RBF neural network pitching interference compensation wind power cabin suspension control method

Abstract

Specific to a complex control structure, a high failure rate and other problems existing in axial suspension and pitching multi-degree-of-freedom control of a wind power cabin, wind power cabin suspension control based on RBF neural network pitching interference compensation is provided. A cabin suspension composite controller is adopted as an independent suspension converter to provide current reference, and suspension control of a cabin axial and pitching two-degree-of-freedom system is completed synergistically. State feedback control, RBF neural network pitching interference estimation anda pitching interference compensation robust controller are included. RBF neural network pitching interference estimation adopts a composite index composed of air gap deviation, deviation differentials, deviation integration and a current Gaussian function value, RBF neural network weight and output are adjusted self-adaptively, cabin pitching interference is estimated in real time, and the pitching interference compensation robust controller is a controller conducting real-time obtaining and compensation on RBF neural network pitching interference evaluated errors.

Description

technical field [0001] The invention discloses an RBF neural network pitching interference compensation method for the suspension control of a wind power nacelle, which is an effective control method for solving the high operation cost and complicated control structure of multi-degree-of-freedom magnetic suspension, and belongs to the field of electrical engineering control. Background technique [0002] The wind turbine yaw system is the core component of large and medium-sized wind turbines, which realizes wind turbine blades facing the wind and wind energy capture. At present, the wind turbine yaw system adopts a multi-motor and multi-gear drive structure, which has problems such as large yaw power consumption and high failure rate. The New Energy Research Institute of Qufu Normal University proposed a wind-powered magnetic suspension yaw system, including a suspension winding, a yaw stator, and a yaw rotating body that integrates the nacelle and the suspension winding. W...

AI Technical Summary

Problems solved by technology

However, the multi-disturbance problem in the axial suspension seriously affects the suspension stability of the nacelle. The adaptive method is used to estimate and compensate the disturbance, and a certain control effect has been achieved. However, the axial disturbance includes wind speed, axial pressure disturbance, cabin pitch disturbance and other unknown Interference, traditional adaptive control has limited control ability when the structure and parameters are completely unknown, and cannot effectively estimate the interference with unknown structure

The RBF neural network has a strong ability to approximate unknown uncertainties, but there are also problems of approximation and estimation errors, which will also cause the suspension fluctuation of the wind turbine nacelle

Images