Fuzzy neural network prediction decoupling control system of bearingless permanent magnet synchronous generator

Abstract

The invention discloses a bearingless permanent magnet synchronous generator fuzzy neural network prediction decoupling control system which is formed by connecting a neural network prediction controller and a fuzzy neural network inverse controller, and the fuzzy neural network inverse controller is composed of a fuzzy neural network system, two analog switch signal modulation modules and an IGBT three-phase inverter. The neural network prediction controller predicts an eccentric displacement control quantity and a voltage control quantity at the next moment, the fuzzy neural network system outputs a suspension force winding reference voltage and a power generation winding reference voltage, and the suspension force winding reference voltage is input into a first analog switch signal modulation module; the reference voltage of the power generation winding is input into a second analog switch signal modulation module; and by adopting the predicted displacement at the next moment, the method not only has the advantages of simple inverse system structure and strong robustness, but also reliably realizes decoupling control between the radial suspension force of the generator and the generating voltage by combining the advantages of fuzzy logic control.

Description

technical field [0001] The invention relates to a bearingless permanent magnet synchronous generator, in particular to a predictive decoupling control system for a bearingless permanent magnet synchronous generator, which is used to control a bearingless permanent magnet synchronous generator and is widely used in wind power generators, gas turbine generators, Hybrid electric vehicle, electric vehicle flywheel energy storage system, aerospace, electric power generation and other fields. Background technique [0002] The bearingless permanent magnet synchronous generator is a complex system with strong coupling, nonlinear multi-input and multi-output. The traditional PID linear control method uses direct torque control to perform double closed-loop decoupling control on the generator. Although the generator can be Decoupling, but the structure of the control system is relatively complex, and in actual operation, due to the complexity of the generator system, it is difficult t...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the above-mentioned problems existing in the existing bearingless permanent magnet synchronous generator control technology, and propose a bearingless permanent magnet synchronous generator with simple structure, strong robustness, low sample requirements, and fast learning speed. Neural network predictive decoupling control system, combining the respective advantages of fuzzy logic control, neural network control, neural network predictive and inverse systems

Images