A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium
Accurate acquisition of the rock stress is crucial for various rock engineering applications. The hollow inclusion (HI) technique is widely used for measuring in-situ rock stress. This technique calculates the stress tensor by measuring strain using an HI strain cell. However, existing analytical so...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | International Journal of Mining Science and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095268625000321 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850049671382171648 |
|---|---|
| author | Changkun Qin Wusheng Zhao Weizhong Chen Peiyao Xie Shuai Zhou |
| author_facet | Changkun Qin Wusheng Zhao Weizhong Chen Peiyao Xie Shuai Zhou |
| author_sort | Changkun Qin |
| collection | DOAJ |
| description | Accurate acquisition of the rock stress is crucial for various rock engineering applications. The hollow inclusion (HI) technique is widely used for measuring in-situ rock stress. This technique calculates the stress tensor by measuring strain using an HI strain cell. However, existing analytical solutions for stress calculation based on an HI strain cell in a double-layer medium are not applicable when an HI strain cell is used in a three-layer medium, leading to erroneous stress calculations. To address this issue, this paper presents a method for calculating stress tensors in a three-layer medium using numerical simulations, specifically by obtaining a constitutive matrix that relates strain measurements to stress tensors in a three-layer medium. Furthermore, using Latin hypercube sampling (LHS) and orthogonal experimental design strategies, 764 groups of numerical models encompassing various stress measurement scenarios have been established and calculated using FLAC3D software. Finally, a surrogate model based on artificial neural network (ANN) was developed to predict constitutive matrices, achieving a goodness of fit (R2) of 0.999 and a mean squared error (MSE) of 1.254. A software program has been developed from this surrogate model for ease of use in practical engineering applications. The method’s accuracy was verified through numerical simulations, analytical solution and laboratory experiment, demonstrating its effectiveness in calculating stress in a three-layer medium. The surrogate model was applied to calculate mining-induced stress in the roadway roof rock of a coal mine, a typical case for stress measurement in a three-layer medium. Errors in stress calculations arising from the use of existing analytical solutions were corrected. The study also highlights the significant errors associated with using double-layer analytical solutions in a three-layer medium, which could lead to inappropriate engineering design. |
| format | Article |
| id | doaj-art-24a3e268af6f4fb4a3a00e53e6b6aec1 |
| institution | DOAJ |
| issn | 2095-2686 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Mining Science and Technology |
| spelling | doaj-art-24a3e268af6f4fb4a3a00e53e6b6aec12025-08-20T02:53:40ZengElsevierInternational Journal of Mining Science and Technology2095-26862025-03-0135336338110.1016/j.ijmst.2025.02.003A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer mediumChangkun Qin0Wusheng Zhao1Weizhong Chen2Peiyao Xie3Shuai Zhou4State Key Laboratory of Geomechanics and Geotechnical Engineering Safety, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaCorresponding author.; State Key Laboratory of Geomechanics and Geotechnical Engineering Safety, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering Safety, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering Safety, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaState Key Laboratory of Geomechanics and Geotechnical Engineering Safety, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; University of Chinese Academy of Sciences, Beijing 100049, ChinaAccurate acquisition of the rock stress is crucial for various rock engineering applications. The hollow inclusion (HI) technique is widely used for measuring in-situ rock stress. This technique calculates the stress tensor by measuring strain using an HI strain cell. However, existing analytical solutions for stress calculation based on an HI strain cell in a double-layer medium are not applicable when an HI strain cell is used in a three-layer medium, leading to erroneous stress calculations. To address this issue, this paper presents a method for calculating stress tensors in a three-layer medium using numerical simulations, specifically by obtaining a constitutive matrix that relates strain measurements to stress tensors in a three-layer medium. Furthermore, using Latin hypercube sampling (LHS) and orthogonal experimental design strategies, 764 groups of numerical models encompassing various stress measurement scenarios have been established and calculated using FLAC3D software. Finally, a surrogate model based on artificial neural network (ANN) was developed to predict constitutive matrices, achieving a goodness of fit (R2) of 0.999 and a mean squared error (MSE) of 1.254. A software program has been developed from this surrogate model for ease of use in practical engineering applications. The method’s accuracy was verified through numerical simulations, analytical solution and laboratory experiment, demonstrating its effectiveness in calculating stress in a three-layer medium. The surrogate model was applied to calculate mining-induced stress in the roadway roof rock of a coal mine, a typical case for stress measurement in a three-layer medium. Errors in stress calculations arising from the use of existing analytical solutions were corrected. The study also highlights the significant errors associated with using double-layer analytical solutions in a three-layer medium, which could lead to inappropriate engineering design.http://www.sciencedirect.com/science/article/pii/S2095268625000321Stress measurementOver-coring stress relief methodThree-layer mediumSurrogate modelNumerical simulation |
| spellingShingle | Changkun Qin Wusheng Zhao Weizhong Chen Peiyao Xie Shuai Zhou A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium International Journal of Mining Science and Technology Stress measurement Over-coring stress relief method Three-layer medium Surrogate model Numerical simulation |
| title | A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium |
| title_full | A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium |
| title_fullStr | A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium |
| title_full_unstemmed | A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium |
| title_short | A surrogate model for estimating rock stress by a hollow inclusion strain cell in a three-layer medium |
| title_sort | surrogate model for estimating rock stress by a hollow inclusion strain cell in a three layer medium |
| topic | Stress measurement Over-coring stress relief method Three-layer medium Surrogate model Numerical simulation |
| url | http://www.sciencedirect.com/science/article/pii/S2095268625000321 |
| work_keys_str_mv | AT changkunqin asurrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT wushengzhao asurrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT weizhongchen asurrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT peiyaoxie asurrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT shuaizhou asurrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT changkunqin surrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT wushengzhao surrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT weizhongchen surrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT peiyaoxie surrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium AT shuaizhou surrogatemodelforestimatingrockstressbyahollowinclusionstraincellinathreelayermedium |