基于倾斜试验的岩体结构面接触区域智能预测方法研究
PDF下载 (126)童烁超,王松挺,陈 杯,邵含璁,吕原君,刘维明,王昌硕.基于倾斜试验的岩体结构面接触区域智能预测方法研究[J].宁波大学学报(理工版),2025,38(5):43-53.DOI:10.20098/j.cnki.1001-5132.2025.0104
TONG Shuochao,WANG Songting,CHEN Bei,SHAO Hancong,LÜ Yuanjun,LIU Weiming,WANG Changshuo.Research of intelligent prediction method for rock joints contact area based on tilting test[J].Journal of Ningbo University(Natural Science & Engineering Edition),2025,38(5):43-53.DOI:10.20098/j.cnki.1001-5132.2025.0104
| Title: | Research of intelligent prediction method for rock joints contact area based on tilting test |
| 作者: | 童烁超, 王松挺, 陈 杯, 邵含璁, 吕原君, 刘维明, 王昌硕 |
| Author(s): | TONG Shuochao, WANG Songting, CHEN Bei, SHAO Hancong, LÜ Yuanjun, LIU Weiming, WANG Changshuo |
| 关键词: | 岩体结构面; 倾斜试验; 空腔体积; 接触区域; 机器学习 |
| Keywords: | rock mass structural plane; tilting test; cavity volume; contact area; machine learning |
| 分类号: | TU45 |
| DOI: | 10.20098/j.cnki.1001-5132.2025.0104 |
| 文献标识码: | A |
| 摘要: | 接触区域作为岩体结构面相对运动时的潜在破坏区域对其抗剪强度具有重要影响。现有结构面接触区域测量方法仅能评估特定状态下的接触区域，缺乏在不同状态下无损识别接触区域的能力。为此，采用倾斜试验和激光扫描技术获取结构面表面形貌和不同滑移距离下的上下盘相对位置信息，提出不同滑移位移下结构面点云空间位置还原方法，将结构面上下盘形貌还原至相应滑移位下的空间位置。通过机器学习以小尺寸结构面的粗糙度参数、折减系数和对应网格的接触状态作为训练数据集构建结构面接触区域预测模型。将大尺寸结构面粗糙度参数和吻合度阈值折减系数作为模型输入，得到接触区域的输出结果，利用ROC曲线和AUC值对其预测性能进行评估。结果表明预测结果与实际情况具有良好的一致性，其中BPNN预测性能最优，集成装袋树次之，KNN最差。为精确评估岩体结构面的接触区域提供了一种新颖且有效的方法。 |
| Abstract: | The contact area, as the potential failure area of the relative motion of the rock mass structural plane, has an important influence on its shear strength. The existing measurement methods can only evaluate the contact area under specific conditions, and they lack the ability to non-destructively identify the contact area under varied conditions. To this end, this paper uses tilting test and laser scanning technology to obtain the surface morphology of the structural plane and the relative position information of the upper and lower plates under different slip distances. The spatial position reduction method of the structural plane point cloud under different slip displacements is proposed to restore the morphology of the upper and lower plates of the structural plane to the spatial position under the corresponding slip position. Through machine learning, the roughness parameters, reduction coefficients and the contact state of the corresponding grid of the small-size structural plane are used as the training data set to construct the prediction model of the contact area. The roughness parameters of the large-scale structural surface and the coincidence threshold reduction coefficient are used as the input to the model to obtain the output results of the contact area. The ROC curve and AUC value are used to evaluate its predictive performance. The results show that the prediction results are consistent with the actual situation, and BPNN has the best prediction performance, followed by integrated bagging tree, and finally KNN. The study provides a novel and effective method for accurately evaluating the contact area of rock mass discontinuities. |
