AI-Assisted Gain Scheduling for Real-Time Temperature Control in Chemical Reactors

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 17 | 01 | Page :
    By

    Amit Pandhare,

  • Aditya Kumbhar,

  • Vaibhav Godase,

  1. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
  2. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India
  3. Assistant Professor, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur, Maharashtra, India

Abstract

Temperature control in continuous stirred-tank reactors (CSTR) represents a critical challenge in chemical process industries due to inherent nonlinearities, time-varying dynamics, and parametric uncertainties. Conventional proportional-integral-derivative (PID) controllers with fixed gains often fail to maintain optimal performance across varying operating conditions, leading to temperature excursions that compromise product quality and safety. This paper presents a novel AI-assisted gain scheduling framework that integrates artificial neural networks (ANN) with adaptive PID control for real-time reactor temperature regulation. The proposed methodology employs a multilayer feedforward neural network to dynamically adjust controller gains based on current process states, thereby accommodating nonlinear reactor dynamics and external disturbances. Lyapunov stability analysis confirms bounded-input bounded-output (BIBO) stability of the closed-loop system under parameter adaptation. Simulation studies conducted on a jacketed CSTR model subjected to inlet temperature disturbances and actuator degradation demonstrate superior performance compared to conventional PID and model predictive control (MPC) approaches. To ensure bounded-input bounded-output (BIBO) stability of the closed-loop system under modeling uncertainty and gain adaption, a rigorous Lyapunov- based stability analysis is created. In order to guarantee tracking error convergence and avoid parameter drift, the adaption law was created. In comparison to traditional PID and model predictive control (MPC) techniques, simulation experiments on a high-fidelity jacketed CSTR model exposed to input temperature disturbances, feed concentration changes, and actuator deterioration show greater dynamic performance. In comparison to fixed-gain PID control, quantitative performance metrics show a 52% improvement in integral of squared error (ISE), a 67% drop in overshoot, and a 43% reduction in settling time. Moreover, maintained performance under ±20% kinetic parameter uncertainty is confirmed by robustness analysis.Quantitative metrics reveal 43% reduction in settling time, 67% decrease in overshoot, and 52% improvement in integral of squared error (ISE) relative to fixed-gain PID. The computational efficiency of the ANN-based scheduler enables deployment on industrial programmable logic controllers (PLCs), facilitating practical implementation in existing process infrastructure.

Keywords: Adaptive control, gain scheduling, neural networks, PID control, chemical reactors, temperature regulation, nonlinear systems, process control

How to cite this article:
Amit Pandhare, Aditya Kumbhar, Vaibhav Godase. AI-Assisted Gain Scheduling for Real-Time Temperature Control in Chemical Reactors. Journal of Control & Instrumentation. 2026; 17(01):-.
How to cite this URL:
Amit Pandhare, Aditya Kumbhar, Vaibhav Godase. AI-Assisted Gain Scheduling for Real-Time Temperature Control in Chemical Reactors. Journal of Control & Instrumentation. 2026; 17(01):-. Available from: https://journals.stmjournals.com/joci/article=2026/view=238763


References

  1. Bequette BW. Process control: modeling, design, and simulation. 2nd ed. Upper Saddle River (NJ): Prentice Hall; 2023.
  2. Qin SJ, Badgwell TA. A survey of industrial model predictive control technology. Control engineering practice. 2003 Jul 1;11(7):733-64.
  3. Anfinsen H, Aamo OM. Adaptive Control of PDEs. InEncyclopedia of Systems and Control 2021 Aug 4 (pp. 11-17). Cham: Springer International Publishing.
  4. Rai S, Thakur J, Pandey A, Singh NL. AI-Driven. AI-Driven Innovations in Electrochemical Technologies for Sustainable Energy Solutions. 2026 Jan 6:144.
  5. Ding C, Gui X, Jiang J. Advancing chemical engineering technology with artificial intelligence. Clean Energy. 2025 Oct;9(5):55-74.
  6. Abubakar AM, Batool K, Asif M, Coto B. Case Studies of Artificial Intelligence in Industrial Fluid and Thermal Processes. Artificial Intelligence and Computational Modeling in Heat Transfer and Fluid Dynamics. 2026 Feb 24:365-93.
  7. Doskenov B, Okuyelu O. Advancing production systems with online reinforcement learning: real-time monitoring, control, and optimization. Current Journal of Applied Science and Technology. 2025 Jan 27;44(2):1-22.
  8. Kiasari M, Aly H. AI-Driven Control Strategies for FACTS Devices in Power Quality Management: A Comprehensive Review. Applied Sciences (2076-3417). 2025 Nov 15;15(22).
  9. Lewis FL, Vrabie D, Syrmos VL. Optimal control. John Wiley & Sons; 2012 Mar 20.
  10. Henson MA, Seborg DE. Adaptive nonlinear control of a pH neutralization process. IEEE transactions on control systems technology. 2002 Aug 6;2(3):169-82.
  11. Chandre DK, Kurhe SS, Dukare NR. Digital Twin Technology for Sustainable Chemical Process Monitoring: An Integrated Ai and Iot Perspective. Available at SSRN 5360810.
  12. Venkatrayalu G, Choudhary S, Poluri KM. AI-Assisted Microalgal Bioprocessing: Innovations, Challenges, and Future Prospects in Sustainable Manufacturing. Industrial Microbiology and Biotechnology: Trends in Microbial Biotechnology. 2026 Feb 6:269- 307.
  13. Bortz M, Dadhe K, Engell S, Gepert V, Kockmann N, Müller-Pfefferkorn R, Schindler T, Urbas L. AI in process industries–current status and future prospects. Chemie Ingenieur Technik. 2023 Jul;95(7):975-88.
  14. Rojas L, Peña Á, Garcia J. AI-driven predictive maintenance in mining: A systematic literature review on fault detection, digital twins, and intelligent asset management. Applied Sciences. 2025 Mar 19;15(6):3337.
  15. Hossain R, Ahmed F, Kobayashi K, Koric S, Abueidda D, Alam SB. Virtual sensing- enabled digital twin framework for real-time monitoring of nuclear systems leveraging deep neural operators. npj Materials Degradation. 2025 Mar 6;9(1):21.
  16. Maguluri LP, Suganthi D, Dhote GM, Kapila D, Jadhav MM, Neelima S. AI-enhanced predictive maintenance in hybrid roll-to-roll manufacturing integrating multi-sensor data and self-supervised learning. The International Journal of Advanced Manufacturing Technology. 2024 Aug 15:1-0.
  17. Priya AK, Devarajan B, Alagumalai A, Song H. Artificial intelligence enabled carbon capture: A review. Science of The Total Environment. 2023 Aug 15;886:163913.
  18. Godase V. Optimized algorithm for face recognition using Deepface and multi-task cascaded convolutional network (MTCNN). Optimum Science Journal. 2025 May 5.
  19. Godase V, Lawande A, Mane K, Davad K, Gangonda S. Pipeline survey robot. Int J Sci Res Dev. 2024;12(3):141–144.
  20. Godase V. Navigating the digital battlefield: An in-depth analysis of cyber-attacks and cybercrime. International Journal of Data Science, Bioinformatics and Cyber Security. 2025 Jan 17;1(1):16-27.
Ahead of Print Subscription Review Article
Volume 17
01
Received 16/02/2026
Accepted 19/02/2026
Published 18/03/2026
Publication Time 30 Days
56

Login


My IP

PlumX Metrics