ePrints

Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models

Lookup NU author(s): Dr Jie ZhangORCiD

Downloads

• Accepted version [.pdf]

Abstract

A neural network based batch-to-batch optimal control strategy is proposed in this paper. In order to overcome the difficulty in developing mechanistic models for batch processes, stacked neural network models are developed from process operational data. Stacked neural networks have enhanced model generalisation capability and can also provide model prediction confidence bounds. However, the optimal control policy calculated based on a neural network model may not be optimal when applied to the true process due to model plant mismatches and the presence of unknown disturbances. Due to the repetitive nature of batch processes, it is possible to improve the operation of the next batch using the information of the current and previous batch runs. A batch-to-batch optimal control strategy based on the linearisation of stacked neural network model is proposed in this paper. Applications to a simulated batch polymerisation reactor demonstrate that the proposed method can improve process performance from batch to batch in the presence of model plant mismatches and unknown disturbances. © 2007 Elsevier Ltd. All rights reserved.

Publication metadata

Author(s): Zhang J

Publication type: Article

Publication status: Published

Journal: Chemical Engineering Science

Year: 2008

Volume: 63

Issue: 5

Pages: 1273-1281

Date deposited: 05/06/2014

ISSN (print): 0009-2509

ISSN (electronic): 1873-4405

Publisher: Pergamon

URL: http://dx.doi.org/10.1016/j.ces.2007.07.047

DOI: 10.1016/j.ces.2007.07.047

Altmetrics

Share