Tool wear monitoring by emitted sound analysis using Hilbert Huang transform and competitive neural network
Turning is one of the important machining processes in manufacturing industries. Tools wear during turning, is one of the major problems which may lead to production loss and machine down time. An effective tool wear monitoring method is therefore required to minimise the above. The work done in thi...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Thesis |
| 出版: |
2014
|
| 主题: | |
| 标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
| 总结: | Turning is one of the important machining processes in manufacturing industries. Tools wear during turning, is one of the major problems which may lead to production loss and machine down time. An effective tool wear monitoring method is therefore required to minimise the above. The work done in this thesis is related to the development of a new method for tool wear monitoring using tool-emitted sound signal in conjunction with newly reported Hilbert Huang Transform (HHT). In the proposed method, the condition of the cutting tool insert is monitored to classify its state into three different categories, namely, fresh, slightly worn and severely worn by analysing the tool-emitted audible sound. A trained competitive neural network is employed for this purpose. The network is trained by using the instantaneous amplitudes and instantaneous frequencies extracted from the tool-emitted sound using HHT. The novelty of the present work is the use of HHT to extract the instantaneous amplitudes and the frequencies of the tool-emitted sound to determine the condition of the cutting tool insert based on its flank wear. HHT is a recently developed signal processing technique more suitable for analysing nonstationary and nonlinear signals such as tool-emitted sound. |
|---|