A contact state recognition method for robot assembly based on gwa-svm

A contact state and identification method technology, applied in machine learning and robot control, using the contact state identification field of industrial robot assembly parts, can solve the problem of low classification accuracy of industrial robot parts assembly force data, and achieve good convergence accuracy and fast convergence. Accurate classification of speed and contact state

Active Publication Date: 2021-08-03
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 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
  • A contact state recognition method for robot assembly based on gwa-svm
  • A contact state recognition method for robot assembly based on gwa-svm
  • A 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: Set...

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, comprising the following steps: Step 1: use industrial robots to assemble parts, and collect force data during the assembly process; Step 2: set initial parameters; Step 3: convert the data set Carry out standardization processing; Step 4: Initialize the population of SVM parameters using the chaotic logic mapping strategy; Step 5: Use the improved reverse learning strategy to optimize the population of SVM parameters; Step 6: Use the GWA operator to update the population; Step 7: Calculate the individual population , and update the optimal individual; Step 8: If the current iteration reaches the maximum allowable number of iterations, then execute Step 9; otherwise, t=t+1 and return to Step 6; Step 9: End the SVM parameter optimization process, and the most The optimal SVM parameters C and γ and the training data set are substituted into the SVM to establish a contact state recognition model based on GWA-SVM; Step 10: Use the contact state model to identify the test data set and draw the classification result map. The classification accuracy of the present invention is higher.

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 Patents(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 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