古叙矿区煤体及其组合的测井曲线识别技术
|
摘要
不同测井曲线对于煤体结构识别具有多解性。为提高判识精度,通过对古叙矿区石宝矿段煤储层特征和常规测井响应特征分析,提取了对煤体结构反应敏感的8条测井曲线,包括自然伽马、井径Ⅰ、井径Ⅱ、深侧向电阻率、浅侧向电阻率、补偿密度、补偿中子、补偿声波,采用BP(back propagation)神经网络算法,通过MTALAB软件,建立了神经元数量为100、训练函数为TRAINLM,适应学习函数为LEARNGDM、误差分析为MSE的二层BP神经网络煤体结构定量识别模型,预测结果与矿区其他井岩心进行对比,结果表明,基于BP神经网络的煤体结构测井识别方法精确度达89%,效果好于传统的测井判识方法。
Different logging curve has multiple solutions for coal body structure identification. In order to improve the identify accuracy,according to the coal reservoirs and logging data on investigation in the Shibao block of the Guxu coal mine,the 8 logging curves which were reflect sensitivity to coal body was extracted,including natural gamma ray,borehole diameter I,borehde diameter Ⅱ,deep investigate double lateral resistivity log,shallow investigate double lateral resistivity,compensated density,compensated neutron and compensated sonic. Using BP neural network algorithm,the two-layer BP neural network coal structure quantitative identification model with 100 neurons,TRAINLM training function type,LEARNGDM adaptive learning function type and MSE error analysis was established by the MATLAB software. The prediction results are compared with other well cores in the mining area. The results show that the accuracy of the coal structure logging identification method based on BP neural network is 89%,which is better than the traditional logging identification method.
Different logging curve has multiple solutions for coal body structure identification. In order to improve the identify accuracy,according to the coal reservoirs and logging data on investigation in the Shibao block of the Guxu coal mine,the 8 logging curves which were reflect sensitivity to coal body was extracted,including natural gamma ray,borehole diameter I,borehde diameter Ⅱ,deep investigate double lateral resistivity log,shallow investigate double lateral resistivity,compensated density,compensated neutron and compensated sonic. Using BP neural network algorithm,the two-layer BP neural network coal structure quantitative identification model with 100 neurons,TRAINLM training function type,LEARNGDM adaptive learning function type and MSE error analysis was established by the MATLAB software. The prediction results are compared with other well cores in the mining area. The results show that the accuracy of the coal structure logging identification method based on BP neural network is 89%,which is better than the traditional logging identification method.
引文
1杨在全.四川古蔺石宝矿段煤层气富集特征及影响因素[J].四川地质学报,2013,33(4):430-434Yang Zaiquan.Accumulation and control factors for coalbed gas in the Shibao block,Gulin coal field[J].Sichuan Journal of Geology,2013,33(4):430-434
2李焕同.华南赋煤区煤系构造变形特征及其构造演化[D].北京:中国矿业大学(北京),2014Li Huantong.Structural deformation of coal meas-ures characteristics and tectonic evolution of South China coal occurrence district[D].Beijing:China University of Mining,Beijing,2014
3刘强,巫晓兵,何俊宏,等.古叙矿区煤层气成藏开采地质条件分析评价[J].四川地质学报,2012,32(4):441-444Liu Qiang,Wu Xiaobing,He Junhong,et al.Accumulation and mining conditions of coalbed gas in the Gulin-Xuyong mine area[J].Sichuan Journal of Geology,2012,32(4):441-444
4陈萍,张荣飞,唐修义.对利用测井曲线判识构造煤方法的认识[J].煤田地质与勘探,2014,42(3):78-81Chen Ping,Zhang Rongfei,Tang Xiuyi.Some under standing of identifying tectonic coal by logging curve[J].Coal Geology&Exploration,2014,42(3):78-81
5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):19-23Chen Yue,Tang Dazhen,Xu Hao,et al.Application of logging data in recognition of coal structure and stratification[J].Coal Geology&Exploration,2014,42(1):19-23
6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):47-51Zhang Chao,Huang Huazhou,Xu Delin,et al.Coal structure identified based on logging curve[J].Coal Science and Technology,2017,5(9):48-51
7黄兆辉.高阶煤层气储层测井评价方法及其关键问题研究[D].北京:中国地质大学(北京),2014Huang Zhaohui.Research on log evaluation of high rank coalbed methane reservoirs and some key issues[D].Beijing:China University of Geosciences,Beijing,2014
