Multilevel Signal Decomposition Layer-Specific Residual Network for Blade Icing Prediction

Wind energy is crucial for sustainable systems but faces reduced productivity due to blade icing. Current detection methods are either costly or heavily reliant on domain-specific knowledge. Data-driven methods show promising performance but encounter challenges such as extracting multi-scale features for blade icing detection from noisy sensor data and addressing the imbalance between icing and non-icing states. To overcome these challenges, we propose an innovative data-driven approach named Multilevel Signal Decomposition Layer-Specific Residual Network (MSD-LRN) for blade icing detection. Our model first employs wavelet decomposition to extract multi-scale features from noisy sensor data and then uses heterogeneous structures to learn the hidden knowledge at each scale. This heterogeneous structure is designed to address the issue of inconsistent information across different scales in wavelet transforms, where information successively decreases. We address data imbalance using resampling techniques. Our approach is validated on three blade icing datasets with varying imbalance ratios, achieving F1 scores of 89.60%, 83.02%, and 78.18%, surpassing existing baselines. Additionally, we introduce random Gaussian noise to test the model's ability to learn robust features from noisy data through wavelet decomposition.