Abstract
An application of artificial neural networks for the design of tool wear monitoring strategy is presented. Back Propagation and ART-2A networks have been chosen as representatives of supervised and unsupervised types of neural networks. Both networks were used to detect the tool flank wear during turning operation. The networks were tested with data containing information from several sensors (sensor integration approach) and only one sensor (smart sensor approach). The main goal of this study was to determine inter/extrapolation features of the networks. Also, network topology and learning algorithms were studied.
| Original language | English |
|---|---|
| Pages | 17-22 |
| Number of pages | 6 |
| Publication status | Published - 1994 |
| Event | Proceedings of the Joint Hungarian - British International Mechatronics Conference - Budapest, Hung Duration: 21 Sept 1994 → 23 Sept 1994 |
Conference
| Conference | Proceedings of the Joint Hungarian - British International Mechatronics Conference |
|---|---|
| City | Budapest, Hung |
| Period | 21/09/94 → 23/09/94 |
ASJC Scopus subject areas
- General Engineering
Fingerprint
Dive into the research topics of 'On designing tool wear monitoring systems using supervised and unsupervised neural networks'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver