Open AccessBroken Rotor Bars Fault Detection Based on Envelope Analysis Spectrum and Neural Network in Induction Motors
Author(s) -
Saddam Bensaoucha,
Sid Ahmed Bessedik,
A. Ameur,
Abdellatif Seghiour
Publication year - 2018
Publication title -
algerian journal of signals and systems
Language(s) - English
Resource type - Journals
eISSN - 2676-1548
pISSN - 2543-3792
DOI - 10.51485/ajss.v3i3.66
Subject(s) - fast fourier transform , induction motor , stator , artificial neural network , hilbert transform , rotor (electric) , matlab , fault (geology) , context (archaeology) , computer science , envelope (radar) , signal (programming language) , control theory (sociology) , algorithm , electronic engineering , engineering , spectral density , artificial intelligence , electrical engineering , telecommunications , paleontology , radar , control (management) , voltage , seismology , geology , biology , programming language , operating system
In this paper, a study has presented the performance of a neural networks technique to detect the broken rotor bars (BRBs) fault in induction motors (IMs). In this context, the fast Fourier transform (FFT) applied on Hilbert modulus obtained via the stator current signal has been used as a diagnostic signal to replace the FFT classic, the characteristics frequency are selected from the Hilbert modulus spectrum, in addition, the different load conditions are used as three inputs data for the neural networks. The efficiency of the proposed method is verified by simulation in MATLAB environment.