Levitation control method of maglev vertical axis wind turbine based on adaptive neural network

Abstract

The invention relates to a levitation control method for a magnetic levitation vertical axis wind turbine based on an adaptive neural network, and belongs to the technical field of electrical engineering. This method adopts the sliding mode adaptive neural network control strategy to make the suspension system of the maglev vertical axis wind turbine realize stable suspension: in the floating stage, the sliding mode control + PID control strategy is adopted to make the rotating body rise to the suspension equilibrium point; Using the adaptive neural network sliding mode control + PID control strategy, use the RBF neural network to estimate the unknown interference item, output to the adaptive neural network sliding mode controller, and then calculate the square root of the output of the sliding mode controller to obtain the suspension air gap The output of the tracking controller, that is, the reference value of the levitation current, is subtracted from its actual value, and the levitation current is tracked by the inner loop levitation current controller to adjust the levitation current in real time to achieve stable levitation. The invention has strong self-adaptive ability, quick dynamic response, strong anti-interference ability and good stability, and can ensure real-time optimum system performance in the whole suspension process.

Description

technical field [0001] The invention relates to a control method, in particular to a suspension control method of a magnetic suspension vertical axis wind turbine based on an adaptive neural network, and belongs to the technical field of electrical engineering. Background technique [0002] At present, high-power wind turbines are mainly horizontal axis wind turbines. However, the horizontal axis wind turbine has inherent defects such as large starting resistance moment, need to yaw to the wind, difficult control, and inconvenient installation, which affect its healthy development. [0003] The magnetic levitation vertical axis wind turbine has no mechanical friction, which greatly reduces the starting resistance torque, so it can further reduce the starting wind speed. It has the advantages of low starting wind speed, easy installation, and no yaw device required. The vertical axis wind turbine does not need to face the wind) wind farm, which is the key direction of future...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is: aiming at the deficiencies and gaps in the prior art, the present invention provides a suspension control method for magnetic levitation vertical axis wind turbines based on an adaptive neural network, through adaptive neural network control, combined with sliding mode control, and adopts The continuous smooth bipolar S-type function replaces the sign function in the traditional sliding mode exponential reaching law, and improves the vertical speed of the magnetic levitation vertical axis wind turbine when the suspension system modeling is inaccurate and is subject to random interference caused by wind speed changes. Suspension control performance of axial wind turbines to achieve stable suspension

Images