한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

Tensile Properties Estimation Method Using Convolutional LSTM Model

  • Choi, Hyeon-Joon (School of Mechanical Engineering, Pusan National University) ;
  • Kang, Dong-Joong (School of Mechanical Engineering, Pusan National University)
  • 투고 : 2018.10.30
  • 심사 : 2018.11.23
  • 발행 : 2018.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, we propose a displacement measurement method based on deep learning using image data obtained from tensile tests of a material specimen. We focus on the fact that the sequential images during the tension are generated and the displacement of the specimen is represented in the image data. So, we designed sample generation model which makes sequential images of specimen. The behavior of generated images are similar to the real specimen images under tensile force. Using generated images, we trained and validated our model. In the deep neural network, sequential images are assigned to a multi-channel input to train the network. The multi-channel images are composed of sequential images obtained along the time domain. As a result, the neural network learns the temporal information as the images express the correlation with each other along the time domain. In order to verify the proposed method, we conducted experiments by comparing the deformation measuring performance of the neural network changing the displacement range of images.

키워드

CPTSCQ_2018_v23n11_43_f0001.png 이미지

Fig. 1. Method for creating sequential image samples using affined transformation.

CPTSCQ_2018_v23n11_43_f0002.png 이미지

Fig. 2. Left: Difference images between real images, Right:Difference images between affine transformed images.

CPTSCQ_2018_v23n11_43_f0003.png 이미지

Fig. 3. Internal structure of Convolutional LSTM model.

CPTSCQ_2018_v23n11_43_f0004.png 이미지

Fig. 4. Convolutional LSTM-based regression model for transformation parameters.

CPTSCQ_2018_v23n11_43_f0005.png 이미지

Fig. 5. Regression results of transformed images using sub-pixel interpolation.

Table 1. Regression results of convolutional LSTM model according to the range of translation parameters

CPTSCQ_2018_v23n11_43_t0001.png 이미지

참고문헌

  1. Feipeng Zhu., Pengxiang Bai, Jingbin Zhang, Dong Lei, and Xiaoyuan He, "Measurement of true stress-strain curves and evolution of plastic zone of low carbon steel under uniaxial tension using digital image correlation" Optics and Lasers in Engineering, Vol. 65, pp. 81-88, Feb. 2015. https://doi.org/10.1016/j.optlaseng.2014.06.013
  2. H. G. Min, D. J. Kang, K. J. Kim, and J. H. Park, "New Non-Contact Measurement Method of Deformation at Tensile Test of Thin Film via Digital Image Correlation Technique", International Journal of Precision Engineering and Manufacturing, Vol. 18, no. 11, pp. 1509-1517, Jun. 2017. https://doi.org/10.1007/s12541-017-0179-0
  3. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. of the IEEE, Vol. 86, pp. 2278-2324, Nov. 1998. https://doi.org/10.1109/5.726791
  4. S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, Vol. 9, no. 8, pp. 1735-1780, Mar. 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  5. Xingjian Shi and Zhourong Chen, "Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting" Computer Vision and Pattern Recognition, 2015. Proceedings CVPR '15, Computer Society Conference on, Sep. 2015.
  6. Ji, S., Xu, W., Yang, M., Yu, K., "3D Convolutional Neural Networks for Human Action Recognition", IEEE transactions on pattern analysis and machine intelligence, Vol. 35, no. 1, pp. 221-231. Sep. 2013. https://doi.org/10.1109/TPAMI.2012.59
  7. Wenxin Hu, and Hong Miao. "Sub-pixel displacement algorithm in temporal sequence digital image correlation based on correlation coefficient weighted fitting", Optics and Lasers in Engineering, Vol. 110, pp. 410-414, Nov. 2018. https://doi.org/10.1016/j.optlaseng.2018.04.006
  8. Huafeng Li, Xinkun Liu, Zhengtao Yu, and Yafei Zhang, "Performance improvement scheme of multifocus image fusion derived by difference images", Signal Processing, Vol. 128, pp. 474-493, Nov. 2016. https://doi.org/10.1016/j.sigpro.2016.05.015
  9. S. Lambert-Lacroix and L. Zwald, "Robust regression through the Hubers criterion and adaptive lasso penalty", Electronic Journal of Statistics, Vol. 5, pp. 1015-1053, 2011. https://doi.org/10.1214/11-EJS635
  10. W. Yin, H. Schutze, "ABCNN: Attention-Based Convoluti onal Neural Network for Modeling Sentence Pairs", Computation and Language, Dec. 2015.
  11. F. Wang and M. Jiang, "Residual Attention Network for Image Classification", Computer Vision and Pattern Recognition, 2017. Proceedings CVPR '17, Computer Society Conference on, Sep. 2017.
  12. Jiasen Lu, Caiming Xiong, Devi Parikh and Richard Socher, "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning", Computer Vision and Pattern Recognition, 2016. Proceedings CVPR '16, Computer Society Conference on, Dec. 2016.
  13. Ilya Sutskever, Oriol Vinyals and Quoc V. Le, "Sequence to Sequence Learning with Neural Networks", Computer Vision and Pattern Recognition, 2014. Proceedings CVPR '14, Computer Society Conference on, Sep. 2014.