Neural Network–Assisted Gradient Approximation and Swarm-Based Optimization for Predictive Control of a Nonlinear Copolymerization Reactor

• Rami Boumegoura

  University of 20th August 1955 - Skikda, Algeria

• Riad Bendib

  University of 20th August 1955 - Skikda, Algeria

• Kamel Menighed

  Department of Petrochemicals, University of 20 August 1955, Skikda 21000

• El-Arkam Mechhoud

  Automatic Laboratory of Skikda (LAS), University of 20 August 1955, Skikda 21000, Algeria

• Abdulaziz Alshareef

  Department of Electrical & Computer Engineering King Abdulaziz University Djeddah KSA

• Hafidha Boudouaia

  University of 20th August 1955 - Skikda, Algeria

Copolymerization reactors are crucial for polymer synthesis but remain tough to regulate due to nonlinear kinetics, heat sensitivity, and disturbances such as inhibitor impurities. Traditional approaches like Proportional-Integral-Derivative (PID) controllers and linear Model Predictive Control (MPC) sometimes struggle with computational efficiency and accuracy trade-offs. This study presents a hybrid framework incorporating MPC, Neural Network (NN)-based gradient approximation, and adaptive Particle Swarm Optimization (PSO). The NN accelerates gradient computation to bypass iterative quadratic programming, while PSO enhances global search capabilities under actuator constraints. Validated on a nonlinear copolymerization reactor model, the hybrid method displays enhanced setpoint tracking and disturbance rejection compared to standard MPC and standalone PSO, with maintained computational feasibility. Robustness is emphasized by effective management of unmeasured inhibitor perturbations, achieving stable input adjustments and precise output regulation.

DOI: 10.61416/ceai.v27i4.9519

• PDF