Please use this identifier to cite or link to this item:
|標題:||Study of high-frequency sound signals for tool wear monitoring in micromilling||關鍵字:||Sound signals;Micromilling;Hidden Markov model (HMM);Tool wear monitoring||Project:||The International Journal of Advanced Manufacturing Technology, Volume 66, Issue 9-12, Page(s) 1785-1792.||摘要:||
This study analyzed the sound signals obtainedfrom the micromilling process for microtool wear monitoring.Various spans of spectral features were created byanalyzing sound signals on tool wear monitoring in microcutting.The selection algorithm based on class mean scatteringcriteria and the hidden Markov model (HMM) modelwas developed to verify the effect of various feature selectionalgorithms on the system performance. The effect of thefeature bandwidth size, the size of observation sequence,and choice of the hidden states for HMM parameters werealso studied. The results indicate that the normalized soundsignals obtained from the single microphone with a frequencyrange between 20 and 80 kHz demonstrated the potentialto provide a solution to monitor micromills with the properselection of feature bandwidth and other parameters.
|Appears in Collections:||機械工程學系所|
Show full item record
TAIR Related Article
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.