This paper proposes a new method using Artificial Neural Network (ANN) for detection of different Inter Turn Short Circuit (ITSC) faults in an induction motor under different loading conditions. The stator current signal was obtained experimentally from a healthy motor and a faulty motor with ITSC faults. The statistical time domain features was extracted from stator current signal, these features are used to train and test an ANN in order to diagnose ITSC faults. A complete study is performed by considering various diagnosis methods from ANN and machine learning algorithms, including Decision Tree (DT), K-Nearest Neighbors (KNN), Naive Bayes (NB), Random Forest (RF) and Support Vector Machine (SVM) for diagnosis ITSC faults. The performance of the proposed method was compared with machine learning algorithms, the proposed method has a higher accuracy than the other algorithms. Trained neural networks are able to classify different states of the ITSC faults with satisfied accuracy. The efficiency of this approach has been proven using experimental tests to diagnose ITCS faults in a 1. 5Hp squirrel cage induction motor.
Detection of Inter Turn Short Circuit Faults in Induction Motor using Artificial Neural Network
2020-04-01
1158170 byte
Conference paper
Electronic Resource
English
Detection of Inter Turn Short Circuit Faults in Induction Motor Using Artificial Neural Network
DOAJ | 2020
|Stator Winding Inter-Turn Short-Circuit Modelling of a Squirrel-Cage Induction Motor
Online Contents | 2016
|Fault detection of motors inter-turn short circuit based on back propagation neural network
Automotive engineering | 2012
|