Abstract
The 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.
Highlights
The initial in situ stress field influences underground engineering design and construction
This paper introduces the generative adversarial network (GAN) to fine-tune lateral stress coefficients in ancient times to optimize the present in situ stress field to meet the demand of engineering analysis
The in situ stress field of the Shuangjiangkou Hydropower Station is mainly composed of tectonic stress and gravity stress, and its distribution is affected by the tectonic stress, geological structure and topography
Summary
The stress field in deep-cut valley area evolves from an ancient regional stress field, accompanied by river valley erosion, surface denudation and other geological effects to shape the valley slope in a long-term unloading process, prompting the rock mass to constantly adjust stress, strain and energy to form a new local stress field[42]. Since the ancient stress field is approximately estimated, there may be a large error in obtaining the present stress field To solve this problem, this paper introduces the generative adversarial network (GAN) to fine-tune lateral stress coefficients in ancient times to optimize the present in situ stress field to meet the demand of engineering analysis. (4) The coordinates of the measurement point, present burial depth, present lateral stress coefficient and regression factors in ancient times are regarded as real data sample. (5) After training in GAN, regression factors ai and bi of the optimized ancient lateral stress coefficients can be obtained. Kj is the lateral stress coefficient matrix of the measured points at present and j is the number of uniform design tests.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
