What question did this study set out to answer?

To develop and evaluate a machine learning framework for detecting and classifying common mechanical and electrical faults in induction motors using stator current signals.

May 31, 2024Istanbul University - Journal of Electrical & Electronics EngineeringOpen Access

A Classification Approach for Induction Motor Faults Based on Empirical Mode Decomposition and Machine Learning Algorithms

View Full Paper

Ask AI

Bookmark

Authors

VRV. RajiniSri Ramachandra Institute of Higher Education and Research KSK. B. SundharakumarShiv Nadar University VNV. S. NagarajanManipal Academy of Higher Education

Discussion

Member takes

Implication

Computational evaluation demonstrates effective fault classification in induction motors, highlighting optimal machine learning models for specific mechanical and electrical defects.

Key Points

To develop and evaluate a machine learning framework for detecting and classifying common mechanical and electrical faults in induction motors using stator current signals.
Extracted current signature features under healthy operation and three fault types: broken rotor bars, interturn faults, and outer race bearing faults using discrete wavelet transform (DWT).
Trained and evaluated five machine learning classification algorithms: support vector machine (SVM), decision tree, random forest, naive Bayes, and extreme gradient boosting (XGBoost).
Discrete wavelet transform feature extraction effectively distinguished between healthy motor signatures and specific fault patterns across varying operating conditions.
Classifier performance varied across different defect categories, allowing the identification of specific, optimal machine learning models tailored to each motor fault type.

Cite This Study

Rajini et al. (2024) studied this question.

synapsesocial.com/papers/69ff6beb831589f3542d8b81 https://doi.org/10.5152/electrica.2024.23038

View Full Paper

Ask AI

Bookmark

Implication

Computational evaluation demonstrates effective fault classification in induction motors, highlighting optimal machine learning models for specific mechanical and electrical defects.

A Classification Approach for Induction Motor Faults Based on Empirical Mode Decomposition and Machine Learning Algorithms

Discussion

Member takes

Implication

Key Points

Cite This Study

A Classification Approach for Induction Motor Faults Based on Empirical Mode Decomposition and Machine Learning Algorithms

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider