JRMGE / Vol 16 / Issue 12

Article

A virtual calibration chamber for cone penetration test based on deep-learning approaches

Mingpeng Liu, Enci Sun, Ningning Zhang, Fengwen Lai, Raul Fuentes

Show More

a Institute of Geomechanics and Underground Technology, RWTH Aachen University, Aachen, 52074, Germany
b School of Qilu Transportation, Shandong University, Jinan, 250061, China
c College of Civil Engineering, Fuzhou University, Fuzhou, 350116, China


2024, 16(12): 5179-5192. doi:10.1016/j.jrmge.2024.10.004


Received: 2023-08-10 / Revised: 2024-10-02 / Accepted: 2024-10-21 / Available online: 2024-10-31

2024, 16(12): 5179-5192.

doi:10.1016/j.jrmge.2024.10.004


Received: 2023-08-10

Revised: 2024-10-02

Accepted: 2024-10-21

Available online: 2024-10-31


Abstract:

The interpretation of the cone penetration test (CPT) still relies largely on empirical correlations that have been predominantly developed in resource-intensive and time-consuming calibration chambers. This paper presents a CPT virtual calibration chamber using deep learning (DL) approaches, which allow for the consideration of depth-dependent cone resistance profiles through the implementation of two proposed strategies: (1) depth-resistance mapping using a multilayer perceptron (MLP) and (2) sequence-to-sequence training using a long short-term memory (LSTM) neural network. Two DL models are developed to predict cone resistance profiles (qc) under various soil states and testing conditions, where Bayesian optimization (BO) is adopted to identify the optimal hyperparameters. Subsequently, the BO-MLP and BO-LSTM networks are trained using the available data from published datasets. The results show that the models with BO can effectively improve the prediction accuracy and efficiency of neural networks compared to those without BO. The two training strategies yielded comparable results in the testing set, and both can be used to reproduce the whole cone resistance profile. An extended comparison and validation of the prediction results are carried out against numerical results obtained from a coupled Eulerian-Lagrangian (CEL) model, demonstrating a high degree of agreement between the DL and CEL models. Ultimately, to demonstrate the usability of this new virtual calibration chamber, the predicted qc is used to enhance the preceding correlations with the relative density (Dr) of the sand. The improved correlation with superior generalization has an R2 of 82% when considering all data, and 89.6% when examining the pure experimental data.

Download PDF:


Keywords: Cone penetration test (CPT), Virtual calibration chamber, Bayesian optimization (BO), Multilayer perceptron (MLP), Long short-term memory (LSTM) network

Show Figure(s)


Supplementary Material

Download Document:


Share and Cite

Mingpeng Liu, Enci Sun, Ningning Zhang, Fengwen Lai, Raul Fuentes, 2024. A virtual calibration chamber for cone penetration test based on deep-learning approaches. J. Rock Mech. Geotech. Eng. 16 (12), 5179-5192.

Author(s) Information

Fengwen Lai

✉️ laifengwen@fzu.edu.cn

Dr. Fengwen Lai is currently an Assistant Professor in the College of Civil Engineering at Fuzhou University, China. He obtained his PhD degree at Southeast University in July 2023. From November 2021 to February 2024, he worked as a researcher at the Geo-Section of the Delft University of Technology. From March 2022 to May 2022, he undertook a visit to the Institute of Soil Mechanics, Foundation Engineering and Computational Geotechnics of the Graz University of Technology. His background is in analytical modeling – standard finite element method – filed monitoring. His research interests lie in the field of soil–structure interaction (SSI), which encompasses a range of problems involving large displacements in various contexts, including off- and on-shore geotechnical engineering, deep excavations/tunneling, retaining structures, and trapdoor problems. His research has been published in more than 30 peer-reviewed journals specializing in geotechnical engineering, including Géotechnique, Canadian Geotechnical Journal, Journal of Rock Mechanics and Geotechnical Engineering, Tunneling and Underground Space Technology, and Computer and Geotechnics.