Nonlinear model predictive controller using neural network

Karahan O., Ozgen C., Halici U. , Leblebicioglu K.

1997 IEEE International Conference on Neural Networks (ICNN 97), Texas, United States Of America, 9 - 12 June 1997, pp.690-693 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icnn.1997.616105
  • City: Texas
  • Country: United States Of America
  • Page Numbers: pp.690-693

Abstract

In this paper, a non-linear Model Predictive Control (MPC) algorithm is proposed which extends the capacities of Linear Model Predictive Controllers to control non-linear systems. A Neural Network (NN) is used to model the deviation of the non-linear system from its linear MPC model. Proposed algorithm is tested in control of an industrial multi-component high purity distillation column by simulation. Results of NN-MPC show high improvement in control of system over linear MPC algorithm.