Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6865485 | Neurocomputing | 2016 | 12 Pages |
Abstract
In this work a model predictive control approach based on a neural network Wiener model is developed and applied for an intensified continuous reactor. The Wiener model is constituted by two parts: a linear state space identified model based on nonlinear first-principle model, a nonlinear neural network model developed to predict the nonlinear controlled output. Next, a local linearization of neural network model at every sample instant is developed to guarantee an efficient online optimization. The performance of nonlinear controller is illustrated by simulations.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Shi Li, Yueyang Li,