An Information Transmission Model For Offshore Wind Turbines Based On Multi-variable Coupling Relationship

The monitoring variables of offshore wind turbines are widely distributed and coupled with each other, and the relationship of information transfer is fuzzy, which brings great challenges to the research of performance characterization and fault diagnosis of wind turbines. Therefore, an information transmission model for offshore wind turbines was proposes based on multi-variable coupling relationships. First, based on the DBSCAN unsupervised clustering method, the different states corresponding to the performance of the wind turbine are obtained. Second, the general symbolic parameters of the monitoring time series are determined, and the adaptive symbolic processing of the monitoring time series is performed. Finally, the transfer entropy of symbolic sequence pair is calculated and the information transmission model is established. By analyzing the change of information transmission between nodes, the performance is characterized, which provides a good model basis for fault traceability.