scholarly journals Inversion Method of Initial In Situ Stress Field Based on BP Neural Network and Applying Loads to Unit Body

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Xiaopeng Li ◽  
Xuejun Zhou ◽  
Zhengxuan Xu ◽  
Tao Feng ◽  
Dong Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Stress Field ◽  
Principal Stress ◽  
Bp Neural Network ◽  
In Situ Stress ◽  
Inversion Method ◽  
Linear Regression Method ◽  
Underground Engineering ◽  
In Situ Stress Field

The initial in situ stress field is the fundamental factor causing the deformation and failure of underground engineering and is an important basis for the feasibility analysis, design, and construction of underground engineering. However, it is difficult to obtain the whole in situ stress field of large-scale underground engineering in difficult and dangerous areas by field measurement. In view of the fact that the measured in situ stress components (σxx, σyy, σzz, τxy, τxz, τyz) of Sichuan-Tibet Railway in China are linear with the buried depth, a method is proposed to solve the in situ stress by applying corresponding loads to all unit bodies in the calculation area based on BP neural network and FLAC3D. Through this method, the in situ stress of the tunnel is inverted. The results show that both the maximum principal stress and minimum principal stress increase with the increase of buried depth, and when the tunnel passes through faults or anticlines, the main stress will suddenly drop. Furthermore, compared with the results of the multiple linear regression method, it is found that the proposed method has higher accuracy; especially for the simulation of the maximum horizontal principal stress and vertical stress, the average relative error is reduced by 26.44% and 77.27%, respectively. The research in this paper can provide a new idea for the initial in situ stress inversion of engineering.

scholarly journals GAN inversion method of an initial in situ stress field based on the lateral stress coefficient

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Li Qian ◽  
Tianzhi Yao ◽  
Zuguo Mo ◽  
Jianhai Zhang ◽  
Yonghong Li ◽  
...  
Keyword(s):  
Stress Field ◽  
In Situ Stress ◽  
Inversion Method ◽  
Burial Depth ◽  
Lateral Stress ◽  
Distribution Law ◽  
Underground Engineering ◽  
Generative Adversarial Network ◽  
In Situ Stress Field

AbstractThe initial in situ stress field influences underground engineering design and construction. Since the limited measured data, it is necessary to obtain an optimized stress field. Although the present stress field can be obtained by valley evolution simulation, the accuracy of the ancient stress field has a remarkable influence. This paper proposed a method using the generative adversarial network (GAN) to obtain optimized lateral stress coefficients of the ancient stress field. A numerical model with flat ancient terrain surfaces is established. Utilizing the nonlinear relationship between measured stress components and present burial depth, lateral stress coefficients of ancient times are estimated to obtain the approximate ancient stress field. Uniform designed numerical tests are carried out to simulate the valley evolution by excavation. Coordinates, present burial depth, present lateral stress coefficients and ancient regression factors of lateral stress coefficients are input to GAN as real samples for training, and optimized ancient regression factors can be predicted. The present stress field is obtained by excavating strata layers. Numerical results show the magnitude and distribution law of the present stress field match well with measured points, thus the proposed method for the stress field inversion is effective.

Measurement and the Distribution Law of In Situ Stresses at Deep Depth of Xingcun Coal Mine

2012 ◽  
Vol 450-451 ◽  
pp. 1601-1607 ◽  
Author(s):  
Jiong Wang ◽  
Zhi Biao Guo ◽  
Feng Zhou ◽  
Feng Bin Su ◽  
Bao Liang Li
Keyword(s):  
Stress Field ◽  
Principal Stress ◽  
Coal Mine ◽  
Stress Measurement ◽  
In Situ Stress ◽  
Distribution Law ◽  
Principal Stresses ◽  
In Situ Stress Measurement ◽  
In Situ Stress Field

Many kinds of in situ stress measurement methods are used nowadays, two most common of which are the overcoring and the hydraulic fracturing methods. In order to study the distribution law of in situ stress field in the deep position of Xingcun coal mine, 4 points of in situ stress measurement were carried out in underground roadways at the -1200 m level adopting the overcoring method. The hollow included technique was used to measure the 4 points of in-situ stress. According to the analysis of the measurement data, the results indicated that: (1) Among the three principal stresses on all measurement points, two principal stresses were nearly horizontal and one was nearly vertical. Furthermore, the maximum horizontal principal stress was more than the vertical principal stress, and the magnitude of vertical stress was equal to the weight of overburden rock mass;(2)The value of the maximum horizontal principal stress reached 52.3 MPa , the directions mainly concentrated on the extension of N42°W – N85°W, and the obliquity mainly concentrated on the extension of -29° – 10°;(3)The ratio of maximum horizontal principal stress to vertical principal stress was 1.42 - 1.64 with an average value of 1.55. The result presented that the in situ stress field in Xingcun coalmine at the depth of -1200m was dominated by tectonic horizontal stress. According to the results above, we gained the in situ stress states and the distribution law in the measured region. At the same time, it can offer reasonable basic parameters for underground roadway layout and support design of Xingcun coalmine.

