Characterization for three-dimensional stress of roadway roof through physics-informed neural network on monitoring data

被引：1

作者：

Tan X.-Y. ^{[1
,2
]}

Zhao W.-S. ^{[1
,2
]}

Chen W.-Z. ^{[1
,2
]}

Gao H. ^{[1
,2
]}

机构：

[1] State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan

[2] University of Chinese Academy of Sciences, Beijing

来源：

Tunnelling and Underground Space Technology | 2023年 / 142卷

基金：

中国国家自然科学基金;

关键词：

Machine learning; Monitoring; Neural network; Stress; Underground engineering;

D O I：

10.1016/j.tust.2023.105390

中图分类号：

学科分类号：

摘要：

Characterizing the mechanical status of underground engineering is crucial for preventing structural disasters and ensuring safe operation. However, it is difficult to sense the three-dimensional stress of the whole structure due to the limitation of sensor and monitoring technology, and the existing sensing methods lack the support of mechanical mechanism. Therefore, we aim to develop a three-dimensional stress sensing method for the whole roadway roof using an energy modified physics-informed neural network (EPINN) on sparse fiber optical monitoring data. First, the sensor monitoring and numerical simulation are used to provide structural mechanical information. Then, EPINN is formulized on the sparse monitoring data and constricted by the physical correlations captured from numerical simulation. Moreover, the strain energy is adopted to modify the pure data-driven model. To indicate the reliability of the presented model, the on-site experiment and the comparison experiments with some widely used models are conducted. Experimental results show that EPINN model can better characterize the overall stress distribution of roadway roof, and the sensing error is much smaller than the existing model. The method is reliable. © 2023 Elsevier Ltd

引用

共 38 条

[1] Behrooz R., Mostafa S., Feng X.T., A comprehensive underground excavation design (CUED) methodology for geotechnical engineering design of deep underground mining and tunneling, Int. J. Rock Mech. Min. Sci., 143, (2021)
[2] Bisdom K., Nick H.M., Bertotti G., Bertotti. An Integrated Workflow for Stress and Flow Modelling Using Outcrop-Derived Discrete Fracture Networks, Comput. Geosci., 103, pp. 21-35, (2017)
[3] Chen M.X., Elasticity and Plasticity, (2007)
[4] Du B.W., Li W.T., Tan X.Y., Ye J.C., Chen W.Z., Sun L.L., Development of Load-Temporal Model to Predict the Further Mechanical Behaviors of Tunnel Structure Under Various Boundary Conditions, Tunnelling and Underground Space Technology, 116, pp. 1-9, (2021)
[5] Du B., Ye J., Zhu H., Sun L., Du Y., Intelligent monitoring system based on spatio-temporal data for underground space infrastructure, Eng. Eng., (2022)
[6] Fekete S., Diederichs M., Integration of three-dimensional laser scanning with discontinuum modelling for stability analysis of tunnels in blocky rockmasses, Int. J. Rock Mech. Min. Sci., 57, pp. 11-23, (2013)
[7] Gao H., Zhao W.S., Chen W.Z., Xie P.Y., Zhong K., Qin C.K., Continuous three-dimensional stress monitoring in roof of coal mines for investigating the rockburst control effect with hydraulic fracturing, Environ. Earth Sci., 81, 17, (2022)
[8] He S.D., Li Y.R., Aydin A., A comparative study of UDEC simulations of an unsupported rock tunnel, Tunn. Undergr. Space Technol., 72, pp. 242-249, (2018)
[9] Jong S.C., Ong D.E.L., Oh E., State-of-the-art review of geotechnical-driven artificial intelligence techniques in underground soil-structure interaction, Tunn. Undergr. Space Technol., 113, (2021)
[10] Kaiser P.K., Yazici S., Maloney S., Mining-induced stress change and consequences of stress path on excavation stability –a case study, Int. J. Rock Mech. Min. Sci., 38, 2, pp. 167-180, (2001)

← 1 2 3 4 →