Journal of the Korean GEO-environmental Society (한국지반환경공학회 논문집)

Korean Geo-Environmental Society (한국지반환경공학회)
권호 표지
DOI QR코드

DOI QR Code

Application of Artificial Neural Networks for Prediction of the Strength Properties of CSG Materials

  • Lim, Jeongyeul (K-water Institute, Infrastructure Research Center) ;
  • Kim, Kiyoung (K-water Institute, Infrastructure Research Center) ;
  • Moon, Hongduk (Department of Civil Engineering, Gyeongnam National University of Science and Technology) ;
  • Jin, Guangri (Department of Civil Engineering, Yanbian University)
  • Received : 2018.01.23
  • Accepted : 2018.04.25
  • Published : 2018.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

The number of researches on the mechanical properties of cemented sand and gravel (CSG) materials and the application of the CSG Dam has been increased. In order to explain the technical scheme of strength prediction model about the artificial neural network, we obtained the sample data by orthogonal test using the PVA (Polyvinyl alcohol) fiber, different amount of cementing materials and age, and established the efficient evaluation and prediction system. Combined with the analysis about the importance of influence factors, the prediction accuracy was above 95%. This provides the scientific theory for the further application of CSG, and will also be the foundation to apply the artificial neural network theory further in water conservancy project for the future.

Keywords

References

  1. Chai, Q. H., Yang, S. F. and Sun, M. Q. (2016), Study on the influence factors of compressive strength of CSG material, Journal of the YELLOW RIVER (China), Vol. 38, No. 7, pp. 86-88.
  2. Erdal, H. I., Karakurt, O. and Namli, E. (2013), High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform, Engineering Applications of Artificial Intelligence, pp. 1246-1254.
  3. Feng, W., Jia, J. S. and Ma, F. D. (2013), Study on design parameters of mix proportion for cemented sand and gravel (CSG), Water Resources and Hydropower Engineering (China), Vol. 44, No. 2, pp. 55-58.
  4. Hanada, H., Tamezawa, T. and Ooyabu, K. (2003.12), CSG method using muck excavated from the dam foundation, Proceedings 4th International Symposium on Roller Compacted Concrete Dams, pp. 447-456.
  5. Harkat, M. F., Mourot, G. and Ragot, J. (2003), Nonlinear PCA combining principal curves and RBF-Networks for process monitoring, In: Proceeding of the 42nd IEEE Conference on Decision and Control, pp. 1956-1961.
  6. Hu, X. (2014), Prediction of high performance concrete strength based on artificial neural network, The Master Thesis, in Hunan University, China, pp. 13-16.
  7. Jin, G. R., Kim, K. Y., Quan, H. C. and Kim, K. W. (2013), Strength characteristics of PVA fiber reinforced CSG materials, Journal of the Korean Geotechnical Society, Vol. 29, No. 12, pp. 95-104. https://doi.org/10.7843/kgs.2013.29.12.95
  8. Kim, I. S., Park, S. K., Yang, D. S., and Lee, J. H. (2002), Prediction on mix proportion factor and strength of concrete using neural network, KCI Concrete Journal, Vol. 14, No. 4, pp. 457-466.
  9. Kim, K. Y., Park, H. G., Lee, S. W. and Cho, S. E. (2006), Prediction of unconfined strength of C.S.G. materials by artificial neural network, 2006 Fall Geotechnical Engineering Conference, pp. 938-843.
  10. Kim, Y. S., Jeong, H. C., Huh, J. W. and Jeong, G. H. (2006), Application of artificial neural network theory for evaluation of unconfined compression strength of deep cement mixing treated soil, 2006 Spring Geotechnical Engineering Conference, pp. 1159-1164.
  11. Kramer, M. A. (1991), Nonlinear principal component analysis using autoassociative neural network, AICHE Journal, Vol. 37, No. 2, pp. 233-243. https://doi.org/10.1002/aic.690370209
  12. Liu, Y. H. (2013), Research on constitutive model of CSG material, The Master Thesis, in North China University Of Water Resources And Electric Power, China, pp. 19-21.
  13. Park, H. I., Kim, Y. T. and Kim, H. J. (2006), Prediction of compressive strength of reinforced lightweight soil using artificial neural network, 2006 Spring Geotechnical Engineering Conference, pp. 1248-1253.
  14. Park, H. I., Kim, Y. T. and Kim, H. J. (2007), Prediction of compressive strength of reinforced lightweight soil using artificial neural network, KSCE Journal of Civil Engineering, Vol. 27, No. 2, pp. 111-119.
  15. Raplael, J. M. (1992), The optimum gravity dam, Proceedings roller compacted concrete III, ASCE, San Diego, California, and 2-5 February, pp. 5-19.
  16. Yang, X. M., Wu, T. Y. and Shi, D. (2014), Sensitivity analysis on influence factors to concrete real-time strength based on artificial neural network, Concrete (China), No. 351, pp. 16-23.
  17. You, J., Che, Y. and Zhong, W. Q. (2011), Predition of concrete strength of existing buildings based on BP neural networks, Journal of Architecture and Civil Engineering (China), Vol. 28, No. 1, pp. 70-75.
  18. Zhang, D. X., Lin, M. X., Wang, C. X. and Zhu, D. X. (2015), Dynamic mechanical properties of CSG and its constitutive relation, Journal of Changsha University of Science and Technology (Natural Science, China), Vol. 12, No. 2, pp. 83-90.
  19. Zhu, X. L., Ding, J. T. and Cai, Y. B. (2016), Experimental research on strength and elasticity modulus of cement sand and gravel, Journal of the YELLOW RIVER (China), Vol. 38, No. 3, pp. 126-128.