DOI QR코드

DOI QR Code

A fundamental study on the automation of tunnel blasting design using a machine learning model

머신러닝을 이용한 터널발파설계 자동화를 위한 기초연구

  • Kim, Yangkyun (Dept. of Earth Resources and Environmental Engineering, Hanyang University) ;
  • Lee, Je-Kyum (Dept. of Earth Resources and Environmental Engineering, Hanyang University) ;
  • Lee, Sean Seungwon (Dept. of Earth Resources and Environmental Engineering, Hanyang University)
  • 김양균 (한양대학교 자원환경공학과) ;
  • 이제겸 (한양대학교 자원환경공학과) ;
  • 이승원 (한양대학교 자원환경공학과)
  • Received : 2022.08.09
  • Accepted : 2022.09.13
  • Published : 2022.09.30

Abstract

As many tunnels generally have been constructed, various experiences and techniques have been accumulated for tunnel design as well as tunnel construction. Hence, there are not a few cases that, for some usual tunnel design works, it is sufficient to perform the design by only modifying or supplementing previous similar design cases unless a tunnel has a unique structure or in geological conditions. In particular, for a tunnel blast design, it is reasonable to refer to previous similar design cases because the blast design in the stage of design is a preliminary design, considering that it is general to perform additional blast design through test blasts prior to the start of tunnel excavation. Meanwhile, entering the industry 4.0 era, artificial intelligence (AI) of which availability is surging across whole industry sector is broadly utilized to tunnel and blasting. For a drill and blast tunnel, AI is mainly applied for the estimation of blast vibration and rock mass classification, etc. however, there are few cases where it is applied to blast pattern design. Thus, this study attempts to automate tunnel blast design by means of machine learning, a branch of artificial intelligence. For this, the data related to a blast design was collected from 25 tunnel design reports for learning as well as 2 additional reports for the test, and from which 4 design parameters, i.e., rock mass class, road type and cross sectional area of upper section as well as bench section as input data as well as16 design elements, i.e., blast cut type, specific charge, the number of drill holes, and spacing and burden for each blast hole group, etc. as output. Based on this design data, three machine learning models, i.e., XGBoost, ANN, SVM, were tested and XGBoost was chosen as the best model and the results show a generally similar trend to an actual design when assumed design parameters were input. It is not enough yet to perform the whole blast design using the results from this study, however, it is planned that additional studies will be carried out to make it possible to put it to practical use after collecting more sufficient blast design data and supplementing detailed machine learning processes.

지금까지 국내에서는 수 많은 터널들이 완공되어 오면서 시공에서뿐 아니라 설계에서도 다양한 경험과 기술이 지속적으로 축적되어 왔다. 따라서 이제는 매우 복잡한 지질조건 또는 특수한 터널구조가 아니라면 일반적인 터널설계작업은 설계 항목에 따라 기존 유사 설계사례를 수정 또는 보완하는 것만으로도 충분한 경우도 적지 않다. 특히 터널발파설계의 경우, 실제 터널시공시 현장에서 시험발파를 통해 시공을 위한 발파설계를 추가로 수행하는 것이 일반적이라는 것을 감안할때, 설계단계에서 수행하는 발파설계는 예비설계 성격을 지니고 있어 기존의 유사 설계사례를 참고하는 것도 타당하다고 사료된다. 한편 최근 4차산업혁명시대에 들어서면서 전 산업분야에 걸쳐 그 활용도가 급증하고 있는 인공지능은 터널 및 발파분야에서도 다양하게 활용되고 있지만, 발파터널의 경우 발파진동 및 암반분류 등의 예측 분야에서 주로 활용되고 있을 뿐 터널발파패턴 설계에 활용된 사례는 많지 않다. 따라서 본 연구에서는 터널발파설계를 인공지능의 한 분야인 머신러닝 모델을 이용하여 자동화하기 위한 시도를 하였다. 이를 위하여 25개 학습용 터널설계 자료 및 2개의 시험용 설계자료에서 4가지의 입력데이터(지보패턴, 도로유형, 상반 및 하반 단면적) 및 16개의 출력데이터(심발공 종류, 비장약량, 천공수, 각 발파공 그룹별 공간격과 저항선 등)를 발췌하였다. 이를 기반으로 3가지 머신러닝 모델, 즉, XGBoost, ANN, SVM 모델을 시험한 결과 XGBoost모델이 상대적으로 최상의 결과를 나타내었다. 또한 이를 이용하여 실제 발파설계 상황을 가정하여 발파패턴을 제안하도록 한 결과 일부 항목에서 보완이 필요하긴 하지만 일반적 설계와 유사한 결과를 나타내었다. 본 연구가 기초연구 성격이어서 전체 발파설계를 완벽하게 수행하기는 아직 부족하지만, 향후 충분한 발파설계데이터를 확보하고 세부적인 처리과정을 보완하여 실용적인 활용이 가능하도록 추가 연구를 수행할 계획이다.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었습니다(과제번호: RS-2021-KA163775, "빅데이터와 인공지능 기반의 발파굴착터널 자동설계기술 개발을 위한 기초연구"). 이에 감사드립니다.

