Permanent magnet spherical motor mechanical decoupling control method based on neural network identifier

A neural network and decoupling control technology, applied in the field of dynamic control of permanent magnet spherical motors, can solve problems such as the robustness requirements of the external disturbance system without considering the model estimation error system, the static and dynamic performance of the algorithm is not ideal, and achieve the realization of Dynamic decoupling control, improved static and dynamic performance, good real-time effect

Inactive Publication Date: 2009-02-18
TIANJIN UNIV
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this algorithm is only suitable for occasions that do not consider model estimation errors and external disturbances of the system, and require low robustness of the system
In fact, model estimation errors and system external disturbances widely exist in the control process of spherical motors, and if their effects are considered, the static and dynamic performance of this algorithm is not ideal

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Permanent magnet spherical motor mechanical decoupling control method based on neural network identifier
  • Permanent magnet spherical motor mechanical decoupling control method based on neural network identifier
  • Permanent magnet spherical motor mechanical decoupling control method based on neural network identifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The structural block diagram of the spherical motor mechanical decoupling control method containing the neural network identifier of the present invention is as follows figure 1 shown. The main controller of Embodiment 1 of the present invention adopts conventional servo control, namely PD control, and uses a neural network identifier to realize feedforward neural network control.

[0040] According to the Lagrangian method or Newton-Euler method, the dynamic equation of the spherical motor can be obtained as follows:

[0041] M ( θ ) θ . . + C ( θ , θ . ) θ . + τ f = τ - - - ( ...

Embodiment 2

[0085] Since the dynamic model of the spherical motor is relatively complicated, in embodiment 2, the PD part in the formula (4) is changed into a two-dimensional fuzzy control, and each fuzzy controller controls a rotation axis of the Calton angle of the spherical motor, To enhance the robustness of the control system. Two-dimensional fuzzy controller such as Figure 6 shown. In the figure, k e and k ec is the quantization factor, and e and The changing range of is converted to the input universe; k u is a proportional factor, which converts the output of the fuzzy control part (corresponding to the output domain of the fuzzy control) into the actual output of the fuzzy controller. The structural block diagram of the control method of embodiment 2 is as Figure 7 shown.

[0086] The fuzzy control input domain and output domain of this two-dimensional fuzzy controller are both set to [-6, 6], and the seven language sets are defined as {PB, PM, PS, Z, NS, NM, NB}, each ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the dynamic control technique field of the permanent magnet spheric electromotor, and relates to a decoupling method for the electromotor dynamics. The method comprises a servo controller and a neural network feedforward controller; wherein, the neural network feedforward controller can be established according to the following steps: a dynamical equation of the spheric electromotor is established; two layers of neural network identifiers are established, input signals of the neural network identifiers are position angle vectors Theta (Alpha, Beta, Gamma ) which are output by the spheric electromotor, and output signals thereof are feedforward compensation torque vectors (Tau[nAlpha], Tau[nBeta], Tau[nGamma]); a weight adjusting equation which is provided with additional momentum can be used to train the neural network identifiers; the neural network identifiers are identified online, so as to achieve the feedforward compensation of the torque vectors (Tau[nAlpha], Tau[nBeta], Tau[nGamma]). The method can effectively weaken module estimation errors and interference effects outside the system.

Description

technical field [0001] The invention belongs to the technical field of dynamic control of permanent magnet spherical motors. The invention relates to a mechanical decoupling control method of a spherical motor. Background technique [0002] In the research and application fields of modern aerospace, military, chemical industry, industrial automation and intelligent robots, it is increasingly necessary to realize multi-degree-of-freedom motion. Traditionally, to achieve multi-degree-of-freedom motion, it is often necessary to jointly control multiple single-degree-of-freedom motors connected through complex transmission mechanisms. This not only makes the mechanical structure of the system complex and bulky, but also makes the system respond slowly, with low positioning accuracy and poor dynamic performance. So people began to pay attention to spherical motors that can provide 2-3 degrees of freedom of motion. The three-degree-of-freedom spherical motor can greatly simplif...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G05B13/02
Inventor 夏长亮郭辰史婷娜
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap