DOI QR코드

DOI QR Code

A TBM data-based ground prediction using deep neural network

심층 신경망을 이용한 TBM 데이터 기반의 굴착 지반 예측 연구

  • 김태환 (SK건설 에코인프라솔루션 3팀) ;
  • 곽노상 (SK C&C Data플랫폼그룹) ;
  • 김택곤 (SK건설 에코인프라솔루션 3팀) ;
  • 정사범 (SK C&C Data플랫폼그룹) ;
  • 고태영 (강원대학교 에너지자원.산업공학부)
  • Received : 2020.11.21
  • Accepted : 2020.12.30
  • Published : 2021.01.31

Abstract

Tunnel boring machine (TBM) is widely used for tunnel excavation in hard rock and soft ground. In the perspective of TBM-based tunneling, one of the main challenges is to drive the machine optimally according to varying geological conditions, which could significantly lead to saving highly expensive costs by reducing the total operation time. Generally, drilling investigations are conducted to survey the geological ground before the TBM tunneling. However, it is difficult to provide the precise ground information over the whole tunnel path to operators because it acquires insufficient samples around the path sparsely and irregularly. To overcome this issue, in this study, we proposed a geological type classification system using the TBM operating data recorded in a 5 s sampling rate. We first categorized the various geological conditions (here, we limit to granite) as three geological types (i.e., rock, soil, and mixed type). Then, we applied the preprocessing methods including outlier rejection, normalization, and extracting input features, etc. We adopted a deep neural network (DNN), which has 6 hidden layers, to classify the geological types based on TBM operating data. We evaluated the classification system using the 10-fold cross-validation. Average classification accuracy presents the 75.4% (here, the total number of data were 388,639 samples). Our experimental results still need to improve accuracy but show that geology information classification technique based on TBM operating data could be utilized in the real environment to complement the sparse ground information.

암반 및 연약지반을 포함한 다양한 지반 조건에서 TBM (Tunnel Boring Machine) 터널링이 활용되고 있다. 굴착 성능을 높이기 위해서 지반 조건에 따라 최적으로 장비를 운영해야 하며, 이를 통해 공기단축을 통한 비용 절감 효과를 기대할 수 있다. 하지만 시추 조사를 통해 획득한 지반 정보는 시추공 사이 불확실성이 존재하므로, 실시간 최적 운전에 부족함이 있다. 본 연구에서는 지반의 불확실성 문제를 해결하고자 5초마다 기록된 TBM 데이터를 활용하여 굴착 지반 예측시스템을 구축하고자 한다. 싱가포르 현장에서 획득한 화강암의 풍화도를 고려하여 암반, 토사, 복합지반 세 가지로 지질로 재분류하였고, 실시간으로 도출되는 기계 데이터로 이를 예측하고자 한다. 현장에서 획득한 TBM 데이터에 대해 이상치 제거, 정규화, 특성 추출 등의 전처리 방법을 적용하였고, 지질을 분류하기 위해 6개의 은닉층을 가진 심층 신경망(Deep Neural Network, DNN)을 활용하였다. 10겹 교차검증을 통해 분류 시스템을 평가한 결과, 평균 75.4%의 정확도를 확인하였다(총 데이터 388,639개). 본 연구를 통해 지질 불확실성을 감소시키고, 지반 조건에 따른 실시간 최적 운전에 도움이 될 것으로 판단된다.

Keywords

References

  1. Barton, N., Lien, R., Lunde, J. (1974), "Engineering classification of rock masses for the design of tunnel support", Rock Mechanics, Vol. 6, No. 4, pp. 189-236. https://doi.org/10.1007/BF01239496
  2. Bieniawski, Z.T. (1973), "Engineering classification of jointed rock masses", The Civil Engineer in South Africa, Vol. 15, No. 12, pp. 335-343.
  3. British Standard Institution (1999), BS 5930: Soils for civil engineering purpose: classification, London.
  4. Han, S.Y., Kwak, N.S., Oh, T., Lee, S.W. (2020), "Classification of pilots' mental states using a multimodal deep learning network", Biocybernetics and Biomedical Engineering, Vol. 40, No. 1, pp. 324-336. https://doi.org/10.1016/j.bbe.2019.12.002
  5. Hong, C.H., Kim, J., Ryu, H.H., Cho, G.C. (2020), "Study on Q-value prediction ahead of tunnel excavation face using recurrent neural network", Journal of Korean Tunnelling and Underground Space Association, Vol. 22, No. 3, pp. 239-248. https://doi.org/10.9711/KTAJ.2020.22.3.239
  6. Jung, J.H., Chung, H.Y., Kwon, Y.S., Lee, I.M. (2019), "An ANN to predict ground condition ahead of tunnel face using TBM operational data", KSCE Journal of Civil Engineering, Vol. 23, No. 7, pp. 3200-3206. https://doi.org/10.1007/s12205-019-1460-9
  7. Kim, J.J., Ryu, H.H., Kim, K.Y., Hong, S.Y., Jung, J.H., Bae, D.S. (2020a), "Development of penetration rate model and optimum operational conditions of shield TBM for electricity transmission tunnels", Journal of Korean Tunnelling and Underground Space Association, Vol. 22, No. 6, pp. 623-641. https://doi.org/10.9711/KTAJ.2020.22.6.623
  8. Kim, T.H., Ko, T.Y., Park, Y.S., Kim, T.K., Lee, D.H. (2020b), "Prediction of uniaxial compressive strength of rock using shield TBM machine data and machine learning technique", Tunnel and Underground Space, Vol. 30, No. 3, pp. 214-225. https://doi.org/10.7474/TUS.2020.30.3.214
  9. Ko, T.Y., Pak, Y.T., Kim, T.K., Son, S.M. (2017), "Effect of rock abrasiveness on slurry shield tunneling", International Conference on Tunnel Boring Machines in Difficult Grounds (TBM DiGs), Wuhan, China, pp. 1-8.
  10. Kwak, N.S., Muller, KR., Lee, S.W. (2017), "A convolutional neural network for steady state visual evoked potential classification under ambulatory environment", PloS one, Vol. 12, No. 2, e0172578. https://doi.org/10.1371/journal.pone.0172578
  11. Lee, H.L., Song, K.I., Cho, G.C. (2016), "Analysis on prediction models of TBM performance: a review", Journal of Korean Tunnelling and Underground Space Association, Vol. 18, No. 2, pp. 245-256. https://doi.org/10.9711/KTAJ.2016.18.2.245
  12. Singapore Standard (2003), CP4:2003 Code practice for foundations, Singapore.