References

  1. Ahn, Y.H., Kim, S.Y. (2017), "Construction industry transition with the 4th industrial revolution technology", Journal of the Korea Institute of Building Construction, Vol. 17, No. 2 (special issue), pp. 19-23.
  2. Alipour, A., Mokhtarian-Asl, M., Asadizadeh, M. (2021), "Support vector machines for the estimation of specific charge in tunnel blasting", Periodica Polytechnica Civil Engineering, Vol. 65, No. 3, pp. 967-976.
  3. Choi, B.H., Ryu, C.H., Jeong, J.H. (2009), "Tunnel blasting design suited to given specific charge", Explosives and Blasting, Vol. 27, No. 2, pp. 33-41.
  4. Choi, Y.K. (2005), "Development of automated pattern generation method for tunnel blasting", Explosives and Blasting, Vol. 23, No. 4, pp. 19-29.
  5. Construction CALS Home page, https://www.calspia.go.kr/io/index.do (July 2, 2022).
  6. Hafner, M., Rajster, D., Zibert, M., Tusar, T., Zenko, B., Znidarsic, M., Fuart, F., Vladusic, D. (2019), "Artificial intelligence support for tunnel design in urban areas", Tunnels and Underground Cities: Engineering and Innovation meet Archaeology, Architecture and Art, Taylor & Francis, London, pp. 2196-2205.
  7. Jang, H., Topal, E. (2013), "Optimizing overbreak prediction based on geological parameters comparing multiple regression analysis and artificial neural network", Tunnelling and Underground Space Technology, Vol. 38, pp. 161-169. https://doi.org/10.1016/j.tust.2013.06.003
  8. Kim, Y. (2021), "An analysis of artificial intelligence algorithms applied to rock engineering", Tunnel and Underground Space, Vol. 31, No. 1, pp. 25-40. https://doi.org/10.7474/TUS.2021.31.1.025
  9. Kim, Y., Bruland, A. (2015), "Comparison of tunnel excavation cycle time for Norwegian and Korean tunnels", Proceedings of the 41th ITA World Tunnel Congress, Dubrovnik, Croatia.
  10. Langefors, U., Kihlstom, B. (1967), The Modern Technique of Rock Blasting, Wiley or Almqvist & Wiksell, New York, pp. 180-229.
  11. Lee, J.K., Choi, W.H., Kim, Y., Lee, S.S. (2021), "A study on the rock mass classification in boreholes for a tunnel design using machine learning algorithms", Journal of Korean Tunnelling and Underground Space Association, Vol. 23, No. 6, pp. 469-484. https://doi.org/10.9711/KTAJ.2021.23.6.469
  12. Lee, T.H. (2016), Development of an artificial neural network for optimization of tunnel blasting design, Doctoral Thesis, City University of Hong Kong, pp. 143-194.
  13. Mitchell, T.M. (1997), Machine Learning, McGraw Hill, pp. 1.
  14. MOLIT (2016), Korean design standard, KDS 27 20 00, Ministry of Land, Infrastructure and Transport, pp. 3-4.
  15. MOLIT Statistics System Home page, http://stat.molit.go.kr/portal/cate/statView.do?hRsId=302&hFormId=4746&hDivEng=&month_yn= (September 24, 2021b).
  16. MOLIT Statistics System Home page, http://stat.molit.go.kr/portal/cate/statView.do?hRsId=65&hFormId=1040&hDivEng=&month_yn= (September 24, 2021a).
  17. Olofsson, S. (1990), Applied Explosives Technology for Construction and Mining, Applex, Arla, pp. 131-173.
  18. Soranzo, E., Guardiani, C., Wu, W. (2022), "The application of reinforcement learning to NATM tunnel design", Underground Space, In Press, pp. 1-13.
  19. Trivedi, R., Singh, T.N., Mudgal, K., Gupta, N. (2014), "Application of artificial neural network for blast performance evaluation", International Journal of Research in Engineering and Technology, Vol. 03, No. 5, pp. 564-574.
  20. Wu, Z., Luo, D., Chen, G. (2020), "Design and realization of the intelligent design system for tunnel blasting in mine based on database", Geofluids, Vol. 2020, Article ID 8878783, pp. 1-11.