# MODELING AND IDENTIFICATION OF HEAT EXCHANGER PROCESS USING LEAST SQUARES SUPPORT VECTOR MACHINES

## Main Article Content

## Abstract

In this paper, Hammerstein model and Nonlinear AutoRegressive with eXogeneous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system without requiring any apriori assumptions regarding its structure. The results indicate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.

## Article Details

**Thermal Science**, [S.l.], mar. 2017. ISSN 2334-7163. Available at: <http://thermal-science.tech/journal/index.php/thsci/article/view/2155>. Date accessed: 22 feb. 2018. doi: https://doi.org/10.2298/TSCI151026204A.

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Authors retain copyright of the published article and have the right to use the article in the ways permitted to third parties under the - Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND) licence. Full bibliographic information (authors, article title, journal title, volume, issue, pages) about the original publication must be provided and a link must be made to the article's DOI.

The authors and third parties who wish use the article in a way not covered by the the -Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND) licence must obtain a written consent of the publisher. This license allows others to download the paper and share it with others as long as they credit the journal, but they cannot change it in any way or use it commercially.

Authors grant to the publisher the right to publish the article, to be cited as its original publisher in case of reuse, and to distribute it in all forms and media.

Accepted 2017-03-13

Published 2017-03-13

## References

[2] Persin, S., Tovornik, B., Real-time implementation of fault diagnosis to a heat exchanger, Control Eng. Practice., 13 (2005), 8, pp. 1061–1069, DOI No. 10.1016/j.conengprac.2004.12.005

[3] Weyer, E., et al., Grey box fault detection of heat exchangers, Control Eng. Practice., 8 (2000), 2, pp. 121–131, DOI No. 10.1016/S0967-0661(99)00132-X.

[4] Zavala-Rio, A., Santiesteban-Cos, R., Reliable compartmental models for double-pipe heat exchangers: an analytical study, Appl. Math. Model,. 31 (2007), 9, pp. 1739–1752, DOI No. 10.1016/j.apm.2006.06.005

[5] Zhang, T., et al., Stability analysis of heat exchanger dynamics, Proceedings of the American Control Conference, St. Louis, MO, USA, 2009, pp. 3656-3661.

[6] Novak, J., Bobal, V., Predictive control of the heat exchanger using local model network, 17th Mediterranean Conference on Control & Automation, Thessaloniki, Greece, 2009, pp. 657-662.

[7] Álvarez, J.D., et al., Repetitive control of tubular heat exchangers, J. Process Control 17 (2007), 9, pp. 689–701 689e701, DOI No. 10.1016/ j.jprocont.2007.02.003.

[8] Lennart, L., System Identification: Theory for the User (2nd. Ed.), Prentice – Hall, New Jersy, 1999.

[9] Ljung, L., Identification of Nonlinear Systems, technical report from Automatic control at Link ping universitet, Sweden, 2007.

[10] Fu, L., Li, P., The research survey of system identification method, fifth International conference on Intelligent Human-machine Systems and Cybernetics, Hangzhou, 2013, Vol. 2, pp. 397-401, DOI No. 10.1109/IHMSC.2013.242.

[11] Al-Dhaifllah, M., Westwick, D., Identification of Auto-Regresive Exogenous Hammerstein Models Based on Support Vector Machine Regression, IEEE Transactions on Control Systems Technology, 21(2013), 6, pp. 2083-2090, DOI No. 10.1109/TCST.2012.2228193.

[12] Greblicki, W., Nonliniarity estimation in Hammerstein systems based on ordered observations, IEEE Trans.Signal Process., 44(1996), 5, pp. 1224-1233, DOI No. 10.1109/78.502334.

[13] Lv, X., Ren, X., Non-iterative identification and model following control of Hammerstein systems with asymmetric dead-zone non-linearities, IET Control Theory A, 6(2012), 1, pp. 84-89, DOI No. 10.1049/iet-cta.2010.0454.

[14] Prakriya, H., Hatzinakos, D., Blind Identification of linear subsystems of LTI-ZMNL-LTI models with cyclostationary inputs, IEEE Trans.Signal Process.,45(1997), 8, pp. 2023-2036, DOI No. 10.1109/78.611201.

[15] Narendra, K.S., Gallman, P.G., An Iterative method for the identification of nonlinear systems using a Hammerstein model, IEEE Trans.Autom.Control., 11(1996), 3, pp. 546-550, DOI No. 10.1109/TAC.1966.1098387.

[16] Bako, L., et al., Recursive Subspace Identification of Hammerstein models based least squares support vector machines, IET Control Theory and Applications., 3(2009), 9, pp. 1209-1216 , DOI No. 10.1049/iet-cta.2008.0339.

[17] Jalaleddini, K., Kearney, R., Subspace Identification of SISO Hammerstein Systems: Application to Stretch Reflex Identification, IEEE Transactions on Biomedical Engineering.,60 (2013), 10, pp- 2725-34, DOI No. 10.1109/TBME.2013.2264216.2013

[18] Xu, X., et al., Identification of Hammerstein system using key-term separation principle, auxiliary model and improved particle swarm optimization algorithm, IET Signal Processing., 7 (2013), 8, pp- 766 - 773, DOI No. 10.1049/iet-spr.2013.0042

[19] Vapnik, V., The Nature of Statistical Learning Theory, Springer-Verlag, New York, U.S.A, 1995.

[20] Goethals, I., et al., Identification of MIMOHammerstein models using least squares support vector machines, Automatica., 41 (2005), 7, pp. 1263 – 1272, DOI No. 10.1016/j.automatica.2005.02.002

[21] Leontaritis, I.J., Billings,S.A., Input–output parametric models for non-linear systems. PartI: Deterministic non-linear systems. International Journal of Control., 41 (1985)., pp. 303–328.

[22] Sjoberg, J., et al., Nonlinear black-box modeling in system identification: A unified overview. Automatica, 31(1995)., 12, pp. 1691–1724, DOI No .10.1016/0005-1098(95)00120-8.

[23] Bai, E.-W., Liu, Y., Recursive direct weight optimization in nonlinear system identification: A minimal probability approach. IEEE Transactions on Automatic Control, 52(2007), 7, 1218–1231, DOI No. 10.1109/TAC.2007.900826

[24] Tillmann Falck et al., Least-Squares Support Vector Machines for the identification of Wiener– Hammerstein systems, Control Engineering Practice., 20 (2012), 11, 1165–1174, DOI No. 10.1016/j.conengprac.2012.05.006

[25] Bittanti, S., Scattolini,R., Optimal stochastic control of a liquid-saturated steam heat exchanger, Time Series Analysis: Theory and Practice, (Edited by 0. D. Anderson), North-Holland, Amsterdam, 1982.

[26] Rohsenow, W. M., Hartnett, J. D., Handbook of Heat Transfer, McGraw-Hill, New York, 1973.

[27] Bittanti, S., Piroddi, I., Nonlinear Identification and Control of a Heat Exchanger:A Neural Network Approach, J. Franklin Inst. 3348 (1997), 1, pp.135-153, DOI No. 10.1016/S0016- 0032(96)00059-2

[28] De Moor, B., Daisy: Database for the identification of systems. Department of Electrical Engineering, ESAT/SISTA, K.U.Leuven, Belgium http://www.esat.kuleuven.ac.be/sista/daisy. Data set name: Hair Dryer, Mechanical Systems, 96-006,2004.