Abstract:Wind turbine blades are prone to damage during operation process,and there are hidden safety risks.To identify and warn the damaged state of wind turbine blades,a strain-based blade material damage model was established through the strain data collected by fiber bragg grating sensors;the finite element model of the wind turbine blade structure was established in the finite element analysis software ABAQUS,and the inherent frequency of the blade was obtained by modal analysis.At the same time,the strain data was performed by Fourier transform to analyze the frequency characteristics of the blade damage condition,and compared with the intrinsic frequency to determine whether the blade resonance occurred.Finally,according to the strain time series data collected during the operation of the wind turbine blade,deep learning method was used to further identify the damage degree of wind turbine blade.The experimental results show that based on the fiber bragg grating strain data,it is a reliable and efficient method to comprehensively analyze and warn the blade damage from blade material strain monitoring,modal frequency monitoring,and neural network model identification,which is important for the health monitoring and safe operation of wind turbines.