スペクトルマップのパターン認識による切削異常の検知 : 第1報, 自励びびり振動の検知

概要

論文の詳細を見る
The fully automated running of machine tools requires early and automatic detection and prevention of abnormal cutting. Therefore, the purpose of this study is to determine a new method of detecting self-excited chatter vibration. Using this method, the occurrence of self-excited chatter vibration during a turning operation is evaluated by a neural network using a spectrum map of cutting tool vibration. The following conclusions were reached as a result of assessing this detection method during an actual turning operation. (i) The performance of the detection method is the most effective when the neural network uses five spectra as a spectrum map for the evaluation. (ii) The proportin of unsuccessful judgements was almost the same as that obtained with previous approaches. (iii) This proportion was almost unrelated to the noise level of the signal used for detection.
一般社団法人日本機械学会の論文
1997-02-25