Resumen
Tool wear is a recurring topic in the cutting field, so obtaining knowledge about the tool wear process and the capability of predicting tool wear is of special importance. Cutting processes can be optimised with predictive models that are able to forecast tool wear with a suitable level of accuracy. This research focuses on the application of some regression approaches, based on machine learning techniques, to a face-turning process for Inconel 718. To begin with, feature extraction of the cutting forces is considered, to generate regression models. Subsequently, the regression models are improved with a reduced set of features obtained by computing the feature importance. The results provide evidence that the gradient-boosting regressor allows an increment in the wear prediction accuracy and the random forest regressor has the capability of detecting relevant features that characterise the turning process. They also reveal higher accuracy in predicting tool wear under high-pressure cooling as opposed to conventional lubrication.
Idioma original | Inglés |
---|---|
Páginas (desde-hasta) | 443-450 |
Número de páginas | 8 |
Publicación | Insight - Non-Destructive Testing and Condition Monitoring |
Volumen | 60 |
N.º | 8 |
DOI | |
Estado | Publicada - ago 2018 |
Palabras clave
- Face turning superalloys
- Machine Learning
- Tool wear prediction
Project and Funding Information
- Project ID
- info:eu-repo/grantAgreement/EC/FP7/620134/EU/High speed metallic material removal under acceptable surface integrity for rotating frame/HIMMOVAL
- Funding Info
- The work was performed as a part of the HIMMOVAL project (grant agreement number: 620134) within the Clean Sky programme, which relates to the SAGE2 project oriented to geared open rotor development, enabling the delivery of the demonstrator part. The work of Roberto Santana has been funded by the IT-609-13 programme (Basque Government) and TIN2016-78365-R (Spanish Ministry of Economy, Industry and Competitiveness).