Research on the visualization method of lithology intelligent recognition based on deep learning using mine tunnel images

Abstract

An image processing and deep learning method for identifying different types of rock images was proposed. Preprocessing, such as rock image acquisition, gray scaling, Gaussian blurring, and feature dimensionality reduction, was conducted to extract useful feature information and recognize and classify rock images using TensorFlow-based convolutional neural network (CNN) and PyQt5. A rock image dataset was established and separated into workouts, confirmation sets, and test sets. The framework was subsequently compiled and trained. The categorization approach was evaluated using image data from the validation and test datasets, and key metrics, such as accuracy, precision, and recall, were analyzed. Finally, the classification model conducted a probabilistic analysis of the measured data to determine the equivalent lithological type for each image. The experimental results indicated that the method combining deep learning, TensorFlow-based CNN, and PyQt5 to recognize and classify rock images has an accuracy rate of up to 98.8%, and can be successfully utilized for rock image recognition. The system can be extended to geological exploration, mine engineering, and other rock and mineral resource development to more efficiently and accurately recognize rock samples. Moreover, it can match them with the intelligent support design system to effectively improve the reliability and economy of the support scheme. The system can serve as a reference for supporting the design of other mining and underground space projects.

Keywords

rock picture recognition / convolutional neural network / intelligent support for roadways / deep learning / lithology determination

References

[1] Radhakrishna BP. Changing trends of scientific practices in India in the twenty-first century. J. Geol. Soc. India, 2010, 75(6): 779.

[2] W.H. Chen, L.M. Su, X.Q. Chen, and Z.H. Huang, Rock image classification using a deep residual neural network with transfer learning, Front. Earth Sci., 10(2023), art. No. 1079447.

[3] Tsui TK, Zhang XP, Androutsos D. Color image watermarking using multidimensional Fourier transforms. IEEE Trans. Inf. Forensics Secur., 2008, 3(1): 16.

[4] Tong QX, Xue YQ, Zhang LF. Progress in hyperspectral remote sensing science and technology in China over the past three decades. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2014, 7(1): 70.

[5] Xiao BL, Miao SJ, Xia DH, Huang HT, Zhang JY. Detecting the backfill pipeline blockage and leakage through an LSTM-based deep learning model. Int. J. Miner. Metall. Mater., 2023, 30(8): 1573.

[6] D. Fu, C. Su, W.J. Wang, and R.Y. Yuan, Deep learning-based lithology classification of drill core images, PLoS One, 17(2022), No. 7, art. No. e0270826.

[7] Chen DP, Yin SH, Long WG, et al. . Heterogeneous information phase space reconstruction and stability prediction of filling body-surrounding rock combination. Int. J. Miner. Metall. Mater., 2024, 31(7): 1500.

[8] Lee JH, Kim DH, Jeong SN, Choi SH. Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm. J. Periodontal. Implant. Sci., 2018, 48(2): 114.

[9] M. Shafiq and Z.Q. Gu, Deep residual learning for image recognition: A survey, Appl. Sci., 12(2022), No. 18, art. No. 8972.

[10] Zhao XF, Wang NN, Han RC, et al. . Urban infrastructure safety system based on mobile crowdsensing. Int. J. Disaster Risk Reduct., 2018, 27: 427.

[11] Chorowski J, Chorowski J, Bahdanau D, et al. . Attention-based models for speech recognition. Proceedings of the 29th International Conference on Neural Information Processing Systems, 2015577Vol. 1

[12] S.X. Zhang, Y.Y. Yang, F.C. Sun, and B. Fang, Application of image sensing system in mineral/rock identification: Sensing mode and information process, Adv. Intell. Syst., 5(2023), No. 11, art. No. 2300206.

[13] W. Lou, D.X. Zhang, and R.C. Bayless, Review of mineral recognition and its future, Appl. Geochem., 122(2020), art. No. 104727.

[14] Wang JL, Wang FM, Zhao YY, et al. . Numerical simulation of 3D-microstructures in solidification processes based on the CAFE method. Int. J. Miner. Metall. Mater., 2009, 16(6): 640

[15] Młynarczuk M, Górszczyk A, Ślipek B. The application of pattern recognition in the automatic classification of microscopic rock images. Comput. Geosci., 2013, 60: 126.

[16] Liu XB, Wang HY, Jing HD, Shao AL, Wang LC. Research on intelligent identification of rock types based on faster R-CNN method. IEEE Access, 2020, 8: 21804.

