Multi-sensor condition monitoring of bearings using support vector machines

摘要

This thesis presents a study on bearing condition monitoring under variable operating conditions using Support Vector Machines. Data collected from multiple sensors including accelerometers, acoustic emission sensors and tachometers are used for the studies presented in this thesis. This work has successfully demonstrated acoustic emission's superiority in bearing incipient fault detection; and the prognostic study has developed an effective prognostic approach to capture the system's dynamics with speed variations and make accurate predictions.