Scientific and Technical Journal

ELECTROTECHNIC AND COMPUTER SYSTEMS

ISSN Print 2221-3937
ISSN Online 2221-3805
NEURAL NETWORK CONTROL SYSTEM OF ELECTRIC DRIVE LOCOMOTIVE
Abstract:

This article describes the process of frictional self-oscillations in the electric mine locomotive, which arise as a consequence of the dynamic instability of the control object and the nonlinearity of the mechanical characteristics of the load. These fluctuations lead to increased wear of wheels and rails gearboxes. To prevent frictional self-oscillations in the electromechanical system proposed closed-loop control that is based onthe feedforward neural network structure NN3-10-1 type perceptron. The methods for training neural networks, their advantages and disadvantages. The graphs of transient electric mine locomotive without a control system and neural network control system. The analysis of the resulting graphs.

Authors:
Keywords
DOI
10.15276/etks.15.91.2014.29
References

1. Volotkovskii S.A. Rudnichnaya elektrovoznaya tyaga [Electric Drive of Mine Locomotive], (1981), Moscow, Russian Federation, Nedra, 389 p (In Russian).

2. Shakhtar' P.S., and Rengevich A.A. Prichiny polo-mok osei rudnichnykh elektrovozov [Sources of Failure in axle Shafts of Mine Electric Locomotives], (1962), Sb. Voprosy Rudnichnogo Transporta, Moscow, Russian Federation, Gosgortekhizdat, pp. 192 – 203 (In Russian).

3. Obruch I.V., and Kutovoi Yu.N. Zamknutye siste-my upravleniya elektroprivodom s dvigatelem posto-yannogo toka posledovatel'nogo vozbuzhdeniya na baze neironnykh setei [Closed Loop Systems Based on Neural nets to Control Series Winding DC Motor], (2013), Vestnik NTU “KhPI”. Seriya: “Problemy Avtomatizirovannogo EP: Teoriya i Praktika”, Spets. Vypusk No.36, pp. 485 – 487 (In Russian).

4. Obruch I.V. Vybor razmera skrytogo sloya neirokontrollera pri upravlenii elektomekhaniche-skoi sistemoi s otritsatel'nym vyazkim treniem [Selecting the Size of Hidden Layer in Neuro-Controller to Control the Electromechanical System with Viscous Friction], (2001), Sbornik Nauchnykh Trudov, Tematicheskii Vypusk “Problemy Avtomatizirovannogo Elektroprivoda. Teoriya i Praktika”, Vestnik NTU “KhPI”, No. 10, pp. 435 – 437 (In Russian).

5. De Jong K.A., (1985), Genetic Algorithms: A 10 Year Perspective, In: Procs of the First Int. Conf. on Genetic Algorithms, pp. 167 – 177 (In English).

6. Narendra K.S., and Parthasarathy K., (1990), Identification and Control of Dynamical Systems Using Neural Networks, IEEE Trans. on Neur. Net, Vol. 1, No. 1, pp. 4 – 27.

7. Rosenblatt F., (1958), The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain, Psychological Review, 65, pp. 386 – 407.

8. Minsky M.L., and Papert S.A., (1969), Perceptions, Cambridge, MA: MIT Press.

9. Schaffer J.D., Whitley D., and Eshelman L.J., (1992), Combinations of Genetic Algorithms and Neural Networks: A Survey of the State of the Art, In: Procs. Of the Int. Workshop on Combinations of Genetic Algorithms and Neural Networks (Eds. L. D. Whitley, J. D. Schaffer), Baltimore, Maryland, pp. 1 – 37.

10. Hornik K., Stinchcomb M., and White H., (1989), Multilayer Feedforward Networks are Universal Approximators, Neural Networks, No. 2, pp. 359 – 366.

Published:
Last download:
2017-11-23 04:28:27

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014. Any use of information from the site is possible only under the condition that the source link! ]
Яндекс.Метрика