Pattern recognition model of coalbed methane productivity based on random forest algorithm

TAN Chenyang; ZHANG Zhansong; ZHOU Xueqing; GUO Jianhong; XIAO Hang; CHEN Tao; QIN Ruibao; YU Jie

Safety in Coal Mines > 2022 > 53(2): 170-178,186.

TAN Chenyang, ZHANG Zhansong, ZHOU Xueqing, GUO Jianhong, XIAO Hang, CHEN Tao, QIN Ruibao, YU Jie. Pattern recognition model of coalbed methane productivity based on random forest algorithm[J]. Safety in Coal Mines, 2022, 53(2): 170-178,186.

Citation:

PDF (5055 KB)

Pattern recognition model of coalbed methane productivity based on random forest algorithm

More Information

Published Date: February 19, 2022

Graphical Abstract

Abstract

Abstract

In order to explore the productivity characteristics of coalbed methane（ＣＢＭ） wells and reasonably allocate the development sequence, according to the actual production data analysis of CBM production wells in Shizhuang south area of Qinshui Basin, four types of characteristic values of the drainage curve were extracted: average daily gas production, peak daily gas production, the time to reach the peak and the production time. Combining the shape of the drainage curve and the 4 characteristic values, three production capacity modes were established, and the production characteristics of the three production capacity modes were analyzed. The random forest algorithm is used to establish the nonlinear relationship between the three productivity models and the geophysical logging data corresponding to the No.3 coal seam. The hyperparameters of the random forest model are determined by grid search combined with cross-validation, and the log curve is established. Classify the prediction model for the capacity pattern of the feature vector. Comparing the predicted category with the actual category, the accuracy rate of prediction reached 91.7%. This shows that the CBM productivity pattern recognition based on the random forest algorithm has high prediction accuracy.
- coalbed methane,
- production mode,
- random forest,
- geophysical logging curve,
- drainage law

FullText(HTML)

References (26)

References

[1]	李贵红，吴信波，刘钰辉，等.沁水潘庄煤层气井全生命周期产气规律与效果评价[J].煤炭学报，2020（S2）：894-903. LI Guihong, WU Xinbo, LIU Yuhui, et al. Full life-circle production and effect evaluation of Panzhuang coalbed methane wells in Qinshui Basin[J]. Journal of China Coal Society, 2020（S2）: 894-903.
[2]	李辛子，王运海，姜昭琛，等.深部煤层气勘探开发进展与研究[J].煤炭学报，2016，41（1）：24-31. LI Xinzi, WANG Yunhai, JIANG Zhaochen, et al. Progress and study on exploration and production for deep coalbed methane[J]. Journal of China Coal Society, 2016, 41（1）: 24-31.
[3]	曹作华，范亚芳，王健，等.我国十年来煤层气研究热点分布转换与产业发展[J].煤炭科学技术，2015，43（2）：5-9. CAO Zuohua, FAN Yafang, WANG Jian, et al. Transformation and industrial development of coalbed methane study hot point distribution in passed ten years of China[J]. Coal Science and Technology, 2015, 43（2）: 5-9.
[4]	秦义，李仰民，白建梅，等.沁水盆地南部高煤阶煤层气井排采工艺研究与实践[J].天然气工业，2011，31（11）：22-25. QIN Yi, LI Yangmin, BAI Jianmei, et al. Technologies in the CBM drainage and production of wells in the southern Qinshui Basin with high-rank coal beds[J]. Natural Gas Industry, 2011, 31（11）: 22-25.
[5]	邵先杰，王彩凤，汤达祯，等.煤层气井产能模式及控制因素-以韩城地区为例[J].煤炭学报，2013，38（2）：271-276. SHAO Xianjie, WANG Caifeng, TANG Dazhen, et al. Productivity mode and control factors of coalbed methane wells: a case from Hancheng Region[J]. Journal of China Coal Society, 2013, 38（2）: 271-276.
[6]	柳迎红，房茂军，廖夏.煤层气排采阶段划分及排采制度制定[J].洁净煤技术，2015，21（3）：121-124. LIU Yinghong, FANG Maojun, LIAO Xia. Production stages division and drainage production system development of coalbed methane[J]. Clean Coal Technology, 2015, 21（3）: 121-124.
[7]	王超文，彭小龙，贾春生，等.枣园区块煤层气生产阶段划分及产能模式研究[J].油气藏评价与开发，2016， 6（4）：74-78. WANG Chaowen, PENG Xiaolong, JIA Chunsheng, et al. Production stage and productivity mode division of coalbed methane in Zaoyuan Block[J]. Reservoir Evaluation and Development, 2016, 6（4）: 74-78.
[8]	陈龙伟，左银卿，田炜，等.樊庄区块煤层气水平井产能模式划分及分类评价[J].煤炭科学技术，2017，45（2）：109. CHEN Longwei, ZUO Yinqing, TIAN Wei, et al. Division evaluation and production mode classification of coalbed methane horizontal well in Fanzhuang Block[J]. Coal Science and Technology, 2017, 45（2）: 109.
[9]	伊永祥，唐书恒，张松航，等.沁水盆地柿庄南区块煤层气井储层压降类型及排采控制分析[J].煤田地质与勘探，2019，47（5）：118-126. YI Yongxiang, TANG Shuheng, ZHANG Songhang, et al. Analysis on the type of reservoir pressure drop and drainage control of coalbed methane well in the southern block of Shizhuang[J]. Coal Geology & Exploration, 2019, 47（5）: 118-126.
[10]	张松航，唐书恒，李忠城，等.煤层气井产出水化学特征及变化规律-以沁水盆地柿庄南区块为例[J].中国矿业大学学报，2015，44（2）：292-299. ZHANG Songhang, TANG Shuheng, LI Zhongcheng, et al. The hydrochemical characteristics and ion changes of the coproduced water: taking Shizhuangnan Block, south of the Qinshui Basin as an example[J]. Journal of China University of Mining & Technology, 2015, 44（2）: 292-299.
[11]	陶俊杰，李叶朋，杨春莉，等.沁水盆地南部高煤阶煤层气井区产气量排采控制及优化[J].煤矿安全，2018， 49（4）：5-8. TAO Junjie, LI Yepeng, YANG Chunli, et al. Drainage and extraction control and optimization of gas production in a high coal rank coalbed gas well in Southern Qinshui Basin[J]. Safety in Coal Mines, 2018, 49（4）: 5-8.
[12]	李士才，邵先杰，接敬涛，等.煤层气水平井产能预测数值模拟研究[J].重庆科技学院学报（自然科学版），2015，17（2）：76-80. LI Shicai, SHAO Xianjie, JIE Jingtao, et al. The establishment of productivity prediction model and numerical simulation of CBM horizontal wells[J]. Journal of Chongqing University of Science and Technology（Natural Sciences Edition）, 2015, 17（2）: 76-80.
[13]	孟召平，田永东，雷旸.煤层含气量预测的BP神经网络模型与应用[J].中国矿业大学学报，2008（4）：456. MENG Zhaoping, TIAN Yongdong, LEI Yang. Prediction models of coal bed gas content based on BP neural networks and its applications[J]. Journal of China University of Mining & Technology, 2008（4）: 456-461.
[14]	李艳芳，程建远，王成.基于支持向量机的地震属性优选及煤层气预测[J].煤田地质与勘探，2012，40（6）：75-78. LI Yanfang, CHENG Jianyuan, WANG Cheng. Seismic attribute optimization based on support vector machine and coalbed methane prediction[J]. Coal Geology & Exploration, 2012, 40（6）: 75-78.
[15]	苗玉，杨建华，卢伟.基于灰色支持向量机的煤层气单井采气参数预测[J].计算机应用，2016，36（S2）：108-111. MIAO Yu, YANG Jianhua, LU Wei. Coal-bed methane well’s parameter prediction based on grey support vector machine[J]. Journal of Computer Applications, 2016, 36（S2）: 108-111.
[16]	李贵红，张泓，崔永君，等.基于多元逐步回归分析的煤储层含气量预测模型-以沁水盆地为例[J].煤田地质与勘探，2005（3）：22-25. LI Guihong, ZHANG Hong, CUI Yongjun, et al. A predictive model of gas content in coal reservoirs based on multiple stepwise regression analysis: a case study from Qinshui Basin[J]. Coal Geology & Exploration, 2005（3）: 22-25.
[17]	胡亚斐，张遂安，吴峙颖.基于地质多元统计分析的煤层气含量建模方法-以沁水盆地南部某区块3号煤层为例[J].煤田地质与勘探，2013，41（2）：33-36. HU Yafei, ZHANG Suian, WU Zhiying. The gas content modeling method based on geological statistical analysis: with seam No.3 in Southern Qinshui Basin as an example[J]. Coal Geology & Exploration, 2013, 41（2）: 33-36.
[18]	郭建宏，张占松，张超谟，等.基于灰色系统与测井方法的煤层气含量预测及应用[J].物探与化探，2020， 44（5）：1190-1200. GUO Jianhong, ZHANG Zhansong, ZHANG Chaomo, et al. Prediction and application of coalbed methane content based on gray system and logging method[J]. Geophysical and Geochemical Exploration, 2020, 44（5）: 1190-1200.
[19]	明盈，汤达祯，陶树，等.煤层气水平井产能预测模型及其适用性研究[J].煤炭科学技术，2016，44（12）：113-117. MING Ying, TANG Dazhen, TAO Shu, et al. Study on productivity prediction model of horizontal coalbed meth-ane well and its applicability[J]. Coal Science and Technology, 2016, 44（12）: 113-117.
[20]	郭建宏，张占松，张超谟，等.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. GUO Jianhong, ZHANG Zhansong, ZHANG Chaomo, et al. The exploration of predicting CBM content by geophysical logging data: a case study based on slope correlation random forest method[J]. Geophysical and Geochemical Exploration, 2021, 45（1）: 18-28.
[21]	朱庆忠，胡秋嘉，杜海为，等.基于随机森林算法的煤层气直井产气量模型[J].煤炭学报，2020，45（8）：2846-2855. ZHU Qingzhong, HU Qiujia, DU Haiwei, et al. A gas production model of vertical coalbed methane well based on random forest algorithm[J]. Journal of China Coal Society, 2020, 45（8）: 2846-2855.
[22]	方匡南，吴见彬，朱建平，等.随机森林方法研究综述[J].统计与信息论坛，2011，26（3）：32-38. FANG Kuangnan, WU Jianbin, ZHU Jianping, et al. A review of technologies on random forests[J].Statistics & Information Forum, 2011, 26（3）: 32-38.
[23]	曹正凤.随机森林算法优化研究[D].北京：首都经济贸易大学，2014.
[24]	雍凯.随机森林的特征选择和模型优化算法研究[D].哈尔滨：哈尔滨工业大学，2008.
[25]	纪昌明，周婷，向腾飞，等.基于网格搜索和交叉验证的支持向量机在梯级水电系统隐随机调度中的应用[J].电力自动化设备，2014，34（3）：125-131. JI Changming, ZHOU Ting, XIANG Tengfei, et al. Application of support vector machine based on grid search and cross validation in implicit stochastic dispatch of cascaded hydropower stations[J]. Electric Power Automation Equipment, 2014, 34（3）: 125-131.
[26]	陈元鹏，罗明，彭军还，等.基于网格搜索随机森林算法的工矿复垦区土地利用分类[J].农业工程学报，2017，33（14）：250-257. CHEN Yuanpeng, LUO Ming, PENG Junhuan, et al. Classification of land use in industrial and mining reclamation area based grid-search and random forest classifier[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33（14）: 250-257.

