Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

Abstract

When wind speeds are above the rated speed of variable speed variable pitch wind turbines, pitch angles are changed to keep output powers and rotor speeds at their rated values. For wind turbines with nonlinear and complex structure, conventional PID variable pitch controller is difficult to achieve precise control. In this paper, a variable pitch controller combining back-propagation(BP) neural network with PID (BP-PID) is proposed. By real-time detecting the deviation of the rotor speeds, the BP neural network with self-learning and weighting coefficient correction capability is used to adjust the PID parameters online and further to achieve the optimal combination of the PID parameters. Considering various uncertain disturbances and parameter changes on the mechanical components of the wind turbines, an active disturbance rejection pitch controller of the wind turbines is designed based on BP-PID algorithm. Combined with a tracking differentiator, an extended state observer (ESO) is employed to observe the state and disturbance of the system. In addition, in order to compensate the BP-PID variable pitch controller, nonlinear state error feedback control laws are designed by configuring nonlinear structures according to the state deviation between the extended state observer and the tracking differentiator. The simulation results show that the variable pitch active disturbance rejection control (ADRC) based on BP-PID can effectively estimate the system states and disturbances. And the proposed controller has good dynamic performance and strong robustness. INDEX TERMS Wind turbine, pitch control, BP-PID, active disturbance rejection control, extended state observer.

Redes neuronales y aprendizaje por refuerzo en el control de turbinas eólicas

“…Por ejemplo, Asghar y Liu en (Asghar y Liu, 2018a) diseñan un algoritmo neuro-difuso para obtener la velocidad óptima del rotor. En (Ren et al, 2020) se aplica una red neuronal combinada con un PID para el control de turbinas. La red neuronal se usa para ajustar los parámetros del PID mientras el sistema está en funcionamiento.…”

Design of an IMCPID Optimized Neural Network for Stepless Flow Control of Reciprocating Mechinery

“…Then, according to the incremental PID principle [31], the output of IMCPID controller can be written as:…”

PD-Based Optimal ADRC with Improved Linear Extended State Observer

“…However, the design of the control law is complicated and there are many control parameters to be tuned. Ren et al [ 24 ] proposed a back-propagation PID with based on a nonlinear ESO to achieve precise control of wind turbines. The method proposed in [ 24 ] used a neural network to optimize only the parameters of the PID, but did not optimize the parameters of the active disturbance rejection controller, which is detrimental to improving the control performance of the system.…”

“…Ren et al [ 24 ] proposed a back-propagation PID with based on a nonlinear ESO to achieve precise control of wind turbines. The method proposed in [ 24 ] used a neural network to optimize only the parameters of the PID, but did not optimize the parameters of the active disturbance rejection controller, which is detrimental to improving the control performance of the system. In addition, the larger gains of ADRC will amplify noise, which may reduce control performance.…”