The group method of data handling (GMDH) is used to identify the non-linear transient behaviour of fluid power elements based upon input/output observations. It is shown how a variety of multi-layered perceptron-type feedforward neural networks evolve for each application due to the heuristic self-organization of the approach. Single-input-single-output systems are considered and a modified algorithm is proposed and developed for multi-input-single-output systems. The technique is applied to a pressure relief valve and a variety of servo-valve-controlled motor systems.
HuntK. J.SbarbaroO.ZbikowskiR.GawthropP. J.Neural networks for control systems—a survey. Automatica, 1992, 28(6), 1083–1112.
2.
AnP. E.BrownM.HarrisC. J.ChenS.Comparative aspects of neural network algorithms for on-line modelling of dynamic processes. Proc. Instn Mech. Engrs, Part I, 1993, 207(I4), 223–241.
3.
PhamD. T.Neural networks in engineering. First National Conference on Applications of AI techniques in engineering, Naples, October 1994, pp. 3–36.
4.
SanadaK.KitagawaA.PingdongW.An application of a neural network to adaptive control of a servo system. In Fluid powerMaedaT.), 1993, pp. 303–308 (E & F N Spon, London).
5.
NewtonD. A.Design and implementation of a neural network controlled electrohydraulic drive, Proc. Instn Mech. Engrs, Part I, 1994, 208(I1), 1994, 31–42.
6.
XuP. et al. Feasibility of training a neural network based hydraulic component simulator using the complex method. Seventh Bath International Fluid Power Workshop, Bath, September 1994.
7.
IvakhnenkoA. G.Polynomial theory of complex systems. IEE Trans. Systems, Man and Cybernetics, October 1971, SMC-1(4).
8.
WattonJ.Fluid power systems, modeling, simulation, analog and microcomputer control, 1989, Prentice-Hall, Englewood Cliffs, New Jersey).
9.
WattonJ.XueY.A new direct measurement method for determining fluid bulk modulus in oil hydraulic systems. Proceedings of FLUCOME '94, Toulouse, France, August 1994, pp. 543–548.
10.
WattonJ.XueY.Identification of fluid power component behaviour using dynamic flow rate measurement. Proc. Instn Mech. Engrs, Part C., 1995, 209(C3), 179–191.
