Bearing Fault Detection in Three-Phase Induction Motors Using Support Vector Machine and Fiber Bragg Grating

Due to its robustness and cost-effectiveness, the three-phase induction motor (TIM) has become the most widespread electric machine today. However, like any other equipment, it is vulnerable to a fault, and about 52% of these are related to bearings. This work presents the detection of flaws in the outer bearing's raceway from the measurement of motor dynamic strain signals collected from sensors based on fiber Bragg grating (FBG). Three different degrees of severity were considered for faults in the outer bearing's raceway. The tests were carried out on the motor operating under no-load conditions, with 47 different power supply frequencies. This work proposes a support vector machine (SVM) classifier to identify fault severity levels. Feature extraction was performed using two techniques: selecting the four highest peaks in the frequency spectrum and principal component analysis (PCA). The supervised SVM classifiers show that the dataset formed from the PCA presented a higher hit rate than the dataset constituted by the four highest peaks, with 99.82% and 92.73%, respectively. Based on the methodology presented in this work, it was possible to validate the use of FBG to detect bearing faults. Regardless of the degree of severity of the fault analyzed, the sensor detected its characteristic frequency. Based on the methodology presented in this work, it was possible to validate the use of FBG to detect bearing faults. Regardless of the degree of severity of the flaw analyzed, the sensor detected its characteristic frequency.

Automated summary

The three-phase induction motor (TIM) is widely used due to its robustness and cost-effectiveness. However, like any other equipment, it is vulnerable to faults, with about 52% of them related to bearings. This work proposes a method using fiber Bragg grating (FBG) sensors to detect flaws in the outer bearing's raceway by measuring motor dynamic strain signals. A support vector machine (SVM) classifier is used for fault severity identification, with feature extraction performed using peak selection and principal component analysis (PCA). The results show that the PCA-based dataset achieved a higher hit rate than the dataset based on peak selection.