Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network

The aim of this work is to present a new methodology for the automated analysis of the cross-sections of experimental chip shapes from orthogonal cutting experiments. It enables, based on image processing methods, the determination of average chip thicknesses, chip curling radii and for segmented ch...

Full description

Saved in:
Bibliographic Details
Main Authors: Hagen Klippel, Samuel Pflaum, Michal Kuffa, Konrad Wegener
Format: Article
Language:English
Published: Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT 2022-11-01
Series:Journal of Machine Engineering
Subjects:
Online Access:http://jmacheng.not.pl/Automated-Evaluation-of-Continuous-and-Segmented-Chip-Geometries-Based-on-Image-Processing,156091,0,2.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850039253062385664
author Hagen Klippel
Samuel Pflaum
Michal Kuffa
Konrad Wegener
author_facet Hagen Klippel
Samuel Pflaum
Michal Kuffa
Konrad Wegener
author_sort Hagen Klippel
collection DOAJ
description The aim of this work is to present a new methodology for the automated analysis of the cross-sections of experimental chip shapes from orthogonal cutting experiments. It enables, based on image processing methods, the determination of average chip thicknesses, chip curling radii and for segmented chips the extraction of chip segmentation lengths, as well as minimum and maximum chip thicknesses. To automatically decide whether a chip at hand should be evaluated using the proposed methods for continuous or segmented chips, a convolutional neural network is proposed, which is trained using supervised learning with available images from embedded chip cross-sections. Data from manual measurements are used for comparison and validation purposes.
format Article
id doaj-art-7c4ae499786643a8a31f0cf7011f85c4
institution DOAJ
issn 1895-7595
2391-8071
language English
publishDate 2022-11-01
publisher Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT
record_format Article
series Journal of Machine Engineering
spelling doaj-art-7c4ae499786643a8a31f0cf7011f85c42025-08-20T02:56:24ZengPublishing House of Wrocław Board of Scientific Technical Societies Federation NOTJournal of Machine Engineering1895-75952391-80712022-11-0122411513210.36897/jme/156091156091Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural NetworkHagen Klippel0https://orcid.org/0000-0002-3348-1168Samuel Pflaum1Michal Kuffa2https://orcid.org/0000-0002-5326-1269Konrad Wegener3https://orcid.org/0000-0002-5921-1422IWF, ETH Zürich, SwitzerlandDTDS, Bühler AG, SwitzerlandIWF, ETH Zürich, SwitzerlandIWF, ETH Zürich, SwitzerlandThe aim of this work is to present a new methodology for the automated analysis of the cross-sections of experimental chip shapes from orthogonal cutting experiments. It enables, based on image processing methods, the determination of average chip thicknesses, chip curling radii and for segmented chips the extraction of chip segmentation lengths, as well as minimum and maximum chip thicknesses. To automatically decide whether a chip at hand should be evaluated using the proposed methods for continuous or segmented chips, a convolutional neural network is proposed, which is trained using supervised learning with available images from embedded chip cross-sections. Data from manual measurements are used for comparison and validation purposes.http://jmacheng.not.pl/Automated-Evaluation-of-Continuous-and-Segmented-Chip-Geometries-Based-on-Image-Processing,156091,0,2.htmlimage processingmachiningchip shapeartificial neural networks
spellingShingle Hagen Klippel
Samuel Pflaum
Michal Kuffa
Konrad Wegener
Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
Journal of Machine Engineering
image processing
machining
chip shape
artificial neural networks
title Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
title_full Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
title_fullStr Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
title_full_unstemmed Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
title_short Automated Evaluation of Continuous and Segmented Chip Geometries Based on Image Processing Methods and a Convolutional Neural Network
title_sort automated evaluation of continuous and segmented chip geometries based on image processing methods and a convolutional neural network
topic image processing
machining
chip shape
artificial neural networks
url http://jmacheng.not.pl/Automated-Evaluation-of-Continuous-and-Segmented-Chip-Geometries-Based-on-Image-Processing,156091,0,2.html
work_keys_str_mv AT hagenklippel automatedevaluationofcontinuousandsegmentedchipgeometriesbasedonimageprocessingmethodsandaconvolutionalneuralnetwork
AT samuelpflaum automatedevaluationofcontinuousandsegmentedchipgeometriesbasedonimageprocessingmethodsandaconvolutionalneuralnetwork
AT michalkuffa automatedevaluationofcontinuousandsegmentedchipgeometriesbasedonimageprocessingmethodsandaconvolutionalneuralnetwork
AT konradwegener automatedevaluationofcontinuousandsegmentedchipgeometriesbasedonimageprocessingmethodsandaconvolutionalneuralnetwork