Article information
Resumen
La calidad superficial es uno de los aspectos más cuidados en la fabricación de piezas. Esta calidad se estima frecuentemente en función a la rugosidad superficial. Trabajos que incorporan técnicas de softcomputing al estudio de la rugosidad superficial en-proceso o pos-proceso son relativamente frecuentes en la literatura. Sin embargo, son casi inexistentes los dedicados al estudio de la rugosidad superficial en pre-proceso, pese a que esto puede ayudar a reducir costes asociados al aseguramiento de la calidad superficial en la producción industrial. En este trabajo se presenta una técnica softcomputing para generar un modelo pre-proceso predictivo de la rugosidad superficial basado en experimentación con características diversas del proceso de fresado a alta velocidad. El modelo de predicción es un clasificador Bayesiano, validado con el método k-fold cross-validation y varios valores de mérito, lo que ha permitido verificar la calidad del modelo predictivo respecto a otros modelos basados en técnicas similares.
Palabras clave:
Mecanizado a alta velocidad
proceso de fresado a alta velocidad
softcomputing
redes Bayesianas
modelos predictivos
Full text is only aviable in PDF
Referencias
[Acebes et al., 2004]
L. Acebes, R. Alves, A. Merino, C. de Prada.
Un entorno de modelado inteligente y simulación distribuida de plantas de proceso.
RIAI: Revista Iberoamericana de Automática e Informática Industrial, 1 (2004), pp. 42-48
[Altintas and Weck, 2004]
Y. Altintas, M. Weck.
Chatter stability of metal cutting and grinding.
CIRP Annals Manufacturing Technology, 53 (2004), pp. 619-642
[Benardos and Vosniakos, 2003]
P.G. Benardos, G.C. Vosniakos.
Predicting surface roughness in machining: a review.
International Journal of Machine Tools & Manufacture, 43 (2003), pp. 833-844
[Correa et al., 2004]
M. Correa, M. Ramírez, J. de, J.R. Alique, C. Rodríguez.
Factores que afectan el acabado superficial en los procesos de mecanizado: técnicas de análisis y modelos.
XXV Jornadas de Automática, (2004),
[Correa et al., 2008]
M. Correa, C. Bielza, M. Ramírez, J.R. Alique.
A Bayesian network model for surface roughness prediction in the machining process.
International Journal of Systems Science, 39 (2008), pp. 1181-1192
[Correa et al., 2009]
M. Correa, C. Bielza, P. Pamies-Teixeira.
Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process.
Expert Systems with Applications, 36 (2009), pp. 7270-7279
[Chow and Liu, 1968]
C.K. Chow, C. Liu.
Approximating discrete probability distributions.
IEEE Transactions on Information Theory, 14 (1968), pp. 462-467
[Ezugwua et al., 2005]
E.O. Ezugwua, D. Faderea, J. Onney, J. Bonney, R.B. Da Silva, W.F. Sales.
Modelling the correlation between cutting and process parameters in high-speed machining of Inconel 718alloy using artificial neural network.
International Journal of Machine Tools & Manufacture, 45 (2005), pp. 1375-1385
[Friedman et al., 1997]
N. Friedman, D. Geiger, M. Goldszmit.
Bayesian network classifiers.
Machine Learning, 29 (1997), pp. 131-161
[Gajate and Heber, 2009]
A. Gajate, R. Heber.
Control Neuroborroso en red. Aplicación al proceso de taladrado de alto rendimiento.
RIAI: Revista Iberoamericana de Automática e Informática Industrial, 6 (2009), pp. 31-38
[Hao et al., 2006]
W. Hao, X. Zhu, X. Li, G. Turyayagyenda.
Prediction of cutting force for self-propelled rotary tool using artificial neural network.
Journal of Material processing Technology, 180 (2006), pp. 23-29
[Ko et al., 2007]
T.J. Ko, J.W. Park, H.S. Kim, S.H. Kim.
Onmachine measurement using a noncontact sensor based on a CAD model.
International Journal of Advanced Manufacturing Technology, 32 (2007), pp. 739-746
[Lee and Chen, 2003]
S. Lee, J.C. Chen.
On-line surface roughness recognition system using artificial neural networks system in turning operations.
International journal of Advanced Manufacturing Technology, 22 (2003), pp. 62-68
[Lela et al., 2009]
B. Lela, D. Bajie, S. Jozié.
Regression analysis, support vector machines, and Bayesian neural Network approaches to modelling surface roughness in face milling.
Advanced Manufacturing Technology, 42 (2009), pp. 1082-1088
[MacQueen, 2003]
J. MacQueen.
Some Methods for Classification Analysis of Multivariate Observations.
pp. 281-297
[Ozel et al., 2009]
T. Ozel, A. Esteves, J. Davim.
Neural network process modelling for turning of steel parts using conventional and wiper inserts.
International Journal of Materials and Product Technology, 35 (2009), pp. 246-258
[Ramírez-Cadena et al., 2005]
M. Ramírez-Cadena, M. Correa, C. Rodríguez-Gonzalez, J.R. Alique.
Surface Roughness Modelling Based on Surface Roughness Feature Concept for High Speed Machining.
American Society of Mechanical Engineers Manufacturing Engineering Division, 16 (2005), pp. 811-817
[Redondo et al., 2009]
R. Redondo, P. Santos, A. Bustillo, J. Sedano, J.R. Villar, M. Correa, J.R. Alique, E. Corchado.
A soft Computing System to Persorm Face Milling Operations.
pp. 1282-1291
[Reddy et al., 2008]
B. Reddy, G. Padmanabhan, K.V. Reddy.
Surface Roughness Prediction Techniques for CNC turning.
Asian Journal of Scientific Research, 1 (2008), pp. 256-264
[Soleimanimehr et al., 2009]
H. Soleimanimehr, M.J. Nategh, S. Amini.
Modelling of Surface Roughness in Vibration Cutting by Artificial Neural Network”.
pp. 386-390
[Stone, 1974]
M. Stone.
Cross-validatory choice and assessment of statistical prediction.
Journal of the Royal Statistical Society B, 36 (1974), pp. 111-147
[Zhou and Cheng, 2009]
L. Zhou, K. Cheng.
Dynamic cutting process modelling and its impact on the generation of surface topography and texture in nano/micro cutting.
pp. 247-266
[Zuperl and Cus, 2003]
U. Zuperl, F. Cus.
Optimization of cutting conditions during cutting by using neural networks.
Robotics and Computer Integrated Manufacturing, 19 (2003), pp. 189-199
Copyright © 2011. Comité Español de Automática