An online learning and active disturbance rejection control-based ANN-inversion robust control scheme of excitation and valve system for turbogenerator

To improve the performance of the terminal voltage and power angle of the turbogenerator, an online learning and active disturbance rejection control (ADRC) based ANN-Inversion(ANNI) robust control scheme is proposed. Firstly, the composite pseudo linear system, which is composed of the ANNI system and the controlled excitation and valve system, is equivalent to a linear system with disturbance. Then, an ESO is designed based on the ADRC method to estimate the states and the disturbance of the composite pseudo linear system online, thus resolves the difficulty of online acquisition of the training samples for online learning of ANN inversion, and the pseudo control input with disturbance compensation is designed for the composite pseudo-linear system. Furthermore, the convergence of the ESO is proved by the linear system theory and an integral order PID controller and a fractional order PID controller are designed for the the composite pseudo linear excitation and valve system. Meanwhile, an online learning algorithm of the ANNI is proposed with online gradient descent method based on offline training, and the convergence of the online learning algorithm of the ANNI is proved according to the Lyapunov stability principles. Finally, case study is fulfilled on a typical two-area four-machine power system and results compared with the conventional AVR/PSS and the offline trained based ANNI control scheme show that the proposed control scheme can greatly improve the transient performance.