作者: Kwaku O. Temeng , Phillip D. Schnelle , Thomas J. McAvoy
DOI: 10.1016/0959-1524(95)95942-7
关键词: Control engineering 、 Feed forward 、 Probabilistic neural network 、 Control theory 、 Model predictive control 、 Control theory 、 Recurrent neural network 、 Artificial neural network 、 Backpropagation through time 、 Engineering 、 Temperature control
摘要: Abstract This paper discusses an industrial application of a multivariable nonlinear feedforward/feedback model predictive control where the is given by dynamic neural network. A multi-pass packed bed reactor temperature profile modelled via recurrent networks using backpropagation through time training algorithm. then used in conjunction with optimizer to build controller. Results show that, compared conventional schemes, network based controller can achieve tighter for disturbance rejection