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

Gluing quality database construction method based on improved extreme learning machine

A technology of extreme learning machine and construction method, which is applied in the field of automobile gluing detection, to achieve the effect of increasing the calculation speed, increasing the operating speed, and improving the problem of low precision

Inactive Publication Date: 2020-06-02
CHANGCHUN UNIV OF TECH
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The problem to be solved by the present invention is to solve the deficiency of the glue quality database construction in the existing robot visual detection technology, and propose a method for establishing the glue quality database of the improved extreme learning machine

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
  • Gluing quality database construction method based on improved extreme learning machine
  • Gluing quality database construction method based on improved extreme learning machine
  • Gluing quality database construction method based on improved extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Further description below in conjunction with accompanying drawings.

[0047] like figure 1 As shown in the general flow chart, the image collected offline by the gluing visual inspection device on the gluing track is processed to obtain the pixel distance, and the proportional coefficient is calculated according to the parameter information of the standard glue strip.

[0048] The coordinates of each position of the robot are used as input, and the proportional coefficient obtained through image processing and calculation is used as output to establish a glue quality database.

[0049] like figure 2 The offline establishment of glue quality database is shown in the flow chart and may specifically include the following steps:

[0050] Network initialization, according to the input and output sequence of the system, determine the number of network input layer nodes L, the number of hidden layer nodes H, and the number of output layer nodes O.

[0051] To determine th...

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 gluing quality data construction method based on an improved extreme learning machine. According to the method, a wavelet theory is introduced into an extreme learning machine; a hidden layer excitation function is constructed by utilizing a wavelet function and any piecewise continuous nonlinear function, a telescopic factor and a translation factor of the wavelet function are initialized according to an input data range, and a gluing quality data construction method based on an improved extreme learning machine is provided in combination with an extreme learning machine sequence inertia online learning method. According to the method, the problem that input data does not have a proportionality coefficient corresponding to the input data in online detection of the gluing quality is solved, necessary prediction information is provided for any position of the gluing track, whether the quality information of the adhesive tape is qualified or not is judged, the detection difficulty of workers is reduced, and the production efficiency of automobile enterprises is improved.

Description

technical field [0001] The invention relates to a method for constructing glue quality data based on an improved extreme learning machine, which belongs to the field of automobile glue detection. Background technique [0002] With the increasing maturity of robot technology and the rapid development of the automobile industry, more and more industrial robots are put into automobile production. It is gradually completing the transformation from manual gluing to robot gluing. Automatic gluing has become a trend. The quality of gluing is easily affected by excessive dilution or viscosity caused by changes in heating temperature, as well as being affected by gluing. The inaccurate coordination between the glue output of the gun and the glue application speed of the robot will affect it. Therefore, it is necessary to inspect the glue application. Nowadays, visual online inspection has become a trend. [0003] Chinese invention patent "On-line Visual Detection Device and Method f...

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): G06K9/62G06N3/04G06N20/00
CPCG06N3/048G06N3/045G06F18/214
Inventor 刘克平乔宇杨宏韬刘富凯李岩
Owner CHANGCHUN 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