| Summary: | 碩士 === 明新科技大學 === 精密機電產業研發碩士外國學生專班 === 98 === ABSTRACT
This technical report provides a method, based on classification techniques, for automatic detection defects of rolling element bearings. We used sound pressure measurement by an 824 sound level meter and a real-time analyzer, which is a production of LARSON DAVIS firm. By measuring sound pressure emission from rolling elements bearings on a model with a fixed motor speed for all bearings, one can collect the signatures of the measured signal. We separate the bearings into two groups, which are a good bearing set and a bad bearing set, where the bad bearings are made artificially damage. Through applying a scattering matrix theory find a set of feature, which can distinguish quality of bearings. We further collect the selected features from the table to train a neural network with target output of a good bearing or a bad bearing. After training, the neural network can detect bearing quality accurately.
|
|---|
