Tool Wear Prediction in Machining of Aluminum Matrix Composites with the Use of Machine Learning Models
Adam Hamrol, Maciej Tabaszewski, Agnieszka Kujawińska, Jakub Czyżycki, Beomjoo Yang, Murali Mohan Cheepu · 2024
Read Tool Wear Prediction in Machining of Aluminum Matrix Composites with the Use of Machine Learning Models by Adam Hamrol, Maciej Tabaszewski, Agnieszka Kujawińska, Jakub Czyżycki, Beomjoo Yang, Murali Mohan Cheepu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11642730.txt.
Description
Cutting tools wear down fast when they mill aluminum composites, a material prized for being light yet hard to cut. Adam Hamrol and co-authors build models that predict that wear in this 2024 study. The models learn from signals recorded during cutting, such as force on the tool and shaking of the workpiece.
The team compared simple models that use one signal against richer models that combine many signals and several learning methods, including tree-based methods and a neural network. The richer models predicted wear more closely, with smaller average and worst errors, and they sorted worn from sound tools with fewer mistakes. Their accuracy reached about 0.97 in the best case. The authors note that simple models, though weaker, rest on simpler gear and may prove sturdier on the shop floor.
Catalog record
| CREATOR | Adam Hamrol, Maciej Tabaszewski, Agnieszka Kujawińska, Jakub Czyżycki, Beomjoo Yang, Murali Mohan Cheepu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |