In recent years, neural networks have attracted much attention for their potential to address a number of difficult problems in modelling and controlling nonlinear dynamic systems, especially in (bio) chemical engineering. The objective of this paper is to review some of the most widely used approaches to neural-network-based modelling, including plain black box as well as hybrid neural network — first principles modelling. Two specific application examples are used for illustration purposes: a simple tank level-control system is studied in simulation while a challenging bioprocess application is investigated based on experimental data. These applications allow some original concepts and techniques to be introduced.
References
1.
AyoubiM. (1996) Nonlinear System Identification Based on Neural Networks with Locally Distributed Dynamics and Application to Technical Processes, VDI-Verlag, Dusseldorf.
2.
BastinGDochainD. (1990). On-line estimation and adaptive control of bioreactors, Elsevier, Amsterdam.
3.
ElmanJ. L. (1990). Finding Structure in Time, Cognitive Sci.14, 179–211.
4.
FunahashiK. I. (1989). On the Approximate Realisation of Continuous Mappings by Neural Networks, Neural Networks2, 183–192.
5.
IrwinG. W.WarwickK.HuntK. J. (Eds.) (1995). Neural Network Applications in Control, IEE, London.
6.
NorgaardM.RavnO.PoulsenN.K.HansenL. K. (2000). Neural Network Modelling and Control Dynamic Systems, Springer.
7.
PhamD. T.LiuX. (1993). Identification of Linear and Nonlinear Systems Using Recurrent Neural Networks, Artificial Intelligence in Engineering8, 67–75.
8.
PsichogiosD. C.UngarL. H. (1992). A Hybrid Neural Network-First Principles Approach to Process Modelling, AlChE J.38, 1499–1511.
9.
RenotteC.Vande WouwerA.RemyM. (2000). Neural Modelling and Control of a Heat Exchanger based on SPSA Techniques, Proc. ACC, 3299–3303.
SpallJ. C. (1992). Multivariate Stochastic Approximation Using a Simultaneous Perturbation Gradient Approximation, IEEE Trans. Automat. Contr.37, 332–341.
12.
SpallJ. C. (2000). Adaptive Stochastic Approximation by the Simultaneous Perturbation Method, IEEE form in Proc. IEEE CDC (1998, 3872–3879).
13.
SuykensJ.VandewalleJ.De MoorB., (1996). Artificial Neural Networks for Modelling and Control of Non-Linear Systems, Kluwer.
14.
ThompsonM. L.KramerM. A. (1994). Modelling Chemical Processes Using Prior Knowledge and Neural Networks, AlChE J.40, 1328–1340.
15.
Vande WouwerA.RenotteC.RemyM. (1999). On the use of Simultaneous Perturbation Stochastic Approximation for Neural Network Training, Proc. ACC, 388–392.