8陈芳林,张宝辉,汪贵华,等.改进的神经网络非均匀性校正算法研究[J].科学技术与工程,2016,16(33):215-220Chen Fanglin,Zhang Baohui,Wang Guihua,et al.Research on improved neural network nonuniformity correction algorithm[J].Science Technology and Engineering,2016,16(33):215-220
9李娜,刘冰,王伟.基于单隐层前馈神经网络的优化算法[J].科学技术与工程,2019,19(1):136-141Li Na,Liu Bing,Wang Wei.An optimization algorithm based on single hidden layer feedforward neural networks[J].Science Technology and Engineering,2019,19(1):136-141
10朱大齐.人工神经网络研究现状及展望[J].江南大学学报,2004,3(1):103-106Zhu Daqi.The research progress and prospects of artificial neural networks[J].Journal of Southern Yangtze University,2004,3(1):103-106
11 Atlas K.神经网络的优化与用于优化的神经网络[D].大连:大连理工大学,2013Atlas K.Optimizations of and by neural networks[D].Dalian:Dalian University of Technology,2013
12张莉.几类神经网络的分析与优化及其应用研究[D].西安:西安电子科技大学,2012Zhang Li.Analysis and optimization of several neural networks and their applications[D].Xi'an:Xidian University,2012
13肖忠祥,赵军龙.煤型气储层测井评价技术[J].中国煤炭地质,2008,20(8):64-66Xiao Zhongxiang,Zhao Junlong.Coaliferous gas reservoir well logging assessment technology[J].Coal Geology of China,2008,20(8):64-66
14张松扬.煤层气地球物理测井技术现状及发展趋势[J].测井技术,2009,33(1):9-15Zhang Songyang.Actualities and progresses coalbed methane geophysical logging technologies[J].Well Logging Technology,2009,33(1):9-15
15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):732-737Chen Jing,Huang Wenhui,Lu Xiaoxia,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
16孟召平,刘珊珊,王保玉,等.晋城矿区煤体结构及其测井响应特征研究[J].煤炭科学技术,2015,43(2):58-63,67Meng Zhaoping,Liu Shanshan,Wang Baoyu,et al.Study on feature of coal body structure and logging response in Jincheng mining area[J].Coal Science and Technology,2015,43(2):58-63,67
17刘丽民,魏庆喜,徐仁桂.煤层气常规测井技术与应用[J].中国煤层气,2008,5(1):28-31Liu Limin,Wei Qingxi,Xu Rengui.Conventional CBM logging technologies and their applications[J].China Coalbed Methane,2008,5(1):28-31
18胡素华,冯迎辉,韦新红,等.煤层气测井资料解释技术在中原油田的应用[J].石油天然气学报,2008,30(2):474-476Hu Suhua,Feng Yinghui,Wei Xinhong,et al.Application of CBMlogging data interpretation tech-nology in Zhongyuan Oilfield[J].Journal of Oil and Gas Technology,2008,30(2):474-476
19刘之的,赵靖舟,时保宏,等.煤层气储层“三品质”测井定量评价方法研究---以鄂尔多斯盆地东缘韩城矿区为例[J].天然气地球科学,2015,26(5):966-978Liu Zhidi,Zhao Jingzhou,Shi Baohong,et al.Study on quantitative evaluation method of“three-quality”logging in coalbed methane reservoir taking Hancheng mining area in the eastern margin of Ordos Basin as an example[J].Natural Gas Geoscience,2015,26(5):966-978
20张吉昌,邢玉忠,郑丽辉.利用人工智能技术进行裂缝识别研究[J].测井技术,2005,29(1):52-54Zhang Jichang,Xing Yuzhong,Zheng Lihui.Using artificial intelligent technique to identify fractures[J].Well Logging Technology,2005,29(1):52-54
21张洪,邹乐君,沈晓华.BP神经网络在测井岩性识别中的应用[J].地质与勘探,2002,38(6):63-65Zhang Hong,Zou Lejun,Shen Xiaohua.Application of BP neural network in logging lithology identification[J].Geology and Exploration,2002,38(6):63-65
22 Zheng Y,Liu Q,Chen E H,et al.Exploiting multi-channels deep convolutional neural networks for multivariate time series classification[J].Frontiers of Computer Science,2015,10(1):96-112
23 Abdel-Hamid O,Mohamed A,Jiang H,et al.Convolutional neural networks for speech recognition[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2014,22(10):1533-1545
2李焕同.华南赋煤区煤系构造变形特征及其构造演化[D].北京:中国矿业大学(北京),2014Li Huantong.Structural deformation of coal meas-ures characteristics and tectonic evolution of South China coal occurrence district[D].Beijing:China University of Mining,Beijing,2014
3刘强,巫晓兵,何俊宏,等.古叙矿区煤层气成藏开采地质条件分析评价[J].四川地质学报,2012,32(4):441-444Liu Qiang,Wu Xiaobing,He Junhong,et al.Accumulation and mining conditions of coalbed gas in the Gulin-Xuyong mine area[J].Sichuan Journal of Geology,2012,32(4):441-444
4陈萍,张荣飞,唐修义.对利用测井曲线判识构造煤方法的认识[J].煤田地质与勘探,2014,42(3):78-81Chen Ping,Zhang Rongfei,Tang Xiuyi.Some under standing of identifying tectonic coal by logging curve[J].Coal Geology&Exploration,2014,42(3):78-81
