耦合岩石图像与锤击音频的岩性分类智能识别分析方法

doi:10.13722/j.cnki.jrme.2019.0748

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (630 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In the process of field geological exploration，geological engineers generally make a preliminary judgment on the lithology classification through the information of rock surface texture，color and hammering audios. Based on experts¢ experience and intelligent mode，a deep learning and intelligent recognition analysis method for rock lithology classification is proposed by using coupled rock images and hammering audios. Firstly，the Transfer learning method based on Inception-V3 is used to carry out deep learning and training on collected 6 types of rock images. Then，measuring the rock strength indicated as the average value of the rebound index by a rebounder and obtaining hammering audio segments by the threshold method，an SVM (Support Vector Machine) regression model of waveform and intensity is established to predict the rock surface strength. Finally，rock classification is intelligently recognized by coupling rock images recognition model with rock audio intensity regression model. The accuracy of rock classification is increased from 83.5%(only using simple images recognition model) to 90.5%. The coupling model can not only effectively identify rock lithology classification but also preliminarily give the rock surface strength，which provides a new auxiliary method for field engineering geological survey and is beneficial to improve the working efficiency of initial field exploration.

Key words： rock mechanics rock lithology intelligent recognition rock images rock hammering audios deep learning transfer learning SVM regression of strength

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LI Mingchao
	FU Jiake
	ZHANG Ye
	LIU Chengzhao

Cite this article:

LI Mingchao,FU Jiake,ZHANG Ye, et al. Intelligent recognition and analysis method of rock lithology classification based on coupled rock images and hammering audios#br#[J]. , 2020, 39(5): 996-1004.

URL:

http://rockmech.whrsm.ac.cn/EN/10.13722/j.cnki.jrme.2019.0748 OR http://rockmech.whrsm.ac.cn/EN/Y2020/V39/I5/996

