A Comparison between Back Propagation and the Maximum Sensibility Neural Network to Surface Roughness Prediction in Machining of Titanium (Ti 6Al 4V) Alloy
Titanium alloys are attractive materials due to their unique high strength, excellent performance at elevated temperatures and exceptional resistance to corrosion. The aerospace and military industries are the main users of this material. Titanium alloys are classified as materials difficult to mach...
| Autor: | |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2008 |
| País: | México |
| Recursos: | Corporación Mexicana de Investigación en Materiales |
| Repositorio: | Repositorio COMIMSA |
| Idioma: | inglés |
| OAI Identifier: | oai:comimsa.repositorioinstitucional.mx:1022/387 |
| Acesso em linha: | http://comimsa.repositorioinstitucional.mx/jspui/handle/1022/387 |
| Access Level: | acceso abierto |
| Palavra-chave: | info:eu-repo/classification/cti/7 |
| Resumo: | Titanium alloys are attractive materials due to their unique high strength, excellent performance at elevated temperatures and exceptional resistance to corrosion. The aerospace and military industries are the main users of this material. Titanium alloys are classified as materials difficult to machine. The correct parameters for machining are a hard to determine, and today researches are looking to develop new models to predict and optimize these parameters. The surface roughness (Ra) in turning of a titanium alloy machining Ti 6Al 4V predicted using neural and maximum sensitivity network is shown. The machining tests were carried out using PVD (TiAIN) coated carbide inserts under different cutting conditions. Confidence intervals were estimated in the model to get correct results. There are various machining parameters and they have an effect on the surface roughness. A set of initial parameters in finished turning of Ti 6Al 4V obtained from literature have been used. These parameters are cutting speed, feed rate and depth of cut. This paper shows the results obtained using these neural networks approaches to analyze the variables to model the machining process. |
|---|