Home > Archive > 2015 > Volume 5 Number 5 (Oct. 2015) >
IJMLC 2015 Vol.5(5): 399-403 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2015.V5.541

Electric Efficiency Modelling of a Complex Cogeneration Process Using Extreme Learning Machines

Sandra Seijo, Inés del Campo, Javier Echanobe, and Javier García-Sedano

Abstract—Extreme learning machine (ELM) has attracted increasing attention recently with its successful applications in classification and regression because it outperforms conventional artificial neural networks (ANN), and support vector machines (SVM) in some aspects. ELM provides a robust learning algorithm, free of local minima, without overfitting problems and less dependent on human intervention than the above methods. ELM is appropriate for the implementation of intelligent autonomous systems with real-time learning capability. Moreover, a number of complex industrial applications demanding a high performance solution could benefit from this approach.
    This work proposes the modelling of a real complex cogeneration plant with the aim of obtaining higher energy production with a lower cost (i.e. maximum energy efficiency) using ELM. The accuracy and training time of the ELM-based model are compared with the results obtained using BP-ANN and SVM. ELM training is significantly faster than SLFNs and SVM while preserving the same accuracy level.

Index Terms—Modelling, extreme learning machine, cogeneration, efficiency.

Sandra Seijo, Inés del Campo, and Javier Echanobe are with the Department of Electricity and Electronics, University of the Basque Country UPV/EHU Leioa, Vizcaya, Spain (e-mail: sandra.seijo@ehu.es, ines@we.lc.ehu.es, javi@we.lc.ehu.es).
Javier García-Sedano is with OPTIMITIVE S.L. Vitoria-Gasteiz, Álava, Spain (e-mail: javierg@optimitive.com).

[PDF]

Cite: Sandra Seijo, Inés del Campo, Javier Echanobe, and Javier García-Sedano, "Electric Efficiency Modelling of a Complex Cogeneration Process Using Extreme Learning Machines," International Journal of Machine Learning and Computing vol.5, no. 5, pp. 399-403, 2015.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net


Article Metrics in Dimensions