hrcak mascot   Srce   HID

Izvorni znanstveni članak

Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining

Marjan Korošec ; Faculty of Mechanical Engineering, University of Ljubljana, Ljubljana, Slovenia
Jože Duhovnik
Janez Kopač

Puni tekst: engleski, pdf (437 KB) str. 71-78 preuzimanja: 498* citiraj
APA 6th Edition
Korošec, M., Duhovnik, J. i Kopač, J. (2010). Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining. Automatika, 51 (1), 71-78. Preuzeto s https://hrcak.srce.hr/51367
MLA 8th Edition
Korošec, Marjan, et al. "Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining." Automatika, vol. 51, br. 1, 2010, str. 71-78. https://hrcak.srce.hr/51367. Citirano 25.06.2019.
Chicago 17th Edition
Korošec, Marjan, Jože Duhovnik i Janez Kopač. "Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining." Automatika 51, br. 1 (2010): 71-78. https://hrcak.srce.hr/51367
Harvard
Korošec, M., Duhovnik, J., i Kopač, J. (2010). 'Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining', Automatika, 51(1), str. 71-78. Preuzeto s: https://hrcak.srce.hr/51367 (Datum pristupa: 25.06.2019.)
Vancouver
Korošec M, Duhovnik J, Kopač J. Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining. Automatika [Internet]. 2010 [pristupljeno 25.06.2019.];51(1):71-78. Dostupno na: https://hrcak.srce.hr/51367
IEEE
M. Korošec, J. Duhovnik i J. Kopač, "Neural Network Based Quality Increase Of Surface Roughness Results In Free Form Machining", Automatika, vol.51, br. 1, str. 71-78, 2010. [Online]. Dostupno na: https://hrcak.srce.hr/51367. [Citirano: 25.06.2019.]

Sažetak
This paper concerns with free form surface reorganization and assessment of free form model complexity, grouping particular surface geometrical properties within patch boundaries, using self organized Kohonen neural network (SOKN). Neural network proved itself as an adequate tool for considering all topological non-linearities appearing in free form surfaces. Coordinate values of point cloud distributed at a particular surface were used as a surface property’s descriptor, which was led into SOKN where representative neurons for curvature, slope and spatial surface properties were established. On a basis of this approach, surface patch boundaries were reorganized in such a manner that finish machining strategies gave best possible surface roughness results. The patch boundaries were constructed regarding to the Gaussian and mean curvature, in order to achieve smooth transition between patches, and in this way preserve or even improve desired curve and surface continuities, (C2 and G2). It is shown that by reorganization of boundaries considering curvature, slope and spatial point distribution, the surface quality of machined free form surface is improved. Approach was experimentally verified on 22 free form surface models which were reorganized by SOKN and machined with finish milling tool-path strategies. Results showed rather good improvement of mean surface roughness profile Ra for reorganized surfaces, when comparing to unorganized free form surfaces.

Ključne riječi
Neural network (NN); Self organized Kohonen neural network (SOKN); Free form surface; place-CAM; Index of surface complexity (ISC)

Hrčak ID: 51367

URI
https://hrcak.srce.hr/51367

[hrvatski]

Posjeta: 842 *