Method for carrying out system identification on two-degree-of-freedom flexible leg based on BP neural network algorithm

A BP neural network and system identification technology, which is applied in the field of system identification of two-degree-of-freedom flexible leg systems, can solve problems such as modeling methods relying on accurate dynamic equations, achieve strong robustness and fault tolerance, and reduce errors , the effect of strong nonlinear mapping ability

Inactive Publication Date: 2020-02-21
BEIJING UNIV OF POSTS & TELECOMM
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to design a more precise control system for the two-degree-of-freedom flexible leg and solve the problem that traditional modeling methods rely on accurate dynamic equations, the present invention proposes a system based on BP neural network algorithm for the two-degree-of-freedom flexible leg. method of identification

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
  • Method for carrying out system identification on two-degree-of-freedom flexible leg based on BP neural network algorithm
  • Method for carrying out system identification on two-degree-of-freedom flexible leg based on BP neural network algorithm
  • Method for carrying out system identification on two-degree-of-freedom flexible leg based on BP neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention relates to a system identification method for a two-degree-of-freedom flexible leg system, the steps of which are as follows:

[0027] The principle of the invention is to use the BP neural network to establish a system identification model of the two-degree-of-freedom flexible leg, and then predict the position and posture of the end foot of the flexible leg. The specific steps are as figure 1 shown, as described below:

[0028] (1) Collect sample data, and calculate the position angle θ of the hip joint and knee joint of the two-degree-of-freedom flexible leg through actual measurement 1 , θ 2 and the pose of the end foot of the two-degree-of-freedom flexible leg, the position angle data of the two joints are passed through the following formula:

[0029]

[0030] Calculate the output torque of the drive motors of the two joints, in the formula τ 1 , τ 2 is the torque on the hip joint and knee joint; θ 1 , θ 2 is the position angle of u...

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 a method for carrying out system identification on a two-degree-of-freedom flexible leg based on a BP neural network algorithm. The method is used for determining the relationbetween the joint position angle and the tail end foot pose of the two-degree-of-freedom flexible leg. The method comprises the following steps: (1) obtaining position angles theta 1 and theta 2 of hip joints and knee joints of the two-degree-of-freedom flexible leg through actual measurement or calculating to obtain driving motor moments tau 1 and tau 2 of the hip joints and the knee joints and poses of tail end feet of the two-degree-of-freedom flexible leg; (2) constructing a BP neural network structure according to the actual parameters, and training through data measured by an experimentto obtain an identification model of the two-degree-of-freedom flexible leg; and (3) predicting the tail end foot pose of the two-degree-of-freedom flexible leg according to the model. According to the method, the dynamic characteristics of the two-degree-of-freedom flexible leg can be obtained more accurately, and an accurate system identification model is established.

Description

technical field [0001] The invention relates to a system identification method of a two-degree-of-freedom flexible leg system, specifically, the output torque of the hip joint and knee joint driving motor of the two-degree-of-freedom flexible leg is used as an input variable, and the terminal pose of the two-degree-of-freedom flexible leg is used as an output Variables, the method of system identification using BP neural network. Background technique [0002] With the rapid development of science and technology, robots are more and more widely used in people's lives, covering many fields such as medical care, industrial manufacturing, and deep exploration, bringing a lot of convenience to people's lives. However, due to the shortcomings of heavy base, high power consumption, short arm, low load-to-weight ratio, narrow operating space, and poor flexibility, traditional industrial robots have gradually been unable to meet people's needs. At the same time, a large number of st...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 张延恒赵欣
Owner BEIJING UNIV OF POSTS & TELECOMM
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