TY - GEN
T1 - Detection of Broken Rotor Bars in Induction Motors Using Supervised Machine Learning Methods
AU - Nkwinika, Rivoningo
AU - Muteba, Mbika
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - This paper presents the detection of broken rotor bars (BRB) in three-phase induction motors (IM) employing three supervised machine learning algorithms (SMLA), including Decision Three Classification (DTC), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The three SMLAs are trained to detect BRB features from measured steady-state line current signatures. The training data were collected in the time domain from laboratory experiments and transformed to the frequency domain through the Discrete Fourier Transform (DFT). A confusion matrix was employed to confirm the models' performance by means of accuracy, precision, recall, and f1-scores. The results evidence that the DTC has better accuracy and precision for both half and full-load operations of the squirrel cage asynchronous motor when compared with the ANN and SVM algorithms. The DTC obtained the best F1 score, accuracy, precision, and recall, followed by the SVM.
AB - This paper presents the detection of broken rotor bars (BRB) in three-phase induction motors (IM) employing three supervised machine learning algorithms (SMLA), including Decision Three Classification (DTC), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The three SMLAs are trained to detect BRB features from measured steady-state line current signatures. The training data were collected in the time domain from laboratory experiments and transformed to the frequency domain through the Discrete Fourier Transform (DFT). A confusion matrix was employed to confirm the models' performance by means of accuracy, precision, recall, and f1-scores. The results evidence that the DTC has better accuracy and precision for both half and full-load operations of the squirrel cage asynchronous motor when compared with the ANN and SVM algorithms. The DTC obtained the best F1 score, accuracy, precision, and recall, followed by the SVM.
KW - artificial neural network
KW - broken rotor bars
KW - decision trees
KW - fault detection
KW - induction motors
KW - steady-state current analysis
KW - supervised machine learning
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=105002677573&partnerID=8YFLogxK
U2 - 10.1109/SAUPEC65723.2025.10944335
DO - 10.1109/SAUPEC65723.2025.10944335
M3 - Conference contribution
AN - SCOPUS:105002677573
T3 - Proceedings of the 33rd Southern African Universities Power Engineering Conference, SAUPEC 2025
BT - Proceedings of the 33rd Southern African Universities Power Engineering Conference, SAUPEC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 33rd Southern African Universities Power Engineering Conference, SAUPEC 2025
Y2 - 29 January 2025 through 30 January 2025
ER -