Skip to main content
SpringerLink
Log in

Quantitative Identification of Mesoscopic Failure Mechanism in Granite by Deep Learning Method Based on SEM Images

  • Original Paper
  • Published:
Rock Mechanics and Rock Engineering Aims and scope Submit manuscript

Abstract

Tensile and shear fractures are fundamental brittle fractures that are usually observed in rock failure processes. Investigating the mesoscopic morphology of shear and tensile fractures is useful for revealing the macroscopic failure mechanism of rock. This paper presented a quantitative method based on scanning electron microscopy (SEM) images and deep learning to identify the mesoscopic failure mechanism of granite, which can obtain the distribution of tensile and shear fractures on failure surfaces. For this purpose, preset angle shear and direct tensile tests were conducted to obtain the shear and tensile fracture surfaces, which were observed by SEM. These SEM images were cropped to form three image databases with different fields of view. Deep learning models (AlexNet) were developed based on training and validation images. Testing performances suggested that the developed AlexNet models had superior capabilities to identify tensile and shear fracture surfaces (accuracy 96–98%). The characteristics of tensile and shear fractures learned by AlexNet models were extracted by the integrated gradients algorithm. Additionally, AlexNet models were implemented to quantitatively evaluate the distribution of tensile and shear fractures in rock fragmentations caused by uniaxial compression load. The evaluation results showed that the proportion of shear fracture in the shear cone was 66.1–95.8%, and the proportion of tensile fracture in the spalling piece was 75–94.9%. The results verified the application of the proposed method, which was beneficial to prove the hypothesis of the failure mechanism of rock under uniaxial compression.

Highlights

  • Propose a quantitative method to identify the mesoscopic failure mechanism in granite based on SEM images and deep learning.

  • Develop the AlexNet models to quantitatively identify tensile and shear fractures in granite.

  • Analyze the mesoscopic characteristics of tensile and shear fractures based on an integrated gradients algorithm.

  • Apply AlexNet models to identify the distribution of tensile and shear fractures on rock fragments under uniaxial compression.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25

Similar content being viewed by others

Data availability

The data that support the fndings of this study are available on request from the corresponding author.

References

  • Basu A, Mishra DA, Roychowdhury K (2013) Rock failure modes under uniaxial compression, Brazilian, and point load tests. Bull Eng Geol Env 72(3):457–475

    Google Scholar 

  • Bisai R, Palaniappan SK, Pal SK (2020) Effects of high-temperature heating and cryogenic quenching on the physico-mechanical properties of limestone. SN Appl Sci 2(2):158

    Google Scholar 

  • Chen Y-L, Wang S-R, Ni J, Azzam R, Fernández-steeger TM (2017) An experimental study of the mechanical properties of granite after high temperature exposure based on mineral characteristics. Eng Geol 220:234–242

    Google Scholar 

  • Chen G, Li T, Li G, Qin CA, He Y (2018) Influence of temperature on the brittle failure of granite in deep tunnels determined from triaxial unloading tests. Eur J Environ Civ Eng 22(Supp 1):s269–s285

    Google Scholar 

  • Chen J, Zhou H, Zeng Z, Lu J (2020) Macro- and microstructural characteristics of the tension-shear and compression-shear fracture of granite. Rock Mech Rock Eng 53(1):201–209

    Google Scholar 

  • Ding JY, Liu JD, Li C, Yi HY (2013) Failure mechanism of layered salt rock in three-point bending test. Appl Mech Mater 256–259:48–56

    Google Scholar 

  • Dong L, Tong X, Li X, Zhou J, Wang S, Liu B (2019) Some developments and new insights of environmental problems and deep mining strategy for cleaner production in mines. J Clean Prod 210:1562–1578

    Google Scholar 

  • Einstein HH (2021) Fractures: tension and shear. Rock Mech Rock Eng 54(7):3389–3408

    Google Scholar 

  • Einstein HH, Dershowitz WS (1990) Tensile and shear fracturing in predominantly compressive stress fields—a review. Eng Geol 29(2):149–172

    Google Scholar 

  • Fakhimi A, Hemami B (2015) Axial splitting of rocks under uniaxial compression. Int J Rock Mech Min Sci 79:124–134

    Google Scholar 

  • Fonseka GM, Murrell SAF, Barnes P (1985) Scanning electron microscope and acoustic emission studies of crack development in rocks. Int J Rock Mech Min Sci Geomech Abstr 22(5):273–289

