A serial hybrid modeling approach is applied to mechanical systems. Here, hybrid means that models are based on combined structural and empirical approaches. The main system behavior is described by a physical model, while complex internal forces are modeled by black box neural networks. For a special class of systems this methodology is extended and a novel approach is presented modeling the whole system behavior by hierarchical neural networks, that fit the relation between system outputs and internal system variables. Useful information about the nonlinear system can be extracted from the resulting models. The power of hybrid modeling is illustrated with experimental results and some important issues considering the practical implementation are dealt with.

1.
Aoyama
A.
, and
Venkatasubramanian
V.
,
1995
, “
Internal Model Control Framework Using Neural Networks for the Modeling and Control of a Bioreactor
,”
Engineering Applications of Artificial Intelligence
, Vol.
8
, No.
6
, pp.
689
701
.
2.
Bohlin
T.
, and
Graebe
S. F.
,
1995
, “
Issues in Non-Linear Stochastic Grey Box Identification
,”
International Journal of Adaptive Control and Signal Processing
, Vol.
9
, pp.
461
464
.
3.
Chassiakos
A. G.
, and
Masri
S. F.
,
1996
, “
Modeling Unknown Structural Systems Through the Use of Neural Networks
,”
Earthquake Engineering and Structural Dynamics
, Vol.
25
, pp.
117
118
.
4.
Faussett, L., 1994, Fundamentals of Neural Networks, Prentice-Hall, ISBN 0-13-042250-9.
5.
Gill, P. E., Murray, W., and Wright, M. H., 1981, Practical Optimization, Academic Press, ISBN 0-12-283950-1.
6.
Johansen
T. A.
,
1996
, “
Identification of Non-Linear Systems Using Empirical Data and Prior Knowledge—An Optimization Approach
,”
Automatica
, Vol.
32
, No.
2
, pp.
159
176
.
7.
Johansen
T. A.
, and
Foss
B. A.
,
1997
, “
Operating Regime Based Process Modeling and Identification
,”
Computers & Chemical Engineering
, Vol.
21
, No.
2
, pp.
159
176
.
8.
Kramer, Mark A., Thompson, Michaael, L., and Bhagat, Phiroz M., 1992, “Embedding Theoretical Models in Neural Networks,” Proceedings of the American Control Conference, pp. 475–479.
9.
Masri
S. F.
,
Chassiakos
A. G.
, and
Caughy
T. K.
,
1993
, “
Identification of Nonlinear Dynamic Systems Using Neural Networks
,”
ASME Journal of Applied Mechanics
, Vol.
60
, pp.
123
133
.
10.
Masri
S. F.
,
1994
, “
A Hybrid Parametric/Non-Parametric Approach for the Identification of Nonlinear Systems
,”
Probabilistic Engineering Mechanics
, Vol.
9
, pp.
47
57
.
11.
Mavrovouniotis
M. L.
, and
Chang
S.
,
1992
, “
Hierarchical Neural Networks
,”
Computers & Chemical Engineering
, Vol.
16
, No.
4
, pp.
347
369
.
12.
Ninness, B., Gomez, J., and Weller, S., 1995, “Mimo System Identification Using Orthonormal Basic Functions,” Proceedings of the 34th IEEE Conference on Decision and Control, pp. 703–709.
13.
Ploemen, I. H. J., 1996, “A Hybrid Modeling Methodology for Non-Linear Mechanical Systems Using Neural Networks,” M.Sc. thesis, report no. WFW 96.064, Mechanical Engineering, Eindhoven University of Technology.
14.
Ploemen, I. H. J., 1997, “Literature Survey Considering Hybrid/Grey Box Identification Techniques,” Internal report, CAPE Centre, University of Queensland, Brisbane, Australia.
15.
Psichogios
D. C.
, and
Ungar
L. H.
,
1992
, “
A Hybrid Neural Networks First Principles Approach to Process Modeling
,”
AIChE Journal
, Vol.
38
, No.
10
, pp.
1499
1511
.
16.
Su, H.-T., Bhat, N., Minderman, P. A., and McAvoy, T. J., 1992, “Integrating Neural Networks with First Principles Models for Dynamic Modeling,” IFAC Symp. on Dynamics and Control of Chemical Reactors, Distillation Columns, and Batch Processes (DYCORD +).
17.
Thompson
M. L.
, and
Kramer
M. A.
,
1994
, “
Modeling Chemical Processes Using Prior Knowledge and Neural Networks
,”
AIChE Journal
, Vol.
40
, No.
8
, pp.
1328
1340
.
18.
Tulleken, H., 1991, “Application of the Grey Box Approach to Parameter Constrained Adaptive Control,” IFAC World Congress, Sydney, Vol. 2, pp. 137–140.
19.
Tulleken
H.
,
1993
, “
Grey-Box Modeling and Identification Using Physical Knowledge and Bayesian Techniques
,”
Automatica
, Vol.
29
, No.
2
, pp.
285
308
.
20.
Van der Linden, G., 1994, “Parameter Estimation by Data Reconstruction,” Proceedings of the American Control Conference, Vol. 1, pp. 525–529.
This content is only available via PDF.
You do not currently have access to this content.