[17] Xu ZH, Ma W, Lin P, Hua YL. Deep learning of rock microscopic images for intelligent lithology identification: Neural network comparison and selection. J. Rock Mech. Geotech. Eng., 2022, 14(4): 1140.

[18] Y.D. Wang, R.T. Armstrong, and P. Mostaghimi, Enhancing resolution of digital rock images with super resolution convolutional neural networks. J. Pet. Sci. Technol., 182(2019), art. No. 106261.

[19] Gao Y, Yu ZX, Chen WQ, Yin Q, Wu JY, Wang W. Recognition of rock materials after high-temperature deterioration based on SEM images via deep learning. J. Mater. Res. Technol., 2023, 25: 273.

[20] Z. Zhang, J.Z. Tang, B. Fan, et al., An intelligent lithology recognition system for continental shale uses digital coring images and convolutional neural networks. Geoenergy Sci. Eng., 239(2024), art. No. 212909.

[21] M. Sidorenko, D. Orlov, M. Ebadi, and D. Koroteev, Deep learning in denoising of micro-computed tomography images of rock samples, Comput. Geosci., 151(2021), art. No. 104716.

[22] Karimpouli S, Tahmasebi P. Segmentation of digital rock images using deep convolutional autoencoder networks. Comput. Geosci., 2019, 126: 142.

[23] Wang SS, Yang RS, Li YL, Yue ZW. Effects of cement content, polypropylene fiber length and dosage on fluidity and mechanical properties of fiber-toughened cemented aeolian sand backfill. Int. J. Miner. Metall. Mater., 2024, 31(11): 2404.

[24] Li XH, Cao S, Yilmaz E. Microstructural evolution and strengthening mechanism of aligned steel fiber cement-based tail backfills exposed to electromagnetic induction. Int. J. Miner. Metall. Mater., 2024, 31(11): 2390.

[25] Xue ZL, Sun HK, Gan DQ, Yan ZP, Liu ZY. Wall slip behavior of cemented paste backfill slurry during pipeline based on noncontact experimental detection. Int. J. Miner. Metall. Mater., 2023, 30(8): 1515.

[26] Hou SK, Liu YR, Yang Q. Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning. J. Rock Mech. Geotech. Eng., 2022, 14(1): 123.

[27] Zhang H, Ma CC, Jiang YP, Li TB, Pazzi V, Casagli N. Integrated processing method for microseismic signal based on deep neural network. Geophys. J. Int., 2021, 226(3): 2145.

[28] Zhu C, Xing XS, He MC, et al. . Failure behavior and strength model of blocky rock mass with and without rockbolts. Int. J. Min. Sci. Technol., 2024, 34(6): 747.

[29] F.Q. Ren, C. Zhu, Z.H. Yuan, M. Karakus, S.B. Tang, and M.C. He, Recognition of shear and tension signals based on acoustic emission parameters and waveform using machine learning methods, Int. J. Rock Mech. Min. Sci., 171(2023), art. No. 105578.

[30] Perez CA, Saravia JA, Navarro CF, Schulz DA, Aravena CM, Galdames FJ. Rock lithological classification using multiscale Gabor features from sub-images, and voting with rock contour information. Int. J. Miner. Process., 2015, 144: 56.

[31] Fan GP, Chen FX, Chen DY, Dong YQ. Recognizing multiple types of rocks quickly and accurately based on lightweight CNNs model. IEEE Access, 2020, 8: 55269.

[32] D.Y. Li, J.J. Zhao, and Z.D. Liu, A novel multitype hybrid rock lithology classification method based on convolutional neural networks, Sensors, 22(2022), No. 4, art. No. 1574.

[33] Ren QB, Wang G, Li MC, Han S. Prediction of rock compressive strength using machine learning algorithms based on spectrum analysis of geological hammer. Geotech. Geol. Eng., 2019, 37(1): 475.

[34] Y. Zhang, M.C. Li, S. Han, Q.B. Ren, and J. Shi, Intelligent identification for rock-mineral microscopic images using ensemble machine learning algorithms, Sensors, 19(2019), No. 18, art. No. 3914.

[35] M. Wu, Y.C. Ye, Q.H. Wang, and N.Y. Hu, Development of rockburst research: A comprehensive review, Appl. Sci., 12(2022), No. 3, art. No. 974.

[36] M. Trott, M. Leybourne, L. Hall, and D. Layton-Matthews, Random forest rock type classification with integration of geochemical and photographic data, Appl. Comput. Geosci., 15(2022), art. No. 100090.