    Google Scholar 

  • Hoek E, Martin CD (2014) Fracture initiation and propagation in intact rock—a review. J Rock Mech Geotech Eng 6(4):287–300

    Google Scholar 

  • Huang L-Q, Wang J, Momeni A, Wang S-F (2021) Spalling fracture mechanism of granite subjected to dynamic tensile loading. Trans Nonferrous Met Soc China 31(7):2116–2127

    Google Scholar 

  • Jiang Q, Yang B, Yan F, Xu D, Feng G, Li S (2021) Morphological features and fractography analysis for in situ spalling in the China Jinping underground laboratory with a 2400 m burial depth. Tunn Undergr Space Technol 118:104194

    Google Scholar 

  • Kazerani T (2013) Effect of micromechanical parameters of microstructure on compressive and tensile failure process of rock. Int J Rock Mech Min Sci 64:44–55

    Google Scholar 

  • Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems

  • Lai Y, Zhao K, He Z, Yu X, Yan Y, Li Q, Shao H, Zhang X, Zhou Y (2022). Fractal characteristics of rocks and mesoscopic fractures at different loading rates. Geomech Energy Environ 2022:100431

  • Li D, Li CC, Li X (2011) Influence of sample height-to-width ratios on failure mode for rectangular prism samples of hard rock loaded in uniaxial compression. Rock Mech Rock Eng 44(3):253–267

    Google Scholar 

  • Li D, Ma J, Wan Q, Zhu Q, Han Z (2021a) Effect of thermal treatment on the fracture toughness and subcritical crack growth of granite in double-torsion test. Eng Fract Mech 253:107903

    Google Scholar 

  • Li X, Chen S, Wang E, Li Z (2021b) Rockburst mechanism in coal rock with structural surface and the microseismic (MS) and electromagnetic radiation (EMR) response. Eng Fail Anal 124:105396

    Google Scholar 

  • Li B, Yu S, Yang L, Zhu W, Xue Y, Feng D, Wang C, Chen Y (2022a) Multiscale fracture characteristics and failure mechanism quantification method of cracked rock under true triaxial compression. Eng Fract Mech 262:108257

    Google Scholar 

  • Li D, Liu Z, Armaghani DJ, Xiao P, Zhou J (2022b) Novel ensemble intelligence methodologies for rockburst assessment in complex and variable environments. Sci Rep 12(1):1844

    Google Scholar 

  • Li D, Liu Z, Armaghani DJ, Xiao P, Zhou J (2022c) Novel ensemble tree solution for rockburst prediction using deep forest. Mathematics 10(5):787

    Google Scholar 

  • Li D, Liu Z, Xiao P, Zhou J, Jahed Armaghani D (2022d) Intelligent rockburst prediction model with sample category balance using feedforward neural network and Bayesian optimization. Undergr Space 7(5):833–846

    Google Scholar 

  • Li D, Su X, Gao F, Liu Z (2022e) Experimental studies on physical and mechanical behaviors of heated rocks with pre-fabricated hole exposed to different cooling rates. Geomech Geophys Geoenergy Georesour 8(4):125

    Google Scholar 

  • Li D, Zhang C, Zhu Q, Ma J, Gao F (2022f) Deformation and fracture behavior of granite by the short core in compression method with 3D digital image correlation. Fatigue Fract Eng Mater Struct 45(2):425–440

    Google Scholar 

  • Li D, Zhao J, Liu Z (2022g) A novel method of multitype hybrid rock lithology classification based on convolutional neural networks. Sensors 22(4):1574

    Google Scholar 

  • Li D, Zhao J, Ma J (2022h) Experimental studies on rock thin-section image classification by deep learning-based approaches. Mathematics 10(13):2317

    Google Scholar 

  • Liu K, Ostadhassan M (2017) Multi-scale fractal analysis of pores in shale rocks. J Appl Geophys 140:1–10

    Google Scholar 

  • Liu Z, Zhou H, Zhang W, Xie S, Shao J (2019) A new experimental method for tensile property study of quartz sandstone under confining pressure. Int J Rock Mech Min Sci 123:104091

    Google Scholar 

  • Liu R, Zhu Z, Li Y, Liu B, Wan D, Li M (2020) Study of rock dynamic fracture toughness and crack propagation parameters of four brittle materials under blasting. Eng Fract Mech 225:106460

