Abstract
A nonlinear model predictive control (MPC) algorithm is proposed which extends the capacities of linear model predictive controllers to control nonlinear systems. A neural network (NN) is used to model the deviation of the nonlinear system from its linear MPC model. The proposed algorithm is tested in the control of an industrial multi-component high purity distillation column by simulation. Results of NN-MPC show high improvement in control of the system over the linear MPC algorithm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have