| Summary: | 碩士 === 國立中興大學 === 機械工程學系所 === 100 === As the demand of the small feature and high accuracy for aerospace, biomedical, and electronic devices continuously increases, the micro mechanical machining plays an important role for improving their manufacturing quality and efficiency. Due to the higher tool wear rate than conventional counterpart, the tool wear monitoring in the micro machining draws much more attention than before.
The objective of this thesis is to analyze the cutting path effect on the performance of tool wear monitoring system integrated with the spindle vibration and acoustic emission (AE) signal obtained from the spindle housing, as well as the study of the effect of system parameters on the system performance.
A micro tool condition monitoring system integrated by sensor system, signal transformation, feature selection, and classifier was developed in this study. In which, the FFT transformation was used for transforming the time domain signal to the frequency domains, the class mean scatter criteria was used to select the features closely related to the tool wear condition, and the Fisher linear discriminant function was the basis for designing the classifier. In the analysis of the parameters effect on the system performance, the bandwidth sizes of frequency domain signal, the length sizes of extracted signal, and the change of cutting path in micro milling were studied. In collecting the signal for system analysis and development, an experiment was implemented along with 700 μm diameter micro end mill and ISO TC-120 work-piece.
The results show that the AE and vibration signal collected on the fixture connected to spindle housing can be used to detect the change of tool wear on a micro end mill and the alteration of different cutting path in milling. The tool wear monitoring system was developed by the vibration signal from the straight line milling detect the tool condition of line cutting path well. As the cutting path switched, the varied signal influence the decrease of system classification rate. In the tool wear classification results, the effect of system parameters such as bandwidth size of frequency domain signal and the length sizes of extracted signal could reduce the effect of cutting path. In consideration of the AE signal case, the influence of cutting path is slight. The feature selection of system development would not affected by the effect of cutting path. But each micro end mill has the different geometry of tool flute, the AE signals are easy varied by the different cutting tool. The variability would influence the tool wear monitoring system ability. In the tool wear classification results, the effect of system parameters such as bandwidth size of frequency domain signal and the length sizes of extracted signal could reduce the influence of the different geometry of tool flute as well.
|
|---|
