Open access
Sep 2026
A Comparative Hybrid Deep Learning Approach for Robust Stator–Rotor Fault Identification in DFIGs Using FFT‐Based Features and CNN–LSTM–Transformer Models Under Nonstationary Wind Turbulence
Validation results obtained from independent test datasets indicate that the proposed CNN–LSTM–Transformer model achieves the best performance, with lower prediction errors and higher coefficients of determination, consistently outperforming the comparative models across all diagnostic scenarios.
Mehdi Mohammadian Mehr, Mohsen Saniei, Mahmood Joorabian et al.
· Engineering Reports · 0 citations