基于支持向量机与地球物理测井资料的煤体结构识别方法

doi:10.11720/wtyht.2021.1556

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(1694 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

煤体结构作为煤层勘探开发研究的重点参数之一,影响着煤层产能,有效识别煤层煤体结构至关重要。本文利用支持向量机算法,以地球物理测井资料为基础进行煤体结构识别,并以沁水煤田柿庄北区3号层为例,对该区块进行煤体结构类型分类,利用支持向量机的双二分类与“一对多”分类两种建模模式,建立基于测井曲线的煤体结构识别模型,再利用交叉验证评价模型的泛化性,并对该模型用未参与建模数据进行准确性评价。结果表明,应用支持向量机算法的两种模式能有效识别煤体结构,模型具有泛化性与准确性,且“一对多”分类模式精度更高,在对有利产出煤和不利产出煤的区分上效果突出,对有利产出煤的具体类型区分上具有准确性,可对后续压裂施工提供指导。总体上,基于支持向量机算法和地球物理测井资料建立的煤体结构识别模型对煤层气勘探开发有指导意义,具有实际应用价值。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	郭建宏
	杜婷
	张占松
	肖航
	秦瑞宝
	余杰
	王灿

关键词 ：煤层煤体结构, 地球物理测井资料, 支持向量机算法, 双二分类模式, “一对多”分类模式

Abstract：

As one of the key parameters of coal seam exploration and development research, coal structure affects coal seam productivity, and it is significant to effectively identify coal structure. In this paper, the support vector machine algorithm was used to identify the coal structure based on geophysical logging data, and the No. 3 layer in Shizhuang North District of Qinshui Basin was taken as an example to classify the coal structure type in this block. Using two modeling modes of support vector machine's two-two classification and "one-to-many" classification, the authors established a coal structure recognition model based on logging curves, then used cross-validation to evaluate the generalization of the model, and finally used the data that did not participate in the model establishment to evaluate the accuracy of the model. The results show that the two models of the support vector machine algorithm can effectively identify the coal structure, the models have generalization and accuracy, and the "one-to-many" classification model has higher accuracy: the distinguishing effect of coal is outstanding, it is accurate in distinguishing the specific types of coal that are beneficial to production, and can provide guidance for subsequent fracturing construction. In general, the coal structure recognition model established based on the support vector machine algorithm and geophysical logging data has guiding significance for the exploration and development of coalbed methane and shows practical application value.

Key words： coal structure of coal seam geophysical logging data support vector machine (SVM) algorithm double binary classification model "one to many" classification mode

收稿日期: 2020-12-07 修回日期: 2021-01-08 出版日期: 2021-06-20

ZTFLH:

P631

基金资助:油气资源与勘探技术教育部重点实验室(长江大学)开放基金(K2018-16)

通讯作者: 杜婷

作者简介: 郭建宏(1997-),男,山东招远人,主要研究方向为测井方法与解释、煤层气测井智能评价。Email: 87942024@qq.com

引用本文:

郭建宏, 杜婷, 张占松, 肖航, 秦瑞宝, 余杰, 王灿. 基于支持向量机与地球物理测井资料的煤体结构识别方法[J]. 物探与化探, 2021, 45(3): 768-777.
GUO Jian-Hong, DU Ting, ZHANG Zhan-Song, XIAO Hang, QIN Rui-Bao, YU Jie, WANG Can. The coal structure identification method based on support vector machine and geophysical logging data. Geophysical and Geochemical Exploration, 2021, 45(3): 768-777.

链接本文:

https://www.wutanyuhuatan.com/CN/10.11720/wtyht.2021.1556 或 https://www.wutanyuhuatan.com/CN/Y2021/V45/I3/768

