Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s): Chen, M. | Hu, D.J. | Shao, H. | Wang, H.L. |
Year: 2003
Citation: JOURNAL OF MATERIALS PROCESSING TECHNOLOGY Volume: 139 Issue: 1-3 Pages: 237-242
Abstract: Acoustic emission (AE) and motor power sensors were used to detect the tool breakage in turning. Time-frequency analysis was used to process different AE signals emitted from the cutting process (normal cutting condition, tool breakage, chip fracture, etc.). Four types of power signal variation were observed in experiments when tool breakage occurred, which suggest that the change of power signals in the time domain was stochastic. Delayed variance is proposed to extract features from the power signals. The tool condition can be recognized through a neural network based on adaptive resonance theory (ART2).
Topics:
Machine Learning,
Applications:
Industrial Control,
Models:
ART 2 / Fuzzy ART,
