Transient control parameter identification method of doubly-fed fan based on LSTM-ISO

Aiming at the problem that it is difficult to obtain the control parameters of doubly-fed fan (DFIG) with high accuracy under transient working condition, a high-accuracy identification method of DFIG control parameters based on long short-term memory (LSTM) and improved snake optimization algorithm (ISO) is proposed. Firstly, the RT-LAB semi-physical simulation platform is used to measure and obtain the hardware in-loop data of the DFIG controller, and the identification model of the DFIG model is constructed in Matlab/simulink; then, the distance correlation coefficient method is used to select the high correlation parameters of the transient phases of the wind turbine; and the control parameters are optimally identified by using the proposed LSTM-ISO method, and compared with the measured data, and the proposed method is verified. The proposed LSTM-ISO method is optimally utilized to identify the control parameters, and compared with the measured data to verify the feasibility, effectiveness and practicality of the proposed method. The results show that compared with the traditional identification method, the proposed LSTM-ISO identification method can effectively improve the identification accuracy of the control parameters of doubly-fed wind turbines under transient conditions.