Research on Online Monitoring of Wind Turbine Blade Damage Based on Working Mode Analysis

Abstract

To solve the problem that the blade damage of wind turbine is difficult to be directly monitored on-line, the blade vibration signal is used to realize the on-line monitoring of the blade damage fault. Firstly, based on the working mode analysis theory, an on-line identification method of wind turbine blade modal parameters based on the transmission rate is constructed, and a blade vibration physical experiment platform is built for the experimental verification of this method. Through the comparison with the experimental results of the traditional force hammer excitation method, the accuracy of the working mode parameter identification method is verified; Then, taking the 5MW offshore wind turbine in fast simulation software as an example, the multi condition operation simulation of blade damage is carried out, and the influence law of blade damage on the normal operation parameters and blade modal parameters of the unit is obtained through data analysis; Finally, using different combinations of blade monitoring data, the accuracy of machine learning algorithm (MLA) applied to blade damage fault diagnosis is tested. The results show that the accuracy of blade damage fault diagnosis can be significantly improved by incorporating online identification of blade modal parameters into the unit operation data.