Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for predicting temperature of dead stock column of iron-making blast furnace core

A technology of ironmaking blast furnace and prediction method, which is applied in the direction of prediction, instrument, character and pattern recognition, etc. It can solve the problems of large local errors, etc., and achieve the effect of improving early warning ability, improving prediction accuracy and optimizing prediction accuracy

Inactive Publication Date: 2021-10-29
ANHUI UNIVERSITY OF TECHNOLOGY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: how to solve the problem that the model in the existing forecasting method is to fit the overall data, resulting in relatively large local errors, which is mainly manifested in the change trend of the predicted value of the temperature value of the furnace core dead material column compared with the actual value at the previous moment. To solve the problem that the value is different from the previous moment, a method for predicting the temperature of the dead material column in the core of the ironmaking blast furnace is provided. The data studied by this method is a time series. The association of the column temperature change trend can adjust part of the predicted value of the regression model according to the correct change trend, further reduce the error, and optimize the prediction result of the dead material column temperature of the ironmaking blast furnace core

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 predicting temperature of dead stock column of iron-making blast furnace core
  • Method for predicting temperature of dead stock column of iron-making blast furnace core
  • Method for predicting temperature of dead stock column of iron-making blast furnace core

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] This embodiment provides a technical solution: a method for predicting the temperature of the core dead stock column of an ironmaking blast furnace, using the time series information of the parameters and the temperature data of the furnace core dead stock column to analyze the relationship between their changing trends and reduce the impact on the The prediction error of the furnace core dead column temperature includes the following steps:

[0042] Step 1: Collect sample data and preprocess, divide the training set and test set based on the maximum information coefficient extraction feature to obtain data set 1, and divide each column in data set 1, namely the extracted parameter sequence and furnace core dead material column temperature sequence in time series The change trend is represented by 1 or -1, and data set 2 is obtained.

[0043] Step 2: Use the ridge regression method to fit the regression model between the parameters and the furnace core dead column tempe...

Embodiment 2

[0064] Step 1: Collect and preprocess the data during blast furnace operation. The specific preprocessing method is to use linear interpolation to fill in the parameters with few missing values, such as image 3 (correspond figure 2 As shown in (a)); for two parameters with correlation, use the complete parameter to estimate the missing value of the missing parameter, such as Figure 4 (correspond figure 2 (b)), for example, the parameter "cross center temperature" has a small number of missing values, and the correlation coefficient with the "edge average temperature" parameter with complete data is 0.91, which belongs to the two parameters with strong correlation. It is more accurate to use mean imputation around missing values. The samples whose furnace core dead material column temperature is lower than 1300°C and higher than 1500°C are classified as abnormal, and those that deviate from the overall data distribution in each parameter are regarded as abnormal values. A...

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 predicting the temperature of a dead stock column of a furnace core of an iron-making blast furnace, which belongs to the technical field of metallurgical information processing, and comprises the following steps: collecting and preprocessing sample data, extracting features based on a maximum information coefficient, dividing a training set and a test set to obtain a data set 1, and representing the change trend of each column of the data set 1 in a time sequence by 1 or-1, obtaining a data set 2; fitting a regression model of the parameters and the furnace core dead stock column temperature on the data set 1 by using a ridge regression method, and analyzing correlation of a change trend on a time sequence on the data set 2 by using a Gaussian kernel support vector machine; adjusting the prediction result of the regression model reasonably in combination with the analysis of the change trend to reduce the prediction error. A single ridge regression model is combined with a change trend analysis method, and the model is optimized by using data time sequence information, so that the prediction error of the temperature of the dead stock column of the furnace core is further reduced, the calculation precision is improved, and the invention has very high practical application value.

Description

technical field [0001] The invention relates to the technical field of metallurgical information processing, in particular to a method for predicting the temperature of a core dead material column of an ironmaking blast furnace. Background technique [0002] Ironmaking is an important process of iron and steel smelting, and plays an important role in the iron and steel industry. The conditions and service life of ironmaking blast furnaces are of great research value. The blast furnace life is affected by many factors, among which the hearth area has a great influence on the operation and life of the blast furnace. The stable operation of the blast furnace requires that the temperature in the furnace is within a reasonable range, and the raw materials are fully burned to ensure the quality and efficiency of tapping. Therefore, it is very important to analyze the state of the hearth accurately in real time. For this, some researchers have proposed to use the activity of the h...

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): G06Q10/04G06K9/62
CPCG06Q10/04G06F18/2411G06F18/214
Inventor 王子米春风周阳李敏杰杨海娟汪文艳卢琨王兵
Owner ANHUI UNIVERSITY OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products