research-article

A genetic algorithms based multi-objective neural net applied to noisy blast furnace data

Authors:

N. Chakraborti,

H. SaxénAuthors Info & Claims

Volume 7, Issue 1

Pages 387 - 397

https://doi.org/10.1016/j.asoc.2005.09.001

Published: 01 January 2007 Publication History

Abstract

A genetic algorithms based multi-objective optimization technique was utilized in the training process of a feed forward neural network, using noisy data from an industrial iron blast furnace. The number of nodes in the hidden layer, the architecture of the lower part of the network, as well as the weights used in them were kept as variables, and a Pareto front was effectively constructed by minimizing the training error along with the network size. A predator–prey algorithm efficiently performed the optimization task and several important trends were observed.

References

[1]

Y. Omori (Ed.), Blast Furnace Phenomena and Modelling, The Iron and Steel Institute of Japan, Elsevier, London, 1987.

[2]

F. Pettersson, J. Hinnelä, H. Saxén, A genetic algorithm evolving charging programs in the ironmaking blast furnace, Mater. Manuf. Process. 20 (2005) 351.

[3]

F. Pettersson, J. Hinnelä, H. Saxén, Evolutionary neural network modeling of blast furnace burden distribution, Mater. Manuf. Process. 18 (2003) 385.

[4]

B. Deo, A. Datta, B. Kukreja, R. Rastogi, K. Deb, Optimization of back-propagation algorithm and gas-assisted ANN models for hot metal desulfurization, Steel Res. 65 (1994) 528.

[5]

N. Chakraborti, Genetic algorithms in materials design and processing, Int. Mater. Rev. 49 (2004) 246.

[6]

R. Östermark, A hybrid genetic fuzzy neural network algorithm designed for classification problems involving several groups, Fuzzy Sets Syst. 114 (2000) 311.

[7]

K. Deb, Multi-objective Optimization using Evolutionary Algorithms, John-Wiley, Chicheter, 2001.

Digital Library

[8]

C.A. Coello Coello, D.A. Van Veldhuizen, G.B. Lamont, Evolutionary Algorithms for Solving Multi-Objective Problems, Kluwer Academic Publishers, New York, 2002.

Digital Library

[9]

M. Helle, H. Saxén, A method for detecting cause–effects in data from complex processes, in: B. Ribeiro, et al. (Eds.), Proceedings of the 7th International Conference on Adaptive and Natural Computing Algorithms, SpringerComputerScience, Wien, 2005, p. 104.

[10]

X. Li, A real-coded predator–prey genetic algorithm for multiobjective optimization, in: C.M. Fonseca, P.J. Fleming, E. Zitzler, K. Deb, L. Thiele (Eds.), Proceedings of the Second International Conference on Evolutionary Multi-Criterion Optimization, Lecture Notes in Computer Science, vol. 2632, LNCS, 2003, p. 207.

[11]

N. Chakraborti, R. Dewri, Simulating recrystallization through cellular automata and genetic algorithms, Model. Simul. Mater. Sci. Eng. 13 (2005) 173.

[12]

K. Price, R. Storn, Differential evolution, Dr. Dobbs J. 22 (4) (1997) 18.

[13]

N. Chakraborti, A. Kumar, The optimal scheduling of a reversing strip mill: studies using multipopulation genetic algorithms and differential evolution, Mater. Manuf. Process. 18 (2003) 433.

[14]

C.M. Fonseca, Multiobjective genetic algorithms with applications to control engineering problems, Ph.D. Thesis, Department of Automatic Control and Systems Engineering, University of Sheffield, Sheffield, UK, 1995.

[15]

M. Helle, F. Pettersson, N. Chakraborti, H. Saxén, Modeling noisy blast furnace data using genetic algorithms and neural networks Steel Res. Int. (2006), in press.

