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

Method for accurately detecting surface quality on line in production process of band steel

A production process, surface quality technology, applied in the direction of optical testing flaws/defects, etc., can solve the problem of not being able to realize online detection and classification of multiple defects at the same time, real-time, comprehensive and accurate detection and classification of strip surface defects, and no proposed detection and classification methods to achieve the effect of improving the defect recognition rate, solving the low detection accuracy rate and wide application range

Active Publication Date: 2013-07-10
NORTHEASTERN UNIV LIAONING
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Chinese patent application number 200610117168.6 "Strip Steel Surface Defect Test Platform and Its Detection Method Based on Machine Vision", and Chinese Patent Application Number 200510010049.6 "Linear Image Type Strip Steel Surface Online Defect Detection Device and Detection Method", respectively Disclosed is a method of constructing a test platform that can simulate the linear motion of the strip, and obtain the best image of the strip defect through the cooperation test of the camera and the light source, and realize the detection on a computer through the structure of an online monitoring device. A method for real-time monitoring of the strip surface, but no new detection and classification methods are proposed, and it is impossible to detect and classify the strip surface defects in real time, comprehensively and accurately
[0005] The Chinese patent "On-line detection method for continuous casting slab surface cracks" with application number 200910092408.5 discloses an online detection method for continuous casting slab surface cracks, which realizes online crack detection for high-temperature slabs; but the The method can only realize online detection for one kind of defect, but cannot realize online detection and classification of multiple defects at the same time

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 accurately detecting surface quality on line in production process of band steel
  • Method for accurately detecting surface quality on line in production process of band steel
  • Method for accurately detecting surface quality on line in production process of band steel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] The intelligent optimization algorithm in this embodiment adopts the particle swarm optimization algorithm PSO, and the defect classification adopts a method combining the support vector machine SVM and the particle swarm optimization algorithm PSO.

[0079] Step 1: online acquisition of defect images, the specific steps are as follows:

[0080] Step a: After the photosensitive element on the camera of the camera senses the target, the photosensitive element converts the light intensity signal into an electrical signal and transmits it through the transmission device. Each time a row of images is transmitted, the computer combines a certain number of rows of images into one The images are then stored in the memory of the computer;

[0081] Step b: read an image from the memory of the computer;

[0082] Step c: Use an adaptive threshold edge detection method to judge whether the image has defects. The defect of the image mentioned in the present invention refers to whet...

Embodiment 2

[0122] The intelligent optimization algorithm in this embodiment adopts the differential evolution algorithm DE, and the defect classification adopts a method combining the support vector machine SVM and the differential evolution algorithm DE.

[0123] Step 1: online acquisition of defect images, the specific steps are as follows:

[0124] Step a: After the photosensitive element on the camera of the camera senses the target, the photosensitive element converts the light intensity signal into an electrical signal and transmits it through the transmission device. Each time a row of images is transmitted, the computer combines a certain number of rows of images into one The images are then stored in the memory of the computer;

[0125] Step b: read an image from the memory of the computer;

[0126] Step c: Use an adaptive threshold edge detection method to judge whether the image has defects. The defect of the image mentioned in the present invention refers to whether there is...

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 online accurate detection method of the surface quality of the strip steel production process belongs to the field of online strip steel surface quality detection technology, and particularly involves an image-based online accurate detection method of the surface quality of the strip steel production process. The invention can realize real-time detection and accurate classification of strip surface defects. It includes the following steps: Step 1: Read the defect image stored in the computer; Step 2: Extract the image features of the defect image; Step 3: Based on the image features of the defect image extracted in Step 2, use support vector machine SVM and intelligent optimization algorithm Classify defects using a combined method; Step 4: Store the detection and classification results, and determine whether to end the detection. If so, perform Step 5; otherwise, return to Step 1; Step 5: End.

Description

technical field [0001] The invention belongs to the technical field of on-line detection of strip steel surface quality, in particular to an image-type online accurate detection method of surface quality of strip steel production process. Background technique [0002] Strip steel has become an indispensable raw material for automobile production, machinery manufacturing, chemical industry, aerospace, shipbuilding and other industries. However, due to the influence of rolling equipment, processing technology and other factors, the surface of strip steel is prone to roll marks, scratches, and holes. etc. Dozens of different types of defects seriously affect the performance and quality of the final product. [0003] In the actual industrial production process, due to the limitation of technical conditions, the surface quality inspection of strip steel is mainly done manually. The manual detection method has the following outstanding disadvantages: it is not suitable for detect...

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): G01N21/88
Inventor 唐立新唐振浩
Owner NORTHEASTERN UNIV LIAONING
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