Identification of failure behaviors of underground structures under dynamic loading using machine learning
Understanding the dynamic responses of hard rocks is crucial during deep mining and tunneling activities and when constructing nuclear waste repositories. However, the response of deep massive rocks with openings of different shapes and orientations to dynamic loading is not well understood. Therefo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Journal of Rock Mechanics and Geotechnical Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1674775524002634 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526303479562240 |
|---|---|
| author | Chun Zhu Yingze Xu Manchao He Yujing Jiang Murat Karakus Lihua Hu Yalong Jiang Fuqiang Ren |
| author_facet | Chun Zhu Yingze Xu Manchao He Yujing Jiang Murat Karakus Lihua Hu Yalong Jiang Fuqiang Ren |
| author_sort | Chun Zhu |
| collection | DOAJ |
| description | Understanding the dynamic responses of hard rocks is crucial during deep mining and tunneling activities and when constructing nuclear waste repositories. However, the response of deep massive rocks with openings of different shapes and orientations to dynamic loading is not well understood. Therefore, this study investigates the dynamic responses of hard rocks of deep underground excavation activities. Split Hopkins Pressure Bar (SHPB) tests on granite with holes of different shapes (rectangle, circle, vertical ellipse (elliptical short (ES) axis parallel to the impact load direction), and horizontal ellipse (elliptical long (EL) axis parallel to the impact load direction)) were carried out. The influence of hole shape and location on the dynamic responses was analyzed to reveal the rocks' dynamic strengths and cracking characteristics. We used the ResNet18 (convolutional neural network-based) network to recognize crack types using high-speed photographs. Moreover, a prediction model for the stress-strain response of rocks with different openings was established using Deep Neural Network (DNN). The results show that the dynamic strengths of the granite with EL and ES holes are the highest and lowest, respectively. The strength-weakening coefficient decreases first and then increases with an increase of thickness-span ratio (h/L). The weakening of the granite with ES holes is the most obvious. The ResNet18 network can improve the analyzing efficiency of the cracking mechanism, and the trained model's recognition accuracy reaches 99%. Finally, the dynamic stress-strain prediction model can predict the complete stress-strain curve well, with an accuracy above 85%. |
| format | Article |
| id | doaj-art-d1def9df291f466b94b9a7f692add176 |
| institution | Kabale University |
| issn | 1674-7755 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Rock Mechanics and Geotechnical Engineering |
| spelling | doaj-art-d1def9df291f466b94b9a7f692add1762025-01-17T04:49:10ZengElsevierJournal of Rock Mechanics and Geotechnical Engineering1674-77552025-01-01171414431Identification of failure behaviors of underground structures under dynamic loading using machine learningChun Zhu0Yingze Xu1Manchao He2Yujing Jiang3Murat Karakus4Lihua Hu5Yalong Jiang6Fuqiang Ren7School of Earth Sciences and Engineering, Hohai University, Nanjing, 210098, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, 210098, China; State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing, 400044, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, 210098, China; State Key Laboratory for Geomechanics & Deep Underground Engineering, Xuzhou, 221116, ChinaGraduate School of Engineering, Nagasaki University, Bunkyo, Nagasaki, 852-8521, JapanSchool of Civil, Environmental and Mining Engineering, The University of Adelaide, Adelaide, 5005, SA, AustraliaState Key Laboratory for Geomechanics & Deep Underground Engineering, Xuzhou, 221116, ChinaState Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure, East China Jiaotong University, Nanchang, 330013, ChinaState Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing, 400044, China; State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure, East China Jiaotong University, Nanchang, 330013, China; School of Civil Engineering, University of Science and Technology Liaoning, Anshan, 114051, China; Corresponding author. State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing, 400044, China.Understanding the dynamic responses of hard rocks is crucial during deep mining and tunneling activities and when constructing nuclear waste repositories. However, the response of deep massive rocks with openings of different shapes and orientations to dynamic loading is not well understood. Therefore, this study investigates the dynamic responses of hard rocks of deep underground excavation activities. Split Hopkins Pressure Bar (SHPB) tests on granite with holes of different shapes (rectangle, circle, vertical ellipse (elliptical short (ES) axis parallel to the impact load direction), and horizontal ellipse (elliptical long (EL) axis parallel to the impact load direction)) were carried out. The influence of hole shape and location on the dynamic responses was analyzed to reveal the rocks' dynamic strengths and cracking characteristics. We used the ResNet18 (convolutional neural network-based) network to recognize crack types using high-speed photographs. Moreover, a prediction model for the stress-strain response of rocks with different openings was established using Deep Neural Network (DNN). The results show that the dynamic strengths of the granite with EL and ES holes are the highest and lowest, respectively. The strength-weakening coefficient decreases first and then increases with an increase of thickness-span ratio (h/L). The weakening of the granite with ES holes is the most obvious. The ResNet18 network can improve the analyzing efficiency of the cracking mechanism, and the trained model's recognition accuracy reaches 99%. Finally, the dynamic stress-strain prediction model can predict the complete stress-strain curve well, with an accuracy above 85%.http://www.sciencedirect.com/science/article/pii/S1674775524002634Dynamic mechanical responseCracking modeHole shape/location effectDeep Neural Network (DNN)Stress-strain prediction |
| spellingShingle | Chun Zhu Yingze Xu Manchao He Yujing Jiang Murat Karakus Lihua Hu Yalong Jiang Fuqiang Ren Identification of failure behaviors of underground structures under dynamic loading using machine learning Journal of Rock Mechanics and Geotechnical Engineering Dynamic mechanical response Cracking mode Hole shape/location effect Deep Neural Network (DNN) Stress-strain prediction |
| title | Identification of failure behaviors of underground structures under dynamic loading using machine learning |
| title_full | Identification of failure behaviors of underground structures under dynamic loading using machine learning |
| title_fullStr | Identification of failure behaviors of underground structures under dynamic loading using machine learning |
| title_full_unstemmed | Identification of failure behaviors of underground structures under dynamic loading using machine learning |
| title_short | Identification of failure behaviors of underground structures under dynamic loading using machine learning |
| title_sort | identification of failure behaviors of underground structures under dynamic loading using machine learning |
| topic | Dynamic mechanical response Cracking mode Hole shape/location effect Deep Neural Network (DNN) Stress-strain prediction |
| url | http://www.sciencedirect.com/science/article/pii/S1674775524002634 |
| work_keys_str_mv | AT chunzhu identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT yingzexu identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT manchaohe identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT yujingjiang identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT muratkarakus identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT lihuahu identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT yalongjiang identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning AT fuqiangren identificationoffailurebehaviorsofundergroundstructuresunderdynamicloadingusingmachinelearning |