Table 1 柿庄北区3号煤层煤体结构类型

Table 2 不同煤体结构对应的地球物理测井资料响应范围

Fig.1 三类煤体结构对应地球物理测井资料响应值范围

Fig.2 低维特征向量映射至高纬特征空间

Fig.3 “一对多”方法结构

Fig.4 煤体结构判别流程结构

Fig.5 交叉验证流程图与结果

Table 3 SVM对煤体结构识别结果

[1]	赵庆波. 中国煤层气地质特征及勘探新领域[J]. 天然气工业, 2004, 24(5):4-7.
[1]	Zhao Q B. Geological features of the coalbed methane in China and its new exploration domains[J]. Natural Gas Industry, 2004, 24(5):4-7.
[2]	万玉金, 曹雯. 煤层气单井产量影响因素分析[J]. 天然气工业, 2005, 25(1):124-126.
[2]	Wan Y J, Cao W. Analysis on production affecting factors of single well for coalbed gas[J]. Natural Gas Industry, 2005, 25(1):124-126.
[3]	Li S, Tang D Z, Xu H, et al. Advanced characterization of physical properties of coals with different coal structures by nuclear magnetic resonance and X-ray computed tomography[J]. Computers & Geosciences, 2012, 48:220-227. doi: 10.1016/j.cageo.2012.01.004
[4]	孟召平, 刘珊珊, 王保玉, 等. 不同煤体结构煤的吸附性能及其孔隙结构特征[J]. 煤炭学报, 2015, 40(8):1865-1870.
[4]	Meng Z P, Liu S S, Wang B Y, et al. Adsorption capacity and its pore structure of coals with different coal body structure[J]. Journal of China Coal Society, 2015, 40(8):1865-1870.
[5]	康志勤, 李翔, 李伟, 等. 煤体结构与甲烷吸附/解吸规律相关性实验研究及启示[J]. 煤炭学报, 2018, 43(5):1400-1407.
[5]	Kang Z Q, Li X, Li W, et al. Experimental investigation of methane adsorption /desorption behavior in coals with different coal-body structure and its revelation[J]. Journal of China Coal Society, 2018, 43(5):1400-1407.
[6]	康永尚, 孙良忠, 张兵, 等. 中国煤储层渗透率主控因素和煤层气开发对策[J]. 地质论评, 2017, 63(5):1401-1418.
[6]	Kang Y S, Sun L Z, Zhang B, et al. The controlling factors of coalbed reservoir Permeability and CBM development strategy in China[J]. Geological Review, 2017, 63(5):1401-1418.
[7]	胡奇, 王生维, 张晨, 等. 沁南地区煤体结构对煤层气开发的影响[J]. 煤炭科学技术, 2014, 42(8):65-68.
[7]	Hu Q, Wang S W, Zhang C, et al. Coal structureaffected to coalbed methane development in Qinnan region[J]. Coal Science and Technology, 2014, 42(8):65-68.
[8]	赵立明, 崔若飞, 彭刘亚. 基于测井曲线重构的岩性反演方法圈定构造煤发育带[J]. 煤矿安全, 2013, 44(8):8-10,13.
[8]	Zhao L M, Cui R F, Peng L Y. Delineating deformed coal development zones with lithological inversion methods based on logging curve reconstruction[J]. Safety in Coal Mines, 2013, 44(8):8-10,13.
[9]	张许良, 单菊萍, 彭苏萍. 地质测井技术划分煤体结构探析[J]. 煤炭科学技, 2009, 37(12):88-92.
[9]	Zhang X L, Shan J P, Peng S P. Discussion and analysis on geological logging technology applied to divide coal mass structure[J]. Coal Science and Technology, 2009, 37(12):88-92.
[10]	彭苏萍, 魏文希, 杜文凤, 等. 基于AVO 反演与叠前同步反演预测构造煤分布[J]. 中国矿业大学报, 2018, 47(5):929-934,968.
[10]	Peng S P, Wei W X, Du W F, et al. AVO inversion associated with prestack simultaneous inversion in determining the distribution of tectonic coal[J]. Journal of China University of Mining & Technology, 2018, 47(5):929-934, 968.
[11]	许启鲁, 黄文辉, 杨延绘, 等. 构造煤的测井曲线判识——以柿庄北区块为例[J]. 科学技术与工程, 2016, 16(3):11-16.
[11]	Xu Q L, Huang W H, Yang Y H, et al. Analysis of Identifying Deformed Coal by Logging Curve in Shizhuang North Block, Qinshui Basin, China[J]. Science Technology and Engineering, 2016, 16(3):11-16.
[12]	张超, 黄华州, 徐德林, 等. 基于测井曲线的煤体结构判识[J]. 煤炭科学技术, 2017, 45(9):47-51.
[12]	Zhang C, Huang H Z, Xu D L, et al. Coal structure identified based on logging curve[J]. Coal Science and Technology, 2017, 45(9):47-51.
[13]	陈晶, 黄文辉, 陆小霞, 等. 沁水盆地柿庄地区构造煤定量分析及其物性特征[J]. 煤炭学报, 2017, 42(3):732-737.
[13]	Chen J, Huang W H, Lu X X, et al. Quantitative analysis on tectonically deformed coal and its physical properties in Shizhuang area of Qinshui Basin[J]. Journal of China Coal Society, 2017, 42(3):732-737.
