| Summary: | 碩士 === 國立高雄第一科技大學 === 機械與自動化工程所 === 95 === Grinding is a manufacturing processes utilized rotary abrasive wheel to generate quality surface. Wheel wears as grinding proceed. A dressing operation is needed to restore the wheel grinding ability as the abrasive particle of wheel worn out. In order to perform automation while keeping the surface quality, wheel status needs to be detected white workpiece is being ground, in order to confirm the guy quality, and decide the timing for dressing operation.
The main objective of this research is to classify the status of CBN grinding process, while the process is being monitored. Acoustic emission signals and grinding power signals are selected for study, which correspond to the variation of abrasives in grinding process. As the signals were collected during the process, it was then classified with support vector machines based ground surface integrity. The relationship between grinding signals and ground surface were then build accuracy experimental result.
The utilization of support vector machines method can efficiently obtain the grinding status model to correctly character grinding status. The model is then used to with regressive model for the result of support vector machines classification, the grinding surface roughness can then predicted with little error, this would be beneficial for grinding process monitor.
|
|---|
