generates comprehensive dynamic fault data. Vibration signals are converted into time-frequency images via frequency-sliced wavelet transform, then classified by the ResNet50-SVM model. Next, transfer learning adapts simulated pre-trained models to target turbines using minimal samples. Results show the ResNet50-SVM model outperforms LSTM approaches, achieving up to 95.24% accuracy and improving precision and recall by 15–30%. Furthermore, transfer learning improved recall by 20–40% using only 4 to 6 target samples. Ultimately, this scalable simulation-to-reality approach enhances wind farm maintenance efficiency and reduces economic losses.