A Comparison between Hybrid and Non-hybrid Classifiers in Diagnosis of Induction Motor Faults

Induction machines (IMs) play a essential role in industry and there is a strong demand for their reliable and safe operation. IMs are susceptible to problems such as stator current imbalance and broken bars, usually detected when the equipment is already broken, and sometimes after irreversible damage has occurred. Condition monitoring can significantly reduce maintenance costs and the risk of unexpected failures through the early detection of potential risks. Several techniques are used to classify the condition of machines. This paper presents a new case study on Hybrid and Non-Hybrid classifiers in on-line condition monitoring of induction motors. Advantages of the system include improved performer of fault classification. The database was developed through a simplified mathematical model of the machine considering the effects caused by asymmetries in the phase impedances of motors. A comparative analysis is presented for simulation using single classifiers (based on the neural networks, k-Nearest neighbor and Naive Bayes), Non-Hybrid classifiers (based on the Bagging and Boosting) and Hybrid (Stacking) approaches. Results demonstrate that the Non-Hybrid systems obtain the better results in comparison with the individual experiments.