Scientific and Technical Journal


ISSN Print 2221-3937
ISSN Online 2221-3805

Nowadayscreation of sensorless control systems is still an actual task. The elimination of the mechanical rotor position sensor increases reliability and reduces costs. The switched reluctance motor (SRM) is a highly nonlinear machine, that makes it an ideal candidate for the application of artificial neural networks (ANNs). In the worksof various authors the neural networks use the measurement of the phase flux linkages and phase currents as inputs to estimate the corresponding rotor position.

This paper presents a new sensorless control system of switched reluctance motorswith a more simple structure of the neural network than existing ones.  A feedforward artificial neural network, that uses only phase currents and supply voltage as the input signals, with the mathematical processing of rotor position data as the network output was synthesized and researched on the experimental plant.

The results of experiment are presented and they show the effectiveness of proposed neuro-estimator. 


1. Bellini A., Filippetti F., Franceschini G., Tassoni C., and Vas P., (1998), Position Sensorless Control of a SRM Drive Using ANN-Techniques,33rd IAS Annual Meeting. Conference of the 1998 IEEE, 1998, Vol.1. – pp. 709 – 714 (In English).

2. Enayati B., and Saghaiannejad S.M., (2006), Sensorless Position Control of Switched Reluctance Motors Based on Artificial Neural Networks, IEEE ISIE, Montreal, Canada, July 9-12, 2006, pp. 2266 – 2271 (In English).

3. Mese E., and Torrey D.A.,(2002), An Approach for Sensorless Position Estimation for Switched Reluctance Motors Using Artifical Neural Networks,IEEE Transactions on Power Electronics, Vol. 17, No. 1, pp. 66 –75 (In English).

4. Mese E., and Torrey D.A.,(1997), Sensorless Position Estimation for Variable-Reluctance Machines Using Artificial Neural Networks,Proc. Industry Applications Conference, August, Vol.1, pp. 540 – 547 (In English).

5.  Reay D.S., Dessouky Y., and Williams B.W. The use of Neural Networks to Enhance Sensorless Position Detection in Switched Reluctance Motors,Systems, Man, and Cybernetics, IEEE International Conference on, 1998, Vol.2, pp. 1774 – 1778 (In English).

6.  Reay D.S., and Williams B.W.(1999), Sensorless Position Detection using Neural Networks for the Control of Switched Reluctance Motors,Control Applications, Proceedings of the 1999 IEEE International Conference on, Vol. 2, pp. 1073 – 1077 (In English).

7. Sharma V.K, Murthy S.S.,and Singh B.,(1999), An Improved Method for the Determination of Saturation Characteristics of Switched Reluctance Motors,Instrumentation and Measurement, IEEE Transactions on Instrumentation and Measurement, Vol. 48, – pp. 995 – 1000 (In English).

8. Bobechko Ju.O, Golovach I.R., andLozyns'kyj A.O. Zastosuvannja shtuchnyh nejronnyh merezh prjamogo poshyrennja sygnalu dlja identyfikacii' polozhennja rotora ventyl'nogo reaktyvnogo dvyguna [Feedforward  Artificial  Neural NetworksfortheRotorPositionDetection of  Switched  Reluctance  Motors], (2011), Visnyk NU “L'vivs'ka politehnika” “Elektroenergetychni ta elektromehanichni systemy”, L'viv, No. 707, pp. 9 – 15 (In Ukrainian).

9. BobechkoJu.O. Zastosuvannjazgladzhu-vannjadanyhnejronnoi' merezhidljavykory-stannjavsystemahkeruvannjaventyl'nymreaktyvnymdvygunom[Smoothing oftheNeural Network’sOutputData in ControlSystemsofSwitchedReluctanceMotors], (2011), NauchnyjVestnykDGMA, No. 2 (8Е), pp. 37 – 41 (In Ukrainian).

10. BobechkoJu.O. Nejroestymatordljabezdavachevoi' systemykeruvannjaventyl'nymreaktyvnymdvygunom[SensorlessControlSystemofSwitchedReluctanceMotorsusingNeuro-Estimator], (2012), TehnichnaElektrodynamika, No. 3, pp. 89 – 90 (In Ukrainian).

Last download:
13 Jan 2020

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014-2018. Any use of information from the site is possible only under the condition that the source link! ]