Abstract
This paper proposes the implementation of hybrid data driven modeling and predictive functional control (PFC) strategy for regulation of oxygen in an industrial coke furnace. A comprehensive model that incorporates simple step-response test and nonlinear optimization using neural network is first developed through process operation data. Then, a nonlinear PFC is designed to improve the dynamic response and steady operation. The proposed PFC overcomes the disadvantages of proportional-integral-derivative or linear advance control strategies because the developed process model yields better process dynamics prediction and facilitates the subsequent PFC controller to improve process operation. In addition, the linear iterative form of the controller design is implemented such that engineers can easily apply it to industrial processes. Results are shown by way of simulations and experimental tests to demonstrate the effectiveness of the proposed strategy.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call