Neural network based manufacturability evaluation of free form machining

Korošec, Marjan; Balič, Jože; Kopač, Janez

doi:10.1016/j.ijmachtools.2004.06.022

Cited by 40 publications

(27 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So patch boundaries can be reorganized in a way to be very suitable for NURBS machining. This access was shown in former contribution [12] . As in curvature clusters, also in this case a relation between number of neurons and ISC can be recorded.…”

Section: Analysis Of Slope Gradient Clusterssupporting

confidence: 55%

“…Fig. 2 It was shown in [12,13], that slope gradient areas have significant influence on a feedrate of milling tool.…”

Section: Clustering With Voronoi Tesselation Using Winning Neurons (mentioning

confidence: 99%

“…The ultimate requirement of this process is to have a set of clusters that minimizes the distance between the centers of each cluster and the input that falls into each cluster. [9,12] Slope gradient presentation of free form surface with Kohonen neural network…”

Section: Clustering With Voronoi Tesselation Using Winning Neurons (mentioning

confidence: 99%

“…Whole family of 22 free form surfaces is prepared in such a manner, that it covers complete ISC index range, as presented in Table 1. The ISC index is explained in greater detail in reference [12]. All free form surfaces were machined with free form milling path strategies in three different CAM systems, using a 42 HRC steel material.…”

Section: Analysis Of Slope Gradient Clustersmentioning

confidence: 99%

See 3 more Smart Citations

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

Korošec

Duhovnik²,

Kopač³

2010

Automatika

View full text Add to dashboard Cite

Original scientific paperThis 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.Key words: Neural network (NN), Self organized Kohonen neural network (SOKN), Free form surface, place-CAM, Index of surface complexity (ISC)Povećanje kvalitete rezultata površinske hrapavosti kod obrade slobodnih površina temeljem neuronskih mreža. Ovaj sečlanak bavi reorganizacijom slobodnih površina i ocjenom kompleksnosti modela slobodnih površina, grupirajući odreena površinska geometrijska svojstva unutar zatvorenih površina, koristeći samoorganizirajuću Kohonenovu neuronsku mrežu (SOKN). Neuronske mreže pokazale su se kao prikladan alat za razmatranje svih topoloških nelinearnosti koje se pojavljuju kod slobodnih površina. Vrijednosti koordinata oblaka točaka raspodijeljenih nad odreenom površinom korišteni su kao svojstveni opis, što je nadalje vodilo prema SOKN-u, gdje su ustanovljeni reprezentativni neuroni za zakrivljenost, nagib i prostorno-površinska svojstva. Na temelju ovoga pristupa reorganizirane su granice zatvorenih površina na takav način da metode površinske obrade daju najbolje moguće rezultate spram površinske hrapavosti. Granice tih površina odreene su prema Gaussovoj i prosječnoj zakrivljenosti kako bi se postigao glatki prijelaz izmeu zatvorenih površina te kako bi se na taj način očuvala iličak unaprijedila željena zakrivljenost i glatkoća površine, (C2 i G2). Pokazano je da se reorganizacijom granica s obzirom na zakrivljenost, nagib i prostornu raspodjelu točaka, poboljšava kvaliteta obraene slobodne površine. Pristup je eksperimentalno potvren na 22 modela slobodne površine koji su reorganizirani SOKN-om i po...

show abstract

Section: Analysis Of Slope Gradient Clusterssupporting

confidence: 55%

“…Fig. 2 It was shown in [12,13], that slope gradient areas have significant influence on a feedrate of milling tool.…”

Section: Clustering With Voronoi Tesselation Using Winning Neurons (mentioning

confidence: 99%

Section: Clustering With Voronoi Tesselation Using Winning Neurons (mentioning

confidence: 99%

Section: Analysis Of Slope Gradient Clustersmentioning

confidence: 99%

See 2 more Smart Citations

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

Korošec

Duhovnik²,

Kopač³

2010

Automatika

View full text Add to dashboard Cite

show abstract

“…There are several techniques that have been implemented to obtain data directly from CAD model such as: feature-based extraction system (Kamrani 1996;Gupta 1997;Brissaud 2000;Jacquel 2000;Jia 2004;Korosec 2005); neutral files usage (Yuyin 1996;Ramana 2006;Tomovic 2006); embedded algorithm into CAD system (Lee 1997); 3D recognition model based on the design specifications on the CAD model (Chen 2001). Even though, most of the developed MASs used feature-extraction system to obtain related data from CAD model but it has some problems.…”

Section: Introductionmentioning

confidence: 99%

An approach of using primitive feature analysis in manufacturability analysis systems for micro-milling/drilling

Syaimak

Axinte

2009

International Journal of Computer Integrated Manufacturing

View full text Add to dashboard Cite

Optimization of mechanical properties of PP/EPDM/ clay nanocomposite fabricated by friction stir processing with response surface methodology and neural networks

2016

View full text Add to dashboard Cite

In this article, effects of friction stir processing parameters such as tool rotational speed, traverse speed, shoulder temperature, and number of passes on tensile modulus and impact strength of polypropylene/ ethylene-propylene diene monomer/clay nanocomposite has been investigated. The Box-Behnken design with four factors at three levels was used for design of experiments. The response surface methodology was employed to develop models capable of predicting the effect of input variable on responses. A multi-layer artificial neural network with back propagation algorithm and 4 -8 -10 -2 topology was also selected for modeling. A set of data on friction stir parameters and experimental results of the mechanical properties were used to train and test the artificial neural network. POLYM. COMPOS., 38:E421-E432,

show abstract

Neural network based manufacturability evaluation of free form machining

Cited by 40 publications

References 10 publications

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

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

An approach of using primitive feature analysis in manufacturability analysis systems for micro-milling/drilling

Optimization of mechanical properties of PP/EPDM/ clay nanocomposite fabricated by friction stir processing with response surface methodology and neural networks

Contact Info

Product

Resources

About