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

A run-length-based method for marking abnormal regions of thermal images of crystallizers

A technology of abnormal area and marking method, which is applied in the field of iron and steel metallurgical continuous casting, can solve the problems of not considering the inclusion characteristics of abnormal areas in the thermal image, and it is difficult to meet the requirements of online detection, so as to reduce storage space, accurately mark, and have strong applicability Effect

Active Publication Date: 2021-04-27
NORTHEAST DIANLI UNIVERSITY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can improve the detection speed of mold bonding. However, this method does not consider the inclusion characteristics of abnormal regions in the thermal image. When there are many abnormal regions with temperature rise in the thermal image, it is difficult to meet the online detection requirements.

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 run-length-based method for marking abnormal regions of thermal images of crystallizers
  • A run-length-based method for marking abnormal regions of thermal images of crystallizers
  • A run-length-based method for marking abnormal regions of thermal images of crystallizers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] A run-based method for marking abnormal regions of crystallizer thermal images according to the present invention comprises the following steps:

[0048] 1) Thermography of the temperature rate of the mold copper plate

[0049] ①Based on the temperature data of mold thermocouples detected online, identify abnormalities in temperature data, and establish a database of billet bonding samples in the mold;

[0050] ②Based on the thermocouple temperature of the crystallizer bonding sample, the temperature at the non-galvanic measuring point is calculated by interpolation, and the temperature rate G[x,y] of the four copper plates is calculated;

[0051] ③According to the corresponding relationship between the temperature rate and the color, the temperature rate thermal image of the mold copper plate is drawn, and the abnormal bonding area in the mold is visualized;

[0052] 2) Run segment search for the area where the slab bonded abnormally

[0053] ①From left to right, from ...

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 present invention is a run-based method for marking abnormal areas of crystallizer thermal images, which is characterized in that it includes: thermal imaging of mold copper plate temperature rate thermal imaging, run-length segment search for billet adhesion abnormal areas, rapid removal of pseudo-adhesion abnormal areas, and run-length segment connectivity It can combine the run-length connectivity judgment method with the detection of the cohesive region, and use the continuity and inclusiveness of the cohesive region to determine the connectivity of the run-length segment. It is scientific and reasonable, has strong applicability, good effect, fast execution speed, and reduces the storage space and the calculation amount of the algorithm, and can realize fast and accurate marking of the bonding area to meet the needs of online detection of breakouts. It is especially suitable for rapid marking of abnormal areas of slabs and round slabs.

Description

technical field [0001] The invention discloses a run-length-based method for marking abnormal regions of thermal images of crystallizers, and belongs to the technical field of iron and steel metallurgy continuous casting. Background technique [0002] In the field of iron and steel metallurgical continuous casting technology, breakout is still the main problem that plagues the safety and stability of continuous casting operations. Bonded breakouts are the main form of breakouts, and other types of breakouts are also accompanied by bonding phenomena. Therefore, the prediction technology for bonded breakouts is mainly developed, and the casting speed is reduced to avoid the occurrence of breakout accidents. [0003] At present, the steel breakout forecasting system at home and abroad mainly detects the temperature of the copper plate, captures the signal mutation or typical mode in the process of bonding occurrence and propagation, and performs online prediction of the steel b...

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): B22D11/16B22D2/00G01K7/02
CPCB22D46/00G01K7/02
Inventor 刘宇徐志强王旭东段海洋姚曼
Owner NORTHEAST DIANLI UNIVERSITY
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