煤岩微观相态FCN智能识别与分形重构

doi:10.13722/j.cnki.jrme.2019.0931

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1312 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要数字岩芯可提供无差别化仿真计算模型，是研究岩石物理力学性质的理想模型，精准高效建模一直制约着数字岩芯重构技术的推广。传统方法处理CT切片扫描数据费时费力，主要受限于2个方面，一是扫描层数有限；二是孔裂隙识别依赖于传统阈值分割算法。以煤岩为例，引入人工智能识别实现4种微观相态：孔隙、裂隙、高密度矿物和基质的智能识别，并开展分形重构。基于微米CT扫描建立4种微观相态数据集并进行了数据增强，开发了专用标注软件可实现跨尺度孔裂隙的准确标注。算法上优化了全卷级神经网络智能识别架构，建立Crack-FCN网络结构，网络层次少且错误率低。同时引入矢量化算法实现了裂隙面积、长度和宽度的定量计算；进而引入中心线细化算法实现了复杂裂隙拓扑结构的有效提取。最后开发局部自相似分形重构算法，并基于优化策略解决了快速插值问题，解决了相邻CT层扫描信息缺失的问题。结果表明分形插值与直线插值和三阶样条插值相比局部粗糙特性明显，且保证了裂隙断面的粗糙性和连续性。工作引入全卷级神经网络智能识别技术用于构造数字岩芯，为高效精准建立数字岩芯提供了新的技术支撑。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	薛东杰1
	2
	3
	唐麒淳1
	王傲4
	易海洋5
	张弛6
	耿传庆1
	周宏伟2
	4

关键词 ：岩石力学, 数字岩芯, CT切片, 人工智能识别, 全卷积神经网络, 微观相态, 分形重构

Abstract：Digital core establishment，as an ideal model to study the physical and mechanical properties of rock, provides an undifferentiated numerical simulation. However，high level of accurate and efficient modeling restricts the promotion of digital core reconstruction technology. The traditional methods are time-consuming and laborious in processing CT slice based scanning data，due to limited number of scanning layers and the pore-fracture recognition depending on the traditional threshold segmentation algorithm. Taking coal as an example，the artificial intelligence recognition is introduced to realize the recognition of four micro phase states of pore，fracture，high-density mineral and coal matrix，and the fractal reconstruction is carried out for filling in information gaps. Data sets of four micro phase states are established and enhanced based on micro CT scanning，and a labelling software is developed for effectively distinguishing four kinds of micro-phases of materials. Especially for improving the efficiency and precision of identification，the FCN architecture is optimized and the Crack-FCN network structure is proposed，which has few network layers and low error rate. Moreover，the Potrace algorithm is introduced to quantitatively calculate fracture area，length and width，and the centerline extraction algorithm is introduced to effectively determine the complex topology. Considering the fractal similarity of fractured surface and to solve the problem of missing information between two adjacent CT slices，a fractal reconstruction algorithm is developed dependent on the local self-similar property and then optimized to improve the computational efficiency. Compared to the line interpolation and cubic spline interpolation，the fractal interpolation is more effective to describe the local roughness，and more importantly，the accuracy of intelligent recognition will continue to be improved with the continuous enhancement of data-set. This paper breaks through the traditional view and introduces the FCN into construct digital core of rock，and provides new technical support for the efficient and accurate establishment of numerical modelling.

Key words： rock mechanics digital core CT slices artificial intelligence identification fully convolutional neural network microphase of material fractal reconstruction

引用本文:

薛东杰1，2，3，唐麒淳1，王傲4，易海洋5，张弛6，耿传庆1，周宏伟2，4. 煤岩微观相态FCN智能识别与分形重构[J]. 岩石力学与工程学报, 2020, 39(6): 1203-1221.
XUE Dongjie1，2，3，TANG Qichun1，WANG Ao4，YI Haiyang5，ZHANG Chi6，GENG Chuanqing1，ZHOU Hongwei2，4. FCN-based intelligent identification and fractal reconstruction of pore-fracture network in coal by micro CT scanning#br#. , 2020, 39(6): 1203-1221.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2019.0931 或 http://rockmech.whrsm.ac.cn/CN/Y2020/V39/I6/1203

