A Physics-Based and Data-Driven Feature Extraction Model for Blades Icing Detection of Wind Turbines

Blades icing will seriously affect the performance of wind turbines with respect to power loss and dynamic load increase. Blades icing detection technique becomes necessary to advance de-icing maintenance. Extracting effective features from supervisory control and data acquisition (SCADA) data has become a challenging task during operating conditions under icing. Current research work lacks for the integration of physical information and insufficient analysis of icing dynamic evolution in the process of feature extraction. In order to eliminate these deficiencies, a multilevel feature extraction model combined with physical information and intelligent algorithm (MFT-PI) is proposed in this article. First, features that characterize the severity of icing are extracted by power characteristic curve technology and feature selection technology in the transient feature extraction level. These techniques are driven by the information of power loss and icing mass growth. Second, a fully connected neural network integrated with triplet loss function is designed for extracting fusion feature, which considers the similarity of data distribution between early-icing stage and non-icing stage. Finally, the proposed feature extraction model is evaluated in two icing wind turbines. Results show that fusion features extracted from the proposed model is more stable, reliable, and accurate by comparing the performance of other feature groups in different classifiers.