ePrints

Optimal Control of Batch Processes Using Particle Swarm Optimisation with Stacked Neural Network Models

Lookup NU author(s): Fernando Herrera Elizalde, Dr Jie ZhangORCiD

Downloads

• Accepted version [.pdf]

Abstract

An optimal control strategy for batch processes using particle swam optimisation (PSO) and stacked neural networks is presented in this paper. Stacked neural network models are developed from historical process operation data. Stacked neural networks are used to improve model generalisation capability, as well as provide model prediction confidence bounds. In order to improve the reliability of the calculated optimal control policy, an additional term is introduced in the optimisation objective function to penalize wide model prediction confidence bounds. The optimisation problem is solved using PSO, which can cope with multiple local minima and could generally find the global minimum. Application to a simulated fed-batch process demonstrates that the proposed technique is very effective.

Publication metadata

Author(s): Herrera F, Zhang J

Publication type: Article

Publication status: Published

Journal: Computers & Chemical Engineering

Year: 2009

Volume: 33

Issue: 10

Pages: 1593-1601

Date deposited: 05/06/2014

ISSN (print): 0098-1354

ISSN (electronic): 1873-4375

Publisher: Pergamon

URL: http://dx.doi.org/10.1016/j.compchemeng.2009.01.009

DOI: 10.1016/j.compchemeng.2009.01.009

Altmetrics

Share