Hui Liu, Xinyue Dai, Gengshe Yang, Yanjun Shen, Pengzhi Pan, Jiami Xi, Borong Li, Bo Liang, Yao Wei, Huiqi Huang
{"title":"结合CT图像和深度学习技术的冻融岩石损伤演化特征","authors":"Hui Liu, Xinyue Dai, Gengshe Yang, Yanjun Shen, Pengzhi Pan, Jiami Xi, Borong Li, Bo Liang, Yao Wei, Huiqi Huang","doi":"10.1007/s10064-024-04010-3","DOIUrl":null,"url":null,"abstract":"<div><p>The surrounding rock of tunnel engineering in an alpine mountainous environment is prone to frequent freeze–thaw action due to fissure water and temperature differential, which leads to crack propagation and even failure in rock. Freezing sandstone CT damage-free scanning studies were conducted. Based on deep learning theory, the U-Net network technique is utilized to naturally merge high-resolution properties of frozen rock CT images in the shrinking path with low-resolution characteristics in the expansion path. Intelligent detection of freezing rock fissures and geometric information parameters at the pixel level has been accomplished. The primary fracture structure and its parameters of the sandstone with natural damage during the freeze–thaw process are obtained, and the pixel-level intelligent identification of the meso-structure and geometric information parameters of the freeze–thaw rock fracture is realized. This justifies the classification of naturally cracked rock under load and freeze–thaw as a discrete time-dimensional evolution system. The dynamic process and mechanical characteristics of meso-damage propagation of naturally fractured rock under freeze–thaw and compression load are investigated using Casrock numerical computation software, which is based on the cellular automata theory. The results reveal that when the number of freeze–thaw cycles rises, the random rate of fracture network structure distribution increases, the uniformity of fracture distribution increases, and the dominating direction decreases. The sandstone's secondary fractures progressively increase as the fracture dominant angle rises, and the rock sample's failure mode eventually shifts from tensile failure to compression-shear mixed failure. When the comprehensive dominant angle of fracture is 60°, the fracture of freeze–thaw rock is more prone to expansion and its mechanical strength deteriorates more. The fractured rock creates narrow strip directional damage along the end of the original fracture when subjected to compressive load, exhibiting typical localization features. The main crack and the secondary crack dominate the crack progression. The number of secondary fractures inside sandstone steadily grows as the fracture's comprehensive dominant angle increases. The direction of the crack penetration development is determined by the comprehensive dominating angle of the fracture.</p></div>","PeriodicalId":500,"journal":{"name":"Bulletin of Engineering Geology and the Environment","volume":"84 1","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Damage evolution characteristics of freeze–thaw rock combined with CT image and deep learning technology\",\"authors\":\"Hui Liu, Xinyue Dai, Gengshe Yang, Yanjun Shen, Pengzhi Pan, Jiami Xi, Borong Li, Bo Liang, Yao Wei, Huiqi Huang\",\"doi\":\"10.1007/s10064-024-04010-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The surrounding rock of tunnel engineering in an alpine mountainous environment is prone to frequent freeze–thaw action due to fissure water and temperature differential, which leads to crack propagation and even failure in rock. Freezing sandstone CT damage-free scanning studies were conducted. Based on deep learning theory, the U-Net network technique is utilized to naturally merge high-resolution properties of frozen rock CT images in the shrinking path with low-resolution characteristics in the expansion path. Intelligent detection of freezing rock fissures and geometric information parameters at the pixel level has been accomplished. The primary fracture structure and its parameters of the sandstone with natural damage during the freeze–thaw process are obtained, and the pixel-level intelligent identification of the meso-structure and geometric information parameters of the freeze–thaw rock fracture is realized. This justifies the classification of naturally cracked rock under load and freeze–thaw as a discrete time-dimensional evolution system. The dynamic process and mechanical characteristics of meso-damage propagation of naturally fractured rock under freeze–thaw and compression load are investigated using Casrock numerical computation software, which is based on the cellular automata theory. The results reveal that when the number of freeze–thaw cycles rises, the random rate of fracture network structure distribution increases, the uniformity of fracture distribution increases, and the dominating direction decreases. The sandstone's secondary fractures progressively increase as the fracture dominant angle rises, and the rock sample's failure mode eventually shifts from tensile failure to compression-shear mixed failure. When the comprehensive dominant angle of fracture is 60°, the fracture of freeze–thaw rock is more prone to expansion and its mechanical strength deteriorates more. The fractured rock creates narrow strip directional damage along the end of the original fracture when subjected to compressive load, exhibiting typical localization features. The main crack and the secondary crack dominate the crack progression. The number of secondary fractures inside sandstone steadily grows as the fracture's comprehensive dominant angle increases. The direction of the crack penetration development is determined by the comprehensive dominating angle of the fracture.