Abstract
Modelling a non-linear plant by employing first principles is a tedious task and the resulting model often does not replicate the true behaviour of the plant. The cooling coil of an air-handling unit exhibits severe non-linearity and it is difficult to develop a first-principle model which can replicate the true plant behaviour. The paper discusses the modelling of a cooling coil of an air-handling unit using first-principle approach as well as artificial neural networks. In order to capture the dynamics of the cooling coil, a type of recurrent neural network, i.e. non-linear autoregressive network with exogenous input (NARX) is used. It has been demonstrated that a recurrent neural network with sufficient training has better performance as compared to the model obtained using first principle.
Similar content being viewed by others
References
Yu W.: Non-linear system identification using discrete time recurrent neural-networks with stable learning algorithms. Inform. Sci. 158, 131–147 (2004)
Chen S., Billings S.A., Grant P.M.: Non-linear system identification using neural networks. Int. J. Control 51, 1191–1214 (1990)
Ciuca, I., Ware, J.A.: Layered neural networks as universal approximators. In: Computational Intelligence theory and Applications, pp. 411–415. Springer, Berlin/Heidelberg (1997)
Kosko B.: Fuzzy Systems as Universal Approximators. IEEE Trans. Comput. 43, 1329–1333 (1994)
Polycarpou M.M., Ioannou P.A.: Learning and convergence analysis of neural-type structured networks. IEEE Trans. Neural Netw. 3, 39–50 (1992)
Ma S.Y., Cai H.T., Zhou Y.L., Liu R.S.: Prediction of SYM-H index by NARX neural network from IMF and solar wind data. Sci. China Ser. E Technol. Sci. 52, 2877–2885 (2009)
Huang, J., Jin, H., Xie, X., Zhang, Q.: Using NARX neural network based load prediction to improve scheduling decision in grid environments. In: Presented at Third International Conference on Natural Computation, 2007 (ICNC 2007) (2007)
Wei H.L., Billings S.A., Balikhin M.A.: Wavelet based non-parametric NARX models for non-linear input output system identification. Int. J. Syst. Sci. 37, 1089–1096 (2006)
Basso M., Giarre L., Groppi S., Zappa G.: NARX models of an industrial power plant gas turbine. IEEE Trans. Control Syst. Technol. 13, 599–604 (2005)
Jing X.J., Lang Z.Q., Billings S.A.: New bound characteristics of NARX model in the frequency domain. Int. J. Control 80, 140–149 (2007)
Wong C.X., Worden K.: Generalized NARX shunting neural network modeling of friction. Mech. Syst. Signal Process. 21, 553–572 (2007)
Bednarz J., Barszcz T., Uhl T.: Rotating machinery diagnostics based on NARX models. Comput. Assist. Mech. Eng. Sci. J. 14, 557–567 (2007)
Cybenko G.: Approximations by superpositions of a sigmoidal functions. Math. Control Signals Syst. 2, 303–314 (1989)
He M., Cai W.J., Li S.Y.: Multiple fuzzy model-based temperature predicitive control for HVAC systems. Inform. Sci. 169, 155–174 (2005)
Husaunndee, A., Lahrech, R., Riederer, P., Nejad, H.V.: SIMBAD Building and HVAC Toolbox. CSTB, Sustainable Development Department, Automation and Energy Management Group, France (2001)
Hagan M.T., Menhaj M.: Training feed-forward netwroks with the Marquardt algorithm. IEEE Trans. Neural Netw. 5, 989–993 (1999)
Foresee, F.D., Hagan, M.T.: Gauss–Newton approximation to Bayesian regularization. In: Proceedings of the 1997 International Joint Conference on Neural networks, pp. 1930–1935 (1997)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kadri, M.B. System Identification of a Cooling Coil Using Recurrent Neural Networks. Arab J Sci Eng 37, 2193–2203 (2012). https://doi.org/10.1007/s13369-012-0317-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-012-0317-z