A method for identifying karst collapse columns based on an improved residual network

Authors

ZHANG Tian, Smart City College, Beijing Union University, Beijing 100101, ChinaFollow
SUN Lianying, College of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101, ChinaFollow
YANG Yan, College of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101, China
TU Shuai, Smart City College, Beijing Union University, Beijing 100101, China
WANG Jinfeng, College of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101, China

Abstract

Coal mining areas have complex geological conditions, and it is critical to predict and identify karst collapse columns in these areas efficiently and accurately. Human-computer interaction is the most frequently employed to interpret karst collapse columns in traditional methods. However, with an increase in the exploration scale and the constant accumulation of generated data, the traditional manual interpretation of karst collapse columns cannot meet the demand for actual coal mining. To improve the identification accuracy of karst collapse columns, this study proposes a Collapse Column Identification Network (CINet) model, which takes the automatic recognition of karst collapse columns as binary classification. The new CINet model is constructed by improving the residual module through the deep learning of residual networks. Moreover, the balanced-cross entropy loss is introduced into the new model to solve the highly imbalanced proportions of data on karst collapse columns and non-karst collapse columns. In this manner, the network model can converge in the correct direction. As shown by the comparison between the results predicted using the CINet model and the actual data, the CINet model can learn more detailed information on features of karst collapse columns from the original data than the traditional machine learning and residual network models, thus improving the identification accuracy. With an F₁ of up to 91.10%, the CINet model allows for the rapid and accurate identification of karst collapse columns. This study can serve as a guide for the prevention of geological disasters in coal mining areas.

Keywords

identification of karst collapse column, Collapse Column Identification Network, data imbalance, residual network

DOI

10.12363/issn.1001-1986.22.10.0773

Recommended Citation

ZHANG Tian, SUN Lianying, YANG Yan, et al. (2023) "A method for identifying karst collapse columns based on an improved residual network," Coal Geology & Exploration: Vol. 51: Iss. 5, Article 18.
DOI: 10.12363/issn.1001-1986.22.10.0773
Available at: https://cge.researchcommons.org/journal/vol51/iss5/18

Reference

[1] 许光泉,孙丰英,李佩全,等. 安徽淮南煤田“陷落柱”成因模式及其综合预测研究[J]. 皖西学院学报,2015,31(5):11−16.

XU Guangquan,SUN Fengying,LI Peiquan,et al. The formed model of “Karst Collapse Column”and its comprehensive forecast method in Huainan Coalfield[J]. Journal of West Anhui University,2015,31(5):11−16.

[2] 聂高众,夏朝旭,范熙伟,等. 基于历史地震数据的建筑物致死性水平研究[J]. 地质科学,2021,56(4):1250−1266.

NIE Gaozhong,XIA Chaoxu,FAN Xiwei,et al. Research on the lethal level of buildings based on historical seismic data[J]. Chinese Journal of Geology,2021,56(4):1250−1266.

[3] 张筌豇,何明友,刘应平,等. 四川石棉地区碲成矿地质背景、地球化学特征及其地质意义[J]. 地质科学,2020,55(1):270−289.

ZHANG Quanjiang,HE Mingyou,LIU Yingping,et al. Geological background of tellurium mineralization,geochemistry and its geological significance in Shimian Region,Sichuan[J]. Chinese Journal of Geology,2020,55(1):270−289.

[4] 王步清,徐秋晨,王艳红,等. 南华北盆地断裂构造特征与油气勘探[J]. 地质科学,2020,55(1):109−121.

WANG Buqing,XU Qiuchen,WANG Yanhong,et al. Structural characteristics of the faults in the southern North China Basin and its relationship with petroleum exploration[J]. Chinese Journal of Geology,2020,55(1):109−121.

[5] 尹尚先,连会青,刘德民,等. 华北型煤田岩溶陷落柱研究70年:成因·机理·防治[J]. 煤炭科学技术,2019,47(11):1−29.

YIN Shangxian,LIAN Huiqing,LIU Demin,et al. 70 years of investigation on karst collapse column in North China Coalfield:Cause of origin,mechanism and prevention[J]. Coal Science and Technology,2019,47(11):1−29.

[6] 阿里木·艾沙. 煤矿井下常见地质构造及其对工作面安全开采的影响探讨[J]. 内蒙古煤炭经济,2018(14):47.

ALIMU A. Discussion on common geological structure in underground coal mine and its influence onsafe mining of working face[J]. Inner Mongolia Coal Economy,2018(14):47.

[7] 杜江. 地质构造对煤矿安全生产的影响[J]. 能源与节能,2021(2):51−52.

DU Jiang. Influence of geological structure on coal mine safety production[J]. Energy and Energy Conservation,2021(2):51−52.

[8] 侯泽明,杨德义. 山西煤矿采区高密度三维地震勘探综述[J]. 煤田地质与勘探,2020,48(6):15−24.

HOU Zeming,YANG Deyi. Summary of high density 3D seismic exploration in the mining districts of coal mines in Shanxi Province[J]. Coal Geology & Exploration,2020,48(6):15−24.

[9] 金学良,王琦. 煤矿采区高密度三维地震勘探模式与效果[J]. 煤田地质与勘探,2020,48(6):1−7.