[24]	STAUFFER D，AHARONY A. Introduction to percolation theory[M]. London：Taylor & Francis，2018：93-120.
[34]	ABU-AIN W，ABDULLAH S N H S，BATANINEH B，et al. Skeletonization algorithm for binary images[J]. Procedia Technology，2013，11：704-709.
[18]	MARESCHAL J C. Fractal reconstruction of sea-floor topography[C]// Fractals in Geophysics. Birkhäuser，Basel：[s. n.]，1989：197-210.
[38]	BEISTER M，KOLDITZ D，KALENDER W A. Iterative reconstruction methods in X-ray CT[J]. Physica Medica，2012，28(2)：94-108.
[35]	SMITH A R. Color gamut transform pairs[J]. ACM Siggraph Computer Graphics，1978，12(3)：12-19.
[19]	HINTON G E，SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science，2006，313(5786)：504-507.
[37]	FESSLER J. Analytical tomographic image reconstruction methods[J]. Image Reconstruction：Algorithms and Analysis，2009，66：67.
[22]	SCHMIDHUBER J. Deep learning in neural networks：An overview[J]. Neural Networks，2015，61：85-117.
[32]	SELINGRE P. Potrace：a polygon-based tracing algorithm[J]. Potrace (online)，http：//potrace. sourceforge. net/potrace. pdf (2009-07-01)，2003.
[2]	ANGNOSTOPOULOS C N E，ANGNOSTOPOULOS I E，LOUMOS V，et al. A license plate-recognition algorithm for intelligent transportation system applications[J]. IEEE Transactions on Intelligent Transportation Systems，2006，7(3)：377-392.
[4]	黄宏伟，李庆桐. 基于深度学习的盾构隧道渗漏水病害图像识别[J]. 岩石力学与工程学报，2017，36(12)：2 861-2 871.(HUANG Hongwei，LI Qingtong. Image recognition for water leakage in shield tunnel based on deep learning[J]. Chinese Journal of Rock Mechanics and Engineering，2017，36(12)：2 861-2 871.(in Chinese))
[6]	ZHOU H W，ZHONG J C，REN W G，et al. Characterization of pore-fracture networks and their evolution at various measurement scales in coal samples using X-ray μCT and a fractal method[J]. International Journal of Coal Geology，2018，189：35-49.
[10]	MAYO S，JOSH M，NESTERETS Y，et al. Quantitative micro-porosity characterization using synchrotron micro-CT and xenon K-edge subtraction in sandstones，carbonates，shales and coal[J]. Fuel，2015，154：167-173.
[12]	CHENG G，GUO W. Rock images classification by using deep convolution neural network[C]// In Journal of Physics：Conference Series. [S.l.]：IOP Publishing，2017，887(1)：012089.
[14]	ZHANG P Y，SUN J M，JIANG Y J，et al. Deep learning method for lithology identification from borehole images[C]// In 79th EAGE Conference and Exhibition. [S. l.]：[s. n.]，2017：1-5.
[30]	SAINATH TN，MOHAMED A，KINGSBURY B，et al. Deep Convolutional Neural Networks for LVCSR[C]// In IEEE International Conference on Acoustics，Speech and Signal Processing. [S .l.]：[s. n.]，2013：8 614-8 618.
[42]	DENG J，DONG W，SOCHER R，et al. Imagenet：A large-scale hierarchical image database[C]// In 2009 IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]：IEEE，2009：248-255.
[44]	ANTLE R. Automated core fracture characterization by computer vision and image analytics of CT images[C]// SPE Oklahoma City Oil and Gas Symposium. [S. l.]：Society of Petroleum Engineers，2019：1-7.
[20]	LECUN Y，BENGIO Y，HINTON G. Deep learning[J]. Nature，2015，521(7553)：436.
[40]	BARNSLEY M F. Fractal functions and interpolation[J]. Constructive Approximation，1986，2(1)：303-329.
[5]	XUE D，ZHOU H，ZHAO Y，et al. Real-time SEM observation of mesoscale failures under thermal-mechanical coupling sequences in granite[J]. International Journal of Rock Mechanics and Mining Sciences，2018，112：35-46.
[8]	YOUSSEF S，ROSNBERG E，GLAND N，et al. Quantitative 3D characterisation of the pore space of real rocks：improved µ-CT resolution and pore extraction methodology[C]// International Symposium of the Society of Core Analysts. Calgary：[s. n.]，2007：1-17.
[15]	MOSSER L，DUBRULE O，BLUNT M J. Reconstruction of three-dimensional porous media using generative adversarial neural networks[J]. Physical Review E，2017，96(4)：043309.
[25]	XUE D，ZHOU J，LIU Y，et al. A strain-based percolation model and triaxial tests to investigate the evolution of permeability and critical dilatancy behavior of coal[J]. Processes，2018，6(8)：127.
