An experimental approach of using a neural network model to identifying a nonlinear non-pressure-compensated flow valve is described in this paper. The conjugate gradient method with Polak-Ribiere formula is applied to train the neural network to approximate the nonlinear relationships represented by noisy data. The ability of the trained neural network to reproduce and to generalize is demonstrated by its excellent approximation of the experimental data. The training algorithm derived from the conjugate gradient method is shown to lead to a stable solution.

1.
Battiti
R.
, and
Masulli
F.
,
1990
, “
BFGS Optimization for Faster and Automated Supervised Learning
,”
INCC 90 Paris, International Neural Network Conference
,
2
, pp.
757
760
.
2.
Box, M. J., 1965, “A New Method of Constrained Optimization and Comparison with Other Methods,” Computer Journal, Vol. 8.
3.
Chester
D. L.
,
1990
, “
Why Two Hidden Layers Better Than One
,”
Proceedings of the International Joint Conference on Neural Networks
, Vol.
1
, pp.
265
268
, Erlbaum.
4.
HOPSAN User’s Manual, 1985, University of Linkoping LITH-IKP-R-388, Revised.
5.
Hornik
K.
,
Stinchcombe
M.
, and
White
H.
,
1989
, “
Multilayer Feed forward Networks are Universal Approximators
,”
Neural Networks
,
2
(
5
), pp.
359
366
.
6.
Johansson
E. M.
,
Dowla
F. U.
, and
Goodman
D. M.
,
1992
, “
Backpropagation Learning for Multilayer Feed-forward Neural Networks Using the Conjugate Gradient Method
,”
International Journal of Neural Systems
, Vol.
2
,
4
, pp.
291
301
.
7.
Luenberger, D. G., 1984, Linear and Nonlinear Programming, Part II, Second Edition, Addison-Wesley, London.
8.
Pike, R. W., 1986, Optimization for Engineering Systems, Van Nostrand Reinhold, New York.
9.
Powell
M. J. D.
,
1977
, “
Restart Procedures for the Conjugate Gradient Method
,”
Mathematical Programming
, Vol.
12
, pp.
241
254
.
10.
Widrow, B., and Lear, M. A., 1990, “30 Years of Adaptive Neural Networks Perception, Madaline and Back Propagation,” Proceedings of the IEEE. Vol. 78, No. 9, Sept.
11.
Xu, X. P., Ramden, T., Burton, R., Krus P., and Sargent, C., 1994, “Feasibility of Training a Neural Network Based on Hydraulic Component Simulator Using the Complex Method,” 1994 International Fluid Power Workshop, University of Bath, England.
12.
Yamada, T., and Yabuta, T., 1993, “Dynamic System Identification Using Neural Networks,” IEEE Transactions on System, Man and Cybernetics, Vol. 23, No. 1, Jan./Feb.
This content is only available via PDF.
You do not currently have access to this content.