nach oben

Experimental Mechanics

Erschienen in:

12.03.2024 | Research paper

Improving Deep Learning-Based Digital Image Correlation with Domain Decomposition Method

verfasst von: Y. Chi, Y. Liu, B. Pan

Erschienen in: Experimental Mechanics | Ausgabe 4/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Background

Deep learning-based digital image correlation (DL-based DIC) has gained increasing attention in the last two years. However, existing DL-based DIC algorithms are impractical because their application scenarios are mostly limited to small deformations.

Objective

To enable the use of DL-based DIC in real-world general experimental mechanics scenarios that would involve large deformations and rotations, we propose to improve DL-based DIC with the domain decomposition method (DDM).

Methods

In the improved method, the region of interest is divided into subimages, and subimages are pre-aligned using the preregistered control points to effectively eliminate the large deformation components. The residual deformations in each subimage are small and limited, which can be well extracted using existing DL-based DIC methods.

Results

Through synthesized and real-world experiments, the improved DL-based DIC method can achieve high-accuracy pixelwise matching in practical applications with strong robustness and high computational efficiency.

Conclusions

The improved DL-based DIC combines the advantages of traditional and DL-based DIC methods but overcomes the limitations, greatly improving the robustness and applicability of existing DL-based methods.

Vorheriger Artikel Residual Stress Measurements in Tensile Armours of Flexible Pipes by the Contour and X-Ray Diffraction Methods

Nächster Artikel Ballistic and Blast-Relevant, High-Rate Material Properties of Physically and Chemically Crosslinked Hydrogels

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Pan B, Qian K, Xie H, Asundi A (2009) Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review. Measure Sci Technol 20:062001. https://doi.org/10.1088/0957-0233/20/6/062001CrossRef

Pan B (2018) Digital image correlation for surface deformation measurement: historical developments, recent advances and future goals. Meas Sci Technol 29:082001. https://doi.org/10.1088/1361-6501/aac55bCrossRef

Schreier H, Orteu J-J, Sutton MA (2009) Image Correlation for Shape, Motion and Deformation Measurements: Basic Concepts,Theory and Applications. Springer US, Boston, MA

Bruck HA, McNeill SR, Sutton MA, Peters WH (1989) Digital image correlation using Newton-Raphson method of partial differential correction. Exp Mechan 29:261–267. https://doi.org/10.1007/BF02321405CrossRef

Lu H, Cary PD (2000) Deformation measurements by digital image correlation: Implementation of a second-order displacement gradient. Exp Mechan 40:393–400. https://doi.org/10.1007/BF02326485CrossRef

Sun Y, Pang JH, Wong CK, Su F (2005) Finite element formulation for a digital image correlation method. Applied Optics 44:7357–7363. https://doi.org/10.1364/AO.44.007357CrossRef

Besnard G, Hild F, Roux S (2006) “Finite-Element” Displacement Fields Analysis from Digital Images: Application to Portevin–Le Châtelier Bands. Exp Mech 46:789–803. https://doi.org/10.1007/s11340-006-9824-8CrossRef

Ma S, Zhao Z, Wang X (2012) Mesh-based digital image correlation method using higher order isoparametric elements. J Strain Analys Eng Des 47:163–175. https://doi.org/10.1177/0309324712437488CrossRef

Wittevrongel L, Lava P, Lomov SV, Debruyne D (2015) A Self Adaptive Global Digital Image Correlation Algorithm. Exp Mech 55:361–378. https://doi.org/10.1007/s11340-014-9946-3CrossRef

10.

Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4:251–257. https://doi.org/10.1016/0893-6080(91)90009-TCrossRef

11.

Boukhtache S, Abdelouahab K, Berry F et al (2021) When Deep Learning Meets Digital Image Correlation. Optics Lasers Eng 136:106308. https://doi.org/10.1016/j.optlaseng.2020.106308CrossRef

12.

Boukhtache S, Abdelouahab K, Bahou A et al (2023) A lightweight convolutional neural network as an alternative to DIC to measure in-plane displacement fields. Optics Lasers Eng 161:107367. https://doi.org/10.1016/j.optlaseng.2022.107367CrossRef

13.

Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Springer International Publishing, Cham, pp 234–241

14.

Dosovitskiy A, Fischer P, Ilg E et al (2015) FlowNet: Learning Optical Flow with Convolutional Networks. In: 2015 IEEE International Conference on Computer Vision (ICCV). 2758–2766

15.

Sun D, Yang X, Liu M-Y, Kautz J (2018) PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8934–8943

16.

Yang R, Li Y, Zeng D, Guo P (2022) Deep DIC: Deep learning-based digital image correlation for end-to-end displacement and strain measurement. J Mater Proc Technol 302:117474. https://doi.org/10.1016/j.jmatprotec.2021.117474CrossRef

17.

Wang Y, Zhao J (2023) DIC-Net: Upgrade the performance of traditional DIC with Hermite dataset and convolution neural network. Optics Lasers in Engineering 160:107278. https://doi.org/10.1016/j.optlaseng.2022.107278CrossRef

18.