[14]	陈跃, 汤达祯, 许浩, 等. 应用测井资料识别煤体结构及分层[J]. 煤田地质与勘探, 2014, 42(1):19-23.
[14]	Chen Y, Tang D Z, Xu H, et al. Application of logging data in recognition of coal structure and stratification[J]. Coal Geology & Exploration, 2014, 42(1):19-23.
[15]	李存磊, 杨兆彪, 孙晗森, 等. 多煤层区煤体结构测井解释模型构建[J]. 煤炭学报, 2020, 45(2):721-730.
[15]	Li C L, Yang Z B, Sun H S, et al. Construction of a logging interpretation model for coal structure from multi-coal seams area[J]. Journal of China Coal Society, 2020, 45(2):721-730.
[16]	陈粤强, 张晓宏, 浦静怡. 利用测井参数定量识别韩城矿区北区煤体结构[J]. 煤炭科学技术, 2017, 45(9):42-46, 91.
[16]	Chen Y Q, Zhang X H, Pu J Y. Logging parameters applied to quantitatively identify coal structure in Northern Hancheng Mining Are[J]. Coal Science and Technology, 2017, 45(9):42-46, 91.
[17]	侯月华, 姚艳斌, 杨延辉, 等. 基于对应分析技术的煤体结构判别:以沁水盆地安泽区块为例[J]. 煤炭学报, 2016, 41(8):2041-2049.
[17]	Hou Y H, Yao Y B, Yang Y H, et al. Discriminate method of coal structure based on correspondence analysis technology: A case study in the Anze area, Qinshui basin[J]. Journal of China Coal Society, 2016, 41(8):2041-2049.
[18]	曹军涛, 赵军龙, 王轶平, 等. 煤层气含量影响因素及预测方法[J]. 西安石油大学学报:自然科学版, 2013, 28(4):28-34, 94.
[18]	Cao J T, Zhao J L, Wang Y P, et al. Review of influencing factors and prediction methods of gas content in coal seams and prospect of prediction methods[J]. Journal of Xi’an Shiyou University:Natural Science Edition, 2013, 28(4):28-34, 94.
[19]	李涛, 李辉, 王福忠. 基于BP神经网络的煤体结构类型判识模型研究[J]. 煤矿安全, 2011, 42(11):19-22.
[19]	Li T, Li H, Wang F Z. Study of the Differentiating Model for Coal Structure Types Based on BP Neural Network[J]. Safety in Coal Mines, 2011, 42(11):19-22.
[20]	刘振明, 王延斌, 韩文龙, 等. 基于测井资料的BP神经网络的煤体结构预测[J]. 中国煤炭, 2018, 44(6):38-41,55.
[20]	Liu Z M, Wang Y B, Han W L, et al. Prediction of coal structure with BP neural network based on shaft logging data[J]. China Coal, 2018, 44(6):38-41, 55.
[21]	连承波, 赵永军, 李汉林, 等. 基于支持向量机回归的煤层含气量预测[J]. 西安科技大学学报, 2008, 28(4):707-709.
[21]	Lian C B, Zhao Y J, Li H L, et al. Prediction of coal bed gas content based on support vector machine regression[J]. Journal Center of Xi’an University of Science and Technology, 2008, 28(4):707-709.
[22]	汤友谊, 田高岭, 孙四清, 等. 对煤体结构形态及成因分类的改进和完善[J]. 焦作工学院学报:自然科学版, 2004(3):161-164.
[22]	Tang Y Y, Tian G L, Sun S Q, et al. Improvement and perfect way for the classification of the shape and cause formation of coal body texture[J]. Journal of Henan Polytechnic University:Natural Science, 2004(3):161-164.
[23]	傅雪海, 姜波, 秦勇, 等. 用测井曲线划分煤体结构和预测煤储层渗透率[J]. 测井技术, 2003, 27(2):140-143, 177.
[23]	Fu X H, Jiang B, Qin Y, et al. Classification of Coalbody Structure and Prediction of Coal Reservoir Permeability with Log Curves[J]. Well Logging Technology, 2003, 27(2):140-143, 177.
[24]	贾承造, 郑民, 张永峰. 中国非常规油气资源与勘探开发前景[J]. 石油勘探与开发, 2012, 39(2):129-136.
[24]	Jia C Z, Zheng M, Zhang Y F. Unconventional hydrocarbon resources in China and the prospect of exploration and development[J]. Petroleum Exploration and Development, 2012, 39(2):129-136.
[25]	陆小霞, 黄文辉, 王佳旗, 等. 沁水盆地柿庄北深部煤层煤体结构发育特征[J]. 煤田地质与勘探, 2014, 42(3):8-11, 16.
[25]	Lu X X, Huang W H, Wang J Q, et al. The development charactecistics of deep coal structure in northern Shizhuang area[J]. Coal Geology & Exploration, 2014, 42(3):8-11, 16.
[26]	陈玮胤, 姜波, 屈争辉, 等. 碎裂煤显微裂隙分形结构及其孔渗特征[J]. 煤田地质与勘探, 2012, 40(2):31-34.
