Determination of quality classes for material extrusion additive manufacturing using image processing

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Alexander Oleff
  • Benjamin Küster
  • Ludger Overmeyer

Externe Organisationen

  • Institut für integrierte Produktion Hannover (IPH) gGmbH
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)1585-1598
Seitenumfang14
FachzeitschriftInternational Journal of Advanced Manufacturing Technology
Jahrgang132
Ausgabenummer3-4
Frühes Online-Datum21 März 2024
PublikationsstatusVeröffentlicht - Mai 2024

Abstract

Tools for implementing a systematic quality management are necessary for the use of material extrusion as an additive manufacturing process for products with high quality requirements. Well-defined quality classes are crucial for ensuring that the requirements for a product can be communicated transparently and that the existing properties can be evaluated. Furthermore, there is a lack of capable measurement equipment for the acquisition of process data during the production process. To address these challenges, the present paper introduces an image processing system that determines quality indicators for individual layers in terms of imperfect surface percentages and the number of imperfections. The central element of the hardware is an adaptive darkfield illumination, which leads to high-contrast images. In addition, five types of layer subareas are identified in a segmentation step. Unsupervised machine learning methods are then used to detect imperfections in each layer subarea. In the segmentation, the current layer can be distinguished from irrelevant image background regions with an F-measure of 0.981. For the layer-wise measurement of the quality indicators, relative measurement errors with standard deviations of 25 to 76.1% are found. After evaluating the capabilities of the image processing system, a proposal for limits of quality classes is derived by monitoring several material extrusion processes. For this purpose, three quality classes for each of the five layer subareas are deduced from the process scatter measured by the image processing system. The results are an important contribution to the industrialization of material extrusion in safety–critical areas such as medical technology or the aerospace industry.

ASJC Scopus Sachgebiete

Zitieren

Determination of quality classes for material extrusion additive manufacturing using image processing. / Oleff, Alexander; Küster, Benjamin; Overmeyer, Ludger.
in: International Journal of Advanced Manufacturing Technology, Jahrgang 132, Nr. 3-4, 05.2024, S. 1585-1598.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Oleff A, Küster B, Overmeyer L. Determination of quality classes for material extrusion additive manufacturing using image processing. International Journal of Advanced Manufacturing Technology. 2024 Mai;132(3-4):1585-1598. Epub 2024 Mär 21. doi: 10.1007/s00170-024-13269-5
Oleff, Alexander ; Küster, Benjamin ; Overmeyer, Ludger. / Determination of quality classes for material extrusion additive manufacturing using image processing. in: International Journal of Advanced Manufacturing Technology. 2024 ; Jahrgang 132, Nr. 3-4. S. 1585-1598.
Download
@article{cd69377091034b24916eb6c8a2bfbefd,
title = "Determination of quality classes for material extrusion additive manufacturing using image processing",
abstract = "Tools for implementing a systematic quality management are necessary for the use of material extrusion as an additive manufacturing process for products with high quality requirements. Well-defined quality classes are crucial for ensuring that the requirements for a product can be communicated transparently and that the existing properties can be evaluated. Furthermore, there is a lack of capable measurement equipment for the acquisition of process data during the production process. To address these challenges, the present paper introduces an image processing system that determines quality indicators for individual layers in terms of imperfect surface percentages and the number of imperfections. The central element of the hardware is an adaptive darkfield illumination, which leads to high-contrast images. In addition, five types of layer subareas are identified in a segmentation step. Unsupervised machine learning methods are then used to detect imperfections in each layer subarea. In the segmentation, the current layer can be distinguished from irrelevant image background regions with an F-measure of 0.981. For the layer-wise measurement of the quality indicators, relative measurement errors with standard deviations of 25 to 76.1% are found. After evaluating the capabilities of the image processing system, a proposal for limits of quality classes is derived by monitoring several material extrusion processes. For this purpose, three quality classes for each of the five layer subareas are deduced from the process scatter measured by the image processing system. The results are an important contribution to the industrialization of material extrusion in safety–critical areas such as medical technology or the aerospace industry.",
keywords = "Additive manufacturing, Fused deposition modeling, Image processing, Material extrusion, Process monitoring, Quality classes",
author = "Alexander Oleff and Benjamin K{\"u}ster and Ludger Overmeyer",
note = "Funding Information: Open Access funding enabled and organized by Projekt DEAL. Substantial parts of this work are part of the research project 20714 N of the Research Community for Quality (FQS), AugustSchanz-Str. 21A, 60433 Frankfurt/Main and have been funded by the AiF within the program for sponsorship by Industrial Joint Research (IGF) of the German Federal Ministry of Economic Afairs and Energy based on an enactment of the German Parliamen",
year = "2024",
month = may,
doi = "10.1007/s00170-024-13269-5",
language = "English",
volume = "132",
pages = "1585--1598",
journal = "International Journal of Advanced Manufacturing Technology",
issn = "0268-3768",
publisher = "Springer London",
number = "3-4",

