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

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.

[1]  Vinesh H. Raja,et al.  Extracting geometric attributes directly from scanned data sets for feature recognition , 2002, Int. J. Comput. Integr. Manuf..

[2]  Yizhou Yu.  Surface Reconstruction from Unorganized Points Using Self-Organizing Neural Networks , 1999 .

[3]  Godfrey C. Onwubolu.  Manufacturing features recognition using backpropagation neural networks , 1999, J. Intell. Manuf..

[5]  José Alfredo Ferreira Costa,et al.  Clustering of complex shaped data sets via Kohonen maps and mathematical morphology , 2001, Data Mining and Knowledge Discovery: Theory, Tools, and Technology.

[6]  Joze Balic,et al.  Neural network based manufacturability evaluation of free form machining , 2005 .

[7]  Mark R. Henderson,et al.  Automatic form-feature recognition using neural-network-based techniques on boundary representations of solid models , 1992, Comput. Aided Des..

[8]  George-Christopher Vosniakos,et al.  Recognizing D shape features using a neural network and heuristics , 1997, Comput. Aided Des..

[9]  Mohammed Bennamoun,et al.  Representation and Recognition of 3D Free-Form Objects , 2002, Digit. Signal Process..

[10]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[11]  Qiang Ji,et al.  Bayesian approach for extracting and identifying features , 1995, Comput. Aided Des..

[12]  Andrew Y. C. Nee,et al.  A hybrid method for recognizing interacting machining features , 2003 .

[13]  Gaile G. Gordon,et al.  Face recognition based on depth maps and surface curvature , 1991, Optics & Photonics.

[14]  Yongtae Jun,et al.  Geometric Feature Recognition for Reverse Engineering using Neural Networks , 2001 .

[15]  Miklos Hofimann.  Free-form Surfaces for Scattered Data by Neural Networks , 1998 .

[16]  Jože Balič,et al.  Intelligent tool path generation for milling of free surfaces using neural networks , 2002 .

[17]  Jose C. Principe,et al.  Neural and adaptive systems : fundamentals through simulations , 2000 .

[18]  S K Ong,et al.  Recognition of overlapping machining features based on hybrid artificial intelligent techniques , 2000 .

[19]  Jose C. Principe,et al.  Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM , 1999 .

[20]  Saeid Motavalli,et al.  Automatic segmentation of digitized data for reverse engineering applications , 2000 .

[21]  Lajos,et al.  Improved Free-form Modelling of Scattered Data by Dynamic Neural Networks , 1999 .