Intelligent rating method of tunnel surrounding rock based on one-dimensional convolutional neural network

2021 ◽  
pp. 1-19
Author(s):  
Gang Yang ◽  
Tianbin Li ◽  
Chunchi Ma ◽  
Lubo Meng ◽  
Hang Zhang ◽  
...  
Keyword(s):  
Sampling Error ◽  
Structural Data ◽  
Surrounding Rock ◽  
Classification Model ◽  
Tunnel Construction ◽  
Tunnel Engineering ◽  
Rock Classification ◽  
One Dimensional ◽  
Rating Method ◽  
Encoding Method

Accurate prediction of surrounding rock grades holds great significance to tunnel construction. This paper proposed an intelligent classification method for surrounding rocks based on one-dimensional convolutional neural networks (1D CNNs). Six indicators collected in some tunnel construction sites are considered, and the degree of linear correlation between these indicators has been analyzed. The improved one-hot encoding method is put forward for transforming these non-image indicators into one-dimensional structural data and avoiding the sampling error in the indicators of surrounding rock collected in the field. We found that the 1D CNNs model based on the improved one-hot encoding method can best extract the features of surrounding rock classification indicators (in terms of both accuracy and efficiency). We applied the well-trained classification model of tunnel surrounding rock to a series of expressway tunnels in China, and the results show that our model could accurately predict the surrounding rock grade and has great application value in the construction of tunnel engineering. It provides a new research idea for the prediction of surrounding rock grades in tunnel engineering.

Stability Analysis of Surrounding Rock Based on QGA-SVM

2014 ◽  
Vol 1065-1069 ◽  
pp. 199-203
Author(s):  
Fu Dong Xie ◽  
Wei Min Yang ◽  
Dao Hong Qiu ◽  
Yi Li
Keyword(s):  
Stability Analysis ◽  
Solution Space ◽  
Surrounding Rock ◽  
Classification Model ◽  
Support Vector ◽  
Rock Classification ◽  
Quantum Genetic Algorithm ◽  
Stability Of Surrounding Rock ◽  
Practical Engineering ◽  
The Stability

In order to analyze the stability of surrounding rock accurately and effectively, a rock classification method based on QGA (quantum genetic algorithm)-SVM (support vector machine) is put forward. QGA was used for global search in the solution space to optimize the kernel function parameters of SVM. And this method improved the classification accuracy of SVM in rock classification. Finally, a rock classification model based on QGA-SVM was established and applied to practical engineering. The result shows that the improved SVM has a higher accuracy in stability analysis of surrounding rock.

Study of Tunnel Surrounding Rock Classification Based on Drifting Degree and Uncertainty Measurement

2013 ◽  
Vol 353-356 ◽  
pp. 1427-1432
Author(s):  
Lan Hu ◽  
Tao Li ◽  
Wen Ge Qiu
Keyword(s):  
Evaluation Method ◽  
Comprehensive Evaluation ◽  
Measurement Theory ◽  
Surrounding Rock ◽  
Classification Model ◽  
Rock Classification ◽  
Evaluation Standard ◽  
Uncertainty Measurement ◽  
Practical Engineering ◽  
Contrast Analysis

Based on contrast analysis of tunnel surrounding rock classification method, five basic indicators were selected as evaluation factors. Evaluation matrix was constructed by uncertainty measurement theory. Weight was established by introducing drifting degree concept. The principle of maximum membership degree was choosed as evaluation criterion.Then a tunnel surrounding rock classification model was built.This comprehensive evaluation method made full use of its own parameters and evaluation standard to completely avoid the subjective influence of traditional weights determination and the sample set, making itself more objectivity and accuracy, having a strong operability. The practical engineering showed that this model applied to tunnel surrounding rock classification was feasible and had certain superiority, providing a new way for tunnel surrounding rock classification.

scholarly journals Intelligent Classification Model of Surrounding Rock of Tunnel using Drilling and Blasting Method

2020 ◽  
Author(s):  
Mingnian Wang ◽  
Siguang Zhao ◽  
Jianjun Tong ◽  
Zhilong Wang ◽  
Meng Yao ◽  
...  
Keyword(s):  
Surrounding Rock ◽  
Classification Model ◽  
Blasting Method

Field Monitoring of Surrounding Rock Stress in Tunnel Construction

2012 ◽  
Vol 170-173 ◽  
pp. 1735-1739
Author(s):  
Ying Na Dong ◽  
Qiang Huang
Keyword(s):  
Spatial Effect ◽  
Field Monitoring ◽  
Surrounding Rock ◽  
Tunnel Construction ◽  
Rock Stress ◽  
Vibrating Wire ◽  
Stress Variation ◽  
Stress Changes ◽  
Tunnel Diameter ◽  
Surrounding Rock Stress