Xiao H, Li C, Feng M (2023) Large Deformation Measurement Method of Speckle Images Based on Deep Learning. Acta Optica Sinica 43:1–13. https://doi.org/10.3788/AOS222084CrossRef

19.

Ma C, Ren Q, Zhao J (2021) Optical-numerical method based on a convolutional neural network for full-field subpixel displacement measurements. Opt Express 29:9137. https://doi.org/10.1364/OE.417413CrossRef

20.

Duan X, Huang J (2022) Deep learning-based digital volume correlation. Extreme Mechan Lett 53:101710. https://doi.org/10.1016/j.eml.2022.101710CrossRef

21.

Duan X, Huang J (2022) Deep-learning-based 3D cellular force reconstruction directly from volumetric images. Biophys J 121:2180–2192. https://doi.org/10.1016/j.bpj.2022.04.028CrossRef

22.

Duan X, Xu H, Dong R et al (2023) Digital image correlation based on convolutional neural networks. Optics Lasers Eng 160:107234. https://doi.org/10.1016/j.optlaseng.2022.107234CrossRef

23.

Yang J, Qian K, Wang L (2024) R³-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement. Opt Express 32:907. https://doi.org/10.1364/OE.505655CrossRef

24.

Hui T-W, Tang X, Loy CC (2018) LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8981–8989

25.

Teed Z, Deng J (2020) RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer Vision – ECCV 2020. Springer International Publishing, Cham, pp 402–419CrossRef

26.

Wang G, Zhang L, Yao X (2022) StrainNet-3D: Real-time and robust 3-dimensional speckle image correlation using deep learning. Optics Lasers Eng 158:107184. https://doi.org/10.1016/j.optlaseng.2022.107184CrossRef

27.

Toselli A, Widlund OB (2005) Domain decomposition methods–algorithms and theory. Springer, BerlinCrossRef

28.

Dolean V, Jolivet P, Nataf F (2015) An Introduction to Domain Decomposition Methods: Algorithms, Theory, and Parallel Implementation. Society for Industrial and Applied Mathematics, Philadelphia, PACrossRef

29.

Passieux J-C, Périé J-N, Salaün M (2015) A dual domain decomposition method for finite element digital image correlation. Int J Numeric Meth Eng 102:1670–1682. https://doi.org/10.1002/nme.4868MathSciNetCrossRef

30.

Chi Y, Pan B (2022) Accelerating parallel digital image correlation computation with feature mesh interpolation. Measurement 199:111554. https://doi.org/10.1016/j.measurement.2022.111554CrossRef

31.

Schreier HW, Sutton MA (2002) Systematic errors in digital image correlation due to undermatched subset shape functions. Exp Mechan 42:303–310. https://doi.org/10.1007/BF02410987CrossRef

32.

Pan B, Xie H, Wang Z et al (2008) Study on subset size selection in digital image correlation for speckle patterns. Optics Exp 16:7037–7048CrossRef

33.

Rupil J, Roux S, Hild F, Vincent L (2011) Fatigue microcrack detection with digital image correlation. J Strain Analys Eng Design 46:492–509. https://doi.org/10.1177/0309324711402764CrossRef

34.

Hild F, Bouterf A, Roux S (2015) Damage measurements via DIC. Int J Fract 191:77–105. https://doi.org/10.1007/s10704-015-0004-7CrossRef

35.

Chi Y, Zhao W, Pan B (2023) Gray level residual field: an effective metric for pixelwise matching quality evaluation in local digital image correlation. Measure Sci Technol 34. https://doi.org/10.1088/1361-6501/accbdf

Titel: Improving Deep Learning-Based Digital Image Correlation with Domain Decomposition Method
verfasst von: Y. Chi
Y. Liu
B. Pan
Publikationsdatum: 12.03.2024
Verlag: Springer US
Erschienen in: Experimental Mechanics / Ausgabe 4/2024
Print ISSN: 0014-4851
Elektronische ISSN: 1741-2765
DOI: https://doi.org/10.1007/s11340-024-01040-6

Premium Partner

Marktübersichten

Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.

Zur Marktübersicht

Springer Professional

Abstract

Background

Objective

Methods

Results

Conclusions

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 4/2024

On the Cover: Improving Deep Learning Based Digital Image Correlation with Domain Decomposition Method by Y. Chi, Y. Liu, B. Pan

Residual Stress Measurements in Tensile Armours of Flexible Pipes by the Contour and X-Ray Diffraction Methods

Near Edge Residual Stress Measurement Using Incremental Hole Drilling

Ballistic and Blast-Relevant, High-Rate Material Properties of Physically and Chemically Crosslinked Hydrogels

Digital Image Correlation at Extreme Temperatures Using Shortwave Ultraviolet (UV-C) Lights and Filters

Development and Analysis of an On-Road Torque Measurement Device for Trucks

Premium Partner

Marktübersichten