Neural network compensation control method for capturing maximum wind energy in wind power system

Abstract

The invention relates to a neural network compensation control method for capturing maximum wind energy in a wind power system. The neural network compensation control method includes a, acquiring the speed of the wind, and acquiring a reference value of the speed of a wind turbine and a corresponding disturbance speed of the wind turbine according to the wind speed, a reference value of a tip speed ratio and a gear ratio of a gear box; b, acquiring a speed error according to the reference value of the speed of the wind turbine and a speed value of the wind turbine, adopting the PID closed-loop regulation on the reference value of the speed of the wind turbine and the speed error, and acquiring a reference value of the steady torque of the wind turbine; c, adopting the reference value of the steady torque of the wind turbine and the disturbance speed of the wind turbine as the input of the the BP neural network, adopting the PSO (particle swarm optimization)algorithm to train until a required torque control value of the wind turbine is outputted, and accordingly controlling the torque of the wind torque through the torque control value of the wind turbine. By the aid of the neural network compensation control method, effective control of the torque of the wind turbine is realized, cost is reduced, adapting range is wide, and the neural network compensation control method is safe and reliable.

Description

technical field [0001] The present invention relates to a neural network compensation control method, in particular to a neural network compensation control method for maximum wind energy capture of a wind power system, specifically a method for neural network compensation control for maximum wind energy capture of double-fed wind turbines, belonging to wind power control technical field. Background technique [0002] Wind energy is one of the most important components of new energy, and it is also the fastest-growing clean energy. It is a new energy with development value and commercial development prospects. When the wind speed is below the rated value, how to effectively improve the utilization coefficient of wind energy has attracted widespread attention. The more commonly used methods include PID control and LPV control. PID control obtains the maximum wind energy by tracking the optimal blade tip speed ratio curve. However, the PID control method is limited to the op...

AI Technical Summary

Problems solved by technology

PID control obtains the maximum wind energy by tracking the optimal blade tip speed ratio curve. However, the PID control method is only limited to the operation of the wind turbine at the linear steady-state operating point. Once the wind turbine slightly deviates from the stable operating point, it will cause the wind turbine to run unstable.

LPV gain scheduling control only guarantees the H∞ stability of the wind turbine, but cannot deal with the uncertain information of the wind turbine, and the operation of the wind turbine is affected by many uncertain factors, so the effect of LPV control is not ideal

Images