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

Method for forecasting alloy composition of molten steel during LF refining process

A technology of refining process and alloy composition, applied in the field of metallurgy, can solve the problems affecting the refining rate of LF refining process, and achieve the effect of reducing refining time and refining cost

Inactive Publication Date: 2013-04-24
SHANXI TAIGANG STAINLESS STEEL CO LTD
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] During the refining process, the alloy composition of molten steel at the sampling time can be obtained through the laboratory value, but the alloy composition of the molten steel at the non-sampling time cannot be obtained. Operators often can only estimate the laboratory value at the non-sampling time through the laboratory value at the sampling time, so that It will affect the refining rate of the LF refining process

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 forecasting alloy composition of molten steel during LF refining process
  • Method for forecasting alloy composition of molten steel during LF refining process
  • Method for forecasting alloy composition of molten steel during LF refining process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The matching software of the present invention is an intelligent forecasting algorithm of molten steel composition in the LF furnace refining process, and its forecasting steps are:

[0059] 1. Collect the test data of the molten steel composition and the quality data of the premelt at the end of the previous process before refining;

[0060] 2. In the refining process, a three-layer BP neural network is established and the logarithmic S-type transfer function is activated. The input layer is the composition value of each element of C, Si, Mn, P, S, molten steel temperature, molten steel weight, and alloy addition. The content of the main elements contained in the alloy and the yield of the element; the hidden layer is twice the number of variables in the input layer; the output layer is the predicted value of the composition including C, Si, Mn, P, and S elements.

[0061] 3. Carry out model training.

[0062] The weight threshold training of common steel types is carri...

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 forecasting alloy composition of molten steel during the LF refining process, which belongs to the technical of metallurgy. The method comprises the following steps: (1) collecting the composition testing data of molten steel and the quality data of pre-melting matters when the former step before refining is ended; (2) establishing an artificial neural network model during the refining process; and (3) carrying out the mode training. The method disclosed by the invention adopts the alloy composition data obtained in the former LF step as the initial value, adopts the molten steel testing value during the refining process as the standard value at sampling time, considers the influence on molten steel composition after adding the related pre-melting matters, slagging material, silk threads, desoxidant and desulphurizer, and adopts the BP neural network to forecast the alloy composition of molten steel at the non-sampling time. The method disclosed by the invention can forecast the alloy composition of molten steel in real time during the LF refining process, can effectively reduce the LF refining time and can reduce the refining cost, so that the LF refining process can be quickly finished.

Description

technical field [0001] The invention belongs to the technical field of metallurgy, and in particular relates to a method for predicting alloy components of molten steel during the refining process of an LF furnace. Background technique [0002] Before the refining of the LF furnace starts, the composition of the molten steel before the end of the previous process is obtained through the test value. When the refining starts, the addition of the premelt related to the production plan will make the alloy composition of the molten steel different from the test data provided by the previous process; during the refining process, Generally, alloy materials are added to adjust the composition of molten steel according to the test value, so as to meet the refining requirements of molten steel composition. At the same time, the addition of slagging materials, deoxidizers, and desulfurizers will also affect the alloy composition of molten steel. [0003] During the refining process, th...

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): C21C7/00
Inventor 杨斌虎赵小彦郝旭明张振祥韩晓东郝娜程宵白小霞
Owner SHANXI TAIGANG STAINLESS STEEL CO LTD
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