The feasibility of using a particular form of neural networks, defined as Dynamic Neural Units (DNU's), to model a pump in a load sensing system is investigated in this paper. Because of the highly complex structure of the pump, its compensators and controlling elements, simulation of load-sensing pump systems pose many challenges to researchers. Several models of pumps, compensators and valves have been developed and published in the literature but they are overly simplified or are in an extremely complex form. One modeling approach which can capture the nonlinear dynamic properties of the pump yet still retain reasonable simplicity in its basic form is to use neural network technology. Previous studies have shown some limited success in using feed forward neurons with dynamic properties being introduced using time delays. A problem referred to a error accumulation has prevented these neural based models from being practical dynamic representations of load sensing systems. Based on the topology of the biological neural systems several new structures, Dynamic Neural Units (DNU's) have been developed. Only one DNU is necessary to capture or represent some of the dynamics of a plant, which a static (feed forward) neuron cannot do. The main advantage of the dynamic neuron is that it reduces the network dimension and the amount of computational requirement and has the potential to avoid this error accumulation problem. The use of Dynamic Neural Networks with Dynamic Neural Units in simulating a variable displacement pump is presented in this paper. Only the pump portion of the load sensing pump system is considered due to problems of interacting operating points. A DNU structure and a DNN (which is comprised of DNU's) are introduced. The simulation results establishes the feasibility of using a Dynamic Neural Networks with DNU's to model a simulated nonlinear hydraulic system such as a load sensing pump.

1.
Manring, N.D., 2005. Hydraulic Control Systems. John Wiley & Sons. NY.
2.
Ivantysyn, J. and Ivantysynova, M., 2000. M. Hydrostatic Pumps and Motors, Principles, Design, Performance, Modeling, Analysis, Control and Testing. Academia Books International, New Delhi (ISMB 81-85522-16-2).
3.
Kavanagh
G.
,
Schoenau
G.
, and
Burton
R.
,
1990
.
Dynamic Analysis of a Variable Displacement Pump
,
Transactions of the ASME Journal of Dynamic Systems and Control
, Vol.
112
, No.
1
, pp
122
122
.
4.
Harris, R., Edge, K., and Tilley, D., 1974. The Spin Motion of Pistons in a Swashplate Type Axial Piston Pump, Proceedings of the Institution of Mechanical Engineers, Vol. 188, Number 17.
5.
Kim, S., Aker, A. and Zeiger, G., 1989. Oil Entrapment in an Axial Piston Pump and its Effect upon Pressures and Swash plate Torques, Proceedings of the National Conference on Fluid Power and Control, Chicago, pp 4
6.
Wu
D.
,
Burton
R.
,
Schoenau
G.
and
Bitner
D.
,
2002
.
Establishing Operating Points of a Linearized Model of a Load Sensing System
,
International Journal of Fluid Power
, Vol.
3
, No.
2
, pp
47
54
.
7.
Xu
X. P.
,
Sargent
C.
and
Burton
R.
,
1996
.
Experimental Identification of a Flow Orifice Using a Neural Network and the Conjugate Gradient Method
,
Transactions of ASME: Journal of Dynamic Systems, Measurement, and Control
, Vol.
118
, June, pp.
273
277
.
8.
McNamara
J.
,
Edge
K.
, and
Vaughan
N.
,
1997
,
Hybrid Analytical/Neural Network Model of Variable Displacement Pump Dynamics
,
American Society of Mechanical Engineers, The Fluid Power and Systems Technology Division (Publication) FPST
, v
4
, Fluid Power Systems and Technology, p
71
76
.
9.
Watton
J.
and
Xue
Y.
,
1997
.
Simulation of Fluid Power Circuits Using Artificial Network Models (Part 1 and 2), Proc
,
Instn. Mech. Engrs.- Part I
, Vol.
211
, pp.
417
438
.
10.
Xu
X. P.
,
Burton
R.
and
Sartent
C.
,
1997
.
Experimental Implementation of a Neural Simulator
.
Fluid Power Systems and Technology
, Vol.
4
, November, pp.
21
26
.
11.
Lamontagne, D, Burton, R. Ukrainetz P., and Ruan, J. 2003. Investigations in Modeling a Load Sensing Pump using Neural Networks, Proceedings of the Fourth International Symposium on Fluid Power Transmission and Control (ISFP’2003), Wuhan, PRC, pp 151–158.
12.
Gupta, M. and Rao, D., 1992. Dynamic Neural Units in the Control of Linear and Nonlinear Systems, Int. Joint Conf. On Neural Networks (IJCNN), Baltimore, pp. 100–105, June 9–12, 1992.
13.
Gupta M. and Rao, D., 1993. Dynamic neural Units and Function Approximation, IEEE Conf. On Neural Networks, San Francisco, pp. 743–748, March 18-April 1.
14.
Song, Y. and Gupta M., 1999. Dynamic Neural Controller for Complex Nonlinear Systems, IEEE North Saskatchewan Symposium, Saskatoon, pp. 25–40, November 16.
15.
Krus, P. 1988. On Load Sensing Fluid Power Systems with Special Reference to Dynamic Properties and Control Aspects, PhD thesis, No 198, Department of Mechanical Engineering, Linkoping, Sweden, (ISBN 91-7870-402-2).
16.
Book
R.
and
Goering
C.
,
1997
.
Load Sensing Hydraulic System Simulation
,
Applied Engineering in Agriculture, ASAE
, Vol.
13
(
1)
, pp
17
25
.
17.
Erkkila, M. 1999. Practical Modelling of Load Sensing Systems. Proceedings of the Sixth Scandinavian International Conference on Fluid Power, SICFP’99, Tampere, Finland, pp 445.
18.
Ivantysynova, M. 2003. Prediction of Pump and Motor Performance by Computer Simulation, First International Conference on Computational Methods in Fluid Power Simulation., Melbourne, Australia, pp 505–522.
19.
Wright
J.
,
Burton
R.
, and
Schoenau
G.
,
1992
.
Design of a Microcomputer Control System for a Variable Displacement Hydraulic Pump
,
The Journal of Fluid Control
, Vol.
21
, No’s.
2–3
, pp.
116
140
.
20.
Narendra
K. S.
, and
Parthasarthy K
K.
.
1990
.
Identification and Control of Dynamical Systems Using Neural Networks
,
IEEE Trans. Neural Networks
, Vol.
1
, pp.
4
27
.
This content is only available via PDF.
You do not currently have access to this content.