Classification of fracture characteristics and fracture mechanisms using deep learning and topography data
-
L. Schmies
was born 1987 in Ahlen, Germany. He received his master’s degree in Energy engineering from RWTH Aachen University in 2015. Since 2021 he is working at the Bundesanstalt für Materialforschung und -prüfung (BAM) in the fields of fractography and semantic segmentation of SEM images.
was born 1992 in Berlin, Germany. He graduated his master’s degree in mechanical engineering at the TU Berlin. Since 2020 he is working at the Society for the Advancement of Applied Computer Science (GFaI e. V.) in the field of digital image processing.
Abstract
In failure analysis, micro-fractographic analysis of fracture surfaces is usually performed based on practical knowledge which is gained from available studies, own comparative tests, from the literature, as well as online databases. Based on comparisons with already existing images, fracture mechanisms are determined qualitatively. These images are mostly two-dimensional and obtained by light optical and scanning electron imaging techniques. So far, quantitative assessments have been limited to macroscopically determined percentages of fracture types or to the manual measurement of fatigue striations, for example. Recently, more and more approaches relying on computer algorithms have been taken, with algorithms capable of finding and classifying differently structured fracture characteristics. For the Industrial Collective Research (Industrielle Gemeinschaftsforschung, IGF) project “iFrakto” presented in this paper, electron-optical images are obtained, from which topographic information is calculated. This topographic information is analyzed together with the conventional 2D images. Analytical algorithms and deep learning are used to analyze and evaluate fracture characteristics and are linked to information from a fractography database. The most important aim is to provide software aiding in the application of fractography for failure analysis. This paper will present some first results of the project.
Kurzfassung
Die mikro-fraktographische Analyse von Bruchflächen wird in der Schadensanalyse meist auf der Basis von Erfahrungswissen vorgenommen, welches aus vorliegenden Untersuchungen, eigenen Vergleichsversuchen und aus der Literatur und online Datenbanken stammt. Durch Vergleiche mit bereits vorliegenden Bildern werden qualitativ Bruchmechanismen ermittelt. Grundlage dafür sind zumeist zweidimensionale Aufnahmen aus licht- und elektronenoptischen Verfahren. Quantitative Aussagen beschränken sich bislang beispielsweise auf makroskopische Anteile von Bruchmechanismen oder die manuelle Ausmessung von Schwingstreifen. In jüngerer Zeit gibt es vermehrt Ansätze, Computer-Algorithmen einzusetzen, die in der Lage sind, unterschiedlich strukturierte Bruchmerkmale zu finden und zu klassifizieren. Im hier vorgestellten IGF-Vorhaben „iFrakto“ werden elektronenoptische Aufnahmen erzeugt und daraus Topographie-Informationen berechnet. Diese gewonnenen Topographie-Informationen werden zusammen mit den klassischen 2D-Bildern ausgewertet. Analytische Algorithmen und Deep Learning werden eingesetzt, um Bruchmerkmale zu analysieren, zu bewerten und mit Informationen aus einer fraktographischen Datenbank zu verknüpfen. Wichtigstes Ziel ist die Bereitstellung von Software zur Unterstützung der Fraktographie in der Schadensanalyse. In diesem Beitrag werden erste Ergebnisse des Vorhabens vorgestellt.
About the authors
was born 1987 in Ahlen, Germany. He received his master’s degree in Energy engineering from RWTH Aachen University in 2015. Since 2021 he is working at the Bundesanstalt für Materialforschung und -prüfung (BAM) in the fields of fractography and semantic segmentation of SEM images.
was born 1992 in Berlin, Germany. He graduated his master’s degree in mechanical engineering at the TU Berlin. Since 2020 he is working at the Society for the Advancement of Applied Computer Science (GFaI e. V.) in the field of digital image processing.
6 Acknowledgements
The authors would like to thank the German Federation of Industrial Research Associations (AiF, Arbeitsgemeinschaft industrieller Forschungsvereinigungen) for informatics for funding the IGF project “iFrakto” (No. 21477 N), the members of the project monitoring committee and the participants of the round robin test conducted for this paper. The authors would also like to thank Michaela Buchheim for acquiring SEM images.
6 Danksagung
Die Autoren bedanken sich bei der AiF-Forschungsvereinigung Informatik für die Förderung des IGF-Vorhabens „iFrakto“ (Nr.: 21477 N), bei den Mitgliedern des projektbegleitenden Ausschusses und bei den Teilnehmer/innen des im Text erwähnten Ringversuchs. Dank gebührt Michaela Buchheim für die Aufnahme von REM-Bildern.
