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

Blast furnace molten iron silicon content online prediction method and system based on deep migration network

A blast furnace molten iron and prediction method technology, applied in biological neural network model, computer-aided design, design optimization/simulation, etc., can solve the problem of low accuracy of online prediction of silicon content in blast furnace molten iron, achieve efficient and accurate prediction, reduce dependence, Solve the effect of low online prediction accuracy

Pending Publication Date: 2021-12-07
CENT SOUTH UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The method and system for online prediction of silicon content in molten iron of blast furnace based on deep migration network provided by the present invention solves the technical problem of low accuracy of online prediction of silicon content of molten iron in existing blast furnace

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
  • Blast furnace molten iron silicon content online prediction method and system based on deep migration network
  • Blast furnace molten iron silicon content online prediction method and system based on deep migration network
  • Blast furnace molten iron silicon content online prediction method and system based on deep migration network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] refer to figure 1 , the method for online prediction of silicon content in blast furnace molten iron based on deep migration network provided by Embodiment 1 of the present invention includes:

[0061] Step S101, using the molten iron temperature data to unsupervisedly train the denoising autoencoder network, and stacking multiple denoising autoencoder networks to obtain a deep denoising autoencoder network;

[0062] Step S102, embedding a dynamic attention mechanism module in the front end of the deep denoising autoencoder network, and adding a layer of regression layer in the back end to obtain a deep network based on the dynamic attention mechanism module, wherein the dynamic attention mechanism module is used to describe the input sample The dynamic relationship between the process variable and the predicted target;

[0063] Step S103, based on the deep network, an online prediction model for the silicon content of the molten iron is obtained, and based on the onli...

Embodiment 2

[0066] The method for online prediction of silicon content in blast furnace molten iron based on deep migration network provided by Embodiment 2 of the present invention includes:

[0067] Step S201, collecting historical data of the blast furnace and performing preprocessing on the historical data of the blast furnace. The preprocessing includes time registration of input and output samples, elimination of abnormal data, normalization processing and variable correlation analysis.

[0068] Specifically, a large amount of historical data is stored in the historical database of the blast furnace, but due to various reasons such as equipment failure or manual operation errors during the collection process, the data cannot truly and accurately reflect the furnace conditions, so the data needs to be preprocessed to Eliminate the above problems and improve the quality of data to build a high-quality data set. Specific steps are as follows:

[0069] (1) Input and output sample time ...

Embodiment 3

[0125] refer to Figure 7 , the embodiment of the present invention provides an online method for predicting the silicon content of blast furnace molten iron based on a deep migration network, taking a 2650m 3 Large-scale blast furnace verification, specifically including the following steps:

[0126] 1) Data preprocessing. Correlation processing is carried out on the data collected on the blast furnace detection device to improve the quality of the data. In this embodiment, the data from August 1, 2020 to December 17, 2020 in the blast furnace historical database are obtained, in which there are 1,160,141 groups of process variables, There are 172,352 sets of molten iron temperature data, and 7,282 sets of silicon content data, including input and output sample time registration, abnormal data processing, normalization processing, and feature selection based on the maximum mutual information coefficient. After processing, there are 111,041 sets of molten iron temperature dat...

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 blast furnace molten iron silicon content online prediction method and system based on a deep migration network. The method comprises the following steps: training de-noising autoencoder networks through molten iron temperature data in an unsupervised manner, and stacking a plurality of de-noising autoencoder networks, thereby obtaining a deep de-noising autoencoder network; embedding a dynamic attention mechanism module into the front end of a deep denoising autoencoder network, obtaining a deep network based on a dynamic attention mechanism, migrating a pre-trained deep network based on the dynamic attention mechanism, and obtaining a molten iron silicon content online prediction model. According to the method and the system, the technical problem of low online prediction precision of blast furnace molten iron silicon content in the prior art is solved, and a dynamic attention mechanism module is embedded into the front end of the deep denoising auto-encoder network, so that a dynamic attention score can be calculated for a process variable of each input sample in real time, the model can dynamically distribute more attention to effective and valuable process variables in each sample, and the molten iron silicon content can be further predicted online more efficiently and accurately.

Description

technical field [0001] The invention mainly relates to the technical field of blast furnace ironmaking, in particular to a method and system for online prediction of silicon content in blast furnace molten iron based on a deep migration network. Background technique [0002] Blast furnace ironmaking is the upstream and key process in the iron and steel process, and the core key unit for the conversion of ferrite material flow. The ironmaking process is a production process of continuous blasting, periodic feeding and iron tapping, and complex physical and chemical reactions in harsh environments such as high temperature, high pressure, and dust. The temperature of molten iron in the hearth of a blast furnace is an important performance index to measure the thermal state in the furnace, the condition of the blast furnace and the quality of molten iron. Due to the closed requirements of the blast furnace smelting process, it is difficult to directly detect the temperature of ...

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): G06F30/27G06N3/04G06F119/08
CPCG06F30/27G06F2119/08G06N3/045
Inventor 蒋朝辉蒋珂谢永芳潘冬桂卫华
Owner CENT SOUTH 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

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