Non-linear Modeling and Design of Control System for an Aero Gas Turbine Engine Using NARMA L-2 Neural Network

Authors

1 Faculty of Aerospace, Malek Ashtar University of Technology, Iran

2 Faculty of Aerospace, Malek Ashtar University of Technology, Iran.

10.22044/jsfm.2025.15197.3904

Abstract

Modeling the behavior of a gas turbine system and designing its control has always been of interest to researchers in this field. Proper modeling allows the implementation of a suitable controller on a dynamic system, and using suitable control, the system can be controlled in the best and safest way possible. In the design of gas turbine control, due to the existence of irreparable risks to the system, protective constraints must be observed. These risks include surge, turbine overheating, and flame extinction. In this study, a non-linear model of the J85 engine was initially built, and its results were validated with the Gasturb software. The validation results show that the maximum error for this engine in the compressor pressure ratio and turbine inlet temperature in transient conditions is 5 and 5.8 percent, respectively. Then, using the Narma L-2 neural network and the Min-Max protection constraints, a controller was designed for this system. The designed controller is able to maintain the surge limit at the idle to maximum speed maneuver above 5% and prevent turbine over temprature and flame-out, and its constant error value at the design point is zero.

Keywords

Main Subjects

References

[1] H. Asgari (2014) Modelling, Simulation and Control of Gas Turbines Using Artificial Neural Networks, Boca Raton, Florida: CRC Press.
[2] Shaun R. Gaudet (2007) Development of a Dynamic Modeling and Control System Design Methodology for Gas Turbines, Ottawa-Carleton Institute (Thesis).
[3] Qusai Z. Al-Hamdan and Munzer S. Y. Ebaid(2006) Modeling and Simulation of a Gas Turbine Engine for Power Generation, Aerican society of mechanical engineers.
[4] Rafael Parra Hemandez, Jaime Alvarez Gall and Marino Sancbez Parra (1997) A Neural Network Speed Controller for Gas Turbine, IFAC Control of Industrial Systems.
[5] C. Wang, Y.G. Li and B.Y.Yang (2017) Transient performance simulation of aircraft engine integrated with fuel and control systems, Applied Thermal Engineering.
[6] O. Mohamed and A. Khalil (2020) Progress in Modeling and Control of Gas Turbine Power Generation Systems: A Survey, MDPI Energies.
[7] P. Lin, X. Du, Y. Shi and X.-M. Sun (2019) Modeling and controller design of a micro gas turbine for power generation, Elsevier Isatrans.
[8] A. Salehi and M. Montazeri-Gh (2018), "Black box modeling of a turboshaft gas turbine engine fuel control unit based on neural NARX," Engineering for the Maritime Environment.
]9[ م. تجلی، ا. محمدی و م. مرتضی (1392) مدلسازی و شبیه سازی توربین گازی دو محوره با در نظرگیری اثرات خنک کاری پره‌های توربین، مکانیک سازه‌ها و شاره‌ها.
[10]  I. M. Ibrahem, O. Akhrif, H. Moustapha and M. Staniszewski (2021) Nonlinear generalized predictive controller based on ensemble of NARX models for industrial gas turbine engine, Elsevier Energy.
]11 [م. منتظری، ع. جعفری و ع. راستی جهرمی (1398) طراحی و پیاده‌سازی کنترل پیشبین مبتنی بر مدل خطی گسسته برای کنترل سوخت موتور توربوفن، مکانیک هوافضا.
 
[12]  H. Asgari, X.Chen and M.Menhaj (2012) ANN-Based System Identification, Modelling and Control of Gas Turbines, Advanced Materials Research, Vols. 622-623.
[13]  I. O. Bachi, A. S. Bahedh and I. A. Kheioon (2021) Design of control system for steel strip-rolling mill using NARMA-L2, Journal of Mechanical Science and Technology, vol. 35, no. 4.
[14]  K. E. Hamidi, M. Mjahed, A. El Kari, H. Ayad and N. El Gmili (2021) Design of Hybrid Neural Controller for Nonlinear MIMO System Based on NARMA-L2 Model, IETE Journal of Research, vol. 69, no. 5.
[15]  A. Gundogdu and R. Celikel (2022) NARMA-L2 controller for stepper motor used in single link manipulator with low-speed-resonance damping, Engineering Science and Technology,, vol. 24, no. 2.
[16]  Y. Kondratenko, K. Wang , O. Kozlov , A. Shevchenko and A. Denysenko (2023) Neural Network Control of the Mobile Robotic Platform’s Adhesion Force, International Scientific Symposium, vol. 5.
[17]  Z. Gu, Q. Li, S. Pang, W. Zhou, J. Wu and C. Zhang (2023) Turbo-shaft engine adaptive neural network control based on nonlinear state space equation, Chinese Journal of Aeronautics, vol. 34, no. 4.
[18]  Link C.Jaw and Jack D.Mattingly (2009), Aircraft Engine Controls, Design, System Analysis and Health Monitoring.
[19]  S. Yarlagadda (2010), Performance Analysis of J85 Turbojet Engine Matching Thrust with Reduced Inlet Pressure to the Compressor, The University of Toledo, (Thesis).
]20[ م. فرجی و م. جهرمی (1394) توسعه یک مدل دینامیکی جهت شبیه‌سازی بلادرنگ رفتار گذرای موتور توربوجت در محیط سیمولینک، مجله علمی-پژوهشی مدل‌سازی در مهندسی.
]21[ م. آزادی اقدم و ا. مسگرپور طوسی (1393) مدلسازی سیستم کنترل موتور توربین گاز با استفاده از تحلیل موتور در خارج از نقطه طرح, کنفرانس بین المللی انجمن هوافضای ایران.
]22[ م. یزدان پناه و ع. ناظقی (1402) کنترل فعال نوسانات سیستم تعلیق هواپیما با استفاده از کنترلر عصبی  NARMA-L2، نشریه علمی مکانیک هوافضا.
Journal of Solid and Fluid Mechanics
Volume 15, Issue 4
September and October 2025
Pages 57-69

Files

Share

How to cite

Statistics