References / Literatur
[1] A. Martens: Materialienkunde für den Maschinenbau. 1. Theil, Verlag Julius Springer Berlin 1898.10.1002/mmnz.4830010103Search in Google Scholar
[2] D. Bettge: Fraktographische online-Datenbank im DGM/DVM Gemeinschaftsausschuss REM.Search in Google Scholar
[3] Stahleisen-Prüfblatt SEP 1100: Begriffe im Zusammenhang mit Rissen und Brüchen; Teil 1 Erscheinungsformen, 1992.Search in Google Scholar
[4] M. Nazir, S. Shakil, and K. Khurshid: Role of deep learning in brain tumor detection and classification (2015 to 2020): A review, Comput Med Imaging Graph, 91 (2021), p. 101940. DOI: 10.1016/j.compmedimag.2021.10194010.1016/j.compmedimag.2021.101940Search in Google Scholar PubMed
[5] M. Ge, F. Su, Z. Zhao, and D. Su: Deep learning analysis on microscopic imaging in materials science, Materials Today Nano, 11 (2020). DOI: 10.1016/j.mtnano.2020.10008710.1016/j.mtnano.2020.100087Search in Google Scholar
[6] A. Sinha and K. S. Suresh: Deep Learning based Dimple Segmentation for Quantitative Fractography, p. arXiv:2007.02267. [Online]. Available: https://ui.adsabs.harvard.edu/abs/2020arXiv200702267S10.1007/978-3-030-68799-1_34Search in Google Scholar
[7] P. Liu, Y. Song, M. Chai, Z. Han, and Y. Zhang: Swin-UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface, Materials (Basel), 14 (2021) 24. DOI: 10.3390/ma1424750410.3390/ma14247504Search in Google Scholar PubMed PubMed Central
[8] M. X. Bastidas-Rodriguez, F. A. Prieto-Ortiz, and E. Espejo: Fractographic classification in metallic materials by using computer vision, Engineering Failure Analysis, 59 (2016), pp. 237–237. DOI: 10.1016/j.engfailanal.2015.10.00810.1016/j.engfailanal.2015.10.008Search in Google Scholar
[9] M. X. Bastidas-Rodriguez, L. Polania, A. Gruson, and F. Prieto-Ortiz: Deep Learning for fractographic classification in metallic materials, Engineering Failure Analysis, 113 (2020). DOI: 10.1016/j.engfailanal.2020.10453210.1016/j.engfailanal.2020.104532Search in Google Scholar
[10] M. Hemmleb and D. Bettge: In-situ Messung der 3D-Topografie von Fracture surfacen im REM, Tagungsband DGM Metallographietagung, 2019.Search in Google Scholar
[11] A. Flachot and K. R. Gegenfurtner: Color for object recognition: Hue and chroma sensitivity in the deep features of convolutional neural networks, Vision Res, 182 (2021), pp. 89–89. DOI: 10.1016/j.visres.2020.09.010.10.1016/j.visres.2020.09.010Search in Google Scholar PubMed
[12] S. D. a. L. Karam: Understanding How Image Quality Affects Deep Neural Networks, 2016, Art no. arXiv 1604.04004.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston, Germany
Articles in the same Issue
- Contents
- Editorial
- Editorial
- Classification of fracture characteristics and fracture mechanisms using deep learning and topography data
- Combination of Digital Image Correlation (DIC) and in situ 3D-μ-CT in the analysis of the relationship between strains and porosity under creep loading
- The effect of shielding gas on weldability of the AISI 420 martensitic stainless steel
- Failure Analysis
- Imperfections in Inner Cavity of Row 4 Turbine Blade Caused by Metal-Core Reaction
- Picture of the Month
- Picture of the Month
- News
- News
- Meeting Dairy
- Meeting Diary
Articles in the same Issue
- Contents
- Editorial
- Editorial
- Classification of fracture characteristics and fracture mechanisms using deep learning and topography data
- Combination of Digital Image Correlation (DIC) and in situ 3D-μ-CT in the analysis of the relationship between strains and porosity under creep loading
- The effect of shielding gas on weldability of the AISI 420 martensitic stainless steel
- Failure Analysis
- Imperfections in Inner Cavity of Row 4 Turbine Blade Caused by Metal-Core Reaction
- Picture of the Month
- Picture of the Month
- News
- News
- Meeting Dairy
- Meeting Diary