The surrounding rock stress field monitor has been done in excavation by vibrating wire transducer. The field monitoring data are compared with numerical simulation results. The result shows: Vibrating wire transducer can record the stress variation of surrounding rock and support. Surrounding rock stress changes violently at every excavation step, such as lower bench excavation, the stress variation is mainly controlled by the spatial effect. When the distance from excavation face to the monitoring section is more than a tunnel diameter, the rock stress variation is mainly affected by time and it is relatively smooth and continuous.

Application of ABAQUS in Surrounding Rock Stability Analysis of Shallow Large Cross-Section Tunnel

2015 ◽  
Vol 777 ◽  
pp. 8-12 ◽  
Author(s):  
Lin Zhen Cai ◽  
Cheng Liang Zhang
Keyword(s):  
Numerical Simulation ◽  
Rock Mass ◽  
Strong Support ◽  
Surrounding Rock ◽  
Tunnel Engineering ◽  
Tunnel Excavation ◽  
Rock Stability ◽  
Rock Bolting ◽  
Excavation Support ◽  
The Stability

HuJiaDi tunnel construction of Dai Gong highway is troublesome, the surrounding-rock mass give priority to full to strong weathering basalt, surrounding rock integrity is poor, weak self-stability of surrounding rock, and tunnel is prone to collapse. In order to reduce disturbance, taking advantage of the ability of rock mass, excavation adopt the method of "more steps, short footage and strong support". The excavation method using three steps excavation, The excavation footage is about 1.2 ~ 1.5 m; The surrounding rock bolting system still produce a large deformation after completion of the first support construction, it shows that the adopted support intensity cannot guarantee the stability of the tunnel engineering. Using ABAQUS to simulate tunnel excavation support, optimizing the support parameters of the tunnel, conducting comparative analysis with Monitoring and Measuring and numerical simulation results, it shows that the displacement - time curves have a certain consistency in numerical simulation of ABAQUS and Monitoring and Measuring.

Back Analysis for Mass Parameters of Tunnel Surrounding Rock

2012 ◽  
Vol 170-173 ◽  
pp. 20-24 ◽  
Author(s):  
Kai Cui ◽  
Xue Kai Pan
Keyword(s):  
Deformation Mechanism ◽  
Strain Softening ◽  
Back Analysis ◽  
Surrounding Rock ◽  
Tunnel Engineering ◽  
Railway Tunnel ◽  
Displacement Back Analysis ◽  
Information Construction ◽  
Engineering Information ◽  
The Common

Tunnel engineering information construction has been widely used, and the back analysis is its core. As the common useful method, displacement back analysis is of special advantages. This paper introduces the calculative method based on the application in a railway tunnel. The result shows that strain softening model can be used to simulate the large deformation mechanism of surrounding rock.

Emission transition of greenhouse gases with the surrounding rock weakened – A case study of tunnel construction

2019 ◽  
Vol 209 ◽  
pp. 169-179 ◽  
Author(s):  
Jianfeng Xu ◽  
Chun Guo ◽  
Xiaofeng Chen ◽  
Zhenhua Zhang ◽  
Lu Yang ◽  
...  
Keyword(s):  
Greenhouse Gases ◽  
Surrounding Rock ◽  
Tunnel Construction ◽  
Emission Transition

Time Series Forecasting of Tunnel Surrounding Rock Displacement

2011 ◽  
Vol 261-263 ◽  
pp. 1789-1793 ◽  
Author(s):  
Guang Xiang Mao ◽  
Yuan You Xia ◽  
Ling Wei Liu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Bp Neural Network ◽  
Time Series Prediction ◽  
Surrounding Rock ◽  
Tunnel Construction ◽  
Rock Stress ◽  
Rock Types ◽  
Network Time ◽  
Tunnel Depth

In the process of tunnel construction, because the rock stress redistribute, the vault and the two groups will generate displacement constantly. This paper adopts the genetic algorithm to optimize the weight and threshold of BP neural network, taking the tunnel depth, rock types and part measured values of displacement as input parameters to construct a neural network time series prediction model of tunnel surrounding rock displacement. The method proposed in the paper has been applied in the Ma Tou Tang tunnel construction successfully, and the results show that the model can predict the displacement of the surrounding rock quickly and accurately.

Sign in / Sign up

Export Citation Format

Share Document