5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):19-23Chen Yue,Tang Dazhen,Xu Hao,et al.Application of logging data in recognition of coal structure and stratification[J].Coal Geology&Exploration,2014,42(1):19-23
6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):47-51Zhang Chao,Huang Huazhou,Xu Delin,et al.Coal structure identified based on logging curve[J].Coal Science and Technology,2017,5(9):48-51
7黄兆辉.高阶煤层气储层测井评价方法及其关键问题研究[D].北京:中国地质大学(北京),2014Huang Zhaohui.Research on log evaluation of high rank coalbed methane reservoirs and some key issues[D].Beijing:China University of Geosciences,Beijing,2014
8陈芳林,张宝辉,汪贵华,等.改进的神经网络非均匀性校正算法研究[J].科学技术与工程,2016,16(33):215-220Chen Fanglin,Zhang Baohui,Wang Guihua,et al.Research on improved neural network nonuniformity correction algorithm[J].Science Technology and Engineering,2016,16(33):215-220
9李娜,刘冰,王伟.基于单隐层前馈神经网络的优化算法[J].科学技术与工程,2019,19(1):136-141Li Na,Liu Bing,Wang Wei.An optimization algorithm based on single hidden layer feedforward neural networks[J].Science Technology and Engineering,2019,19(1):136-141
10朱大齐.人工神经网络研究现状及展望[J].江南大学学报,2004,3(1):103-106Zhu Daqi.The research progress and prospects of artificial neural networks[J].Journal of Southern Yangtze University,2004,3(1):103-106
11 Atlas K.神经网络的优化与用于优化的神经网络[D].大连:大连理工大学,2013Atlas K.Optimizations of and by neural networks[D].Dalian:Dalian University of Technology,2013
12张莉.几类神经网络的分析与优化及其应用研究[D].西安:西安电子科技大学,2012Zhang Li.Analysis and optimization of several neural networks and their applications[D].Xi'an:Xidian University,2012
13肖忠祥,赵军龙.煤型气储层测井评价技术[J].中国煤炭地质,2008,20(8):64-66Xiao Zhongxiang,Zhao Junlong.Coaliferous gas reservoir well logging assessment technology[J].Coal Geology of China,2008,20(8):64-66
14张松扬.煤层气地球物理测井技术现状及发展趋势[J].测井技术,2009,33(1):9-15Zhang Songyang.Actualities and progresses coalbed methane geophysical logging technologies[J].Well Logging Technology,2009,33(1):9-15
15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):732-737Chen Jing,Huang Wenhui,Lu Xiaoxia,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
16孟召平,刘珊珊,王保玉,等.晋城矿区煤体结构及其测井响应特征研究[J].煤炭科学技术,2015,43(2):58-63,67Meng Zhaoping,Liu Shanshan,Wang Baoyu,et al.Study on feature of coal body structure and logging response in Jincheng mining area[J].Coal Science and Technology,2015,43(2):58-63,67
17刘丽民,魏庆喜,徐仁桂.煤层气常规测井技术与应用[J].中国煤层气,2008,5(1):28-31Liu Limin,Wei Qingxi,Xu Rengui.Conventional CBM logging technologies and their applications[J].China Coalbed Methane,2008,5(1):28-31
18胡素华,冯迎辉,韦新红,等.煤层气测井资料解释技术在中原油田的应用[J].石油天然气学报,2008,30(2):474-476Hu Suhua,Feng Yinghui,Wei Xinhong,et al.Application of CBMlogging data interpretation tech-nology in Zhongyuan Oilfield[J].Journal of Oil and Gas Technology,2008,30(2):474-476
19刘之的,赵靖舟,时保宏,等.煤层气储层“三品质”测井定量评价方法研究---以鄂尔多斯盆地东缘韩城矿区为例[J].天然气地球科学,2015,26(5):966-978Liu Zhidi,Zhao Jingzhou,Shi Baohong,et al.Study on quantitative evaluation method of“three-quality”logging in coalbed methane reservoir taking Hancheng mining area in the eastern margin of Ordos Basin as an example[J].Natural Gas Geoscience,2015,26(5):966-978
20张吉昌,邢玉忠,郑丽辉.利用人工智能技术进行裂缝识别研究[J].测井技术,2005,29(1):52-54Zhang Jichang,Xing Yuzhong,Zheng Lihui.Using artificial intelligent technique to identify fractures[J].Well Logging Technology,2005,29(1):52-54
21张洪,邹乐君,沈晓华.BP神经网络在测井岩性识别中的应用[J].地质与勘探,2002,38(6):63-65Zhang Hong,Zou Lejun,Shen Xiaohua.Application of BP neural network in logging lithology identification[J].Geology and Exploration,2002,38(6):63-65
22 Zheng Y,Liu Q,Chen E H,et al.Exploiting multi-channels deep convolutional neural networks for multivariate time series classification[J].Frontiers of Computer Science,2015,10(1):96-112
23 Abdel-Hamid O,Mohamed A,Jiang H,et al.Convolutional neural networks for speech recognition[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2014,22(10):1533-1545