Application of Temperature Forecasting in Cupola Melting Process Based on BP Neural Network

Xiao Yu Sun; Jian Xin Zhou; Liang Sun; Hong Wang

doi:10.4028/www.scientific.net/AMM.364.594

Paper Titles

Effect of Li on Corrosion Resistance of Nearly Eutectic Al-Si Casting Alloys
p.573

Influence of Sizing and Cooling Process on Properties of N80-1 Seamless Casing Using Steel 40Mn2V and the Process Parameter Control
p.577

LJ707-Crnimo Flux Cored Wire of Basic Slag System Be Applied to Non-Preheating Welding Technology of HSLA
p.584

Effect of Isothermal-Rolling Process on the Morphology, Size and Distribution of Type II MnS
p.589

Application of Temperature Forecasting in Cupola Melting Process Based on BP Neural Network
p.594

Study on Corrosion Electrochemical Behavior of X42 and 16Mn Steel in Seawater
p.599

Numerical Analysis of Temperature Field of Co-Based Alloy Coatings by Laser Cladding on the Mild Steel
p.603

Study on the Microstructure and Oxidation Properties of near Eutectic Nb-Si Alloys
p.609

Thermal Kinetics Phase Field Model for the Metals' Solidification - Mathematic Derivation of the Dendrite Growth Phase Field Variable Diffusion Model
p.614

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 364Application of Temperature Forecasting in Cupola...

Application of Temperature Forecasting in Cupola Melting Process Based on BP Neural Network

Abstract:

In cupola melting process, the temperature of molten iron is an important indicator of the quality of cast iron. Its difficult to optimize the design because of the varicosity of influencing factors in cupola melting process. This article established a BP neural network model to forecast the temperature of molten iron in cupola melting process, thus use the genetic algorithm to optimize the model. Comparing the average errors of the temperature of molten iron before and after optimization, it indicated that the BP neural network model using genetic algorithm optimization forecasted the actual situation in cupola melting more accurately.

You might also be interested in these eBooks

Mechanical Automation and Materials Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 364)

Pages:

594-598

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.364.594

Citation:

Cite this paper

Online since:

August 2013

Authors:

Xiao Yu Sun, Jian Xin Zhou, Liang Sun, Hong Wang

Keywords:

BP Network Model, Cupola Melting, Genetic Algorithm (GA), Temperature Forecasting

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Qinsheng Wei. Study on the Calculation of Chemical and Phase Equilibrium in Complex System [D]. Qingdao: Ocean University of China, (2007).

Google Scholar

[2] Zhenzhong Shi, Jianxin Zhou. Thermodynamics Modeling for Chemical Composition Changes in Cupola Melting Process [J]. Foundry, 2011, (3): 243-246.

Google Scholar

[3] McCulloch W, Pitts W. A logical calculus of the idea immanent in nervous activity [J]. Bull Math Biophys, 1943, 5(4): 115-133.

Google Scholar

[4] Donggang Hu. Modeling and Control of Neural Network for Cupola [D]. Taiyuan: Taiyuan University of Science and Technology, (2008).

Google Scholar

[5] Xiaomei Chen, Xiaoxi Ma. Prediction models of boiler slagging based on improved BP neural network [J]. East China Electric Power. 2005, 33(7): 43-44.

Google Scholar

[6] Suqing L, Xin Q, Donggang H, et al. The Simulation and Investigation of Neural Network Technology in the Controlling Process of Cupola Melting [C]. International Conference on Broadcast Technology and Multimedia Communication. Chongqing, (2010).

Google Scholar

[7] KEARNSM. Abound on the error of cross validation using the approximation and estimation rates with consequences of for the training–test split [J]. Neural Computation，1997, 9(5): 1143-1161.

DOI: 10.1162/neco.1997.9.5.1143

Google Scholar

[8] BHANDARI D，MURTHY C A，PAL S K. Genetic algorithm with elitist model and its convergence [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1996, 10(6): 731-747.

DOI: 10.1142/s0218001496000438

Google Scholar