Autors: Stoitseva-Delicheva, D. R., Yordanova, S. T.
Title: Gain-Scheduled PID Control of Nonlinear Plant via Artificial Neural Networks
Keywords: artificial neural network, experimental data, gain-scheduling control, robust performance, robust stability, simulations, temperature

Abstract: The high-performance control of nonlinear industrial plants in a wide operation range requires intelligent techniques. The aim of the present research is to develop an engineering approach for adaptation of the gains of the well-mastered and widely applied linear PID controller based on an offline-trained backpropagation artificial neural network (BANN) that assesses the plant parameters for the current operation point. The controller’s gains are online-computed from the empirical relationship with the plant parameters. Robust stability and robust performance conditions are derived for the gain-scheduled BANN-PID system. Their fulfilment ensures system feasibility in an industrial environment. The approach is demonstrated for the control of temperature in a laboratory dryer for fruits. The BANN training is based on data derived and validated from experiments using the Takagi–Sugeno–Kang nonlinear plant model. Simulations show that the BANN-PID system outperforms both the gain-scheduled fuzzy logic PID control system, designed in previous research, and the PID real-time control system by reducing overshoot six times and settling time 1.8 times and improving robustness 1.3 times.

References

  1. Haykin S. Neural Networks: A Comprehensive Foundation Prentice Hall Englewood Cliffs, NJ, USA 1999
  2. Kramer A. Morgado-Dias F. Applications of artificial neural networks in process control applications: A review Proceedings of the 2018 International Conference on Biomedical Engineering and Applications (ICBEA) Funchal, Portugal 9–12 July 2018 1 6 10.1109/ICBEA.2018.8471743
  3. Rodriguez-Abreo O. Rodriguez-Resendiz J. Fuentes-Silva C. Hernandez-Alvarado R. Falcon MDCPT, Self-tuning neural network PID with dynamic response control IEEE Access 2021 9 65206 65215 10.1109/ACCESS.2021.3075452
  4. Wasserman P.D. Neural Computing. Theory and Practice ANZA Research Van Nostrand Reinholds New York, NY, USA 1992
  5. Lewis F. Ge S.S. Neural Networks in Feedback Control Systems Mechanical Engineers’ Handbook: Instrumentation, Systems, Controls, and MEMS 3rd ed. Chapter 19 Kutz M. Wiley New York, NY, USA 2006 Volume 2 10.1002/0471777455.ch19
  6. Çelik D. Khosravi N. Khan M.A. Waseem M. Ahmed H. Advancements in nonlinear PID controllers: A comprehensive review Comput. Electr. Eng. 2026 129 110775 10.1016/j.compeleceng.2025.110775
  7. Rahman M.H.R.F. Devanathan R. Kuanyi Z. Neural network approach for linearizing control of nonlinear process plants IEEE Trans. Ind. Electron. 2000 47 470 477 10.1109/41.836363
  8. Neshkov T. Yordanova S. Topalova I. Process Control and Production Automation TU-Sofia Sofia, Bulgaria 2007
  9. Silva S. Integration of neural networks with model predictive control for nonlinear thermal systems Int. J. Eng. Res. Technol. (IJERT) 2025 14 10.5281/zenodo.18104203
  10. Adıgüzel F. Kurtuluş K. Türker T. A gain-scheduling attitude controller with nn supervisor for quadrotor UAVs Int. J. Control Autom. Syst. 2024 22 3777 3791 10.1007/s12555-024-0458-3
  11. Chen D. Wang L. Adaptive automatic generation control based on gain-scheduling and neural networks Proceedings of the 2017 IEEE Power & Energy Society General Meeting Chicago, IL, USA 16–20 July 2017 10.1109/PESGM.2017.8274457
  12. Majumder A. Sarkar D. Chakraborty S. Singh A. Roy S.S. Arora A. neural network-based gain-scheduled position control of a pneumatic artificial muscle Proceedings of the 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) Bangalore, India 8–10 July 2022 1 6 10.1109/CONECCT55679.2022.9865817
  13. Tronci S. Baratti R. A Gain-Scheduling PI Control Based on Neural Networks Complexity 2017 2017 9241254 10.1155/2017/9241254
  14. Tsamatsoulis D. Robust enhanced auto-tuning of pid controllers for optimal quality control of cement raw mix via neural networks Chem. Eng. 2025 9 52 10.3390/chemengineering9030052
  15. Astrom K.J. Wittenmark B. Adaptive Control Addison-Wesley Publishing Company Reading, MA, USA 1993
  16. Almachi J.C. Vicente R. Bone E. Montenegro J. Cando E. Reina S. Implementation of a neural network for adaptive PID tuning in a high-temperature thermal system Energies 2025 18 3113 10.3390/en18123113
  17. Sajona J. Velilla W. Fábregas J. Palencia A. Fuzzy gain-scheduling: Comparison of the control strategy J. Eng. Sci. Technol. 2022 17 1356 1368
  18. Hamdani C.N. Adi W.W. Anggriawan D.O. Comparative study on fuzzy supervision and gain-scheduling for nonlinear level control system Advances in Engineering Research, Proceedings of the 2nd Borobudur International Symposium on Science and Technology (BIS-STE 2020) Atlantis Press Dordrecht, The Netherlands 2021 Volume 203 493 497
  19. Han S.Y. Dong J.F. Zhou J. Chen Y.H. Adaptive fuzzy PID control strategy for vehicle active suspension based on road evaluation Electronics 2022 11 921 10.3390/electronics11060921
  20. Yordanova S. Stoitseva-Delicheva D. Performance enhancement of PID control of nonlinear industrial plants via online fuzzy logic auto-tuning and genetic algorithms optimisation Proceedings of the 2025 International Conference Automatics and Informatics (ICAI) Varna, Bulgaria 9–11 October 2025 187 194 10.1109/ICAI67591.2025.11324699
  21. Yordanova S. Stoitseva-Delicheva D. TSK Modelling of Nonlinear Plants Using Experimental Data for Control Algorithms Proceedings of the 2025 International Conference Automatics, Robotics and Artificial Intelligence (ICARAI) Sozopol, Bulgaria 13–15 June 2025 1 6 10.1109/ICARAI67046.2025.11137814
  22. Beale M. Hagan M. Demuth H. Neural Networks Toolbox User’s Guide MathWorks Inc. Natick, MA, USA 1992
  23. NeuroSystems. User’s Manual version 5.0 Siemens AG Munich, Germany 2006
  24. Morari M. Zafiriou B. Robust Process Control Prentice Hall Upper Saddle River, NJ, USA 1989
  25. Karlova-Sergieva V. Robust Performance Assessment of Control Systems with Root Contours Analysis Cybern. Inf. Technol. 2025 25 83 99 10.2478/cait-2025-0013

Issue

Applied Sciences (Switzerland), vol. 16, 2026, Albania, https://doi.org/10.3390/app16083785

Вид: статия в списание, публикация в реферирано издание, индексирана в Scopus