}

Download

TY - JOUR

T1 - Determination of quality classes for material extrusion additive manufacturing using image processing

AU - Oleff, Alexander

AU - Küster, Benjamin

AU - Overmeyer, Ludger

N1 - Funding Information: Open Access funding enabled and organized by Projekt DEAL. Substantial parts of this work are part of the research project 20714 N of the Research Community for Quality (FQS), AugustSchanz-Str. 21A, 60433 Frankfurt/Main and have been funded by the AiF within the program for sponsorship by Industrial Joint Research (IGF) of the German Federal Ministry of Economic Afairs and Energy based on an enactment of the German Parliamen

PY - 2024/5

Y1 - 2024/5

N2 - Tools for implementing a systematic quality management are necessary for the use of material extrusion as an additive manufacturing process for products with high quality requirements. Well-defined quality classes are crucial for ensuring that the requirements for a product can be communicated transparently and that the existing properties can be evaluated. Furthermore, there is a lack of capable measurement equipment for the acquisition of process data during the production process. To address these challenges, the present paper introduces an image processing system that determines quality indicators for individual layers in terms of imperfect surface percentages and the number of imperfections. The central element of the hardware is an adaptive darkfield illumination, which leads to high-contrast images. In addition, five types of layer subareas are identified in a segmentation step. Unsupervised machine learning methods are then used to detect imperfections in each layer subarea. In the segmentation, the current layer can be distinguished from irrelevant image background regions with an F-measure of 0.981. For the layer-wise measurement of the quality indicators, relative measurement errors with standard deviations of 25 to 76.1% are found. After evaluating the capabilities of the image processing system, a proposal for limits of quality classes is derived by monitoring several material extrusion processes. For this purpose, three quality classes for each of the five layer subareas are deduced from the process scatter measured by the image processing system. The results are an important contribution to the industrialization of material extrusion in safety–critical areas such as medical technology or the aerospace industry.

AB - Tools for implementing a systematic quality management are necessary for the use of material extrusion as an additive manufacturing process for products with high quality requirements. Well-defined quality classes are crucial for ensuring that the requirements for a product can be communicated transparently and that the existing properties can be evaluated. Furthermore, there is a lack of capable measurement equipment for the acquisition of process data during the production process. To address these challenges, the present paper introduces an image processing system that determines quality indicators for individual layers in terms of imperfect surface percentages and the number of imperfections. The central element of the hardware is an adaptive darkfield illumination, which leads to high-contrast images. In addition, five types of layer subareas are identified in a segmentation step. Unsupervised machine learning methods are then used to detect imperfections in each layer subarea. In the segmentation, the current layer can be distinguished from irrelevant image background regions with an F-measure of 0.981. For the layer-wise measurement of the quality indicators, relative measurement errors with standard deviations of 25 to 76.1% are found. After evaluating the capabilities of the image processing system, a proposal for limits of quality classes is derived by monitoring several material extrusion processes. For this purpose, three quality classes for each of the five layer subareas are deduced from the process scatter measured by the image processing system. The results are an important contribution to the industrialization of material extrusion in safety–critical areas such as medical technology or the aerospace industry.

KW - Additive manufacturing

KW - Fused deposition modeling

KW - Image processing

KW - Material extrusion

KW - Process monitoring

KW - Quality classes

UR - http://www.scopus.com/inward/record.url?scp=85188153702&partnerID=8YFLogxK

U2 - 10.1007/s00170-024-13269-5

DO - 10.1007/s00170-024-13269-5

M3 - Article

AN - SCOPUS:85188153702

VL - 132

SP - 1585

EP - 1598

JO - International Journal of Advanced Manufacturing Technology

JF - International Journal of Advanced Manufacturing Technology

SN - 0268-3768

IS - 3-4

ER -