Inverse Analysis of Regional In Situ Stress Prediction Based on Multi-Points Measurement and BP Neural Network

2014 ◽  
Vol 510 ◽  
pp. 226-231 ◽  
Author(s):  
Wei Qun Liu ◽  
Ting Song ◽  
Yu Shou Li ◽  
Shu Fei Zheng ◽  
Jing Yang
Keyword(s):  
Neural Network ◽  
Stress Field ◽  
In Situ Stress ◽  
Engineering Problem ◽  
Regional Stress ◽  
Geological Conditions ◽  
Stress Prediction ◽  
Stress Estimation ◽  
In Situ Stress Field

Based on the measurement of in-situ stress and engineering-geological conditions, we built computing models with pre-exerting boundary loads and simulated the regional stress field involved. Boundary loads can be approximately determined by use of the multiple linear regressions, and be further optimized with the artificial neural network. By calculation, the corresponding initial in-situ stress field can reach ideal accuracy. As an example, we inversely analyzed an engineering problem in Chinese Wo-bei mine. The results shows that the simulation can meet the point measurement very well, and the regional-stress estimation may play an important role in engineering.

scholarly journals Local Stress Field Correction Method Based on a Genetic Algorithm and a BP Neural Network for In Situ Stress Field Inversion

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Tianzhi Yao ◽  
Zuguo Mo ◽  
Li Qian ◽  
Jianhua He ◽  
Jianhai Zhang
Keyword(s):  
Stress Field ◽  
Bp Neural Network ◽  
Local Stress ◽  
In Situ Stress ◽  
Regression Method ◽  
Geological Conditions ◽  
Multiple Regression Method ◽  
In Situ Stress Field ◽  
Local Stress Field

The in situ stress field is the fundamental factor causing deformation and damage in geotechnical engineering, so it is the main basis for underground engineering design and excavation. However, it is difficult to accurately obtain the in situ stress through most existing inversion methods in areas with complex geological conditions. For the problem of a relatively discrete and nonlinear relationship of measured stress in the Yebatan Hydropower Station area, a new in situ stress inversion method called the local stress field correction (LSFC) method combining a genetic algorithm (GA), backpropagation (BP) neural network, and submodel method is proposed. The inverted in situ stress results produced by this method show that the distribution of in situ stress is greatly influenced by tectonic movements in the Yebatan area, there is no obvious linear relationship with depth, and the stress release phenomenon occurs at the faults. By comparison with the multiple regression method, it is found that the method still has high inversion accuracy under complex geological conditions, and the average relative error of LSFC inversion results is 17.05%, which is much lower than the value of 43.58% via the multiple regression method. Therefore, the LSFC method can be used for the inversion of in situ stress in complex geological regions and provide a reference for engineering design and construction.

scholarly journals Characteristics of the In Situ Stress Field and Engineering Effect along the Lijiang to Shangri-La Railway on the Southeastern Tibetan Plateau, China

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Chunyang Chai ◽  
Sixiang Ling ◽  
Xiyong Wu ◽  
Ting Hu ◽  
Dai Sun
Keyword(s):  
Tibetan Plateau ◽  
Stress Field ◽  
Principal Stress ◽  
Pressure Coefficient ◽  
In Situ Stress ◽  
Burial Depth ◽  
The Tibetan Plateau ◽  
Rock Masses ◽  
In Situ Stress Field

This work aims to characterize the in situ stress field along the Lijiang to Shangri-La railway and identify possible engineering geological problems when constructing tunnels along this railway on the margin of the Tibetan Plateau. The in situ stress measured at 76 points in 12 boreholes by the hydraulic fracturing method was analysed. A rose diagram of the maximum principal stress direction was plotted based on the measured in situ stress data. The results show that the measured in situ stress is mainly horizontal stress, corresponding to a strike-slip fault-related tectonic stress field with a moderate to high in situ stress value. The main stress values have a good linear relationship with the burial depth, and the maximum horizontal principal stress (σH) increases by 1.1–8.8 MPa per 100 m, with an average gradient value of 3.6 MPa per 100 m. The maximum and minimum horizontal principal stresses and the stress differences increase with depth, and the lateral pressure coefficient (σH/ σ v ) is generally 1–1.5. The ratio of the maximum and minimum effective stresses is less than the threshold at which faulting occurs, resulting in faults that are relatively stable at present. The direction of the maximum horizontal principal stress is oriented at a small angle to the axial direction of the deeply buried tunnel along the railway line; therefore, the tunnel sidewalls could readily deform during the construction process. Rock bursts are expected to occur in strong rock masses with high risk grades, whereas slight to moderate deformation of the rock surrounding the tunnel is expected to occur in weak rock masses. This study has significance for understanding the regional fault activity and issues related to the construction of deeply buried tunnels along the Lijiang to Shangri-La railway.

Sign in / Sign up

Export Citation Format

Share Document