[26]	Chen W Y, Jiang B, Qu Z H, et al. Fractal structure of microfractures and characteristics of porosity and permeability in cataclastic coals[J]. Coal Geology & Exploration, 2012, 40(2):8-34.
[27]	张俊杰, 赵俊龙. 老厂矿区煤体结构测井判识与分布规律[J]. 地质与勘探, 2019, 55(2):570-578.
[27]	Zhang J J, Zhao J L. Logging discrimination of coal structures and their distribution in the Laochang mining area,eastern Yunnan province[J]. Geology and Exploration, 2019, 55(2):570-580.
[28]	程相振, 胡秋嘉, 杨莹莹. 井径曲线与煤体结构关系探讨——以沁水盆地南部樊庄区为例[J]. 非常规油气, 2016, 3(3):35-38.
[28]	Cheng X Z, Hu Q J, Yang Y Y. Discussion about caliper curves and coal structure:A case study ofFanzhuang area in Qinshui Basin[J]. Unconventional Oil & Gas, 2016, 3(3):35-38.
[29]	姚军朋, 司马立强, 张玉贵. 构造煤地球物理测井定量判识研究[J]. 煤炭学报, 2011, 36(S1):94-98.
[29]	Yao J P, Sima L Q, Zhang Y G. Quantitative identification of deformed coals by geophysical logging[J]. Journal of China Coal Society, 2011, 36(S1):94-98.
[30]	马火林, 汪剑, 王文娟, 等. 构造煤煤层气及裂隙的测井响应和敏感参数分析:以沁水盆地郑庄地区为例[J]. 现代地质, 2015, 29(1):171-178.
[30]	Ma H L, Wang J, Wang W J, et al. Sensitive parameter analysis and logging response characteristics on coalbed methane and fracture of deformed coal:A case study in the Zhengzhuang Block of Qinshui Basin[J]. Geoscience, 2015, 29(1):171-178.
[31]	陶传奇, 王延斌, 倪小明, 等. 基于测井参数的煤体结构预测模型及空间展布规律[J]. 煤炭科学技术, 2017, 45(2):173-177,196.
[31]	Tao C Q, Wang Y B, Ni X M, et al. Prediction model of coal-body structure and spatial distribution law based on logging parameters[J]. Coal Science and Technology, 2017, 45(2):173-177,196.
[32]	雍世和, 张超馍. 测井数据处理与综合解释[M]. 东营: 中国石油大学出版社, 2007:134-139.
[32]	Yong S H, Zhang C M. Logging data processing and comprehensive interpretation[M]. Dongying: China University of Petroleum Press, 2007:134-139.
[33]	陈跃, 汤达祯, 许浩, 等. 基于测井信息的韩城地区煤体结构的分布规律[J]. 煤炭学报, 2013, 38(8):1435-1442.
[33]	Chen Y, Tang D Z, Xu H, et al. The distribution of coal structure in Hancheng based on well logging data[J]. Journal of China Coal Society, 2013, 38(8):1435-1442.
[34]	梅放, 康永尚, 李喆, 等. 中高煤阶煤层煤体结构识别测井法适用性评价研究[J]. 煤炭科学技术, 2019, 47(7):95-107.
[34]	Mei F, Kang Y S, Li Z, et al. Applicability evaluation of logging method for recognition of coal body structure in medium and high rank coal seams[J]. Coal Science and Technology, 2019, 47(7):95-107.
[35]	Sunkens J A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3):293-300. doi: 10.1023/A:1018628609742
[36]	Vapnik V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Network, 1999, 10(5):988-999. doi: 10.1109/72.788640
[37]	马德锋, 李培军. 加入多尺度图像纹理的岩性分类[J]. 岩石学报, 2008, 24(6):1425-1430.
[37]	Ma D F, Li P J. The use of multiscale texture in image classification for lithologic mapping[J]. Acta Petrologica Sinica, 2008, 24(6):1425-1430.
[38]	陈中杰, 蒋刚, 蔡勇. 基于SVM一对一多分类算法的二次细分法研究[J]. 传感器与微系统, 2013, 32(4):44-47.
[38]	Chen Z J, Jiang G, Cai Y. Research of secondary subdivision method for one-versus-one multi-classification algorithm based on SVM[J]. Transducer and Microsystem Technologies, 2013, 32(4):44-47.
[39]	牟丹, 王祝文, 黄玉龙, 等. 基于SVM测井数据的火山岩岩性识别——以辽河盆地东部坳陷为例[J]. 地球物理学报, 2015, 58(5):1785-1793.
[39]	Mou D, Wang Z W, Huang W L, et al. Lithological identification of volcanic rocks from SVM well logging data: Case study in the eastern depression of Liaohe Basin[J]. Chinese Journal of Geophysics, 2015, 58(5):1785-1793.

[1]	郭建宏, 张占松, 张超谟, 周雪晴, 肖航, 秦瑞宝, 余杰. 用地球物理测井资料预测煤层气含量——基于斜率关联度—随机森林方法的工作案例[J]. 物探与化探, 2021, 45(1): 18-28.

Viewed

Full text

Abstract

Cited

Shared

Discussed