Stability Prediction of Soil Slopes Based on Digital Twinning and Deep Learning

被引:8
作者
Chen, Gongfa [1 ]
Kang, Xiaoyu [1 ]
Lin, Mansheng [1 ]
Teng, Shuai [1 ]
Liu, Zongchao [2 ]
机构
[1] Guangdong Univ Technol, Sch Civil & Transportat Engn, Guangzhou 510006, Peoples R China
[2] Guangzhou Univ, Sch Civil Engn, Guangzhou 510006, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 11期
关键词
slope stability; digital twins; convolutional neural network; safety factor; non-circular slip surface; RELIABILITY;
D O I
10.3390/app13116470
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
This paper proposes a slope stability prediction model based on deep learning and digital twinning methods. To establish a reliable slope database, 30 actual slopes were collected, and 100 digital twin (DT) models were generated for each actual slope by fine-tuning the slope profiles. The safety factors of all slope samples were calculated using the Limit Equilibrium Methods (LEMs). A convolutional neural network (CNN) regression model was established, and the root mean square error (RMSE) was used as the evaluation indicator. In order to find an excellent CNN model, the K-fold (K = 10) cross-validation was used to compare the predictive effect of 1D CNN and 2D CNN on the slope safety factor. On this basis, CNN models with different network depths were compared. The results showed that the 2D CNN model with six convolutional layers had the best network prediction effect for the slope dataset. To validate the generalization ability of the model, an actual slope was input into the CNN model; its prediction result was 1.0229, and the absolute error with its real safety factor (1.0197) was 0.0032. With the slope stability prediction model proposed in this paper, the safety factor of slopes can be obtained from their geological and physical data, which greatly simplifies the calculation of the safety factor and has great engineering significance.
引用
收藏
页数:24
相关论文
共 30 条
[1]   Locating Global Critical Slip Surface Using the Morgenstern-Price Method and Optimization Technique [J].
Bai, Tao ;
Qiu, Tong ;
Huang, Xiaoming ;
Li, Chang .
INTERNATIONAL JOURNAL OF GEOMECHANICS, 2014, 14 (02) :319-325
[2]   Optimizing Levenberg-Marquardt backpropagation technique in predicting factor of safety of slopes after two-dimensional OptumG2 analysis [J].
Bui, Xuan-Nam ;
Muazu, Mohammed Abdullahi ;
Hoang Nguyen .
ENGINEERING WITH COMPUTERS, 2020, 36 (03) :941-952
[3]   Prediction of slope stability using multiple linear regression (MLR) and artificial neural network (ANN) [J].
Chakraborty, Arunav ;
Goswami, Diganta .
ARABIAN JOURNAL OF GEOSCIENCES, 2017, 10 (17)
[4]   A simplified method for 3D slope stability analysis [J].
Chen, ZY ;
Mi, HL ;
Zhang, FM ;
Wang, XG .
CANADIAN GEOTECHNICAL JOURNAL, 2003, 40 (03) :675-683
[5]   EXTENSIONS TO THE GENERALIZED-METHOD OF SLICES FOR STABILITY ANALYSIS [J].
CHEN, ZY ;
MORGENSTERN, NR .
CANADIAN GEOTECHNICAL JOURNAL, 1983, 20 (01) :104-119
[6]   Classification of slopes and prediction of factor of safety using differential evolution neural networks [J].
Das, Sarat Kumar ;
Biswal, Rajani Kanta ;
Sivakugan, N. ;
Das, Bitanjaya .
ENVIRONMENTAL EARTH SCIENCES, 2011, 64 (01) :201-210
[7]  
Duncan J.M., 2005, SOIL STRENGTH SLOPE
[8]   Comparative Approaches to Probabilistic Finite Element Methods for Slope Stability Analysis [J].
Dyson, Ashley P. ;
Tolooiyan, Ali .
SIMULATION MODELLING PRACTICE AND THEORY, 2020, 100
[9]  
Erzin Y, 2014, GEOMECH ENG, V6, P1
[10]   Reliability analysis of a rock slope based on plastic limit analysis theory with multiple failure modes [J].
Li, Ze ;
Hu, Zheng ;
Zhang, Xiaoyan ;
Du, Shigui ;
Guo, Yakun ;
Wang, Junxing .
COMPUTERS AND GEOTECHNICS, 2019, 110 :132-147