Neural network prediction decoupling controller for five-degree-of-freedom bearingless permanent magnet synchronous generator

A decoupling controller and neural network technology, applied in the field of bearingless permanent magnet synchronous generators, achieves the effects of low sample requirements, improved control efficiency, and simple and easy-to-understand principles

CN114448310APending Publication Date: 2022-05-06JIANGSU UNIV
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-05-06

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a five-degree-of-freedom bearingless permanent magnet synchronous generator neural network prediction decoupling controller, which is characterized in that the input end of a fuzzy neural network system is respectively connected with two neural network dynamic prediction modules in series, and the output end of the fuzzy neural network system is connected with a composite controlled object comprising a five-degree-of-freedom bearingless permanent magnet synchronous generator; the first neural network dynamic prediction module outputs a composite control quantity ja at the t + 1 moment, and the second neural network dynamic prediction module outputs a composite control quantity jb and a power generation voltage control quantity at the t + 1 moment; the output of the fuzzy neural network system is a power generation winding reference voltage component, a rotor radial suspension force winding reference voltage component and a rotor axial displacement control voltage at the t + 1 moment; according to the method, the advantages of low sample requirement of fuzzy logic control and good dynamic performance of the neural network on system learning ability and prediction control are combined, various static and dynamic performance such as good rotor radial displacement and power generation voltage control can be obtained, and the control efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The present invention relates to a bearingless permanent magnet synchronous generator, in particular its predictive decoupling controller, suitable for nonlinear, multi-variable five degrees of freedom bearingless permanent magnet synchronous generator high-speed and high-precision control, widely used in electric vehicle flywheel energy storage system, aerospace, power generation and other fields Background

[0002] Permanent magnet synchronous generators are not only small in size, low cost and reliable in operation, but also have the advantages of high efficiency, high power factor, fast response and wide power generation voltage range. Bearingless permanent magnet synchronous generator is the combination of bearingless technology and magnetic bearing technology with permanent magnet synchronous generator, that is, by adding an additional set of suspension force windings to make the permanent magnet synchronous generator rotor suspended, to avoid mechan...

Examples

Embodiment Construction

[0018] as Figure 1 The five degrees of freedom of the present invention without bearing permanent magnet synchronous generator neural network prediction decoupling controller 17, which consists of two neural network dynamic prediction modules 4, 5 and a fuzzy neural network system 3 in series, the outputs of the two neural network dynamic prediction modules 4 and 5 are connected in series to the input end of the fuzzy neural network system 3, and the input terminal of the fuzzy neural network system 3 is connected comprising a composite controlled object 2 of the five-degree-of-freedom bearingless permanent magnet synchronous generator.

[0019] The output of the composite controlled object 2 is the five-degree-of-freedom bearingless permanent magnet synchronous generator in the x and y directions of four radial displacements {x). a ,y a ,x b ,y b }, an axial displacement z a and a power generation voltage u. The input of the first neural network dynamic prediction module 4 is th...