- 권한신청
- P-ISSN2233-8292
- E-ISSN2287-4747
- KCI
ISSN : 2233-8292
인공신경망을 이용한 터널 주변 폭파 시 파쇄영역의 빠른 예측에 관한 연구
A study on the fast prediction of the fragmentation zone using artificial neural network when a blasting occurs around a tunnel
전석원 (서울대학교)
초록
터널 인근에서 폭발이 일어나 붕괴가 발생될 경우 터널의 기능을 회복시키기 위해서는 파쇄영역에 대하여 빠르게 파악하여야 한다. 본 연구에서는 폭발에 따른 거동을 파악하고 파쇄영역을 빠르게 예측할 수 있는 방법을 서술하였다. 이를 위해 SolidWorks를 이용하여 다양한 3차원 요소망을 작성하고, AUTODYN을 이용하여 폭발해석을 수행하였다. 민감도 분석을 실시하여 해석결과를 이용해 폭발위치 등과 같은 폭발변수가 파쇄부피에 미치는 영향을 살펴보았다. 또한 인공신경망 학습자료로 구축하고, 최적의 학습모델을 선정하고, 파쇄부피와 반지름의 예측결과를 검증하였다. 연구결과, 본 연구에서 서술된 방법이 파쇄영역을 빠르고 효과적으로 예측할 수 있음을 확인하였다.
- keywords
- Blasting, Tunnel, Artificial neural network, Fragmentation zone, 폭발, 터널, 인공신경망, 파쇄영역
Abstract
When collapse occurs due to explosion near a tunnel, fragmentation zone should be quickly comprehended to recover the function of the tunnel. In this study, explosion behavior is to be understood and a method is described for a fast prediction of the fragmentation zone. To this end, the various 3D-meshes were made by using SolidWorks and explosion analyses were performed by using AUTODYN. The influence of explosion variables such as explosion location on fragmentation volume was examined by performing sensitivity analyses and analyzing their results. Also, a training database was established for an artificial neural network analysis, the optimal training model was selected, and the predicted results for fragmentation volume and radius were verified. As a result, it was confirmed that the demonstrated mothed in this study could be effectively used for the fast prediction of fragmentation zone.
- keywords
- Blasting, Tunnel, Artificial neural network, Fragmentation zone, 폭발, 터널, 인공신경망, 파쇄영역
참고문헌
1. Ahn, M.S., Ryu C.H., Park, J.N., Kwun J.A. (2001), “A study on the safe blast design to increase slope stability”, The Journal of Korea Society for Explosives and Blasting Engineering, Vol. 19, No. 1, pp. 85-92.
2. ANSYS, Inc. (2010), ANSYS AUTODYN, Ver. 13, ANSYS Inc., USA.
3. Cho, J.W., Yu, S.H., Jeon, S.W., Chang, S.H. (2008), “Numerical study on rock fragmentation by TBM disc cutter”, Journal of Korea Tunnelling Association, Vol. 10, No. 2, pp. 139-152.
4. Konya, C.J., Walter, E.J. (1991), Rock blasting and overbreak control, National Highway Institute, p. 430.
5. Math Works Inc. (2010), MATLAB : Neural Network ToolboxTM User's Guide, Ver. R2011b, Math Works Inc., p. 404.
6. Pao, Y. (1989), Adaptive pattern recognition and neural networks, Addison - Wesley, p. 309.
7. Park, J.W. (2012), Analysis of structure subjected to blast load using parallel and domain, Master Thesis, Hanyang University, p. 50
8. Riedel, W., Thoma, K., Hiermaier, S., Schmolinske, E. (1999), “Penetration of reinforced concrete by BETAB-500 numerical analysis using a new macroscopic concrete model for hydrocodes” The 9th Int. Sym. Interaction of the Effects of Munitions with Structures, Berlin, Germany, pp. 315-322.
9. Shin, H.S., Kwon, Y.C. (2009), “Development of a window-shifting ANN training method for a quantitative rock classification in unsampled rock zone”, Journal of Korea Tunnelling Association, Vol. 11, No. 2, pp. 151-162.
10. SolidWorks Corp. (2011), SolidWorks 3D, Ver. 2011, SolidWorks Corp, Massachusetts, USA.
11. Wasserman, P.D. (1989), Neural computing : Theory and practice, Van Nostrand Reinhold Co., New York, USA, p. 230.
12. You, K.H., Kim, D.H. (2012), “A study on the influence of blasting location on tunnel fragmentation zone”, 2012 Korean Geotechnical Society, Geo Expo, pp. 1611-1615.
13. You, K.H., Son, M.K. (2013), “Hauling time prediction of the muck generated by a blasting around a tunnel”, Journal of Korean Tunnelling and Underground Space Association, Vol. 15, No. 1, pp. 33-47.
14. You. K.H., Song, W.Y. (2012), “A case study on a tunnel back analysis to minimize the uncertainty of ground properties based on artificial neural network”, Journal of Korean Tunnelling and Underground Space Association, Vol. 14, No. 1, pp. 37-53.
- 다운로드 수
- 조회수
- 0KCI 피인용수
- 0WOS 피인용수