Rock block shape classification and numerical simulation of soil-rock mixture based on machine learning algorithms

doi:10.3785/j.issn.1008-973X.2024.10.016

Journal of ZheJiang University (Engineering Science)

2024, Vol. 58

Issue (10): 2119-2127 DOI: 10.3785/j.issn.1008-973X.2024.10.016

Rock block shape classification and numerical simulation of soil-rock mixture based on machine learning algorithms

Haiying ZENG1(

),Peinan YE1,Huahui JIN2,Jingyu LIU3,Duofeng CEN4,*(

)

1. Yuhuan Agriculture and Water Conservancy Bureau, Taizhou 317600, China
2. Zhejiang Guangchuan Engineering Consultation Limited Company, Hangzhou 310020, China
3. School of Civil and Transportation Engineering, Hebei University of Technology, Tianjin 300401, China
4. Institute of Rock Mechanics, Ningbo University, Ningbo 315211, China

Download:

HTML

PDF(3047KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

Existing numerical models of rock block shape characteristics either oversimplified the block shapes or did not carry out the statistics of the block shapes. A new modeling method was proposed based on the principal component analysis algorithm (PCA) and K-means clustering algorithm. Matlab programs were used to digitally process the cross-section photos of the soil-rock mixture to obtain the contour samples of rock blocks, and the standardization processings of rock block contour such as moving the centroid to the origin, rotating the long-axis to the horizontal-axis, and normalizing the polar radius were performed to obtain standardized silhouette vectors of rock blocks. The PCA was used to reduce the dimension of the contour vector of the rock blocks, and the K-means clustering algorithm was used to cluster the contour vector after the dimension reduction. The shapes of the rock blocks were classified and the frequencies of various types of rock blocks were counted. A random model of soil-rock mixture considering the shape classification and frequency, grain composition, and inclination was established. The biaxial compression numerical simulation was carried out, and the characteristics of the plastic strain and the stress-strain curves were analyzed. The models of the deformation and compression strength of the soil-rock mixture considering the rock block shape are significantly different from those of the traditional soil-rock mixture models with polygonal rock blocks, under the conditions of higher rock content and larger rock block size.

Key words： soil-rock mixture rock block shape principal component analysis algorithm(PCA) K-means clustering algorithm

Received: 08 August 2023 Published: 27 September 2024

CLC:

P 642.3

Corresponding Authors: Duofeng CEN E-mail: 617660521@qq.com;cdfschool@126.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Haiying ZENG
	Peinan YE
	Huahui JIN
	Jingyu LIU
	Duofeng CEN

Cite this article:

Haiying ZENG,Peinan YE,Huahui JIN,Jingyu LIU,Duofeng CEN. Rock block shape classification and numerical simulation of soil-rock mixture based on machine learning algorithms. Journal of ZheJiang University (Engineering Science), 2024, 58(10): 2119-2127.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2024.10.016 OR https://www.zjujournals.com/eng/Y2024/V58/I10/2119

基于机器学习算法的块石形状分类及土石混合体数值模拟

现有块石形状特征的数值模型或过于简化块石形状或未进行块石形状的频率统计，为此基于主成分分析算法（PCA）和K均值聚类算法，提出新的建模方法. 利用Matlab对土石混合体断面照片进行数字图像处理，得到块石轮廓样本；对块石轮廓进行形心原点化、长轴水平化、最大极径归一化等标准化处理，得到标准化后的块石轮廓向量. 分别采用PCA和K均值聚类算法对块石轮廓向量进行降维和聚类，对得到的分类块石形状进行频率统计. 建立考虑块石形状分类及频率、颗粒级配、块石倾角的土石混合体随机模型，进行双轴压缩数值模拟，分析塑性应变和应力-应变曲线特征. 在较高含石量和较大块石粒径情况下比较模型的变形和抗压强度，考虑块石形状的土石混合体模型与传统含多边形块石的土石混合体模型差异明显.

