The Converter Steelmaking End Point Prediction Model Based on RBF Neural Network

2014 ◽  
Vol 577 ◽  
pp. 98-101
Author(s):  
Xian Liang Dong ◽  
Shi Dong
Keyword(s):  
Neural Network ◽  
Mathematical Model ◽  
Prediction Model ◽  
Carbon Content ◽  
Rbf Neural Network ◽  
Converter Steelmaking ◽  
Prediction Problem ◽  
Model Based ◽  
End Point ◽  
The Mathematical Model

The mathematical model of convert steelmaking end point prediction model based on RBF(Radical Basis Function) is presented in this paper. According to the end point prediction problem of the converter steelmaking production prediction problem, we establish the forecast model of converter steelmaking process which describes the relationship between variables such as hot metal quality, oxygen blowing, the quality of the cooling agent and additives etc. and the end point molten steel temperature and carbon content. The prediction system is multidimensional and nonlinear. The model between variables and the target is unknown. For this situation, this paper applies RBF neural network to forecast target, establishing the prediction model based on RBF neural network. So as to obtain the variables and the mathematical model between steel endpoint temperature and carbon content.

Optimization Research on Converter Steelmaking Process Parameters Based on DOE

2013 ◽  
Vol 579-580 ◽  
pp. 128-132 ◽  
Author(s):  
Bi Hong Lu ◽  
Yu Kai Li ◽  
Bao Zhang Qu
Keyword(s):  
Neural Network ◽  
Carbon Content ◽  
Process Parameters ◽  
Rbf Neural Network ◽  
Converter Steelmaking ◽  
Steelmaking Process ◽  
Initial Weight ◽  
End Point ◽  
Significant Factors ◽  
The Ideal

The temperature and carbon content at blow end point should be controlled strictly during the BOF converter steelmaking process. Meanwhile many factors have impact on the temperature and carbon content at blow end point. These factors include initial weight of molten iron, initial weight of scrap steel, oxygen blow duration, the temperature and carbon content when lowering the sublance, as well as the weight of all kinds of addition reagents. In order to determine the optimized process parameters so as to reach the ideal temperature and carbon content at blow end point, this paper built a series of experiment programs based on DOE. According to the experiment programs, authors conducted these experiments with the help of RBF neural network and analyzed each parameters as well as some interactions impact on target. According to the statistical analysis results of experiment data (the SNR), authors extract significant factors and reached an optimized process parameters A3B3C2D1E1F3G2H3J2. According to the RBF neural network, the prediction error of carbon content and temperature is only 0.0063 and 0.0159 respectively. The result proves that DOE is an effective method in optimizing process parameters, and worth promoting and applying in converter steelmaking process.

Prediction Model of End-Point Carbon Content for BOF Based on LM BP Neural Network

2011 ◽  
Vol 189-193 ◽  
pp. 4446-4450
Author(s):  
Chang Rong Li ◽  
Hao Wen Zhao ◽  
Qing Yin
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Carbon Content ◽  
Bp Neural Network ◽  
Static Model ◽  
Influential Factors ◽  
Target Error ◽  
End Point ◽  
Endpoint Control ◽  
Lm Algorithm

Reaction process of BOF steelmaking is a very complex physical chemistry process which is very difficult to describe linearity. The traditional static model has poor accuracy, and the target hit rate is low. Based on the analysis of the major influential factors, the influential factors of converter smelting on the endpoint control of carbon content are fixed in this paper. A prediction model of end-point carbon content for BOF is established based on Levenberg-Marquardt (LM) algorithm of BP neural network. The simulated results show that the hitting rates of end-point carbon content reached 80% when accuracy of target error is ±0.025%.

Sign in / Sign up

Export Citation Format

Share Document