Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Contact state recognition method for robot assembly based on GWA-SVM

A contact state and recognition method technology, which is applied in character and pattern recognition, instruments, gene models, etc., can solve the problem of low classification accuracy of assembly force data of industrial robot parts, and achieve the effect of accurate contact state classification

Active Publication Date: 2019-10-22
ZHEJIANG UNIV OF TECH
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing classification methods for the low classification accuracy of the assembly force data of industrial robot parts, the present invention provides a contact state recognition method for robot assembly based on GWA-SVM with high classification accuracy

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
  • Contact state recognition method for robot assembly based on GWA-SVM
  • Contact state recognition method for robot assembly based on GWA-SVM
  • Contact state recognition method for robot assembly based on GWA-SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] refer to Figure 1 ~ Figure 3 , a contact state recognition method for robot assembly based on GWA-SVM, comprising the following steps:

[0041] Step 1: Use the Mitsubishi industrial robot RV-2F to assemble the parts, collect multiple sets of force data during the assembly process through the six-dimensional force sensor 4F-FS001-W200, and establish a training data set {X1 , L 1} with the test dataset {X 2 , L 2}. where X 1 ,X 2 is the six-dimensional force data X=(f x , f y , f z ,m x ,m y ,m z ), f x , f y , f z Respectively force data along the x, y, z axis directions, m x ,m y ,m z are the torque data around the x, y, and z axes, respectively. L 1 , L 2 for respectively with X 1 ,X 2 The corresponding contact state, that is, the category to which the data belongs, the training data X 1 It is divided into 6 categories.

[0042] Step 2:...

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

A contact state recognition method for robot assembly based on GWA-SVM comprises the following steps: 1, using an industrial robot to assemble parts, and collecting force data in the assembly process;2, setting initial parameters; 3, standardizing the data set; 4, initializing a population of SVM parameters by using a chaotic logic mapping strategy; 5, optimizing the population of SVM parametersby using an improved reverse learning strategy; 6, updating the population by using a GWA operator; 7, calculating the fitness of population individuals, and updating the optimal individual; 8, if thecurrent iteration reaches the maximum allowable iteration frequency, executing the step 9, otherwise, t=t+1 and returning to the step 6; 9, ending the SVM parameter optimization process, substitutingthe optimal SVM parameters C and gamma and the training data set into the SVM, and establishing a GWA-SVM based contact state identification model; and 10, identifying the test data set by using thecontact state model, and drawing a classification result graph. The method is high in classification precision.

Description

technical field [0001] The invention belongs to the technical field of machine learning and robot control, and is applicable to the field of contact state identification of parts assembled by industrial robots. Specifically, it relates to a contact state recognition method based on a global optimal whale algorithm (G-best Whale Algorithm, hereinafter referred to as GWA) and a support vector machine (Support Vector Machine, hereinafter referred to as SVM). Background technique [0002] Industrial robots are the core equipment of flexible automation. In the application of production, industrial robots can improve labor productivity, improve product quality, improve working conditions, improve the competitiveness and adaptability of enterprises, promote the establishment and development of new industries, change the labor structure, and promote technological progress in related disciplines. All played a significant social and economic benefits. When the end of the robot arm h...

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): G06K9/62G06N3/12
CPCG06N3/126G06F18/2411G06F18/214
Inventor 胥芳卓信概陈教料张立彬鲍官军
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com