[1]	LI Tao, ZOU Yingjie, FAN Hongdong, LIN Tao. InSAR mining subsidence basin detection method based on DBD-Net[J]. Safety in Coal Mines, 2024, 55(4): 177-186. DOI: 10.13347/j.cnki.mkaq.20230593
[2]	ZHANG Hongyue, WANG Daoshun. InSAR monitoring and analysis of surface subsidence in mining area under adjacent mining face[J]. Safety in Coal Mines, 2023, 54(6): 184-192.
[3]	WANG Fengyun, TAO Qiuxiang, CHEN Yang, HAN Yu, GUO Zaijie. Monitoring and early-warning of surface deformation in mine goaf based on InSAR[J]. Safety in Coal Mines, 2022, 53(6): 195-203.
[4]	WANG Xinling, DU Yuling, JIANG Jinxiong, ZHAO Feng, YAN Shiyong. Monitoring of temporal and spatial evolution of surface deformation in Yuncheng Mining Area with DS-InSAR[J]. Safety in Coal Mines, 2021, 52(5): 120-125.
[5]	YANG Ju, WU Kan, DIAO Xinpeng, ZHOU Dawei. Application of SBAS-InSAR Deformation Characteristic Monitoring in Cause Analysis of Building Damage[J]. Safety in Coal Mines, 2020, 51(6): 174-178,183.
[6]	LENG Hongwei, TAO Qiuxiang, LIU Guolin. Mining Subsidence Monitoring Based on Combination Method of Multi-Look and Full-Resolution Interferogram[J]. Safety in Coal Mines, 2020, 51(2): 124-127.
[7]	LIU Xiao-fei, DENG Ka-zhong. Residual Deformation Monitoring of Goaf Based on D-InSAR[J]. Safety in Coal Mines, 2013, 44(7): 193-195.
[8]	PENG Ke-xiang, GUO Guang-li, WU Wen-juan. Monitoring Surface Subsidence in Mining Area Based on TerraSAR-X Data[J]. Safety in Coal Mines, 2013, 44(6): 48-50,54.
[9]	YU Yong, LIU Zhen-guo. Experimental Study of Using TerraSAR-X Image to Monitor Mine Area Subsidence[J]. Safety in Coal Mines, 2013, 44(4): 75-77.
[10]	LIU Xiao-Fei, DENG Ka-Zhong, XUE Ji-Qun, CHEN Bing-Qian, WANG Jiang-Tao. Deformation Monitoring of Highway Goaf Based on D-InSAR Technology[J]. Safety in Coal Mines, 2012, 43(8): 207-209.

Cited By

Get Citation

PDF

XML

Article views (32) PDF downloads (9)

Turn off MathJax

Article Contents

Abstract

References

Pattern recognition model of coalbed methane productivity based on random forest algorithm

Abstract

References

Related Articles

Catalog

Pattern recognition model of coalbed methane productivity based on random forest algorithm

Abstract

References

Related Articles

Catalog

Export File

Citation

Format

Content