[37] Ç. Suiçmez, H. Tolga Kahraman, A. Suiçmez, C. Yılmaz, and F. Balcı, Detection of melanoma with hybrid learning method by removing hair from dermoscopic images using image processing techniques and wavelet transform, Biomed. Signal Process. Control, 84(2023), art. No. 104729.

[38] Wang D, He T, Li ZR, et al. . Image feature-based affective retrieval employing improved parameter and structure identification of adaptive neuro-fuzzy inference system. Neural Comput. Appl., 2018, 29(4): 1087.

[39] Li XZ, Yu Q, Alzahrani B, et al. . Data fusion for intelligent crowd monitoring and management systems: A survey. IEEE Access, 2021, 9: 47069.

[40] L. Yu, B.B. Li, and B. Jiao, Research and implementation of CNN based on TensorFlow, IOP Conf. Ser.: Mater. Sci. Eng., 490(2019), art. No. 042022.

[41] Wang ZY, Zuo RG, Yang FF. Geological mapping using direct sampling and a convolutional neural network based on geochemical survey data. Math. Geosci., 2023, 55(7): 1035.

[42] Zhao DF, Zhang SY, Zhao YL. Recycling arsenic-containing bio-leaching residue after thermal treatment in cemented paste backfill: Structure modification, binder properties and environmental assessment. Int. J. Miner. Metall. Mater., 2024, 31(10): 2136.

[43] C. Shorten, T.M. Khoshgoftaar, and B. Furht, Text data augmentation for deep learning, J. Big Data, 8(2021), art. No. 101.

[44] Zhao L, Liu T, Peng X, Metaxas D. Maximum-entropy adversarial data augmentation for improved generalization and robustness. Proceedings of the 34th International Conference on Neural Information Processing Systems, 202014435

[45] Zhou BL, Zhou BL, Lapedriza A, et al. . Learning deep features for scene recognition using places database. Proceedings of the 28th International Conference on Neural Information Processing Systems, Vol. 1, 2014487

[46] Chen S, Yue ZQ, Tham LG. Digital image-based numerical modeling method for prediction of inhomogeneous rock failure. Int. J. Rock Mech. Min. Sci., 2004, 41(6): 939.

[47] Wang L, Han M, Li XJ, Zhang N, Cheng HD. Review of classification methods on unbalanced data sets. IEEE Access, 2021, 9: 64606.

[48] Du YX, Zhang H, Liang L, Zhang JH, Song B. Applications of machine vision in coal mine fully mechanized tunneling faces: A review. IEEE Access, 2023, 11: 102871.

[49] Abdullah-Al-Wadud M, Kabir MH, Ali Akber Dewan M, Chae O. A dynamic histogram equalization for image contrast enhancement. 2007 Digest of Technical Papers International Conference on Consumer Electronics, 20071

[50] Lim WH, Isa NAM. Color to grayscale conversion based on neighborhood pixels effect approach for digital image. ELECO 2011 7th International Conference on Electrical and Electronics Engineering, 2011157

[51] Zhang L, Shen PY, Peng XL, et al. . Simultaneous enhancement and noise reduction of a single low-light image. IET Image Proc., 2016, 10(11): 840.

[52] Yan RM, Shao L. Blind image blur estimation via deep learning. IEEE Trans. Image Process., 2016, 25(4): 1910

[53] Barton N. The shear strength of rock and rock joints. Int. J. Rock Mech. Min. Sci. Geomech. Abstr., 1976, 13(9): 255.

[54] Aloysius N, Geetha M. A review on deep convolutional neural networks. 2017 International Conference on Communication and Signal Processing (ICCSP), 20180588

[55] Ahmed U, Issa GF, Khan MA, et al. . Prediction of diabetes empowered with fused machine learning. IEEE Access, 2022, 10: 8529.

[56] Song RY, Li TY, Wang Y. Mammographic classification based on XGBoost and DCNN with multi features. IEEE Access, 2020, 8: 75011.

[57] A. Kumaravel and T. Vijayan, Comparing cost sensitive classifiers by the false-positive to false-negative ratio in diagnostic studies, Expert Syst. Appl., 227(2023), art. No. 120303.

[58] J. Mijalkovic and A. Spognardi, Reducing the false negative rate in deep learning based network intrusion detection systems, Algorithms, 15(2022), No. 8, art. No. 258.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing