Korean Journal of Construction Engineering and Management (한국건설관리학회논문집)

Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

Image based Concrete Compressive Strength Prediction Model using Deep Convolution Neural Network

심층 컨볼루션 신경망을 활용한 영상 기반 콘크리트 압축강도 예측 모델

  • Jang, Youjin (Department of Architecture and Architectural Engineering, Hanyang University) ;
  • Ahn, Yong Han (Department of Architecture and Architectural Engineering, Hanyang University) ;
  • Yoo, Jane (Department of Financial Engineering, Ajou University) ;
  • Kim, Ha Young (Department of Financial Engineering, Ajou University)
  • Received : 2018.03.29
  • Accepted : 2018.05.28
  • Published : 2018.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the inventory of aged apartments is expected to increase explosively, the importance of maintenance to improve the durability of concrete facilities is increasing. Concrete compressive strength is a representative index of durability of concrete facilities, and is an important item in the precision safety diagnosis for facility maintenance. However, existing methods for measuring the concrete compressive strength and determining the maintenance of concrete facilities have limitations such as facility safety problem, high cost problem, and low reliability problem. In this study, we proposed a model that can predict the concrete compressive strength through images by using deep convolution neural network technique. Learning, validation and testing were conducted by applying the concrete compressive strength dataset constructed through the concrete specimen which is produced in the laboratory environment. As a result, it was found that the concrete compressive strength could be learned by using the images, and the validity of the proposed model was confirmed.

노후화된 아파트의 재고가 폭발적으로 증가하게 될 것으로 예상됨에 따라 콘크리트 시설물의 내구성을 향상시키기 위한 유지관리의 중요성이 증대되고 있다. 콘크리트 압축강도는 콘크리트 시설물의 내구성을 나타내는 대표적인 지표로, 시설물 유지관리를 위한 정밀 안전 진단에 있어서 중요한 항목이다. 그러나 콘크리트 압축강도를 측정하고 유지관리를 판단하는데 있어서 기존의 방법들은 시설물의 안전 문제, 고비용 문제, 낮은 신뢰성 문제 등의 한계점을 가진다. 기존의 콘크리트 시설물의 압축강도 진단 방법을 대체할 수 있는 방안으로, 본 연구는 심층 컨볼루션 신경망 기법을 활용하여 영상을 통해 콘크리트 압축강도를 예측할 수 있는 모델을 제안하였다. 또한 실험실 환경에서 콘크리트 시편 제작을 통해 구축한 콘크리트 압축강도 데이터셋을 적용하여 학습, 검증 및 테스트를 진행하였다. 그 결과 콘크리트 표면 영상으로 콘크리트 압축강도를 학습할 수 있음을 알 수 있었고, 본 연구에서 제안하는 모델의 유효성을 확인하였다.

Keywords

References

  1. Al-Amoudi, O. S. B., Al-Kutti, W. A., Ahmad, S., and Maslehuddin, M. (2009). "Correlation between compressive strength and certain durability indices of plain and blended cement concretes." Cement and Concrete Composites, 31, pp. 672-676. https://doi.org/10.1016/j.cemconcomp.2009.05.005
  2. Basyigit, C., Comak, B., Kilincarslan, and Uncu, I. S. (2012). "Assessment of concrete compressive strength by image processing technique." Construction and Building Materials, 37, pp. 526-532. https://doi.org/10.1016/j.conbuildmat.2012.07.055
  3. Baygin, M., Ozkaya, S.G, Alperen, M. and Kazaz, I. (2017). "A new approach based on image processing for measuring compressive strength of structures." International Journal of Intelligent Systems and Applications in Engineering, Special Issue, pp. 21-25.
  4. Cho, H., Yoon, S., and Jee, N. (2003). "The estimation of compressive strength of ready-mixed concrete on the basis of mix design." Journal of the Architectural Institute of Korea Structure & Construction, 19(4), pp. 105-112.
  5. Chung, S. Y., Han, T. S., Yeom, K. S., and Kim, J. S. (2013). "Analysis of constituents of insulating concrete using Micro CT images." Journal of the Korean Society of Hazard Mitigation, 13(2), pp. 43-48. https://doi.org/10.9798/KOSHAM.2013.13.2.043
  6. Dogan, G., Arslan, M.H., and Ceylan, M. (2017). "Concrete compressive strength detection using image processing based new test method." Measurement, 109, pp. 137-148. https://doi.org/10.1016/j.measurement.2017.05.051
  7. Jamkar, S. S., and Rao, C. B. K. (2004). "Index of aggreate particle shape and texture of coarse aggregate as a parameter for concrete mix proportioning." Cement and Concrete Research, 34, pp. 2021-2027. https://doi.org/10.1016/j.cemconres.2004.03.010
  8. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2016). "Caffe: Convolutional architecture for fast feature embedding." in Processing of the ACM International Conference on Multimedia, pp. 675-678.
  9. Kim, M. H., Choi, S. J., Kang, S. P., Kim, J. H. and Jang, J. H. (2002). "A study on the application of non-destructive testing equation for the estimation of compressive strength of high strength concrete." Journal of the Korea Institute of Building Construction, 2(3), pp. 123-130. https://doi.org/10.5345/JKIC.2002.2.3.123
  10. Kim, M. W., Oh, H., and Oh, K. C. (2016). "Estimating the Compressive strength of high-strength concrete using surface rebound value and ultrasonic velocity." Journal of the Korea Institute for Structural Maintenance and Inspection, 20(2), pp. 1-9. https://doi.org/10.11112/jksmi.2016.20.2.001
  11. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). "Imagenet classification with deep convolutional neural networks." in Processing of the Advances in Neural Information Processing Systems, pp. 1097-1105.
  12. Kwon, Y. W., Park, S. C., and Kim, M. S. (2006). "Strength prediction equations for high strength concrete by schmidt hammer test." Journal of the orea Concrete Institute, 18(3), pp. 389-395. https://doi.org/10.4334/JKCI.2006.18.3.389
  13. Lee, H. K, Lee, B. J., Oh, J. C., and Kim, Y.Y. (2015). "Reliability evaluation for prediction of concrete compressive strength through impact resonance method and ultra pulse velocity method." Journal of the Korea Institute for Structural Maintenance and Inspection, 29(4), pp. 18-24.
  14. Lee, H. S., and Kwon, S. J. (2012). "Modeling on compressive strength in high performance concrete using porosity." Journal of the Korean Institute for Structural Maintenance and Inspection, 16(6), pp. 124-133. https://doi.org/10.11112/jksmi.2012.16.6.124
  15. Polat, R., Yadollahi, M. M., Sagsoz, A. E., and Arasan, S. (2013). "The correlation between aggregate shape and compressive strength of concrete: Digital image processing approach." International Journal of Structural and Civil Engineering Research, 2(3), pp. 62-80.
  16. Song, H. W., Cho, H. J., Park, S. S., Byun, K. J., and Maekawa, K. (2001). "Early-age cracking resistance evaluation of concrete structure." Concrete Science and Engineering, 3, pp. 62-72.
  17. Tiberti, G., Minelli, F., and Plizzar, G. (2015). "Cracking behavior in reinforced concrete members with steel fibers: a comprehensive experimental study." Cement and Concrete Research, 68, pp. 24-34. https://doi.org/10.1016/j.cemconres.2014.10.011
  18. Yoon, J. E., and Kang, K. I. (2005). "Prediction of the compressive strength of recycled aggregate concrete by data mining technique." Journal of the Architectural Institute of Korea Structure & Construction, 21(10), pp. 119-126.