Integrating Machine Learning in Geotechnical Engineering: A Novel Approach for Railway Track Layer Design Based on Cone Penetration Test Data

被引:0
|
作者
Bernard, Matthieu [1 ]
机构
[1] Infrabel, Dept Track Renewal, 85 Rue France, B-1060 Brussels, Belgium
关键词
cone penetration test; trackbed; layer thickness; machine learning; random forest;
D O I
10.3390/infrastructures9080121
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The cone penetration test (CPT) has emerged as a cost-effective and time-efficient method for assessing soil conditions relevant to railway track infrastructure. The geotechnical data obtained from the CPT serve as crucial input for asset managers in designing optimal sublayers and form layers for track renewal works. To properly assess the condition of soil layers, various soil behavior type charts and machine learning models based on CPT data have been published to help engineers classify soils into groups with similar properties. By understanding the properties of the soils, an optimal substructure can be designed to minimize extensive maintenance and reduce the risk of derailment. However, when analyzing multiple CPTs, the diversity and non-uniformity of subsoil characteristics pose challenges in designing a new optimal trackbed. This study presents an automated approach for recommending thicknesses of sublayers and form layers in railway tracks based on CPT data, employing machine learning algorithms. The proposed approach was tested using CPT data from the Belgian railway network and showed very good agreement with results from traditional soil investigation interpretations and layer design. A Random Forest classifier, fine-tuned through Bayesian optimization with a cross-validation technique and trained on 80% of the datasets, achieved an overall accuracy of 83% on the remaining 20%. Based on these results, we can conclude that the proposed model is highly effective at accurately designing sub-ballast layers using CPT data.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Unsupervised machine learning for detecting soil layer boundaries from cone penetration test data
    Hudson, Kenneth S.
    Ulmer, Kristin J.
    Zimmaro, Paolo
    Kramer, Steven L.
    Stewart, Jonathan P.
    Brandenberg, Scott J.
    EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2023, 52 (11): : 3201 - 3215
  • [2] A multiple model machine learning approach for soil classification from cone penetration test data
    Carvalho, Lucas O.
    Ribeiro, Dimas B.
    SOILS AND ROCKS, 2021, 44 (04):
  • [3] Machine Learning Techniques for Soil Characterization Using Cone Penetration Test Data
    Chala, Ayele Tesema
    Ray, Richard P. P.
    APPLIED SCIENCES-BASEL, 2023, 13 (14):
  • [4] A smarter approach to liquefaction risk: harnessing dynamic cone penetration test data and machine learning for safer infrastructure
    Singh, Shubhendu Vikram
    Ghani, Sufyan
    FRONTIERS IN BUILT ENVIRONMENT, 2024, 10
  • [5] Utilizing Machine Learning for Cone Penetration Test-Based Soil Classification
    Fatehnia, Milad
    Mahmoudabadi, Vahidreza
    Amiri, Sharid
    Transportation Research Record, 2678 (11): : 1639 - 1648
  • [6] Utilizing Machine Learning for Cone Penetration Test-Based Soil Classification
    Fatehnia, Milad
    Mahmoudabadi, Vahidreza
    Amiri, Sharid
    TRANSPORTATION RESEARCH RECORD, 2024, 2678 (11) : 1639 - 1648
  • [7] Design of laterally loaded piles in clays based on cone penetration test data: a reliability-based approach
    Haldar, S.
    Babu, G. L. Sivakumar
    GEOTECHNIQUE, 2009, 59 (07): : 593 - 607
  • [8] Soil classification based on unsupervised learning using cone penetration test data
    Zhang, Jinzhang
    Mao, Zhiyang
    Huang, Hongwei
    Zhang, Dongming
    GEOSHANGHAI INTERNATIONAL CONFERENCE 2024, VOL 8, 2024, 1337
  • [9] Assessing the Performance of Machine Learning Algorithms for Soil Classification Using Cone Penetration Test Data
    Chala, Ayele Tesema
    Ray, Richard
    APPLIED SCIENCES-BASEL, 2023, 13 (09):
  • [10] Soil Classification System from Cone Penetration Test Data Applying Distance-Based Machine Learning Algorithms
    Carvalho, L. O.
    Ribeiro, D. B.
    SOILS AND ROCKS, 2019, 42 (02): : 167 - 178