关键词： 土石混合体, 块石形状, 主成分分析算法(PCA), K均值聚类算法

Fig.1 Contour extraction of rock blocks

Fig.2 Collection of coordinates of rock block contour points

Fig.3 Schematic diagram of rock block after standardized processing

Fig.4 Polar radius of rock block after standardized processing

Fig.5 Rock block samples after standardized processing

Fig.6 Schematic diagram of reducing two-dimensional vector to one-dimensional vector

Fig.7 Vector distribution of rock block contour reduced to two-dimensional

Fig.8 Relationship between number of clusters and sum of squared errors

Tab.1 Classification result of rock block shapes

Tab.2 Ratio of long and short axes of rock blocks

Fig.9 Histogram of rock block size frequency

Fig.10 Histogram of rock block inclination angle

Fig.11 Schematic diagram of position relationship between rock blocks and boundary

Fig.12 Schematic diagram of position relationship between points and polygons

Fig.13 Simulation section of soil-rock mixture

Fig.14 Mesh image of Abaqus model

Tab.3 Physical and mechanical parameters of soil and rock block in models

Fig.15 Plastic strain maps of specimens with different rock block contents

Fig.16 Deviatoric stress and axial strain curves of specimens with different rock block contents

Fig.17 Plastic strain maps of specimens with different rock block size gradations

Fig.18 Deviatoric stress and axial strain curves of specimens with different rock block size gradations


[1]	徐文杰, 张海洋土石混合体研究现状及发展趋势[J]. 水利水电科技进展, 2013, 33 (1): 80- 88 XU Wenjie, ZHANG Haiyang Research status and development trend of soil-rock mixture[J]. Advances in Science and Technology of Water Resources, 2013, 33 (1): 80- 88

[2]	胡峰, 李志清, 胡瑞林, 等基于大型直剪试验的土石混合体剪切带变形特征试验研究[J]. 岩石力学与工程学报, 2018, 37 (3): 766- 778 HU Feng, LI Zhiqing, HU Ruilin, et al Research on the deformation characteristics of shear band of soil-rock mixture based on large scale direct shear test[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37 (3): 766- 778

[3]	XU W, XU Q, HU R Study on the shear strength of soil-rock mixture by large scale direct shear test[J]. International Journal of Rock Mechanics and Mining Sciences, 2011, 48 (8): 1235- 1247 doi: 10.1016/j.ijrmms.2011.09.018

[4]	李晓, 廖秋林, 赫建明, 等土石混合体力学特性的原位试验研究[J]. 岩石力学与工程学报, 2007, 26 (12): 2377- 2384 LI Xiao, LIAO Qiulin, HE Jianming, et al Study on in-situ tests of mechanical characteristics on soil-rock aggregate[J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26 (12): 2377- 2384 doi: 10.3321/j.issn:1000-6915.2007.12.001

[5]	CEN D, HUANG D, REN F Shear deformation and strength of the interphase between the soil-rock mixture and the benched bedrock slope surface[J]. Acta Geotechnica, 2017, 12 (2): 391- 413 doi: 10.1007/s11440-016-0468-2

[6]	涂义亮, 刘新荣, 任青阳, 等含石量和颗粒破碎对土石混合料强度的影响研究[J]. 岩土力学, 2020, 41 (12): 3919- 3928 TU Yiliang, LIU Xinrong, REN Qingyang, et al Effects of rock contents and particle breakage on strength characteristics of soil-rock aggregate[J]. Rock and Soil Mechanics, 2020, 41 (12): 3919- 3928

[7]	涂义亮, 李军, 柴贺军, 等剪切作用下土石混合料的颗粒破碎演化规律[J]. 铁道工程学报, 2022, 39 (3): 19- 25 TU Yiliang, LI Jun, CHAI Hejun, et al Evolution of particle breakage of soil-rock mixture under shearing[J]. Journal of Railway Engineering Society, 2022, 39 (3): 19- 25 doi: 10.3969/j.issn.1006-2106.2022.03.004

[8]	油新华. 土石混合体的随机结构模型及其应用研究[D]. 北京: 北方交通大学, 2001. YOU Xinhua. Stochastic structural model of the earth-rock aggregate and its application [D]. Beijing: Northern Jiaotong University, 2001.

[9]	宋来忠, 沈涛, 彭刚, 等土石混合体二维细观结构的模拟方法研究[J]. 岩石力学与工程学报, 2014, 33 (7): 1488- 1495 SONG Laizhong, SHEN Tao, PENG Gang, et al Two dimensional mesoscale simulation of soil-rock mixture[J]. Chinese Journal of Rock Mechanics and Engineering, 2014, 33 (7): 1488- 1495

[10]	XU W, YUE Z, HU R Study on the mesostructure and mesomechanical characteristics of the soil-rock mixture using digital image processing based finite element method[J]. International Journal of Rock Mechanics and Mining Sciences, 2008, 45 (5): 749- 762 doi: 10.1016/j.ijrmms.2007.09.003

