Determination method of addition amount of silicon-manganese alloy in converter tapping based on yield prediction
A silicon-manganese alloy and a technology for determining methods, which are applied in the field of iron and steel metallurgy, can solve problems such as the difficulty in obtaining a prediction effect model, the inability to take into account the metallurgical mechanism of alloying reaction, and poor generalization effect, so as to improve generalization ability and prediction The effect, the effect of good economic benefit
Active Publication Date: 2021-06-01
UNIV OF SCI & TECH BEIJING
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] At present, intelligent algorithms are widely used in the field of forecasting. It can be considered to train through a large number of existing historical data to establish a prediction model of yield rate. BP artificial neural network is the most commonly used one, and general intelligent algorithm training only depends on Historical data cannot take into account the relevant metallurgical mechanism of the alloying reaction process, the generalization effect is poor, and it is difficult to obtain a model with better prediction effect
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0055] A steelmaking plant produces HRB400 series steel grades. During the tapping process, silicon-manganese alloys need to be added to the molten steel to increase manganese, so as to meet the requirements of the Mn element content of the finished steel. In actual production, the amount of silicon-manganese alloy added is estimated by the operator based on experience, which often leads to waste or multiple additions of silicon-manganese alloy. In order to solve this problem, the method of the present invention is used to establish a prediction model for the yield of Mn element, and based on this, the addition amount of the silicon-manganese alloy is calculated.
[0056] The production data of a 120t converter in the plant were collected, and the furnaces whose values fell outside the reasonable range were eliminated, and 483 sets of valid data were obtained. In order to eliminate the adverse impact of different variables on the model due to different magnitudes, the data i...
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
Login to View More Abstract
The present invention relates to the technical field of iron and steel metallurgy, and provides a method for determining the addition amount of silicon-manganese alloy in converter tapping based on yield prediction, including S1 collecting and normalizing the production data of multiple furnaces of converter; S2 determining model input variables ; S3 determines the factors that affect the alloy yield in the converter tapping process, as the input variable of the model; S4 establishes a BP artificial neural network Mn element yield prediction model with monotonic constraints; S5 adjusts the model parameters to obtain an optimized prediction result; S6 Determine the predicted addition amount of silicon-manganese alloy for converter tapping. The method of the present invention improves the BP artificial neural network by adopting a monotonic constraint mode, so that it can be combined with the metallurgical reaction mechanism, and is used to predict the yield rate of the Mn element at the end point of converter smelting, and can obtain better results than the ordinary BP artificial neural network. The prediction effect; it has good accuracy and economic benefits, and can provide useful guidance for the addition of alloys in the on-site production process.
Description
technical field [0001] The invention relates to the technical field of iron and steel metallurgy, in particular to a method for determining the addition amount of silicon-manganese alloy for converter tapping based on yield prediction. Background technique [0002] In recent years, the intelligent manufacturing technology in the field of iron and steel metallurgy has continued to develop, and the control technology of converter steelmaking has gradually developed from manual experience and static control to intelligent control based on models. The tapping and alloying operation in the converter steelmaking process is an important part of the whole smelting process. During the tapping process, operators need to add corresponding alloys according to the technological requirements of smelting steel types. While removing excess oxygen from molten steel, the content of alloy elements such as silicon and manganese in molten steel can meet the composition requirements of steel type...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27G06N3/08C21C5/28G06F111/04
CPCC21C5/28G06N3/084G06F30/27G06F2111/04
Inventor 刘青周凯啸林文辉孙建坤冯小明
Owner UNIV OF SCI & TECH BEIJING