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

Post-rolling cooling long-termed self-learning method based on case-based reasoning

A self-learning method and case-based technology, applied in metal rolling, metal rolling, workpiece surface treatment equipment, etc., can solve problems such as coiling difficulties and production stoppages

Inactive Publication Date: 2011-12-21
NORTHEASTERN UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the hysteresis characteristics of post-rolling cooling, there is no good way to intervene in the high or low end cooling temperature of the head in the actual production process, especially due to seasonal factors or changing rolls and specifications, or resuming after a long-term suspension of rolling. In rolling, it is possible that when the first piece of steel is rolled, the coiling is difficult due to the low final cooling temperature of the head, and the stacking of steel will cause production to stop

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
  • Post-rolling cooling long-termed self-learning method based on case-based reasoning
  • Post-rolling cooling long-termed self-learning method based on case-based reasoning
  • Post-rolling cooling long-termed self-learning method based on case-based reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention is described in detail in combination with specific embodiments and accompanying drawings.

[0040] As shown in the attached figure, when rolling the first piece of steel or initial coil for specification change, the post-rolling cooling model first extracts the descriptive features of the current operating conditions (final rolling temperature T F , rolling speed V, rolling piece thickness H, water temperature T W etc.), and retrieve historical cases similar to the current working conditions in the case library according to this description feature. After two-stage filtering, the long-term self-learning coefficients of qualified highly similar working conditions are directly reused; the long-term self-learning coefficients of relatively similar working conditions are corrected, based on actual production considerations, in order to avoid head chilling or overcooling, It needs to be compared with the model self-learning layer data, and the larger ...

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 post-rolling cooling long-termed self-learning method based on case-based reasoning, which belongs to the technical field of rolling. The method comprises the steps: Step 1: case construction; Step 2: case searching; Step 3: case reuse; and Step 4: case correction. The post-rolling cooling long-termed self-learning method based on case-based reasoning has the advantages that: based on a large amount of on-site production data, the method makes decisions for a long-termed self-learning coefficient in a control cooling mathematic model through case construction, case searching, case reuse, case correction and other case-based reasoning technologies beginning with how to effectively utilize empirical knowledge. For rolled steel specifications, the method can effectively prevent heads from a super-cooling phenomenon, and simultaneously can significantly improve the set precision of sheet and strip head final-cooling temperature models. The post-rolling cooling long-termed self-learning method based on case-based reasoning can make post-rolling cooling models possess the self-adaptive capability of changing with working conditions, and can significantly improve the head setting precision of the models.

Description

technical field [0001] The invention belongs to the technical field of rolling, in particular to a long-term self-learning method for post-rolling cooling based on case reasoning. Background technique [0002] The post-rolling cooling process of hot-rolled strip is not only a heat transfer process with many influencing factors, but also a complex industrial control process. As far as the full length of the strip is concerned, the feedback control based on PID or SMITH estimation can theoretically ensure good control of the middle and tail of the strip, while the control of the strip head completely depends on the setting accuracy of the model. Due to the hysteresis characteristics of post-rolling cooling, there is no good way to intervene in the high or low end cooling temperature of the head in the actual production process, especially due to seasonal factors or changing rolls and specifications, or resuming after a long-term suspension of rolling. In rolling, it is possib...

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): B21B45/02
Inventor 彭良贵刘恩洋张殿华刘相华高扬陈华昕
Owner NORTHEASTERN 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