[16]

L. Ljung, System Identification, in: Theory for the User, second ed., PTR Prentice Hall, Upper Saddle River, NJ, 1999.

[17]

R. Reed, Pruning algorithms—a survey, IEEE Trans. Neural Netw. 4 (1993) 740.

Digital Library

[18]

F. Pettersson, H. Saxén, A hybrid algorithm for weight and connectivity optimization in feedforward neural networks, in artificial neural nets and genetic algorithms, in: D.W. Pearson, N.C. Steele, R.F. Albrecht (Eds.), Proceedings of the International Conference on Artificial Neural Nets and Genetic Algorithms Roanne, France, Springer-Verlag Vienna, Austria, April 23–25, 2003.

[19]

H. Maaranen, K. Miettinen, M.M. Mäkelä, Training multi layer perceptron network using a genetic algorithm as a global optimizer in applied optimization, in: M.G.C. Resende, J.P. De Sousa, A. Viana (Eds.), Metaheuristics: Computer Decision-Making (Applied Optimization), Kluwer Academic Publishers, Norwell, MA, USA, 2004.

[20]

B.J. Reardon, Optimizing the hot isostatic pressing process, Mater. Manuf. Process. 18 (2003) 493.

[21]

I.N. Egorov-Yegorov, G.S. Dulikravich, Chemical composition design of superalloys for maximum stress, temperature and time-to-rupture using self-adapting response surface optimization, Mater. Manuf. Process. 20 (2005) 569.

[22]

N. Chakraborti, P. Mishra, A. Aggarwal, A. Banerjee, S.S. Mukherjee, The Williams and Otto chemical plant re-evaluated using a Pareto optimal formulation aided by genetic algorithms, Appl. Soft Comp. 6 (2006) 189–197.

[23]

N.K. Nath, K. Mitra, Mathematical modeling and optimization of two-layer sintering process for sinter quality and fuel efficiency using genetic algorithm, Mater. Manuf. Process. 20 (2005) 335.

[24]

A. Kumar, D. Sahoo, S. Chakraborty, N. Chakraborti, Gas injection in steelmaking vessels: coupling a fluid dynamic analysis with a genetic algorithms based Pareto-optimality, Mater. Manuf. Process. 20 (2005) 363.

[25]

G.Q.P. Zhang, Neural networks for classification: A survey, IEEE Trans. Syst. Man Cybern. Part C: Appl. Rev. 30 (2000) 451.

[26]

A.E. Elalfi, R. Haque, M.E. Elalami, Extracting rules from trained neural network using GA for managing E-business, Appl. Soft Comp. 4 (2004) 65.

Cited By

Salles Melo Lima MEryarsoy EDelen D(2021)Predicting and Explaining Pig Iron Production on Charcoal Blast FurnacesInterfaces10.1287/inte.2020.105851:3(213-235)Online publication date: 1-May-2021
https://dl.acm.org/doi/10.1287/inte.2020.1058
Ibrahim AShamsuddin SAbraham AQasem S(2019)Adaptive memetic method of multi-objective genetic evolutionary algorithm for backpropagation neural networkNeural Computing and Applications10.1007/s00521-018-03990-031:9(4945-4962)Online publication date: 1-Sep-2019
https://dl.acm.org/doi/10.1007/s00521-018-03990-0
Tian YCheng RZhang XJin Y(2017)PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum]IEEE Computational Intelligence Magazine10.1109/MCI.2017.274286812:4(73-87)Online publication date: 1-Nov-2017
https://dl.acm.org/doi/10.1109/MCI.2017.2742868
Show More Cited By

Index Terms

A genetic algorithms based multi-objective neural net applied to noisy blast furnace data

Index terms have been assigned to the content through auto-classification.

