Journal of the Korean Geotechnical Society (한국지반공학회논문집)

Korean Geotechnical Society (한국지반공학회)
권호 표지
DOI QR코드

DOI QR Code

Consideration of the Relationship between Independent Variables for the Estimation of Crack Density

균열밀도 산정을 위한 독립 변수 간의 관계 고찰

  • 윤형구 (대전대학교 재난안전공학과 )
  • Received : 2024.08.01
  • Accepted : 2024.08.10
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this paper is to analyze the significance of independent variables in estimating crack density using machine learning algorithms. The algorithms used were random forest and SHAP, with the independent variables being compressional wave velocity, shear wave velocity, porosity, and Poisson's ratio. Rock samples were collected from construction sites and processed into cylindrical forms to facilitate the acquisition of each input property. Artificial weathering was conducted twelve times to obtain values for both independent and dependent variables with multiple features. The application of the two algorithms revealed that porosity is a crucial independent variable in estimating crack density, whereas shear wave velocity has a relatively low impact. These results suggested that the four physical properties set as independent variables were sufficient for estimating crack density. Additionally, they presented a methodology for verifying the appropriateness of the independent variables using algorithms such as random forest and SHAP.

해당 논문의 목적은 균열밀도 산정 시 독립변수로 설정한 값이 얼마나 중요하게 작용하는지를 기계학습 기반의 알고리즘으로 분석하는 것이다. 논문에서 사용한 알고리즘은 random forest와 SHAP이며, 독립변수는 압축파 속도, 전단파 속도, 간극률 그리고 포아송 비로 결정하였다. 암석 시료는 건설현장에서 채취하였으며, 원기둥 형태로 가공하여 각 입력 물성치의 획득이 용이하게 고려하였다. 다수의 특징이 포함된 독립 및 종속 변수 값을 얻고자 인위적인 풍화를 진행하였으며, 총 12회 진행하였다. 2가지 알고리즘 적용 결과 간극률이 균열밀도 산정시 매우 중요한 독립변수로 나타났으며, 전단파 속도가 상대적으로 낮은 영향을 미치는 인자로 나타났다. 이와 같은 결과는 독립변수로 설정한 4개의 물성치로 충분히 균열밀도를 추정할 수 있음을 시사하며 random forest 및 SHAP과 같은 알고리즘을 통해 설정된 독립 변수가 적절하게 구성되었는지 확인할 수 있는 방법론도 제시하였다.

Keywords

References

  1. Bae, B., Choi, Y., Yun, K., and Ahn, J. (2024), "Application of Mask R-CNN Algorithm to Detect Cracks in Concrete Structure", Journal of The Korean Geotechnical Society, Vol.40, No.3, pp. 33-39.  https://doi.org/10.7843/KGS.2024.40.3.33
  2. Biot, M. A. (1952), "The Interaction of Rayleigh and Stoneley Waves in the Ocean Bottom", Bulletin of the Seismological Society of America, Vol.42, No.1, pp.81-93.  https://doi.org/10.1785/BSSA0420010081
  3. Feng, R., Grana, D., and Balling, N. (2021), "Imputation of Missing Well Log Data by Random Forest and its Uncertainty Analysis", Computers & Geosciences, Vol.152, 104763. 
  4. Jang, B. S., Kim, Y. S., Kim, S. W., Choi, H. J., and Yoon, H. K. (2023a), "Assessment of Frozen Soil Characterization Via Electrical Resistivity Survey", Journal of The Korean Geotechnical Society, Vol.39, No.12, pp.115-125.  https://doi.org/10.7843/KGS.2023.39.12.115
  5. Jang, B. S., Kim, Y. S., Kim, S. W., Choi, H. J., and Yoon, H. K. (2023b), "Assessment of Applicability of CNN Algorithm for Interpretation of Thermal Images Acquired in Superficial Defect Inspection Zones", Journal of The Korean Geotechnical Society, Vol.39, No.10, pp.41-48.  https://doi.org/10.7843/KGS.2023.39.10.41
  6. Kim, J., Kang, J. M., and Baek, S. H. (2021), "Development of Random Forest Model for Sewer-induced Sinkhole Susceptibility", Journal of The Korean Geotechnical Society, Vol.37, No.12, pp. 117-125.  https://doi.org/10.7843/KGS.2021.37.12.117
  7. Lee, S. Y., Kim D. H., and Jeong. S. S. (2016), "A Study on the Excavation Damage Zone (EDZ) under TBM Advancement Based on Large Deformation Technique (Coupled Eulerian-Lagrangian)", Journal of The Korean Geotechnical Society, Vol.32, No.12, pp.5-13.  https://doi.org/10.7843/KGS.2016.32.12.5
  8. Min, D. H., Kim, Y. S., Kim, S., Choi, H. J., and Yoon, H. K. (2023), "Neural Network-Based Prediction of Dynamic Properties", Journal of The Korean Geotechnical Society, Vol.39, No.12, pp. 37-46.  https://doi.org/10.7843/KGS.2023.39.12.37
  9. Min, D. H. and Yoon, H. K. (2021), "Suggestion for a New Deterministic Model Coupled with Machine Learning Techniques for Landslide Susceptibility Mapping", Scientific Reports, Vol.11, No.1, pp.1-24.  https://doi.org/10.1038/s41598-020-79139-8
  10. Park, J., Kim, K. Y., and Yun, T. S. (2023), "Morphological Analysis of Hydraulically Stimulated Fractures by Deep-Learning Segmentation Method", Journal of The Korean Geotechnical Society, Vol.39, No.8, pp.17-28.  https://doi.org/10.7843/KGS.2023.39.8.17
  11. Park, S. S., Kim, S. H., and Bae, D. H. (2018), "Strength Characteristics of Sedimentary Rock in Daegu-Gyungbuk Area Followed by Saturation and Crack Initiation", Journal of The Korean Geotechnical Society, Vol.34, No.12, pp.29-42.  https://doi.org/10.7843/KGS.2018.34.12.29
  12. Seo, S. and Chung, M. (2023), "Development of an Ensemble Prediction Model for Lateral Deformation of Retaining Wall Under Construction", Journal of The Korean Geotechnical Society, Vol.39, No.4, pp.5-17.  https://doi.org/10.7843/KGS.2023.39.4.5
  13. Wang, H., Yang, F., and Luo, Z. (2016), "An Experimental Study of the Intrinsic Stability of Random Forest Variable Importance Measures", BMC bioinformatics, Vol.17, pp.1-18. 
  14. Yoon, H. K. (2023), "Method for Assessing Landslide Susceptibility Using SMOTE and Classification Algorithms", Journal of The Korean Geotechnical Society, Vol.39, No.6, pp.5-12.  https://doi.org/10.7843/KGS.2023.39.6.5
  15. Zhang, F. and Yang, X. (2020), "Improving Land Cover Classification in an Urbanized Coastal Area by Random Forests: The Role of Variable Selection", Remote Sensing of Environment, Vol.251, 112105.