| 参考文献 /References: | [1] 杜时贵, 胡晓飞, 罗战友, 等. 节理抗剪强度综合评价的试验研究[J]. 工程地质学报, 2008, 16(1):89-97. [2] 曾纪全, 杨宗才. 岩体抗剪强度参数的结构面倾角效应[J]. 岩石力学与工程学报, 2004, 23(20):3418-3425. [3] 彭勃, 刘亚群, 李海波, 等. 基于三维形貌的节理抗剪强度弱化规律研究[J]. 岩石力学与工程学报, 2021, 40(增刊2):3191-3200. [4] 杨松林, 李详新. 岩石节理的表面形态与力学特性[J]. 长江职工大学学报, 2000, 17(4):15-17, 10. [5] 肖维民, 余欢, 李锐, 等. 薄层充填岩石节理抗剪强度特性试验研究[J]. 岩石力学与工程学报, 2019, 38(增刊2):3420-3428. [6] PARK J W, SONG J J. Numerical method for the determination of contact areas of a rock joint under normal and shear loads[J]. International journal of rock mechanics and mining sciences, 2013, 58:8-22. [7] BANDIS S C, LUMSDEN A C, BARTON N R. Fundamentals of rock joint deformation[J]. International journal of rock mechanics and mining sciences & geomechanics abstracts, 1983, 20(6):249-268. [8] PYRAK-NOLTE L J, MYER L R, COOK N G W. Transmission of seismic waves across single natural fractures[J]. Journal of geophysical research: solid earth, 1990, 95(B6):8617-8638. [9] HAKAMI E, LARSSON E. Aperture measurements and flow experiments on a single natural fracture[J]. International journal of rock mechanics and mining sciences & geomechanics abstracts, 1996, 33(4):395-404. [10] NEMOTO K, WATANABE N, HIRANO N, et al. Direct measurement of contact area and stress dependence of anisotropic flow through rock fracture with heterogeneous aperture distribution[J]. Earth and planetary science letters, 2009, 281(1/2):81-87. [11] KIM D H, GRATCHEV I, BALASUBRAMANIAM A. Back analysis of a natural jointed rock slope based on the photogrammetry method[J]. Landslides, 2015, 12(1):147- 154. [12] GE Y F, TANG H M, XIA D, et al. Automated measurements of discontinuity geometric properties from a 3D-point cloud based on a modified region growing algorithm[J]. Engineering geology, 2018, 242:44-54. [13] 熊祖强, 江权, 龚彦华, 等. 基于三维扫描与打印的岩体自然结构面试样制作方法与剪切试验验证[J]. 岩土力学, 2015, 36(6):1557-1565. [14] HUANG J D, ZHANG J, GAO Y. Intelligently predict the rock joint shear strength using the support vector regression and firefly algorithm[J]. Lithosphere, 2021, 2021(Special 4):2467126. [15] LI Y, ZENG J, SUHATRIL M, et al. Analyzing the shear strength of jointed magmatic rock mass excavatability using the hybridization of metaheuristic model of ELM-SVM[J]. Acta geotechnica, 2023, 18(4):1793-1819. [16] GE Y F, XIE Z G, TANG H M, et al. Determination of the shear failure areas of rock joints using a laser scanning technique and artificial intelligence algorithms[J]. Engineering geology, 2021, 293:106320. [17] WANG L Q, WANG C S, KHOSHNEVISAN S, et al. Determination of two-dimensional joint roughness coefficient using support vector regression and factor analysis[J]. Engineering geology, 2017, 231:238-251. [18] 黄曼, 夏才初, 马成荣, 等. 系列尺度岩体结构面形貌渐进覆盖统计方法[J]. 岩石力学与工程学报, 2019, 38(8):1533-1541. [19] 雍睿, 钟祯, 杜时贵, 等. 岩体结构面基本摩擦角研究现状与展望[J]. 岩石力学与工程学报, 2022, 41(2):254- 270. [20] ALEJANO L R, MURALHA J, ULUSAY R, et al. A benchmark experiment to assess factors affecting tilt test results for sawcut rock surfaces[J]. Rock mechanics and rock engineering, 2017, 50(9):2547-2562. [21] 王松挺, 王昌硕, 杜时贵, 等. 基于机器学习的岩体结构面剪切破坏区域预测研究[J]. 地质与勘探, 2024, 60(2):388-406. [22] 汤志立, 徐千军. 基于9种机器学习算法的岩爆预测研究[J]. 岩石力学与工程学报, 2020, 39(4):773-781. [23] 汤志立, 王雪, 徐千军. 基于过采样和客观赋权法的岩爆预测[J]. 清华大学学报(自然科学版), 2021, 61(6): 543-555. [24] WANG Y K, TANG H M, HUANG J S, et al. A comparative study of different machine learning methods for reservoir landslide displacement prediction[J]. Engineering geology, 2022, 298:106544. [25] 赵洪波, 师旭超. 岩石节理抗剪强度的支持向量机预测[J]. 长江科学院院报, 2004, 21(6):45-46, 50. |
| 备注/Memo: | 收稿日期：2025−01−04 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ 基金项目：国家自然科学基金（42207175）；宁波市自然科学基金（2022J115） 第一作者：童烁超，硕士研究生，主要研究方向为岩土工程。E-mail: tsc2653@163.com *通信作者：王昌硕，副研究员，主要研究方向为岩土工程。E-mail: wangchangshuo@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
