Toggle Main Menu Toggle Search

Open Access padlockePrints

Recurrent neural network model based batch-to-batch iterative optimising control

Lookup NU author(s): Dr Zhihua Xiong, Dr Jie ZhangORCiD


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Recurrent neural networks are used to model batch processes from process operational data in order to address the difficulties in developing detailed mechanistic models. Due to model-plant mismatches and unmeasured disturbances, the calculated optimal control profile from the recurrent neural network model may not be optimal when applied to the actual process. To overcome this problem, model prediction errors from previous batch runs are used to improve neural network model predictions for the current batch. Since the main interest in batch process operation is on the end of batch product quality, a quadratic objective function is introduced to track the desired qualities at the end-point of a batch. Because model errors are gradually reduced from batch to batch, the control trajectory gradually approaches the optimal control policy. The proposed scheme is illustrated on a simulated batch reactor.

Publication metadata

Author(s): Xiong Z, Zhang J

Editor(s): Hamza, MH

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: IASTED International Conference on Neural Networks and Computational Intelligence

Year of Conference: 2004

Pages: 1-6

Publisher: ACTA Press

Notes: Article number 413-040

Library holdings: Search Newcastle University Library for this item

ISBN: 0889863733