[28]	KRIZHEVSKY A，SUTSKEVER I，HINTON G E. Imagenet classification with deep convolutional neural networks[C]// In Advances in Neural Information Processing Systems. [S. l.]：[s. n.]，2012：1 097-1 105.
[45]	MARQUES V G，DA SILVA L R D，CARVALHO B M，et al. Deep learning-based pore segmentation of thin rock sections for aquifer characterization using color space reduction[C]// In 2019 International Conference on Systems，Signals and Image Processing(IWSSIP). [S.l.]：IEEE，2019：235-240.
[3]	薛东杰，唐麒淳，王傲，等. 基于FCN的岩石混凝土裂隙几何智能识别[J]. 岩石力学与工程学报，2019，38(增2)：2 861-2 871. (XUE Dongjie，TANG Qichun，WANG Ao，et al. FCN-based intelligent identification of crack geometry in rock or concrete[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(Supp.2)：2 861-2 871.(in Chinese))
[13]	FERREIRA A，GIRALDI G. Convolutional neural network approaches to granite tiles classification[J]. Expert Systems with Applications，2017，84：1-11.
[23]	LONG J，SHELHAMER E，DARRELL T. Fully convolutional networks for semantic segmentation[C]// In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]：[s. n.]，2015：3 431-3 440.
[33]	MARAGOS P，SCHAFER R. Morphological skeleton representation and coding of binary images[J]. IEEE Transactions on Acoustics，Speech，and Signal Processing，1986，34(5)：1 228-1 244.
[43]	KARIMPOULI S，TAHMASEBI P. Image-based velocity estimation of rock using Convolutional Neural Networks[J]. Neural Networks，2019，111：89-97.
[1]	JACKSON P C. Introduction to artificial intelligence[M]. [S.l.]：Courier Dover Publications，2019：330-385.
[11]	SRISUTTHIYAKORN N. Deep-learning methods for predicting permeability from 2D/3D binary-segmented images[C]// In SEG Technical Program Expanded Abstracts 2016. Society of Exploration Geophysicists，2016：3 042-3 046.
[21]	GOODFELLOW I，BENGIO Y，COURVILLE A. Deep learning[M]. [S. l.]：MIT Press，2016：110-130.
[31]	ZEILER M D，FERGUS R. Visualizing and understanding convolutional networks[C]// European Conference on Computer Vision. Cham：Springer，2014：818-833.
[41]	BARNSLEY M F. Fractals everywhere[M]. Academic Press，2014：48-100.
[7]	JU Y，ZHENG J，EPSTEIN M，et al. 3D numerical reconstruction of well-connected porous structure of rock using fractal algorithms[J]. Computer Methods in Applied Mechanics and Engineering，2014，279：212-226.
[9]	ZHOU T，ZHU J B. Application of 3D printing and micro-CT scan to rock dynamics[C]// Rock Dynamics：From Research to Engineering，Taylor & Francis Group，London，2016：247-252.
[16]	LALOY E，HÉRAULT R，LEE J，et al. Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network[J]. Advances in Water Resources，2017，110：387-405.
[17]	ALQAHTANI N，ARMSTRONG R T，MOSTAGHIMI P. Deep learning convolutional neural networks to predict porous media properties[C]// In SPE Asia Pacific Oil and Gas Conference and Exhibition. [S. l.]：Society of Petroleum Engineers，2018：1-10.
[26]	SIMONYAN K，ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]// In International Conference on Learning Representations. [S. l.]：[s. n.]，，2015：1-14.
[27]	ZHANG X，ZHOU X，LIN M，et al. Shufflenet：An extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [S. l.]：[s. n.]，2017：1-9.
[29]	EVERINGHAM M，VAN GOOL L，WILLIAMS C K I，et al. The pascal visual object classes (voc) challenge[J]. International Journal of Computer Vision，2010，88(2)：303-338.
[36]	MEZIROW J. Perspective transformation[J]. Adult Education，1978，28(2)：100-110.
[39]	THIBAULT J B，SAUER K D，BOUMAN C A，et al. A three‐dimensional statistical approach to improved image quality for multislice helical CT[J]. Medical Physics，2007，34(11)：4 526-4 544.
[46]	KASHIWA T，NAGAI K，TATSUTA H，et al. Development of delamination detection system for concrete decks by using convolutional neural network[C]// Proceedings of the Multidisciplinary Digital Publishing Institute. [S. l.]：[s. n.]，2018：418.