Meticulous evaluation of rock mass quality in mine engineering based on machine learning of core photos
-
摘要: 矿山工程为了获取准确的资源储量而进行的地质钻探往往会获取大量的岩芯图像,从中提取岩体结构信息进行岩体质量评价具有现实的工程意义。目前人工对钻孔岩芯进行岩石质量指标RQD的编录方法效率低下且受主观因素影响,为此首先使用Mask-RCNN深度学习实例分割网络从钻孔岩芯图像中自动识别出单排岩芯,进而从单排岩芯中识别出长度大于等于10 cm的岩芯段,进行RQD的计算；然后结合钻孔信息与地质模型,使用普通克里金插值得到可表征RQD非均匀性的块体模型,实现对岩体质量的精细化评价。乌山铜钼矿的应用结果表明深度学习方法可以准确地从岩芯图像中计算出RQD,同时地质统计学的使用可以有效地对岩体质量进行精细化表征,提出的方法在矿山工程中具有广泛的应用前景。Abstract: In mining engineering, the geological drilling boreholes are used to obtain accurate reserves of mineral resources, and many core photos are gathered in this process. It has a practical engineering significance to get the structural information from those core photos in order to evaluate rock mass quality. However, the current manual method for geological borehole logging is inefficient, and the results are usually affected by subjective factors. A method for evaluation of rock mass quality is proposed using the Mask-RCNN deep learning instance segmentation network. Firstly, the core strips are cut from the core photos automatically, and the core segments longer than 10 cm are identified from those core strips, then the rock quality designation RQD is calculated. Finally, using the information of boreholes and the geological model, the ordinary Kriging method is employed to get a heterogenous RQD block model to achieve a meticulous evaluation of rock mass quality. The case study in Wushan Copper and Molybdenum Mine indicates that the machine learning method can accurately calculate the RQD from core photos, and the geostatistical method can effectively evaluate the rock mass quality. The results show that the rock mass quality evaluation based on deep learning is consistent with the actual situation, and the proposed method has a wide range of application prospects in mining engineering.
-
Keywords:
- deep learning /
- core photo /
- boreholes logging /
- RQD /
- rock mass quality evaluation /
- geostatistics
-
-
![]()
图 6 乌山铜钼矿钻孔RQD编录（2019年底地表）
Figure 6. RQD logging of boreholes in Wushan Copper and Molybdenum Mine (surface in the end of 2019)
-
[1] LIU F Y, YANG T H, ZHOU J R, et al. Spatial variability and time decay of rock mass mechanical parameters: a landslide study in the Dagushan open-pit mine[J]. Rock Mechanics and Rock Engineering. 2020, 53(7): 3031-3053. doi: 10.1007/s00603-020-02109-z
[2] STAVROPOULOU M, EXADAKTYLOS G, SARATSIS G. A combined three-dimensional geological geostatistical numerical model of underground excavations in rock[J]. Rock Mechanics and Rock Engineering, 2007, 40(3): 213-243. doi: 10.1007/s00603-006-0125-4
[3] GUO J T, WU L X, ZHANG M M, et al. Towards automatic discontinuity trace extraction from rock mass point cloud without triangulation[J]. International Journal of Rock Mechanics and Mining Sciences, 2018, 112: 226-237. doi: 10.1016/j.ijrmms.2018.10.023
[4] RIQUELME A, ABELLAN A, TOMAS R, et al. A new approach for semi-automatic rock mass joints recognition from 3D point clouds[J]. Computers and Geosciences, 2014, 68: 38-52. doi: 10.1016/j.cageo.2014.03.014
[5] 詹伟, 章杨松. 基于图像处理的岩体结构面迹线半自动检测[J]. 岩土工程技术, 2020, 34(1): 7-12. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGJ202001002.htm ZHAN Wei, ZHANG Yang-song. Semi-automatic detection of rock mass discontinuity trace based on image processing[J]. Geotechnical Engineering Technique, 2020, 34(1): 7-12. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTGJ202001002.htm
[6] 邹先坚, 王川婴, 韩增强, 等. 全景钻孔图像中结构面全自动识别方法研究[J]. 岩石力学与工程学报, 2017, 36(8): 1910-1920. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201708010.htm ZHOU Xian-jian, WANG Chuan-ying, HAN Zeng-qiang, et al. Fully automatic identifying the structural planes with panoramic images of boreholes[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(8): 1910-1920. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201708010.htm
