A novel diffusion model with Shapley value analysis for anomaly detection and identification of wind turbine

Abstract

Anomaly detection and identification methods for wind turbine based on deep learning have become a current research hotspot due to their superior performance in feature extraction. However, the existed methods have limitations in fusion mechanisms of different physical features, and the logical relationships between parameters are difficult to interpret. To address these issues, an innovative Physical Information Dynamic Fusion (PIDF) mechanism and a Dynamic Fusion Conditional Diffusion (DFCD) model are proposed, along with a new operational state evaluation indicator derived from Shapley (SHAP) value analysis, for anomaly detection and fault identification in wind turbines. First, this proposed DFCD model based on PIDF mechanism enables the deep fusion of multiple physical parameters and overcomes the limitations of traditional models, which often struggle to effectively handle diverse information sources . Next, a quantitative approach based on SHAP values is proposed to analyze the relationship between condition parameters and the target parameter for evaluating the wind turbine’s operating status. Finally, a new evaluation indicator for operational state of wind turbines is proposed based on the logical relationship. This indicator provides an intuitive and easily comprehensible way to assess the system behavior learned by the model. Through the analysis of datasets from two real wind farms, this method is capable of effectively identifying the anomaly state and fault locations , which enhances the operational efficiency of wind turbine . This work provides a new scientific tool for technology transfer, which will contribute to intelligent condition monitoring and information management in advanced engineering.

Topics & Concepts