Analysis of Effects of Loading Conditions on Condition Monitoring of Induction Machines
Date
2024-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
I.O.E
Abstract
effectiveness,
robustness, and high efficiency. However, as with all electrical machines, they
are prone to degradation over time, necessitating expensive repairs and maintenance. Detecting
faults early is critical to minimizing unplanned downtime and reducing operational
costs. One significant fault that can significantly impact the performance of induction machines
is broken rotor bars.
Broken rotor bars can lead to various undesirable effects, including increased vibration,
reduced efficiency, and potential catastrophic failure if left undetected. Motor current
signature analysis (MCSA) is a widely adopted technique for monitoring the condition of
induction machines during normal operation. By analyzing the frequency spectrum of the
stator current, MCSA provides valuable insights into the health of the machine and can
detect anomalies indicative of broken rotor bars.
This study specifically focuses on analyzing the stator current signals of a squirrel cage
induction machine to detect and diagnose broken rotor bar faults under different load conditions.
The research employs a multi-layer perceptron (MLP) model, a type of artificial
neural network known for its ability to learn complex patterns, to study the impact of
varying operational loads on fault detection accuracy.
Description
This study specifically focuses on analyzing the stator current signals of a squirrel cage
induction machine to detect and diagnose broken rotor bar faults under different load conditions.
The research employs a multi-layer perceptron (MLP) model, a type of artificial
neural network known for its ability to learn complex patterns, to study the impact of
varying operational loads on fault detection accuracy.
Keywords
Induction Motor, Condition Monitoring, Fourier Transform, Broken Rotor Bars