</p></div>\",\"PeriodicalId\":500,\"journal\":{\"name\":\"Bulletin of Engineering Geology and the Environment\",\"volume\":\"84 1\",\"pages\":\"\"},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-12-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bulletin of Engineering Geology and the Environment\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10064-024-04010-3\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ENVIRONMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin of Engineering Geology and the Environment","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10064-024-04010-3","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
Damage evolution characteristics of freeze–thaw rock combined with CT image and deep learning technology
The surrounding rock of tunnel engineering in an alpine mountainous environment is prone to frequent freeze–thaw action due to fissure water and temperature differential, which leads to crack propagation and even failure in rock. Freezing sandstone CT damage-free scanning studies were conducted. Based on deep learning theory, the U-Net network technique is utilized to naturally merge high-resolution properties of frozen rock CT images in the shrinking path with low-resolution characteristics in the expansion path. Intelligent detection of freezing rock fissures and geometric information parameters at the pixel level has been accomplished. The primary fracture structure and its parameters of the sandstone with natural damage during the freeze–thaw process are obtained, and the pixel-level intelligent identification of the meso-structure and geometric information parameters of the freeze–thaw rock fracture is realized. This justifies the classification of naturally cracked rock under load and freeze–thaw as a discrete time-dimensional evolution system. The dynamic process and mechanical characteristics of meso-damage propagation of naturally fractured rock under freeze–thaw and compression load are investigated using Casrock numerical computation software, which is based on the cellular automata theory. The results reveal that when the number of freeze–thaw cycles rises, the random rate of fracture network structure distribution increases, the uniformity of fracture distribution increases, and the dominating direction decreases. The sandstone's secondary fractures progressively increase as the fracture dominant angle rises, and the rock sample's failure mode eventually shifts from tensile failure to compression-shear mixed failure. When the comprehensive dominant angle of fracture is 60°, the fracture of freeze–thaw rock is more prone to expansion and its mechanical strength deteriorates more. The fractured rock creates narrow strip directional damage along the end of the original fracture when subjected to compressive load, exhibiting typical localization features. The main crack and the secondary crack dominate the crack progression. The number of secondary fractures inside sandstone steadily grows as the fracture's comprehensive dominant angle increases. The direction of the crack penetration development is determined by the comprehensive dominating angle of the fracture.
期刊介绍:
Engineering geology is defined in the statutes of the IAEG as the science devoted to the investigation, study and solution of engineering and environmental problems which may arise as the result of the interaction between geology and the works or activities of man, as well as of the prediction of and development of measures for the prevention or remediation of geological hazards. Engineering geology embraces:
• the applications/implications of the geomorphology, structural geology, and hydrogeological conditions of geological formations;
• the characterisation of the mineralogical, physico-geomechanical, chemical and hydraulic properties of all earth materials involved in construction, resource recovery and environmental change;
• the assessment of the mechanical and hydrological behaviour of soil and rock masses;
• the prediction of changes to the above properties with time;
• the determination of the parameters to be considered in the stability analysis of engineering works and earth masses.