Development of Improvement Effect Prediction System of C.G.S Method based on Artificial Neural Network

인공신경망을 기반으로 한 C.G.S 공법의 개량효과 예측시스템 개발

  • Kim, Jeonghoon (Dept. of Civil and Environmental Engineering, Hanyang University) ;
  • Hong, Jongouk (Dept. of Civil and Environmental Engineering, Hanyang University) ;
  • Byun, Yoseph (Dept. of Civil and Environmental Engineering, Hanyang University) ;
  • Jung, Euiyoup (DENVER KOREA E&C) ;
  • Seo, Seokhyun (DENVER KOREA E&C) ;
  • Chun, Byungsik (Dept. of Civil and Environmental Engineering, Hanyang University)
  • Published : 2013.09.01

Abstract

In this study installation diameter, interval, area replacement ratio and ground hardness of applicable ground in C.G.S method should be mastered through surrounding ground by conducting modeling. Optimum artificial neural network was selected through the study of the parameter of artificial neural network and prediction model was developed by the relationship with numerical analysis and artificial neural network. As this result, C.G.S pile settlement and ground settlement were found to be equal in terms of diameter, interval, area replacement ratio and ground hardness, presented in a single curve, which means that the behavior pattern of applied ground in C.G.S method was presented as some form, and based on such a result, learning the artificial neural network for 3D behavior was found to be possible. As the study results of artificial neural network internal factor, when using the number of neural in hidden layer 10, momentum constant 0.2 and learning rate 0.2, relationship between input and output was expressed properly. As a result of evaluating the ground behavior of C.G.S method which was applied to using such optimum structure of artificial neural network model, is that determination coefficient in case of C.G.S pile settlement was 0.8737, in case of ground settlement was 0.7339 and in case of ground heaving was 0.7212, sufficient reliability was known.

본 연구는 C.G.S공법 적용 지반을 설치 직경, 설치 간격, 면적 치환율, 지반강성에 따른 모델링을 실시함으로써 주변 지반의 거동을 파악하고자 하였고, 인공신경망의 매개변수 연구를 통해 본 연구에 가장 적합한 인공신경망 모델을 선정하여 수치해석과 인공신경망 연계를 통한 인공신경망 예측 모델을 개발하였다. 그 결과, C.G.S 말뚝 침하량 및 지반 침하량은 직경, 설치 간격, 면적 치환율, 지반강성 별로 일치하여 하나의 곡선으로 나타났으며, 이는 C.G.S 공법 적용 지반의 거동양상이 일정한 형태로 나타남을 의미하는 것으로, 이러한 결과를 바탕으로 3차원 거동에 대한 인공신경망 학습이 가능한 것으로 파악되었다. 인공신경망의 내적인자 연구 결과, 은닉층 뉴런수 10개, 모멘텀 상수 0.2, 학습률의 경우 0.2를 사용할 경우 입력과 출력간의 관계가 적절히 표현되는 것으로 나타났다. 이러한 인공신경망 모델의 최적구조를 이용하여 C.G.S 공법의 지반 거동을 평가한 결과는 결정계수 값이 C.G.S 말뚝 침하의 경우는 0.8737, 지반 침하의 경우는 0.7339, 지반 융기의 경우는 0.7212로 나타나 충분한 신뢰도를 보이고 있음을 알수 있었다.

Keywords

References

  1. 천병식(2011), 약액주입의 원리와 실제, (사)건설산업연구소, 구미서관, pp. 191-192, pp. 191-213.
  2. Barai, S. V. and Pandey, P. C.(1995), Vibration signature analysis using artficial neural networks, Vol. 8, No. 2, pp. 211-221.
  3. Cherubini, C.(2000), Probabilistic approach to the design of anchored sheet pile walls. Computers and Geotechnics, Vol. 26, No. 3-4, pp. 309-330. https://doi.org/10.1016/S0266-352X(99)00044-0
  4. Chun, B. S., Yeoh, Y. H., Choi, H. S. and Oh, I. S.(1999), A study on the ground improvement by compaction grouting system, KSCE Soft Ground Processing Committee, pp. 1-13 (in Korean).
  5. Chun, B. S. and Yeoh, Y. H.(2003a), A study on the behavior characteristics of soft clay ground by C.G.S method, The Journal of KGS, Vol. 19, No. 6, pp. 307-323 (in Korean).
  6. Chun, B. S., Yeoh, Y. H., Joung, Y. K. and Sagong, M.(2003b), A case study on the reduction of settlement caused by compaction grouting system, 3rd International Symposium on Deformation Characteristic of Geomaterials, 22-24 Sep, 2003, Lyon, France, pp. 1411-1416.
  7. Eagen, J. T., Tins, J. and Nonamaker, F.(1992), Grouting practices in southern california, engineering geology practice in southern california, Edited by Pipkin, B. W. and Proctor, R. J., Special Publication No. 4, Association of Engineering Geologists, Southern California Section, Star Publishing Company, pp. 433-452.
  8. Ellis, G. W., Yao, C. and Zhao, R.(1992), Neural network modeling of the mechanical behavior of sand, Proceedings of the Engineering Mechanics, ASCE, New York, N.Y., pp. 421-424.
  9. Goh, A.T.C.(1996), Neural network modeling of CPT seismic liquefaction data, Journal of Geotechnical Enginearing, Vol. 122, No. 1, pp. 70-73. https://doi.org/10.1061/(ASCE)0733-9410(1996)122:1(70)
  10. Haibagahi, G. and Bamdad, A.(2003), A neural network framework for mechanical behavior of unsaturated soils, Journal of Geotechnical Engineering, Vol. 40, No. 3, pp. 684-693. https://doi.org/10.1139/t03-004
  11. Haykin, Simon(1998), Neural networks, Prentice-Hall, Inc, New Jersey, pp. 69-94.
  12. Kiefa, M. A.(1998), General regression neural networks for driven piles in cohesionless soils, Journal of Geotechnical and Geoenvironmental Engineering, Vol. 124, No. 12, pp. 1177-1185. https://doi.org/10.1061/(ASCE)1090-0241(1998)124:12(1177)
  13. Peumadu, D., Zhao, R., Yao, C. and Ellis, G.W.(1995), Stressstrain modeling of sands using artificial neural network, Journal of Geotechnical Engineering, Vol. 121, No. 5, pp. 429-435. https://doi.org/10.1061/(ASCE)0733-9410(1995)121:5(429)
  14. Rumelhart, D. E., Hinton, G. E. and McClelland, J. L.(1986), A general framework fot parallel distributed Processing, Vol. 1, MIT Press, Cambridge, MA, pp. 318-362.
  15. Shahin, M. A., Maier, H. R. and Jaksa, M. B.(2002), Predicting settlement of shallow foundations using neural networks, Journal of Geotechnical and Geoenvironmental Engineering, Vol. 128, No. 9, pp. 285-793.
  16. Teh, C. I., Wong, K. S., Goh, A.T.C. and Jaritngam, S.(1997), Prediction of pile capacity using neural networks, Journal of Computing in Civil Enginnering, Vol. 11, No. 2, pp. 129-138. https://doi.org/10.1061/(ASCE)0887-3801(1997)11:2(129)
  17. Warner, J.(1978), Compaction grouting - a significant case history, Journal of Geotechnical Engineering, Vol. 104, No. 7, pp. 837-847.