b24777af-a901-44ac-902c-293e41bcb59820210318073430799wseamdt@crossref.orgMDT DepositWSEAS TRANSACTIONS ON SYSTEMS AND CONTROL1991-876310.37394/23203http://wseas.org/wseas/cms.action?id=4073220202022020201510.37394/23203.2020.15http://wseas.org/wseas/cms.action?id=23195NNARX Networks on Didactic Level System IdentificationA. F.Santos NetoCEFET-MG, Department of Eletroelectronics, Leopoldina, BRAZILM. F.SantosCEFET-MG, Department of Eletroelectronics, Leopoldina, BRAZILA. C.SantiagoUFJF, Department of Energy Systems, Jos ́e Lourenc ̧o Kelmer Street, Juiz de Fora, BRAZILV. F.VidalUFJF, Department of Energy Systems, Jos ́e Lourenc ̧o Kelmer Street, Juiz de Fora, BRAZILP.MercorelliLeuphana University of L ̈uneburg, Institute of Product and Process Innovation, Luneburg, GERMANYThis work has as main objective to propose the identification of a small scale non-linear system through the Neural Network AutoRegressive with eXternal input. The use of this network requires an adequate methodology for its configuration and, consequently, a good training set. Then, it is proposed that the main definitions of the network parameters be obtained through the analysis of nonintrusive performance indices. Additionally, using a database based on the system’s response, excited by the Pseudo-Random Binary Sequence signal. The methodology will be applied in two specific open-loop identification situations: numerical simulation of a fourth order polynomial system (Case 01), and an experimental system that controls a nonlinear water tank level (Case 02). The results of the identified models were able to represent the system dynamics with high fidelity, presenting an average identification error of less than 0:14 and 0:34% for Case 1 and 2, respectively. Also, it is observed that the learning and generalization evidence could represent the process intrinsic nonlinearities satisfactorily. Besides, it will be possible to find the potentiality and usefulness of the developed network in nonlinear system identification.51120205112020184190https://www.wseas.org/multimedia/journals/control/2020/a385103-052.pdf10.37394/23203.2020.15.19http://www.wseas.org/multimedia/journals/control/2020/a385103-052.pdfL. Ljung,Identification of nonlinear systems.Link ̈oping University Electronic Press, 2007.O. Nelles,Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer Science & Business Media, 2013.L. Ljung, “Perspectives on system identification,”Annual Reviews in Control, vol. 34, no. 1,pp. 1–12, 2010.R. Isermann and M. M ̈unchhof,Identification of dynamic systems: an introduction with applications. Springer Science & Business Media,2010.10.1007/s12273-019-0597-2B.Delcroix, J. Le Ny, M. Bernier, M. Azam,B. Qu, and J.-S. Venne, “Autoregressive neural networks with exogenous variables for indoor temperature prediction in buildings,” in Building Simulation, pp. 1–14, Springer, 2020.10.1109/eiconrus.2018.8317455Y. Naung, A. Schagin, H. L. Oo, K. Z. Ye,and Z. M. Khaing, “Implementation of data driven control system of dc motor by using system identification process,” in2018 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), pp. 1801–1804, IEEE, 2018.I. Sow, E. Murimi, and U. Mutwiwa, “Evaporative cooler climate prediction using artificial neural network,”JOURNAL OF SUSTAINABLE RESEARCH IN ENGINEERING, vol. 5, no. 3,pp. 113–127, 2020.10.4028/www.scientific.net/amr.871.304Z. H. Xiao, Z. P. An, S. Q. Wang, and S. Q.Zeng, “Research on the nnarx model identification of hydroelectric unit based on improved lm algorithm,” in Advanced Materials Research,vol. 871, pp. 304–309, Trans Tech Publ, 2014.M. Rajalakshmi,G. Saravanakumar, and C. Karthik, “Nonlinear identification of ph processes by using nnarx model,” in Proceedings of the International Conference on Computing and Control Engineering (ICCCE’12), 2012.10.1109/icsengt.2014.7111799R.Adnan, A. M. Samad, Z. M. Zain, and F. A.Ruslan, “5 hours flood prediction modeling using improved nnarx structure: case study kuala lumpur,” in2014 IEEE 4th International Conference on System Engineering and Technology (ICSET), vol. 4, pp. 1–5, IEEE, 2014.10.1063/1.4981181T. Mulyana, “Nnarx model structure for the purposes of controller design and optimization of heat exchanger process control training system operation,” in AIP Conference Proceedings, vol. 1831, p. 020040, AIP Publishing LLC,2017.10.1109/cspa.2017.8064941F. A. Ruslan, A. M. Samad, and R. Adnan, “Modelling of flood prediction system using hybrid nnarx and extended kalman filter,” in 2017 IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA), pp. 149–152, IEEE, 2017.10.1109/cspa.2009.5069250M. H. F. Rahiman, M. N. Taib, R. Adnan, and Y. M. Salleh, “Analysis of weight decay regularisation in NNARX nonlinear identification,” in 5th International Colloquium on Signal Processing Its Applications, pp. 355–361, March 2009.10.1016/j.ijheatmasstransfer.2009.09.040M.Girault, E. Videcoq, and D. Petit, “Estimation of time-varying heat sources through inversion of a low order model built with the modal identification method from in-situ temperature measurements,”International Journal of Heat and Mass Transfer, vol. 53, pp. 206–219, 012010.10.1109/72.80202K. S. Narendra and K. Parthasarathy, “Identification and control of dynamical systems using neural networks,”Transactions of Neural Networks,pp. 4–27, 1990.10.1007/978-1-4471-0453-7_3M. Norgaard, O. Ravn, N. Poulsen, and L. Hansen,Neural networks for modelling and control of dynamic systems: a practitioner’s handbook. Advanced textbooks in control and signal processing. Springer, Berlin, 2000.[17] L. A. Aguirre, Introducaoa Identificacao de Sistemas – T ́ecnicas Lineares e N ̃ao-Lineares Apli-cadas a Sistemas Reais. Editora UFMG, 2007.