Přístupnostní navigace
E-application
Search Search Close
Publication detail
ZEZULA, L.
Original Title
INTER TURN SHORT-CIRCUIT DETECTION IN VECTOR CONTROLLED PMS MOTOR USING AI
English Title
Type
article in a collection out of WoS and Scopus
Language
Czech
Original Abstract
This paper deals with the diagnostics of inter turn faults in a vector controlled synchronous motor with permanent magnets. Inter turn faults are detected by a convolution neural network from adequately preprocessed current signals of the stator phases. The goal is to create a model within which different severity of inter turn faults will be simulated. Data from the simulations are preprocessed and transformed using Wavelet transform and the resulting scalograms are fed to a pre-trained convolution neural network GoogLeNet. This neural network’s diagnostic capabilities are tested on a physical drive, capable of emulating faults.
English abstract
Keywords
PMSM, ITF, Inter turn fault, Inter turn short-circuit, Vector control, Convolutional neural network, Motor fault diagnostics
Key words in English
Authors
Released
23. 4. 2020
ISBN
978-80-214-5867-3
Book
Proceedings I of the 26th Conference STUDENT EEICT 2020
Edition number
1
Pages from
63
Pages to
66
Pages count
4
BibTex
@inproceedings{BUT179036, author="Lukáš {Zezula}", title="INTER TURN SHORT-CIRCUIT DETECTION IN VECTOR CONTROLLED PMS MOTOR USING AI", booktitle="Proceedings I of the 26th Conference STUDENT EEICT 2020", year="2020", number="1", pages="63--66", isbn="978-80-214-5867-3" }