Classification of fracture characteristics and fracture mechanisms using deep learning and topography data

被引：7

作者：

Schmies, L. ^{[1
]}

Botsch, B. ^{[2
]}

Le, Q. -H. ^{[1
]}

Yarysh, A. ^{[1
]}

Sonntag, U. ^{[2
]}

Hemmleb, M. ^{[3
]}

Bettge, D. ^{[1
]}

机构：

[1] BAM Bundesanstalt Mat Forschung & Prufung, Berlin, Germany

[2] Gesell Forderung angewandter Informat eV, Berlin, Germany

[3] Point Elect GmbH, Halle, Germany

来源：

PRAKTISCHE METALLOGRAPHIE-PRACTICAL METALLOGRAPHY | 2023年 / 60卷 / 02期

关键词：

deep learning; fractography; classification;

D O I：

10.1515/pm-2022-1008

中图分类号：

TF [冶金工业];

学科分类号：

0806 ;

摘要：

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.

引用

页码：76 / 92

页数：17

共 12 条

[1]

[Anonymous], 1992, STAHLEISEN PRUFBLATT

[2] Fractographic classification in metallic materials by using computer vision [J].

Bastidas-Rodriguez, M. X. ;

Prieto-Ortiz, F. A. ;

Espejo, Edgar .

ENGINEERING FAILURE ANALYSIS, 2016, 59 :237-252

[3] Deep Learning for fractographic classification in metallic materials [J].

Bastidas-Rodriguez, Maria X. ;

Polania, Luisa ;

Gruson, Adrien ;

Prieto-Ortiz, Flavio .

ENGINEERING FAILURE ANALYSIS, 2020, 113

[4]

Bettge D., FRAKTOGRAPHISCHE ONL

[5]

Dodge S, 2016, Arxiv, DOI [arXiv:1604.04004, DOI 10.1109/QOMEX.2016.7498955]

[6] Color for object recognition: Hue and chroma sensitivity in the deep features of convolutional neural networks [J].

Flachot, Alban ;

Gegenfurtner, Karl R. .

VISION RESEARCH, 2021, 182 :89-100

[7] Deep learning analysis on microscopic imaging in materials science [J].

Ge, M. ;

Su, F. ;

Zhao, Z. ;

Su, D. .

MATERIALS TODAY NANO, 2020, 11

[8]

Hemmleb M., 2019, IN SITU MESSUNG 3D T

[9] Swin-UNet plus plus : A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface [J].

Liu, Pan ;

Song, Yan ;

Chai, Mengyu ;

Han, Zelin ;

Zhang, Yu .

MATERIALS, 2021, 14 (24)

[10]

Martens A., 1898, MATERIALIENKUNDE MAS, V1

← 1 2 →