Recommendations

Neural network crossover in genetic algorithms using genetic programming
Abstract
The use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity in recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from ...
Single-objective and multi-objective formulations of solution selection for hypervolume maximization
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computation

A new trend in evolutionary multi-objective optimization (EMO) is the handling of a multi-objective problem as an optimization problem of an indicator function. A number of approaches have been proposed under the name of indicator-based evolutionary ...
Numerical Simulation on the Flow Field at the Hearth and Bottom of Blast Furnace
ICICTA '11: Proceedings of the 2011 Fourth International Conference on Intelligent Computation Technology and Automation - Volume 02

It's one of major accidents in the process of iron making that the hearth and bottom of the blast furnace was burn through. As the intensity of the blast furnace process improved, t hearth and bottom of the blast furnace have got easily been eroded ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Applied Soft Computing

Applied Soft Computing Volume 7, Issue 1

Jan 2007

479 pages

ISSN:1568-4946

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 January 2007

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

22
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 08 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Salles Melo Lima MEryarsoy EDelen D(2021)Predicting and Explaining Pig Iron Production on Charcoal Blast FurnacesInterfaces10.1287/inte.2020.105851:3(213-235)Online publication date: 1-May-2021
https://dl.acm.org/doi/10.1287/inte.2020.1058
Ibrahim AShamsuddin SAbraham AQasem S(2019)Adaptive memetic method of multi-objective genetic evolutionary algorithm for backpropagation neural networkNeural Computing and Applications10.1007/s00521-018-03990-031:9(4945-4962)Online publication date: 1-Sep-2019
https://dl.acm.org/doi/10.1007/s00521-018-03990-0
Tian YCheng RZhang XJin Y(2017)PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum]IEEE Computational Intelligence Magazine10.1109/MCI.2017.274286812:4(73-87)Online publication date: 1-Nov-2017
https://dl.acm.org/doi/10.1109/MCI.2017.2742868
Pan RWang XYi CZhang ZFan YBao W(2017)Multi-objective optimization method for thresholds learning and neighborhood computing in a neighborhood based decision-theoretic rough set modelNeurocomputing10.1016/j.neucom.2017.05.068266:C(619-630)Online publication date: 29-Nov-2017
https://dl.acm.org/doi/10.1016/j.neucom.2017.05.068
Ojha VAbraham ASnel V(2017)Metaheuristic design of feedforward neural networksEngineering Applications of Artificial Intelligence10.1016/j.engappai.2017.01.01360:C(97-116)Online publication date: 1-Apr-2017
https://dl.acm.org/doi/10.1016/j.engappai.2017.01.013
Song XJian LSong Y(2017)A chunk updating LS-SVMs based on block Gaussian elimination methodApplied Soft Computing10.1016/j.asoc.2016.12.00451:C(96-104)Online publication date: 1-Feb-2017
https://dl.acm.org/doi/10.1016/j.asoc.2016.12.004
Gong YGe YLi JZhang JIp W(2016)A splicing-driven memetic algorithm for reconstructing cross-cut shredded text documentsApplied Soft Computing10.1016/j.asoc.2016.03.02445:C(163-172)Online publication date: 1-Aug-2016
https://dl.acm.org/doi/10.1016/j.asoc.2016.03.024
Xu XHua CTang YGuan X(2016)Modeling of the hot metal silicon content in blast furnace using support vector machine optimized by an improved particle swarm optimizerNeural Computing and Applications10.1007/s00521-015-1951-727:6(1451-1461)Online publication date: 1-Aug-2016
https://dl.acm.org/doi/10.1007/s00521-015-1951-7
Martínez-Álvarez ACuenca-Asensi SOrtiz ACalvo-Zaragoza JVivas Tejuelo L(2015)Tuning compilations by multi-objective optimizationApplied Soft Computing10.1016/j.asoc.2015.01.02929:C(461-470)Online publication date: 1-Apr-2015
https://dl.acm.org/doi/10.1016/j.asoc.2015.01.029
Povalej Ž(2014)Quasi-Newton's method for multiobjective optimizationJournal of Computational and Applied Mathematics10.5555/2753878.2754068255:C(765-777)Online publication date: 1-Jan-2014
https://dl.acm.org/doi/10.5555/2753878.2754068
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents