Advertisement

Composite SVR Based Modelling of an Industrial Furnace

  • Daniel Santos
  • Luís Rato
  • Teresa GonçalvesEmail author
  • Miguel Barão
  • Sérgio Costa
  • Isabel Malico
  • Paulo Canhoto
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1126)

Abstract

Industrial furnaces consume a large amount of energy and their operating points have a major influence on the quality of the final product. Designing a tool that analyzes the combustion process, fluid mechanics and heat transfer and assists the work done during energy audits is then of the most importance.

This work proposes a hybrid model for such a tool, having as its base two white-box models, namely a detailed Computational Fluid Dynamics (CFD) model and a simplified Reduced-Order (RO) model, and a black-box model developed using Machine Learning (ML) techniques.

The preliminary results presented in the paper show that this composite model is able to improve the accuracy of the RO model without having the high computational load of the CFD model.

Keywords

Energy efficiency Industrial furnaces CFD Reduced order model Support vector regression Hybrid model 

Notes

Acknowledgements

This study was funded by the Alentejo 2020, Portugal 2020 program (Contract nr: 2017/017980) and by FCT – Fundação para a Ciência e Tecnologia (project UID/EMS/50022/2013).

References

  1. 1.
    ANSYS: FLUENT software. https://www.ansys.com/products/fluids/ansys-fluent. Accessed 02 Aug 2019
  2. 2.
    Bernieri, A., D’Apuzzo, M., Sansone, L., Savastano, M.: A neural network approach for identification and fault diagnosis on dynamic systems. IEEE Trans. Instrum. Meas. 43(6), 867–873 (1994).  https://doi.org/10.1109/19.368083CrossRefGoogle Scholar
  3. 3.
    Cavaleiro Costa, S., et al.: Simulation of a billet heating furnace. In: V Congreso Ibero-Americano de Emprendimiento, Energía, Ambiente y Tecnología (CIEEMAT 2019), vol. 1, September 2019Google Scholar
  4. 4.
    Chon, K.H., Cohen, R.J.: Linear and nonlinear ARMA model parameter estimation using an artificial neural network. IEEE Trans. Biomed. Eng. 44(3), 168–174 (1997).  https://doi.org/10.1109/10.554763CrossRefGoogle Scholar
  5. 5.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995).  https://doi.org/10.1023/A:1022627411411CrossRefzbMATHGoogle Scholar
  6. 6.
    Drucker, H., Burges, C.J.C., Kaufman, L., Smola, A.J., Vapnik, V.: Support vector regression machines. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 155–161. MIT Press, Cambridge (1997). http://papers.nips.cc/paper/1238-support-vector-regression-machines.pdfGoogle Scholar
  7. 7.
    Hachino, T., Takata, H.: Identification in nonlinear systems by using an automatic choosing function and a genetic algorithm. Electr. Eng. Jpn. 125(4), 43–51 (1999)CrossRefGoogle Scholar
  8. 8.
    IPS, UEv: Simulações CFD. Descriçõo de Resultados. Deliverable 3.3. Audit Furnace Project (2019)Google Scholar
  9. 9.
    Liao, Y., Wu, M., She, J.: Modeling of reheating-furnace dynamics using neural network based on improved sequential-learning algorithm. In: 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, and 2006 IEEE International Symposium on Intelligent Control, pp. 3175–3181, October 2006.  https://doi.org/10.1109/CACSD-CCA-ISIC.2006.4777146
  10. 10.
    Ljung, L. (ed.): System Identification: Theory for the User, 2nd edn. Prentice Hall, Upper Saddle River (1999)zbMATHGoogle Scholar
  11. 11.
    Ljung, L.: Perspectives on system identification. IFAC Proc. Vol. 41(2), 7172–7184 (2008).  https://doi.org/10.3182/20080706-5-KR-1001.01215. 17th IFAC World CongressCrossRefGoogle Scholar
  12. 12.
    Ljung, L.: Approaches to identification of nonlinear systems. In: Proceedings of 29th Chinese Control Conference, Beijing, China, July 2010Google Scholar
  13. 13.
    Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Netw. 1(1), 4–27 (1990).  https://doi.org/10.1109/72.80202CrossRefGoogle Scholar
  14. 14.
    Narendra, K.S., Parthasarathy, K.: Neural networks and dynamical systems. Int. J. Approximate Reasoning 6(2), 109–131 (1992).  https://doi.org/10.1016/0888-613X(92)90014-QCrossRefzbMATHGoogle Scholar
  15. 15.
    Patra, J.C., Modanese, C., Acciarri, M.: Artificial neural network-based modelling of compensated multi-crystalline solar-grade silicon under wide temperature variations. IET Renew. Power Gener. 10(7), 1010–1016 (2016).  https://doi.org/10.1049/iet-rpg.2015.0375CrossRefGoogle Scholar
  16. 16.
    Rajesh, N., Khare, M., Pabi, S.: Application of Ann modelling techniques in blast furnace iron making. Int. J. Model. Simul. 30(3), 340–344 (2010).  https://doi.org/10.1080/02286203.2010.11442589CrossRefGoogle Scholar
  17. 17.
    Trinks, W., Mawhinney, M., Shannon, R.A., Reed, R.J., Garvey, J.R.: Industrial Furnaces. Wiley, New York (2004)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Daniel Santos
    • 1
  • Luís Rato
    • 1
  • Teresa Gonçalves
    • 1
    Email author
  • Miguel Barão
    • 1
  • Sérgio Costa
    • 2
    • 4
  • Isabel Malico
    • 2
    • 4
  • Paulo Canhoto
    • 2
    • 3
  1. 1.Computer Science DepartmentUniversity of ÉvoraÉvoraPortugal
  2. 2.Physics DepartmentUniversity of ÉvoraÉvoraPortugal
  3. 3.ICT Institute of Earth SciencesUniversity of ÉvoraÉvoraPortugal
  4. 4.LAETA, IDMECUniversity of LisbonLisbonPortugal

Personalised recommendations