Process Estimated Temperature Model of Molten Steel in LF Based on BP Neural Network Combined with Expert System

Qiang Li; Gang Cao; Jiang Li; Ning Wang

doi:10.4028/www.scientific.net/AMM.48-49.853

Paper Titles

Precise Control of Thrust Force on the Shield Tunneling Machine
p.834

Predictive Artificial Potential Field Method and its Application on Robot Soccer Path Planning
p.840

Preparation and Characterization of Steel Slag Adsorbent
p.844

Preparation of Silicon Reinforced Poplar Wood Composites and their Thermal Properties
p.848

Process Estimated Temperature Model of Molten Steel in LF Based on BP Neural Network Combined with Expert System
p.853

Quantitative Analysis for Near-Field Characteristics of Converter Circuits
p.858

Quasi Resonant Direct Power Control of Three-Phase Grid-Connected Inverters in Distributed Generation Systems
p.863

Rapid Locking Assembly Variant Design Based on Product Configuration Model and CBR
p.868

Rapid Method for Point Clouds Registration Based on Reference Points
p.873

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 48-49Process Estimated Temperature Model of Molten...

Process Estimated Temperature Model of Molten Steel in LF Based on BP Neural Network Combined with Expert System

Abstract:

The process estimated temperature model of molten steel is based by analyzing the various factors which influence the rise and fall temperature of molten steel and the arts and crafts process of the production. The model has been used to estimate the temperature of molten steel in LF refining. And results of statistic analysis on estimated temperature show when the deviation of process estimated temperature by this model in LF refining is on more than ±5°C to the measured temperature, the hitting probability arrives at 85%.

You might also be interested in these eBooks

Measuring Technology and Mechatronics Automation

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 48-49)

Pages:

853-857

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.48-49.853

Citation:

Cite this paper

Online since:

February 2011

Authors:

Qiang Li, Gang Cao, Jiang Li, Ning Wang

Keywords:

Estimated Temperature, Expert System, Neural Network (NN)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Sun Zengqi, in: Intelligent Control Theory and Technology. Tsinghua University Press. 1997. 4.

Google Scholar

[2] Han Liqun, in: Intelligent Control Theory and Applications. China Machine Press. 2007. 11.

Google Scholar

[3] Cai Zixing, John Durkin(USA), Gong Tao, in: Advanced Expert System: Principles, Design and Application. Science Press. (2005).

Google Scholar

[4] Wu Bo, Ma Yuxiangin: Expert System. Beijing Institute of Technology Press. (2001).

Google Scholar

[5] Rick Greenwald, Robert Stackowiak, Gary Dodge, David Klein, Ben Shapiro, Christopher G. Chelliah, in: Professional Oracla Programming. Wiley Publishing Inc. (2005).

Google Scholar

[6] Anders Hejlsberg, Mads Torgersen, Scott Wiltamuth, Peter Golde, in: The C# Programming Language, Third Edition. Addison Wesley Professional. 2008. 8.

Google Scholar

[7] Li Jing, in: LF Refining Technology. Metallurgical Industry Press. 2009. 1.

Google Scholar

[8] Wu Xiaodong, Liu Xulan, Zheng Jianzhong, in: Model of prediction for the terminal temperature of molten steel in LF refining. Steelmaking. 2007 volume 23 No. 6.

Google Scholar

[9] Tian Huixin, in: End Temperature Prediction of Molten Steel in LF Based on Genetic Algorithm and BP Neural Network[Master thesis]. Northeastern University. 2005. 2.

Google Scholar

[10] Yan Liyi, Zhan Dongping, Cao Hongtao, in: Prediction and Control of Molten Steel Temperature in LF Refining. Gongye Jiare. (2010).

Google Scholar