Three-phase induction motor fault identification using optimization algorithms and intelligent systems

The present work proposes the study and development of a strategy that uses an optimization algorithm combined with pattern classifiers to identify short-circuit stator failures, broken rotor bars and bearing wear in three-phase induction motors, using voltage, current, and speed signals. The Differ...

Full description

Saved in:
Bibliographic Details
Published in:Soft computing (Berlin, Germany) Germany), 2024-05, Vol.28 (9-10), p.6709-6724
Main Authors: Guedes, Jacqueline Jordan, Goedtel, Alessandro, Castoldi, Marcelo Favoretto, Sanches, Danilo Sipoli, Serni, Paulo José Amaral, Rezende, Agnes Fernanda Ferreira, Bazan, Gustavo Henrique, de Souza, Wesley Angelino
Format: Article
Language:English
Subjects:
Algorithms
Application of Soft Computing
Artificial Intelligence
Artificial neural networks
Bearings
Computational Intelligence
Control
Electric potential
Energy consumption
Engineering
Evolutionary computation
Failure
Genetic algorithms
Induction motors
Intelligent systems
Load fluctuation
Machine learning
Mathematical Logic and Foundations
Mechatronics
Neural networks
Optimization algorithms
Parameter identification
Particle swarm optimization
Robotics
Short circuits
Simulated annealing
Support vector machines
Voltage
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present work proposes the study and development of a strategy that uses an optimization algorithm combined with pattern classifiers to identify short-circuit stator failures, broken rotor bars and bearing wear in three-phase induction motors, using voltage, current, and speed signals. The Differential Evolution, Particle Swarm Optimization, and Simulated Annealing algorithms are used to estimate the electrical parameters of the induction motor through the equivalent electrical circuit and the failure identification arises by variation of these parameters with the evolution of each fault. The classification of each type of failure is tested using Artificial Neural Network, Support Vector Machine and k-Nearest Neighbor. The database used for this work was obtained through laboratory experiments performed with 1-HP and 2-HP line-connected motors, under mechanical load variation and unbalanced voltage.
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-023-09519-5