Title :
Nonlinear model predictive controller using neural network
Author :
Karahan, Özgür ; Ozgen, Canan ; Hahci, U. ; Leblebicioglu, Kemal
Author_Institution :
Dept. of Chem. Eng., Middle East Tech. Univ., Ankara, Turkey
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
Keywords :
distillation; neurocontrollers; nonlinear control systems; predictive control; process control; industrial multi-component high purity distillation column; linear model predictive controllers; neural network; nonlinear model predictive controller; Control system synthesis; Electrical equipment industry; Industrial control; Neural networks; Nonlinear control systems; Nonlinear systems; Prediction algorithms; Predictive control; Predictive models; Testing;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616105
