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

Converter steel-making endpoint determination method and system based on flame image CNN recognizing and modeling process

A flame image, converter steelmaking technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems that artificial features cannot represent complete information of flame blowing and are subjective, and cannot judge the end point of converter steelmaking.

Active Publication Date: 2016-06-15
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a method and system for judging the end point of converter steelmaking based on flame image CNN recognition modeling, which is used to solve the shortcomings that artificial features are difficult to represent the complete information of flame blowing and has subjectivity, and solve the problem of inability to real-time and accurate conversion of converters. The problem of judging the end point of steelmaking

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
  • Converter steel-making endpoint determination method and system based on flame image CNN recognizing and modeling process
  • Converter steel-making endpoint determination method and system based on flame image CNN recognizing and modeling process
  • Converter steel-making endpoint determination method and system based on flame image CNN recognizing and modeling process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Example 1: Such as Figure 1-3 As shown, a method for determining the end point of converter steelmaking based on flame image CNN recognition modeling, the specific steps of the method are as follows:

[0059] Step1. Collect the flame image of the converter furnace mouth to provide data for the next image processing; the size of the collected image is 640×480;

[0060] Step2. First convert the collected flame image to HSI space. The relationship between HSI color space and RGB color space is shown in the following formula, where R, G, and B respectively represent the three components of red, green and blue:

[0061] I = 1 3 ( R + G + B ) ;

[0062] S = 1 - 3 R + G + B [ m i n ( R , G , B ) ] ;

[0063] H = arccos { [ ( R - G ) + ( R - B ) ] / 2 [ ( R - G ) 2 + ( R - B ) ( G - B ) ] 1 ...

Embodiment 2

[0083] Example 2: Such as Figure 1-3 As shown, a method for determining the end point of converter steelmaking based on flame image CNN recognition modeling, the specific steps of the method are as follows:

[0084] Step1. Collect the flame image of the converter furnace mouth to provide data for the next image processing;

[0085] Step2. First convert the collected flame image to HSI space. The relationship between HSI color space and RGB color space is shown in the following formula, where R, G, and B respectively represent the three components of red, green and blue:

[0086] I = 1 3 ( R + G + B ) ;

[0087] S = 1 - 3 R + G + B [ m i n ( R , G , B ) ] ;

[0088] H = arccos { [ ( R - G ) + ( R - B ) ] / 2 [ ( R - G ) 2 + ( R - B ) ( G - B ) ] 1 / 2 } G ≥ B ; 2 ...

Embodiment 3

[0109] Example 3: Such as Figure 1-3 As shown, a method for determining the end point of converter steelmaking based on flame image CNN recognition modeling, the specific steps of the method are as follows:

[0110] Step1. Collect the flame image of the converter furnace mouth to provide data for the next image processing; the size of the collected image is 640×480;

[0111] Step2. First convert the collected flame image to HSI space. The relationship between HSI color space and RGB color space is shown in the following formula, where R, G, and B respectively represent the three components of red, green and blue:

[0112] I = 1 3 ( R + G + B ) ;

[0113] S = 1 - 3 R + G + B [ m i n ( R , G , B ) ] ;

[0114] H = arccos { [ ( R - G ) + ( R - B ) ] / 2 [ ( R - G ) 2 + ( R - B ) ( G - B ) ] 1 ...

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 relates to a converter steel-making endpoint determination method and a system based on the flame image CNN recognizing and modeling process and belongs to the field of artificial intelligence. According to the technical scheme of the invention, firstly, acquired flame images are converted into an HSI space, and then the threshold segmentation is conducted. Secondly, segmented images are combined and a simply connected flame image is obtained through the post processing process. Thirdly, disturbance points generated due to poor segmentation are removed, and then segmented images can be obtained. Fourthly, images are pre-processed and a convolution neural network recognition model is constructed. The pre-processed images are directly input into the convolution neural network recognition model and the network is trained in the off-line state based on the gradient descent method. The off-line well trained convolution neural network recognition model is subjected to on-line judgment. The flame image of a converter is acquired, pre-processed and input into the network model and then the model outputs a judgment result. According to the technical scheme of the invention, the subjective influence on the converter flame observation process of workers and the error of the endpoint determination among workers can be avoided. Meanwhile, the endpoint of the converter can be accurately judged in real time.

Description

technical field [0001] The invention relates to a method and system for judging the end point of converter steelmaking based on flame image CNN recognition modeling and belongs to the technical field of artificial intelligence. Background technique [0002] The judgment of the end point of converter blowing is an important operation at the end of converter blowing. The prediction of the end point of converter in small and medium-sized steel mills in my country mainly relies on manual experience and sub-lance detection. The existing converter steelmaking mainly relies on manual experience and sub-lance detection to judge the end point of the converter. Manual experience relies on workers to visually observe the color, shape, texture, strobe and other characteristics of the converter flame, and make a judgment on the end point of the converter based on experience. However, in actual situations , the operator will be subjectively affected when observing the converter flame, and...

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): G06K9/62G06K9/46
CPCG06V10/56G06F18/24
Inventor 刘辉江帆
Owner KUNMING UNIV OF SCI & 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