Toggle Main Menu Toggle Search

Open Access padlockePrints

Hybrid neural network modelling for process monitoring and control

Lookup NU author(s): Dr Moritz von Stosch, Dr Jie ZhangORCiD, Dr Mark Willis


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


© 2017 Nova Science Publishers, Inc. The performance of neural network approaches in process modelling, operation and design has been observed to improve significantly when they are combined with models derived from fundamental knowledge (e.g., first-principles). Mathematical models that combine neural network approaches with fundamental process knowledge are normally referred to as hybrid grey-box, hybrid neural (network), hybrid semi-parametric or just hybrid models. In this chapter, static and dynamic hybrid modelling concepts are introduced and their application in process monitoring and control are discussed. Two case studies are presented. The first, considers the development of a hybrid model for the monitoring of biomass in E.coli fermentations and the second, the optimal control of a polymerization reactor.

Publication metadata

Author(s): von Stosch M, Zhang J, Willis M

Publication type: Book Chapter

Publication status: Published

Book Title: Artificial Neural Networks in Chemical Engineering

Year: 2017

Pages: 205-228

Print publication date: 01/01/2017

Acceptance date: 02/04/2016

Publisher: Nova Science Publishers, Inc.

Place Published: New York

Library holdings: Search Newcastle University Library for this item

ISBN: 9781536118681