[7] 周永章, 王俊, 左仁广, 等. 地质领域深度学习、深度学习及实现语言[J]. 岩石学报, 2018, 34(11): 3173-3178. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXB201811002.htm ZHOU Yong-zhang, WANG Jun, ZUO Ren-guang, et al. Machine learning, deep learning and Python language in field of geology[J]. Acta Petrologica Sinica, 34(11): 3173-3178. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXB201811002.htm
[8] ZHANG K, HOU R B, ZHANG G H, et al. Rock drillability assessment and lithology classification based on the operating parameters of a drifter: case study in a coal mine in China[J]. Rock Mechanics and Rock Engineering, 2016, 49(1): 329-334. doi: 10.1007/s00603-015-0723-0
[9] 李明超, 符家科, 张野, 等. 耦合岩石图像与锤击音频的岩性分类智能识别分析方法[J]. 岩石力学与工程学报, 2020, 39(5): 996-1004. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202005013.htm LI Ming-chao, FU Jia-ke, ZHANG Ye, et al. Intelligent recognition and analysis method of rock lithology classification based on coupled rock images and hammering audios[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(5): 996-1004. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX202005013.htm
[10] 王鹏宇, 王述红. 四类常见边坡岩石类别识别和边界范围确定的方法[J]. 岩土工程学报, 2019, 41(8): 1505-1512. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201908018.htm WANG Peng-yu, WANG Shu-hong. Method for identifying four common rock types of slopes and determining boundary range[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(8): 1505-1512. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201908018.htm
[11] 张夏林, 师志龙, 吴冲龙, 等. 基于移动设备的野外地质大数据智能采集和可视化技术[J]. 地质科技通报, 2020, 39(4): 21-28. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202004003.htm ZHANG Xia-lin, SHI Zhi-long, WU Chong-long, et al. Intelligent data acquisition and visualization technology of field geology based on mobile device[J]. Bulletin of Geological Science and Technology, 2020, 39(4): 21-28. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202004003.htm
[12] 郑帅, 姜谙男, 张峰瑞, 等. 基于深度学习与可靠度算法的围岩动态分级方法及其工程应用[J]. 岩土力学, 2019, 40(增刊1): 308-318. ZHENG Shuai, JIANG An-nan, ZHANG Rui-feng, et al. Dynamic classification method of surrounding rock and its engineering application based on machine learning and reliability algorithm[J]. Rock and Soil Mechanics, 2019, 40(S1): 308-318. (in Chinese)
[13] 柳厚祥, 李汪石, 查焕奕, 等. 基于深度学习技术的公路隧道围岩分级方法[J]. 岩土工程学报, 2018, 40(10): 1809-1817. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201810008.htm LIU Hou-xiang, LI Wang-shi, ZHA Zhuan-yi, et al. Method for surrounding rock mass classification of highway tunnels based on deep learning technology[J]. Chinese Journal of Geotechnical Engineering, 2018, 40(10): 1809-1817. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201810008.htm
[14] 王运敏. 现代采矿手册[M]. 北京: 冶金工业出版社, 2011. WANG Yun-min. Modern Mining Manual[M]. Beijing: Metallurgical Industry Press, 2011. (in Chinese)
[15] MAYER J M, STEAD D. A comparison of traditional, step-path, and geostatistical techniques in the stability analysis of a large open pit[J]. Rock Mechanics and Rock Engineering, 2017, 50: 927-949.
[16] EIVAZY H, ESMAIELI K, JEAN R Modeling geomechanical heterogeneity of rock masses using direct and indirect geostatistical conditional simulation methods[J]. Rock Mechanics and Rock Engineering 2017, 50: 3175-3195.
[17] HE K, GKIOXARI G, PIOTR D, et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision (ICCV), 2017, Venice: 2980-2988.
[18] 陈昌彦, 王贵荣. 各类岩体质量评价方法的相关性探讨[J]. 岩石力学与工程学报, 2002, 21(12): 1894-1900. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX200212033.htm CHEN Chang-yan, WANG Gui-rong. Discussion on the interrelation of various rock mass quality classification systems at home and abroad[J]. Chinese Journal of Rock Mechanics and Engineering, 2002, 21(12): 1894-1900. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX200212033.htm
[19] SHEPHARD M S, GEORGES M K. Automatic three- dimensional mesh generation by the finite octree technique[J]. International Journal for Numerical Methods in Engineering, 1991, 32(4): 709-749.
下载:
计量
- 文章访问数:
- HTML全文浏览量: 0
- PDF下载量:
