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

Method for intelligently detecting multiple flaws of ceramic substrate by using YOLOV4 network

A ceramic substrate and intelligent detection technology, which is applied in the field of deep learning target detection, can solve the problems of difficult detection, small sample size, large size span, etc., and achieve the effect of ensuring detection accuracy, fast and accurate detection, and optimizing detection effect

Active Publication Date: 2022-06-07
JIANGNAN UNIV
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the shape of ceramic substrate defects is changeable, the size span is large, and there are many small targets in gold-rich and porcelain-deficient defects, the sample size is small, and the number of various types of defects is unevenly distributed. for accurate testing

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 intelligently detecting multiple flaws of ceramic substrate by using YOLOV4 network
  • Method for intelligently detecting multiple flaws of ceramic substrate by using YOLOV4 network
  • Method for intelligently detecting multiple flaws of ceramic substrate by using YOLOV4 network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0037] The present application discloses an intelligent detection method for multiple defects of a ceramic substrate using the YOLOV4 network. The method includes the following steps:

[0038]Step 1, prepare a ceramic substrate defect training set containing several sample images. The sample image is an image of a ceramic substrate containing a defect target, and the position and size information, confidence level and target category of the real frame are marked at the defect target. The target category is also That is to reflect the defect type. The ceramic substrate defect training set in this application covers various types of defect targets, so that the intelligent detection model obtained by subsequent training can detect various types of defect targets.

[0039] In actual operation, labellmg image labeling software is used for manual l...

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 intelligently detecting multiple flaws of a ceramic substrate by using a YOLOV4 network, and relates to the field of deep learning target detection.According to the method, an intelligent detection model is constructed based on the YOLOV4 network to intelligently detect the multiple flaws of the ceramic substrate, a calculation method of a loss function is optimized according to the characteristics of the flaws of the ceramic substrate, and the defect detection accuracy of the ceramic substrate is improved. A confidence coefficient loss function in the loss function is calculated by utilizing the confidence coefficients of prediction frames and corresponding real frames in all unit grids based on a gradient equalization mechanism, so that the detection accuracy of the intelligent detection model obtained by training can be ensured, and meanwhile, the defect detection rate is greatly improved; and the defects of the ceramic substrate can be efficiently, quickly and accurately detected.

Description

technical field [0001] The invention relates to the field of deep learning target detection, in particular to an intelligent detection method for multiple defects of a ceramic substrate using a YOLOV4 network. Background technique [0002] Ceramic substrate is the basic material of current high-power power electronic circuit structure technology and interconnection technology, and has a wide range of applications in the field of electronic manufacturing. In the production process of ceramic substrates, due to the influence of manufacturing process and equipment problems, five typical defects such as damage to the gold-plated layer, excess gold on the edge and lack of ceramics on the ceramic substrate, contamination and foreign matter will appear. It is of great practical significance to study the efficient, fast and accurate automatic detection method of ceramic substrate defects for the quality control and fault detection of ceramic substrates. [0003] With the developmen...

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): G06T7/00G06T7/60G06V10/74G06V10/762G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/001G06T7/60G06N3/08G06T2207/10004G06T2207/30108G06N3/045G06F18/23213G06F18/22G06F18/24
Inventor 朱启兵郭峰黄敏赵鑫
Owner JIANGNAN UNIV
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