JIN Xueliang,WANG Qi. Pattern and effect of the high density 3D seismic exploration in coal mining districts[J]. Coal Geology & Exploration,2020,48(6):1−7.

[10] 李水利. 三维地震属性技术在岩溶陷落柱探测中的应用[J]. 华北自然资源,2019(3):38−41.

LI Shuili. Application of 3D seismic attributes in the detection of karst collapse columns[J]. Huabei Natural Resources,2019(3):38−41.

[11] 焦阳,卫金善,杨新亮,等. 煤矿陷落柱槽波探查技术及应用[J]. 能源与环保,2019,41(1):62−69.

JIAO Yang,WEI Jinshan,YANG Xinliang,et al. Slot wave detection technology and application of collapsed column in coal mine[J]. China Energy and Environmental Protection,2019,41(1):62−69.

[12] 王赟,杨德义,石昆法. CSAMT法基本理论及在工程中的应用[J]. 煤炭学报,2002,27(3):383−387.

WANG Yun,YANG Deyi,SHI Kunfa. The basic principle of CSAMT method and its application in the engineering field[J]. Journal of China Coal Society,2002,27(3):383−387.

[13] 杨武洋. 煤矿陷落柱赋水特征的综合物探探查原理与方法[J]. 采矿与安全工程学报,2013,30(1):45−50.

YANG Wuyang. Integrated geophysical prospecting principle and method of explorating the water enrichment of coal mine collapse column[J]. Journal of Mining & Safety Engineering,2013,30(1):45−50.

[14] HUANG Lei,DONG Xishuang,CLEE T E. A scalable deep learning platform for identifying geological features from seismic attributes[J]. The Leading Edge,2017,36(3):1−32.

[15] WU Xinming,LIANG Luming,SHI Yunzhi,et al. FaultSeg 3D:Using synthetic data sets to train an end–to–end convolutional neural network for 3D seismic fault segmentation[J]. Geophysics,2019,84(3):35−45.

[16] 杨午阳,杨佳润,陈双全,等. 基于U–Net深度学习网络的地震数据断层检测[J]. 石油地球物理勘探,2021,56(4):688−697.

YANG Wuyang,YANG Jiarun,CHEN Shuangquan,et al. Seismic data fault detection based on U−Net deep learning network[J]. Oil Geophysical Prospecting,2021,56(4):688−697.

[17] 王紫蕊，吴帮玉，刘乃豪，等. 卷积神经网络在地震断层自动识别中的应用[C]//中国石油学会2019年物探技术研讨会论文集. 成都，2019：1515–1518.

[18] DUVENAUD D，RIPPEL O，ADAMS R P，et al. Avoiding pathologies in very deep networks[J]. IEICE Transactions on Fundametales of Electronics，Communications and Computer Science，2014，abs/1402：5836.

[19] SIU C. Residual networks behave like boosting algorithms[J]. IEICE Transactions on Fundametales of Electronics，Communications and Computer Science，2019，abs/1909：11790.

[20] HE Kaiming，ZHANG Xiangyu，REN Shaoqing，et al. Identity mappings in deep residual networks[J]. IEICE Transactions on Fundametales of Electronics，Communications and Computer Science，2016，abs/1603：05027.

[21] 金玮,孟晓曼,武益超. 深度学习在图像分类中的应用综述[J]. 现代信息科技,2022,6(16):29−31.

JIN Wei,MENG Xiaoman,WU Yichao. A review of the application of deep learning in image classification[J]. Modern Information Technology,2022,6(16):29−31.

[22] 陶新民,郝思媛,张冬雪,等. 不均衡数据分类算法的综述[J]. 重庆邮电大学学报(自然科学版),2013,25(1):101−110.

TAO Xinmin,HAO Siyuan,ZHANG Dongxue,et al. Overview of classification algorithms for unbalanced data[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition),2013,25(1):101−110.

[23] 李青,赵唱,鞠永慧,等. 基于深度学习的不均衡网络数据分类技术研究[J]. 信息工程大学学报,2021,22(2):215−221.

LI Qing,ZHAO Chang,JU Yonghui,et al. Imbalanced network data classification technologies based on deep learning[J]. Journal of Information Engineering University,2021,22(2):215−221.

[24] 于滟,胡广朋. 基于K–means和改进MaxDistance规则的集成非均衡数据分类方法[J]. 计算机与数字工程,2020,48(8):1948−1953.

YU Yan,HU Guangpeng. Integration imbalanced data classification method based on K−means and improved MaxDistance rule[J]. Computer & Digital Engineering,2020,48(8):1948−1953.

[25] HE Kaiming，ZHANG Xiangyu，REN Shaoqing，et al. Deep residual learning for image recognition[C]//the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas，2016：770–778.

[26] MOU Lili，LI Ge，ZHANG Lu，et al. Convolutional neural networks over tree structures for programming language processing[J]. AAAI Press，2016.

[27] GAL Y，HRON J，KENDALL A. Concrete dropout[J]. arXiv preprint arXiv：1705. 07832，2017.

[28] COVER T M,HART P E. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory,1967,13(1):21−27.