Asymmetric electro-hydraulic servo system internal model control method based on neural network model switching, system and readable storage medium

A technology of electro-hydraulic servo system and neural network model, which is applied in the field of machinery and electronics, can solve the problems of in-depth research, difficult control, and nonlinear system modeling, and achieve the effect of avoiding solving and reducing the order

Active Publication Date: 2019-11-22
CHANGSHA AERONAUTICAL VACATIONAL AND TECHNICAL COLLEGE
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the change of the internal flow state of the servo valve is also one of the reasons for the nonlinearity of the system. However, most of the control research, such as feedback linearization control, ignores the influence of the overlapping amount and the flow state, and establishes a nearly linear servo valve model, which will lead to poor performance of the control system. decline
The inverse system method is a branch of feedback linearization control. Dai Xianzhong of Southeast University proposed to use the neural network to approximate the function of nonlinear functions, and to construct an inverse system by exchanging the input and output variables of the original system, and to form a pseudo-linear compound in series with the original system. system, which solves the problems of difficult modeling and control of nonlinear systems, but the research on the application of inverse system method to valve-controlled asymmetric cylinder system has not been in-depth

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
  • Asymmetric electro-hydraulic servo system internal model control method based on neural network model switching, system and readable storage medium
  • Asymmetric electro-hydraulic servo system internal model control method based on neural network model switching, system and readable storage medium
  • Asymmetric electro-hydraulic servo system internal model control method based on neural network model switching, system and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0051] An internal model control method of an asymmetric electro-hydraulic servo system based on neural network switching of multiple inverse system models, the internal structure diagram of the asymmetric electro-hydraulic servo system, as shown in figure 1 As shown, there is a certain amount of negative overlap in the servo valve, and the zero-zone flow characteristics of the servo valve are complex, which affects the control accuracy of the system.

[0052] Step 1: Establish the state model of the asymmetric electro-hydraulic servo system, analyze the reversibility, and reduce the order of the system; use the asymmetric electro-hydraulic servo system in (y 0 , u) Reversible in the neighborhood, solve the relative order of the asymmetric electro-hydraulic servo system, and obtain the model of the inverse system of the asymmetric electro-hydraulic serv...

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 discloses an asymmetric electro-hydraulic servo system internal model control method based on neural network model switching, system and a readable storage medium. A neural network inverse system method is put forward to convert a nonlinear and asymmetric system into a linear system, so as to convert a nonlinear system control problem into a linear system control problem. In view oftwo flow states existing when openings of a servo valve are different, in order to improve the precision of an inverse system model, an inverse system is solved for a small-opening state and a large-opening state through a neural network, switching of the small-opening state model and the large-opening state model is achieved based on the principle of reference speed switching, and a second-orderpseudo-linear system is formed through series connection of the inverse system model and an original system model. Aiming at the problem that a neural network solution inverse model has a certain error, an internal model control strategy is adopted for the pseudo-linear system, so that the influence of the negative superposition amount of the servo valve on the precision is eliminated, the asymmetric response characteristic of the system is eliminated, and the high-precision control of the asymmetric electro-hydraulic servo system is realized.

Description

technical field [0001] The invention belongs to the technical field of machinery and electronics, and in particular relates to an internal model control method, system and readable storage medium of an asymmetric electro-hydraulic servo system based on neural network model switching. Background technique [0002] In order to improve the response performance of the valve-controlled asymmetric cylinder system and eliminate the asymmetric response caused by load and structure, scholars design a differential pressure compensation control strategy, which can reduce the influence of load disturbance to a certain extent, improve the control accuracy of the system, and the method is simple to implement. The processing error of the shoulder of the servo valve port leads to different degrees of negative overlap in the servo valve, which has a certain impact on the system control performance, especially the accuracy. In addition, the change of the internal flow state of the servo valve...

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 & AuthorityApplications(China)
IPC IPC(8): G05B13/04
CPCG05B13/042G05B13/027
Inventor曾乐许文斌谭建平杨俊
OwnerCHANGSHA AERONAUTICAL VACATIONAL AND TECHNICAL COLLEGE