Experimental Frequency-Domain Vibration Based Fault Diagnosis of Roller Element Bearings Using Support Vector Machine

In heavy rotating machines and assembly lines, bearing failure in any one of them may result in shut down and affects the overall cost and quality of the product. Condition monitoring of bearing systems avoids breakdown and saves time and cost of preventive and corrective maintenance. This research paper proposes advanced fault detection strategies for taper rolling bearings. In this, a mathematical model using dimension analysis by matrix method (DAMM) and support vector machine (SVM) is developed to predict the vibration characteristic of the rotor-bearing system. Various types of defects created using an electric discharge machine (EDM) are analyzed by correlating dependent and independent parameters. Experiments were performed to classify the rotor dynamic characteristic of the bearings and validated the models developed using DAMM and SVM. Results showed the potential of DA and SVM to predict the dynamic response and contribute to the service life extension, efficiency improvement, and reduce failure of bearings. Thus, the automatic online diagnosis of bearing faults is possible with a developed model-based by DAMM and SVM.

Automated summary

This research proposes advanced fault detection strategies for taper rolling bearings, utilizing mathematical models and experiments to demonstrate the potential of DAMM and SVM in predicting dynamic response, extending service life, and reducing bearing failures.