Design and Application of Artificial Neural Network Algorithm for Digital Speckle Correlation Method

Lili Li; Joan P. Lazaro

doi:10.62677/IJETAA.2406120

Authors

Lili Li University of the East, Manila, Philippines Author
Joan P. Lazaro University of the East, Manila, Philippines Author

DOI:

https://doi.org/10.62677/IJETAA.2406120

Keywords:

Digital Speckle Correlation Method (DSCM), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Deformation Measurement, Image Processing

Abstract

This study explores the design and application of an Artificial Neural Network (ANN) algorithm for Digital Speckle Correlation Method (DSCM). DSCM, as a non-contact full-field deformation measurement technique, has significant applications in materials science and structural engineering. However, traditional DSCM has limitations in handling complex deformations and noise interference. To overcome these challenges, we propose an ANN-DSCM algorithm based on Convolutional Neural Networks (CNN). The algorithm comprises four main modules: feature extraction, correlation calculation, displacement estimation, and refinement, capable of learning and predicting deformation fields directly from speckle image pairs.
We constructed comprehensive training and testing datasets using synthetic and experimental data, covering various deformation modes and image quality conditions. The network was trained using supervised learning methods, and its performance was validated using multiple evaluation metrics. Results show that ANN-DSCM demonstrates higher accuracy and robustness compared to traditional DSCM methods in handling large deformations, discontinuous deformations, and noise interference. Moreover, ANN-DSCM exhibits advantages in computational efficiency due to its parallel computing capabilities.
This research not only advances DSCM technology but also provides new insights into applying deep learning in experimental mechanics. Future work will focus on further optimizing network structures, expanding application ranges, and exploring the potential applications of ANN-DSCM in material characterization and structural health monitoring.

Downloads

Download data is not yet available.

References

B. Wang and B. Pan, ”Subset-based local vs. finite element-based global digital image correlation: A comparison study,” Theor. Appl. Mech. Lett., vol. 6, no. 5, pp. 200–208, 2020.

D. Zhang, D. D. Arola, and J. A. Rouland, ”A new digital image correlation method for small strain measurement,” Exp. Mech., vol. 60,no. 1, pp. 75–89, 2021.

B. Pan, B. Wang, and G. Lubineau, ”Comparison of subset-based local and FE-based global digital image correlation: Theoretical error analysis and validation,” Opt. Lasers Eng., vol. 82, pp. 148–158, 2022.

Y. LeCun, Y. Bengio, and G. Hinton, ”Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2020.

Y. Guo, F. Gao, and L. Nie, ”Deep learning for visual understanding: A review,” Neurocomputing, vol. 187, pp. 27–48, 2021.

M. A. Sutton, J. J. Orteu, and H. Schreier, Image Correlation for Shape,Motion and Deformation Measurements: Basic Concepts, Theory and Applications. Springer Science & Business Media, 2022.

B. Pan, K. Qian, H. Xie, and A. Asundi, ”Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review,” Meas. Sci. Technol., vol. 20, no. 6, p. 062001, 2023.

J. Blaber, B. Adair, and A. Antoniou, ”Ncorr: Open-source 2D digital image correlation Matlab software,” Exp. Mech., vol. 55, no. 6, pp.1105–1122, 2020.

X. Xu, Y. Su, and Q. Zhang, ”Theoretical analysis on the load-induced out-of-plane displacement error in two-dimensional digital image correlation measurements,” Strain, vol. 53, no. 2, p. e12217, 2021.

R. Zhu, H. Xie, Z. Hu, and L. Wang, ”Fabrication of speckle patterns by focused ion beam deposition and its application to micro-scale residual stress measurement,” Meas. Sci. Technol., vol. 29, no. 3, p. 035402,2022.

P. L. Reu, ”A study of the influence of calibration uncertainty on the global uncertainty for digital image correlation using a Monte Carlo approach,” Exp. Mech., vol. 53, no. 9, pp. 1661–1680, 2023.

G. M. Hassan, C. MacNish, and A. Dyskin, ”Extending digital image correlation to reconstruct displacement and strain fields around discontinuities in geomechanical structures under deformation,” IEEE Access,vol. 6, pp. 30850–30872, 2020.

B. Pan, B. Wang, G. Lubineau, and A. Moussawi, ”Comparison of subset-based local and finite element-based global digital image correlation,” Exp. Mech., vol. 55, no. 5, pp. 887–901, 2021.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT press,2022.

J. Schmidhuber, ”Deep learning in neural networks: An overview,” Neural Netw., vol. 61, pp. 85–117, 2023.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, ”Imagenet classification with deep convolutional neural networks,” in Adv. Neural Inf. Process.Syst., 2020, vol. 25, pp. 1097–1105.

K. He, X. Zhang, S. Ren, and J. Sun, ”Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2021,pp. 770–778.

Z. Wang, J. Chen, and S. C. H. Hoi, ”Deep learning for image superresolution: A survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 10, pp. 3365–3387, 2022.

O. Ronneberger, P. Fischer, and T. Brox, ”U-net: Convolutional networks for biomedical image segmentation,” in Int. Conf. Med. Image Comput. Comput. Assist. Interv., 2023, pp. 234–241.

K. Simonyan and A. Zisserman, ”Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2020.

J. Long, E. Shelhamer, and T. Darrell, ”Fully convolutional networks for semantic segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2021, pp. 3431–3440.

D. P. Kingma and J. Ba, ”Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2022.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, ”Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2023.

L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, ”Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834–848, 2020.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, ”Pyramid scene parsing network,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2021,pp. 2881–2890.

S. Ioffe and C. Szegedy, ”Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Int. Conf. Mach.Learn., 2022, pp. 448–456.

X. Glorot and Y. Bengio, ”Understanding the difficulty of training deep feedforward neural networks,” in Proc. 13th Int. Conf. Artif. Intell. Stat.,2023, pp. 249–256.

O. Russakovsky et al., ”Imagenet large scale visual recognition challenge,” Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, 2020.

F. Chollet, ”Xception: Deep learning with depthwise separable convolutions,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2021, pp.1251–1258.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, ”Rethinking the inception architecture for computer vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2022, pp. 2818–2826.