    Google Scholar 

  • Liu S, Lan H, Martin CD (2022a) Progressive transition from extension fracture to shear fracture of altered granite during uniaxial tensile tests. Rock Mech Rock Eng 55:5355–5375

    Google Scholar 

  • Liu Z, Ma C, Wei X-A (2022c) Electron scanning characteristics of rock materials under different loading methods: a review. Geomech Geophys Geoenergy Georesour 8(2):80

    Google Scholar 

  • Liu Z, Ma C, Wei XA, Xie W (2022d) Experimental study of rock subjected to triaxial extension. Rock Mech Rock Eng 55(2):1069–1077

    Google Scholar 

  • Liu Z, Armaghani D-J, Fakharian P, Li D, Ulrikh D-V, Orekhova N-N, Khedher K-M (2022b) Rock strength estimation using several tree-based ML techniques. Comput Model Eng Sci 133(3):799–824

  • Luo S, Gong F (2023) Evaluation of energy storage and release potentials of highly stressed rock pillar from rockburst control perspectives. Int J Rock Mech Min Sci 163:105324

    Google Scholar 

  • Ma J, Li D, Zhu Q, Liu M, Wan Q (2022) The mode I fatigue fracture of fine-grained quartz-diorite under coupled static loading and dynamic disturbance. Theoret Appl Fract Mech 117:103140

    Google Scholar 

  • Mahanta B, Tripathy A, Vishal V, Singh TN, Ranjith PG (2017) Effects of strain rate on fracture toughness and energy release rate of gas shales. Eng Geol 218:39–49

    Google Scholar 

  • Meng B, Jing H, Chen K, Su H (2013) Failure mechanism and stability control of a large section of very soft roadway surrounding rock shear slip. Int J Min Sci Technol 23(1):127–134

    Google Scholar 

  • Mighani S, Sondergeld CH, Rai CS (2016) Observations of tensile fracturing of anisotropic rocks. SPE J 21(04):1289–1301

    Google Scholar 

  • Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) PyTorch: an imperative style, high-performance deep learning library. In: Wallach H, Larochelle H, Beygelzimer A, d'Alché-Buc F, Fox E, Garnett R (eds), Advances in neural information processing systems, vol 32. Curran Associates, Inc., New York, pp 8024–8035

  • Ramsey JM, Chester FM (2004) Hybrid fracture and the transition from extension fracture to shear fracture. Nature 428(6978):63–66

    Google Scholar 

  • Rao Q-H, Sun Z-Q, Wang G-Y, Xu J-C, Zhang J-Y (2001) Microscopic characteristics of different fracture modes of brittle rock. J Cent South Univ Technol 8(3):175–179

    Google Scholar 

  • Rao Q, Sun Z, Stephansson O, Li C, Stillborg B (2003) Shear fracture (Mode II) of brittle rock. Int J Rock Mech Min Sci 40(3):355–375

    Google Scholar 

  • Stacey TR (1981) A simple extension strain criterion for fracture of brittle rock. Int J Rock Mech Min Sci Geomech Abstr 18(6):469–474

    Google Scholar 

  • Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: International conference on machine learning, pp 3319–3328

  • Tang H-D (2020) Multi-scale crack propagation and damage acceleration during uniaxial compression of marble. Int J Rock Mech Min Sci 131:104330

    Google Scholar 

  • Tang CA, Liu H, Lee PKK, Tsui Y, Tham LG (2000) Numerical studies of the influence of microstructure on rock failure in uniaxial compression—part I: effect of heterogeneity. Int J Rock Mech Min Sci 37(4):555–569

    Google Scholar 

  • Tao R, Sharifzadeh M, Zhang Y, Feng X-T (2020) Analysis of mafic rocks microstructure damage and failure process under compression test using quantitative scanning electron microscopy and digital images processing. Eng Fract Mech 231:107019

    Google Scholar 

  • Wagner H (2019) Deep mining: a rock engineering challenge. Rock Mech Rock Eng 52(5):1417–1446

    Google Scholar 

  • Waibel A (1989) Modular construction of time-delay neural networks for speech recognition. Neural Comput 1(1):39–46

    Google Scholar 

  • Wang P, Xu J, Fang X, Wen M, Zheng G, Wang P (2017) Dynamic splitting tensile behaviors of red-sandstone subjected to repeated thermal shocks: deterioration and micro-mechanism. Eng Geol 223:1–10