[17]	LECUN Y，BENGIO Y，HINTON G. Deep learning[J]. Nature，2015，521(7553)：436-444.
[27]	VAPNIK V. The Nature of statistical learning theory[M]. 2nd ed. New York：Springer，1999：181-190.
[19]	郭超，刘烨. 多色彩空间下的岩石图像识别研究[J]. 科学技术与工程，2014，14(18)：247-251.(GUO Chao，LIU Ye. Recognition of Rock Images Based on Multiple Color Spaces[J]. Science Technology and Engineering，2014，14(18)：247-251.(in Chinese))
[26]	PAN S J，YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering，2009，22(10)：1 345-1 359.
[1]	佘诗刚，林鹏. 中国岩石工程若干进展与挑战[J]. 岩石力学与工程学报，2014，33(3)：433-457.(SHE Shigang，LIN Peng. Some developments and challenging issues in rock engineering field in China[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(3)：433-457.(in Chinese))
[8]	汪洋. 北京白查A型花岗岩的地球化学特征及其成因与构造指示意义[J]. 岩石学报，2009，25(1)：13-24.(WANG Yang. Geochemistry of the baicha a-type granite in Beijing municipality：petrogenetic and tectonic implications[J]. Acta Petrologica Sinica，2009，25(1)：13-24.(in Chinese))
[9]	冉明佳，钟康惠，罗明非，等. 西藏冈底斯带东段石炭纪构造环境讨论[J]. 地质论评，2012，58(2)：250-258.(RAN Mingjia，ZHONG Kanghui，LUO Mingfei，et al. A discussion on carboniferous tectonic settings in the eastern sector of gangdise belt，Xizang(Tibet)[J]. Geological Review，2012，58(2)：250-258.(in Chinese))
[11]	刘烨，程国建，马微，等. 基于铸体薄片图像颜色空间与形态学梯度的岩石分类[J]. 中南大学学报：自然科学版，2016，47(7)：2 375-2 382.(LIU Ye，CHENG Guojian，MA Wei，et al. Rock classification based on features form color space and morphological gradient of rock thin section image[J]. Journal of Central South University：Science and Technology，2016，47(7)：2 357-2 382.(in Chinese))
[18]	张野，李明超，韩帅. 基于岩石图像深度学习的岩性自动识别与分类方法[J]. 岩石学报，2018，34(2)：333-342.(ZHANG Ye，LI Mingchao，HAN Shuai. Automatic identification and classification in lithology based on deep learning in rock images[J]. Acta Petrologica Sinica，2018，34(2)：333-342.(in Chinese))
[21]	SINGH T N，KAINTHOLA A，VENKATESH A. Correlation between point load index and uniaxial compressive strength for different rock types[J]. Rock Mechanics and Rock Engineering，2012，45(2)：259-264.
[3]	HACK R，HUISMAN M. Estimating the intact rock strength of a rock mass by simple means[C]// Proceedings of the 9th Congress of the International Association for Engineering Geology and the Environment. Durban，South Africa：[s. n.]，2002：1 971-1 977.
[5]	王子娟，刘新荣，傅晏，等. 两种岩石试件的“超声-回弹-密度”综合筛选法研究[J]. 岩石力学与工程学报，2018，37(增1)：3 575-3 583.(WANG Zijuan，LIU Xinrong，Fu Yan，et al. Comprehensive screening method of “ultrasonic-rebound-density”for two kinds of rock specimens[J]. Chinese Journal of Rock Mechanics and Engineering，2018，37(Supp.1)：3 575-3 583.(in Chinese))
[7]	郭清宏，周永章，曹姝旻，等. 广绿玉玉石的矿物学研究[J]. 中山大学学报(自然科学版)，2010，49(3)：146-151.(GUO Qinghong，ZHOU Yongzhang，CAO Shumin，et al. Study on Mineralogy of Guangning Jade[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni，2010，49(3)：146-151.(in Chinese))
[10]	高阳，王永诗，李孝军，等. 基于岩石孔喉结构的致密砂岩分类方法——以济阳坳陷古近系为例[J]. 油气地质与采收率，2019，26(2)：32-41.(GAO Yang，WANG Yongshi，LI Xiaojun，et al. Classification method of tight sandstone based on pore throat structure：a case study of paleogene in Jiyang depression[J]. Petroleum Geology and Recovery Efficiency，2019，26(2)：32-41.(in Chinese))
[13]	ESTEVA A，KUPREL B，NOVOA RA，et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature，2017，542(7639)：115-118.
[15]	SIMONYAN K，ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]// 3rd International Conference on Learning Representations. San Diego，CA：[s. n.]，2015：1-14.
[20]	KAMANI M，AJALLOEIAN R. Evaluation of the mechanical degradation of carbonate aggregate by rock strength tests[J]. Journal of Rock Mechanics and Geotechnical Engineering，2019，11(1)：121-134.
[23]	TSIAMBAOS G ，SABATAKAKIS N . Considerations on strength of intact sedimentary rocks[J]. Engineering Geology，2004，72(3/4)：261-273.
[25]	周胜，刘三民. 基于迁移学习的数据流分类研究综述[J]. 天津理工大学学报，2019，35(3)：24-29.(ZHOU Sheng，LIU Sanmin. A survey of data stream classification research based on transfer learning[J]. Journal of Tianjin University of Technology，2019，35(3)：24-29.(in Chinese))
[4]	MARINOS P，HOEK E. Estimating the geotechnical properties of heterogeneous rock masses such as flysch[J]. Bulletin of engineering geology and the environment，2001，60(2)：85-92.
[6]	樊磊，赵文吉，宫兆宁，等. 基于包络线消除法的岩石光谱对应分析[J]. 吉林大学学报：地球科学版，2012，42(2)：575-582.(FAN Lei，ZHAO Wenji，GONG Zhaoning，et al. Correspondence analysis of rock spectra based on continuum removing[J]. Journal of Jilin University：Earth Science Edition，2012，42(2)：575-582.(in Chinese))
[14]	SZEGEDY C，VANHOUCKE V，IOFFE S，et al. Rethinking the inception architecture for computer vision[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas：[s. n.]，2016：2 818-2 826.
[16]	KRIZHEVSKY A，SUTSKEVER I，HINTON G E. Imagenet classification with deep convolutional neural networks[C]// Advances in Neural Information Processing Systems. Lake Tahoe，NV：[s. n.]，2012：1 097-1 105.
[24]	REN Q，WANG G，LI M，et al. Prediction of rock compressive strength using machine learning algorithms based on spectrum analysis of geological hammer[J]. Geotechnical and Geological Engineering，2018，(3)：1-15.
[2]	柴华，李宁，夏守姬，等. 高清晰岩石结构图像处理方法及其在碳酸盐岩储层评价中的应用[J]. 石油学报，2012，33(增2)：154-159.(CHAI Hua，LI Ning，XIA Shouji，et al. High-resolution rock structure image processing method and its applications in carbonate reservoir evaluation[J]. Acta Petrolei Sinica，2012，33(Supp.2)：154-159.(in Chinese))
[12]	BIANCO S，BUZZELLI M，MAZZINI D，et al. Deep learning for logo recognition[J]. Neurocomputing，2017，245：23-30.
[22]	SINGH V K ，SINGH D P . Correlation between point load index and compressive strength for quartzite rocks[J]. Geotechnical and Geological Engineering，1993，11(4)：269-272.