System Identification of an Aeronautical Application Precooler Heat Exchanger Using Neural Networks in an E-TUNI Configuration

Authors

Keywords:

System Identification, Multi-Step Time-Series Prediction, Dynamic Systems, Neural Networks, Precoolher Heat Exchanger, Aeronautics, Universal Numerical Integrator

Abstract

Modeling heat and mass transfer in engineering applications is of great importance for the development of efficient systems, especially in aeronautics, where weight and performance are critical. Conventional modeling of heat exchangers using white-box and regression techniques relies heavily on manual adjustment of parameters for high and low fidelity models, which increases cost and limits the direct use of available data. In this article, we apply a black-box approach and present the Euler Type Universal Numeric Integrator (E-TUNI) framework, a novel method for identifying systems. We then compare the performance of 40 topologies of E-TUNI and NARX in reproducing a reference model of the heat exchanger, showing E-TUNI's better performance than conventional direct use of Neural Networks for time-series prediction.

Downloads

Download data is not yet available.

Author Biographies

Rafael Peluzio, Instituto Tecnologico de Aeronautica

Rafael Peluzio received his Bachelor’s degree in Electrical Engineering at the Universidade Federal de Vicosa (UFV) in 2023. He is currently pursuing a Master’s degree in Aeronautical Engineering at the Instituto Tecnológico de Aeronautica (ITA) and he is a systems development engineer at Embraer S.A. His research  interests include multi-physics simulation, system identification, control systems, numerical integration of dynamic systems,  machine learning and thermal systems.

Paulo Marcelo Tasinaffo, Instituto Tecnologico de Aeronautica (ITA)

Paulo Marcelo Tasinaffo received his Ph. D. degree in Space Engineering at the Instituto Nacional de Pesquisas Espaciais (INPE) in 2003. Received his MS degree in Mechanical Engineering in 1998 and his Bachelor’s degree in Mechanical Engineering in 1996 at Universidade Federal de Itajuba (UNIFEI). He is a Professor at the Instituto Tecnol´ogico de Aeronautica (ITA). His core expertise encompasses  aerospace and computer engineering, focusing deeply on artificial intelligence, nonlinear dynamic system modeling, and artificial neural networks (including both neural control systems and machine learning applications).

Celso Yukio Nakashima, Embraer S.A.

Celso Yukio Nakashima received his PhD degree in Mechanical Engineering at the Universidade de Sao Paulo (USP) in 2005. Received his MS degree in Mechanical Engineering at USP in 2000. Received his Bachelor’s degree in Mechanical Engineering at USP in 1997. He is a systems development engineer at Embraer S.A. His research interests include thermodynamics, heat exchanger design, thermal  stratification models and dynamic system modeling and applications).

References

Rahul VR and Ajith Kumar R, “Parametric study of heat transfer and pressure drop characteristics of a rectangular offset strip fin

compact heat exchanger,” vol. 71, pp. 1381–1386, 2018. DOI: 10.3303/CET1871231

M. H. Teruel, C. Y. Nakashima, and P. Paglione, “Rectangular Offset Strip-Fin Heat Exchanger Lumped Parameters Dynamic Model ,” 2009. DOI: Unavailable

S. Cai, Z. Wang, S. Wang, P. Perdikaris, and G. E. Karniadakis, “Physics-Informed Neural Networks for Heat Transfer Problems,” vol.

, no. 6, p. 060801, 2021. DOI: 10.1115/1.4050542

K. Narendra and K. Parthasarathy, “Identification and control of dynamical systems using neural networks,” vol. 1, no. 1, pp. 4–27,

DOI: 10.1109/72.80202

P. M. Tasinaffo, G. S. Gonc¸alves, J. C. Marques, L. A. V. Dias, and A. M. Da Cunha, “The Euler-Type Universal Numerical Integrator

(E-TUNI) with Backward Integration,” vol. 18, no. 3, p. 153, 2025. DOI: 10.3390/a18030153

P. M. Tasinaffo, G. S. Goncalves, A. M. Cunha, and L. A. V. Dias, “An introduction to universal numerical integrators,” International Journal of Innovative Computing, Information and Control, vol. 15, no. 1, pp. 383–406, 2019. DOI: 10.24507/ijicic.15.01.383

Yi-Jen Wang and Chin-Teng Lin, “Runge-Kutta neural network for identification of dynamical systems in high accuracy,” vol. 9, no. 2, pp.

–307, 1998. DOI: 10.1109/72.661124

K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” vol. 2, no. 5, pp. 359–366,

DOI: 10.1016/0893-6080(89)90020-8

G. Cybenko, “Approximation by superpositions of a sigmoidal function,” vol. 2, no. 4, pp. 303–314, 1989. DOI: 10.1007/BF02551274

A. Parlos, K. Chong, and A. Atiya, “Application of the recurrent

multilayer perceptron in modeling complex process dynamics,” vol. 5, no. 2, pp. 255–266, 1994. DOI: 10.1109/72.279189

M. Mohanraj, S. Jayaraj, and C. Muraleedharan, “Applications of artificial neural networks for thermal analysis of heat exchangers – A

review,” vol. 90, pp. 150–172, 2015. DOI: 10.1016/j.ijthermalsci.2014.11.030

R. Katarya and S. Rastogi, “A study on neural networks approach to time-series analysis,” pp. 116–119, 2018. DOI: 10.1109/ICISC.2018.

A. Naimi, J. Deng, A. Abdulrahman, V. Vajpayee, V. Becerra, and N. Bausch, “Dynamic Neural Network-based System Identification

of a Pressurized Water Reactor,” pp. 100–104, 2020. DOI: 10.1109/ICCMA51325.2020.9301483

N. Mohajerin and S. L. Waslander, “Multistep Prediction of Dynamic Systems With Recurrent Neural Networks,” vol. 30, no. 11, pp.

–3383, 2019. DOI: 10.1109/TNNLS.2019.2891257

A. Rios Neto, “Dynamic Systems Numerical Integrators in Neural Control Schemes,” pp. 85–88, 2001. DOI: 10.21528/CBRN2001-019

Z. Bin, “Comparison of different order adams-bashforth methods in an atmospheric general circulation model,” Acta Meteorologica Sinica, vol. 25, no. 6, pp. 754–764, 2011. DOI: 10.1007/s13351-011-0606-6

E. Misirli and Y. Gurefe, “Multiplicative adams-bashforth-moulton methods,” Numerical Algorithms, vol. 57, no. 4, pp. 425–439, 2011.

DOI: 10.1007/s11075-010-9437-2

N. E. Cotter, “The stone-weierstrass theorem and its application to neural networks,” IEEE Transactions on Neural Networks, vol. 1, no. 4, pp. 290–295, 1990. DOI: 10.1109/72.80265

P. M. Tasinaffo, L. A. V. Dias, and A. M. da Cunha, “A qualitative approach to universal numerical integrators (unis) with computational

application,” Human-Centric Intelligent Systems, vol. 4, pp. 1–28, 2024. DOI: 10.1007/s44230-024-00087-x

Downloads

Published

2026-08-30

How to Cite

Peluzio, R., Tasinaffo, P. M., & Nakashima, C. Y. (2026). System Identification of an Aeronautical Application Precooler Heat Exchanger Using Neural Networks in an E-TUNI Configuration. IEEE Latin America Transactions, 24(10), 1117–1126. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/10812

Issue

Vol. 24 No. 10 (2026): Ordinary Issue

Section

Computing