    Google Scholar 

  • Wang H, Dyskin A, Pasternak E, Dight P (2022) Possible mechanism of spallation in rock samples under uniaxial compression. Eng Fract Mech 269:108577

    Google Scholar 

  • Xiao P, Li D, Zhao G, Liu H (2021a) New criterion for the spalling failure of deep rock engineering based on energy release. Int J Rock Mech Min Sci 148:104943

    Google Scholar 

  • Xiao P, Li D, Zhao G, Liu M (2021b) Experimental and numerical analysis of mode I fracture process of rock by semi-circular bend specimen. Mathematics 9(15):1769

    Google Scholar 

  • Xiao P, Liu H, Zhao G (2023) Characteristics of ground pressure disaster and rockburst proneness in deep gold mine. Lithosphere 2022(Special 11):1

  • Yan J, Zou Z, Guo S, Zhang Q, Hu X, Luo T (2022) Mechanical behavior and damage constitutive model of granodiorite in a deep buried tunnel. Bull Eng Geol Env 81(3):118

    Google Scholar 

  • Yu Q, Xiong Z, Du C, Dai Z, Soltanian MR, Soltanian M, Yin S, Liu W, Liu C, Wang C, Song Z (2020) Identification of rock pore structures and permeabilities using electron microscopy experiments and deep learning interpretations. Fuel 268:117416

    Google Scholar 

  • Zhai S, Su G, Yin S, Zhao B, Yan L (2020) Rockburst characteristics of several hard brittle rocks: a true triaxial experimental study. J Rock Mech Geotech Eng 12(2):279–296

    Google Scholar 

  • Zhang QB, Zhao J (2013) Effect of loading rate on fracture toughness and failure micromechanisms in marble. Eng Fract Mech 102:288–309

    Google Scholar 

  • Zheng Z, Feng X-T, Yang C-X, Zhang X-W, Li S-J, Qiu S-L (2020) Post-peak deformation and failure behaviour of Jinping marble under true triaxial stresses. Eng Geol 265:105444

    Google Scholar 

  • Zhou Z, Cai X, Ma D, Chen L, Wang S, Tan L (2018) Dynamic tensile properties of sandstone subjected to wetting and drying cycles. Constr Build Mater 182:215–232

    Google Scholar 

  • Zhu Q, Li D, Han Z, Li X, Zhou Z (2019) Mechanical properties and fracture evolution of sandstone specimens containing different inclusions under uniaxial compression. Int J Rock Mech Min Sci 115:33–47

    Google Scholar 

  • Zhu Q, Ma C, Li X, Li D (2021) Effect of filling on failure characteristics of diorite with double rectangular holes under coupled static-dynamic loads. Rock Mech Rock Eng 54(6):2741–2761

    Google Scholar 

  • Zhu Q, Li D, Han Z, Xiao P, Li B (2022a) Failure characteristics of brittle rock containing two rectangular holes under uniaxial compression and coupled static-dynamic loads. Acta Geotech 17(1):131–152

    Google Scholar 

  • Zhu Q, Li X, Li D, Ma C (2022b) Experimental investigations of static mechanical properties and failure characteristics of damaged diorite after dynamic triaxial compression. Int J Rock Mech Min Sci 153:105106

    Google Scholar 

  • Zuo J-P, Wang X-S, Mao D-Q (2014) SEM in-situ study on the effect of offset-notch on basalt cracking behavior under three-point bending load. Eng Fract Mech 131:504–513

    Google Scholar 

Download references

Acknowledgements

The present research was financially supported by the National Natural Science Foundation of China (52074349).

Author information

Authors and Affiliations

  1. School of Resources and Safety Engineering, Central South University, Changsha, 410083, Hunan, China

    Diyuan Li, Zida Liu, Quanqi Zhu, Chenxi Zhang, Peng Xiao & Jinyin Ma

Authors
  1. Diyuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zida Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Quanqi Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chenxi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Peng Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jinyin Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zida Liu.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, D., Liu, Z., Zhu, Q. et al. Quantitative Identification of Mesoscopic Failure Mechanism in Granite by Deep Learning Method Based on SEM Images. Rock Mech Rock Eng 56, 4833–4854 (2023). https://doi.org/10.1007/s00603-023-03307-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00603-023-03307-1

Keywords

Search

Navigation