Abstract: A new wind turbine structure flexibility evaluation method based on the radial basis function（RBF） neural network is presented in this paper.The effect of multiple load components on the stracture stress of the wind turbine is comprehensively considered to wind stress into account.Compared with the current single variable and linear interpolation prediction methods,this new flexibility evaluation method has higher precision and is more reliable.Compared with the finite element method,it is no doubt a more efficient way.The strength evaluation of wind head parts and key connection bolt can be completed in one minute by using this evaluation method,and the maximum stress prediction error is less than 1%.