[11]	赵鑫曜, 陈建功, 张海权, 等基于块石形状数据库的土石混合体模型随机生成方法[J]. 岩土力学, 2018, 39 (12): 4691- 4697 ZHAO Xinyao, CHEN Jiangong, ZHANG Haiquan, et al Random generation of soil-rock mixture models by rock shape database using digital imaging technology[J]. Rock and Soil Mechanics, 2018, 39 (12): 4691- 4697

[12]	ZHANG W, HAN L, WANG Z, et al Generation of 3D geotechnical particles using random angular bend algorithm[J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2023, 47 (8): 1313- 1330 doi: 10.1002/nag.3515

[13]	WANG Z, THOMAS B, ZHANG W, et al A novel random angular bend (RAB) algorithm and DEM modeling of thermal cracking responses of sandstone[J]. Geomechanics for Energy and the Environment, 2022, 32: 100335 doi: 10.1016/j.gete.2022.100335

[14]	PHOON K, ZHANG W Future of machine learning in geotechnics[J]. Georisk, 2023, 17 (1): 7- 22

[15]	ZHANG W, GU X, TANG L, et al Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: comprehensive review and future challenge[J]. Gondwana Research, 2022, 109: 1- 17 doi: 10.1016/j.gr.2022.03.015

[16]	ZHANG W, LI H, LI Y, et al Application of deep learning algorithms in geotechnical engineering: a short critical review[J]. Artificial Intelligence Review, 2021, 54: 5633- 5673 doi: 10.1007/s10462-021-09967-1

[17]	崔丹丹. K-means聚类算法的研究与改进[D]. 合肥: 安徽大学, 2012. CUI Dandan. Research and improvement of the K-means clustering algorithm [D]. Hefei: Anhui University, 2012.

[18]	徐文杰, 王玉杰, 陈祖煜, 等. 基于数字图像技术的土石混合体边坡稳定性分析[J]. 岩土力学, 2008, 28(增1): 341−346. XU Wenjie, WANG Yujie, CHEN Zuyu, et al. Stability analysis of soil-rock mixed slope based on digital image technology [J]. Rock and Soil Mechanics , 2008, 28(Suppl. 1): 341–346.

[19]	马昊, 黄达, 肖衡林, 等江北机场高填方夯后碎块石土剪切力学性质研究[J]. 水文地质工程地质, 2019, 46 (3): 88- 94 MA Hao, HUANG Da, XIAO Henglin, et al A study of the shear mechanical properties of high-filled gravel-block soil after dynamic compaction near the Jiangbei airport[J]. Hydrogeology and Engineering Geology, 2019, 46 (3): 88- 94

[20]	徐文杰, 胡瑞林, 岳中崎土-石混合体随机细观结构生成系统的研发及其细观结构力学数值试验研究[J]. 岩石力学与工程学报, 2009, 28 (8): 1652- 1665 XU Wenjie, HU Ruilin, YUE Z Q Development of random mesostructure generating system of soil-rock mixture and study of its mesostructural mechanics based on numerical test[J]. Chinese Journal of Rock Mechanics and Engineering, 2009, 28 (8): 1652- 1665 doi: 10.3321/j.issn:1000-6915.2009.08.017

[21]	MEDLEY E W. The engineering characterization of mélanges and similar block-in-matrix rocks (bimrocks) [D]. Berkeley: University of California at Berkeley, 1994.

[22]	喻江武, 苟志龙, 雷瑜, 等基于傅里叶逆变换的土石混合体模型生成研究[J]. 水利水电技术, 2019, 50 (4): 7- 15 YU Jiangwu, GOU Zhilong, LEI Yu, et al Inverse Fourier transform-based study on generating model of soil-rock mixture[J]. Water Resources and Hydropower Engineering, 2019, 50 (4): 7- 15

[23]	丁巍, 楚锡华, 常江芳横观各向同性岩土材料的应变局部化分析[J]. 地震工程学报, 2017, 39 (3): 481- 487 DING Wei, CHU Xihua, CHANG Jiangfang Numerical analysis of strain localization for transversely isotropic geomaterials[J]. China Earthquake Engineering Journal, 2017, 39 (3): 481- 487 doi: 10.3969/j.issn.1000-0844.2017.03.0481

[1]	Han ZHANG,Xin-li HU,Shuang-shuang WU. Damage evolution of soil-rock mixture based on Fourier series approximations method[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(10): 1955-1965.

[2]	WANG Qiang, HU Xin-li, XU Ying, ZHOU Chang, XU Chu. Investigation on compaction characteristics and meso-mechanism of soil-rock mixture with soft rock blocks[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(12): 2295-2305.

Viewed

Full text

Abstract

Cited

Shared

Discussed