ISSN:
1662-9752
Source:
Scientific.Net: Materials Science & Technology / Trans Tech Publications Archiv 1984-2008
Topics:
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
The paper evaluates the feasibility of monitoring cutting forces for in-process predictionof the workpiece surface roughness, using regression based models (RG) and artificial neuralnetwork (ANN) techniques. The three orthogonal cutting force components (Fx, Fy, Fz) and themachined length L have been chosen as input variables. In the experimental test, AISI-1045 steelmaterial was turned using a TiN coated carbide tool and employing a range of machining conditions(cutting speed: v=150, 200, 250 m/min; feed rate: f=0.15, 0.20, 0.25 mm/rev; depth-of-cut: d=1, 2, 3mm). The results provided a wide range of measured cutting force and surface roughness values (Raand Rq), which were used for adjustment and validation of the prediction models. Two predictionmodels were developed and subsequently the model accuracy was assessed by comparing thesurface roughness predicted by the models with that measured by a 2D profilometer. The resultshighlighted the reasonably good fit given by both models, with the ANN based model providing bestaccuracy for surface roughness prediction. The prediction of the output surface roughness in anautomated turning process was established and was found to be feasible by the monitoring ofcutting forces
Type of Medium:
Electronic Resource
URL:
http://www.tib-hannover.de/fulltexts/2011/0528/02/13/transtech_doi~10.4028%252Fwww.scientific.net%252FMSF.526.211.pdf
Permalink