	US 11,987,855 B2
	Method and system for determining converter tapping quantity
Yanping Bao, Beijing (CN); Ruixuan Zheng, Beijing (CN); and Lihua Zhao, Beijing (CN)
Assigned to UNIVERSITY OF SCIENCE AND TECHNOLOGY BEIJING, Beijing (CN)
Filed by UNIVERSITY OF SCIENCE AND TECHNOLOGY BEIJING, Beijing (CN)
Filed on Apr. 28, 2023, as Appl. No. 18/308,784.
Claims priority of application No. 202210767075.7 (CN), filed on Jul. 1, 2022.
Prior Publication US 2024/0002964 A1, Jan. 4, 2024
Int. Cl. C21C 5/30 (2006.01); G06N 5/00 (2023.01)

CPC C21C 5/30 (2013.01) [G06N 5/00 (2013.01); C21C 2300/06 (2013.01)]

6 Claims

1. A method for determining tapping amount of a converter, comprising following steps:

S1, collecting a converter production data set and establishing a prediction model database; the converter production data set includes: blowing cycle, oxygen supply time, total oxygen content, whether to blow carbon or not;

S2, conducting data screening and elutriation on the collected converter production data set, and conducting normalization preprocessing on the screened and elutriated data;

S3, determining process parameter variables that affect tapping amount of the converter as input variables to a prediction model of RBF neural network for converter tapping capacity;

the step S3 comprises: determining the input variables by conducting a bivariate correlation analysis to examine a relationship between process parameter variables in step S1 and the tapping amount of the converter;

S4, performing dimensionality reduction processing on converter production process data using principal component analysis (PCA);

the principal component analysis comprises:

1) data standardization processing, and an obtained standardization matrix;

2) calculating a correlation coefficient matrix of the standardization matrix;

3) solving an eigenvalues and eigenvectors of the correlation coefficient matrix;

4) calculating a variance contribution rate and a cumulative variance contribution rate of the principal component variables;

5) selecting first m principal component variables with a cumulative variance contribution rate greater than 80% as the target variable after dimensionality reduction;

S5, establishing the prediction model of RBF neural network for converter tapping capacity;

S6, training and testing the prediction model;

S7, collecting real-time data of on-site smelting process;

S8, performing dimensionality reduction processing on the collected real-time data using the principal component analysis;

S9, applying the prediction model based on RBF neural network to predict the tapping amount of the converter;

S10, adding ferroalloy during the tapping process based on the tapping amount obtained by the prediction model; after the tapping process, storing the tapping amount in the prediction model database to update the prediction model based on the RBF neural network.