ELECTRIC MOTOR DIAGNOSTICS OF SWITCHES BASED ON THE NEURAL NETWORK DATA MODELING THE SPECTRAL DECOMPOSITION OF THE CURRENTS

O. M. Shvets

Abstract


The method of automated diagnostics of electric motors is offered. It uses a neural network revealing the electric motor faults on the basis of analysis of frequency spectrum of current flowing through the motor.


Keywords


diagnostics; neural network modeling; current; motor; turnout translation; spectral decomposition

GOST Style Citations


1. Нуссбаумер, Г. Быстрое преобразование Фурье и алгоритмы вычисления сверток [Текст] : [пер. с англ.] / Г. Нуссбаумер. – М.: Радио и связь, 1985.

2. Хайкин, С. Нейронные сети: полный курс [Текст] : [пер. с англ.]. – 2-е изд. / С. Хайкин. – М.: Изд. дом «Вильямс», 2006.

3. Stone, M. Cross-validation choice and assessment of statistical predictions [Text] / M. Stone // J. Roy.Statistical Soc. – 1974. – Vol. B36. – P. 111-133.

4. Statistical theory of overtraining – Is crossvalidation asymptotically effective? [Text] / S. Amari et al. // Advances in Neural Informational Processing Systems. – 1996a. – Vol. 8. – Cambridge, MA: MIT Press. – P. 176-182.





Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

 

ISSN 2307–3489 (Print)
ІSSN 2307–6666 (Online)