鄂尔多斯盆地保德区块二叠系太原组—山西组主采煤层脆性评价——基于卷积神经网络方法

张庆丰; 李子玲; 张继坤; 郝帅; 孙晓光; 尚延洁; 左运

doi:10.11781/sysydz2025010204

鄂尔多斯盆地保德区块二叠系太原组—山西组主采煤层脆性评价——基于卷积神经网络方法

doi: 10.11781/sysydz2025010204

中石油煤层气有限责任公司，北京 100028

详细信息

作者简介:
张庆丰(1985—)，硕士，高级工程师，主要从事煤层气地质研究及勘探开发工作。E-mail: zqf2012@petrochina.com.cn

通讯作者:
李子玲(1990—)，工程师，主要从事煤层气地质研究及勘探开发工作。E-mail: lzl_cbm@petrochina.com.cn

中图分类号: TE132.2
计量
- 文章访问数: 86
- HTML全文浏览量: 36
- PDF下载量: 16
- 被引次数: 0
出版历程
- 收稿日期: 2024-04-02
- 修回日期: 2024-11-11
- 刊出日期: 2025-01-28

Brittleness evaluation of main coal seams in Permian Taiyuan-Shanxi formations, Baode block, Ordos Basin: based on a convolutional neural network method

PetroChina Coalbed Methane Co., Ltd., Beijing 100028, China

摘要

摘要: 鄂尔多斯盆地东北缘保德区块二叠系太原组—山西组煤层具有丰富的煤层气资源，但井间产能差异大，其重要原因在于储层脆性区域差异导致的强非均质性特征。岩石力学参数法是常用的储层脆性评价方法。研究岩石力学参数和脆性可为压裂改造提供重要参数基础，但当前方法多借助经验公式，评价精度有限。基于卷积神经网络方法，构建实验获取的弹性模量、泊松比与多测井曲线转换模型，建立了岩石力学剖面，进而实现脆性定量评价。结果显示：基于卷积神经网络预测含煤层系岩石力学参数适用性较好。保德区块主采4+5^#和8+9^#煤层脆性指数均整体较低，4+5^#煤层较8+9^#煤层脆性指数值略高，两套主采煤层平面分布具有一定的相似性，均在研究区中部和东南部脆性值低。矿物成分差异影响岩石脆性，石英含量越高，弹性模量和脆性指数越大，具有线性关系。
- 卷积神经网络 /
- 煤层脆性 /
- 太原组—山西组 /
- 二叠系 /
- 保德区块 /
- 鄂尔多斯盆地
Abstract: The coal seams of the Permian Taiyuan-Shanxi formations in the Baode block of the northeastern margin of the Ordos Basin have abundant coalbed methane resources. However, the productivity varies greatly among wells, mainly attributed to the strong heterogeneity caused by regional differences in reservoir brittleness. Rock mechanical parameter method is commonly used to evaluate reservoir brittleness. Studying rock mechanical parameters and brittleness can provide an important basis for fracturing modification. However, current methods mostly rely on empirical formulas, leading to limited evaluation accuracy. In this study, a convolutional neural network (CNN) was utilized to construct a conversion model between experimentally obtained elastic modulus, Poisson's ratio, and multi-logging curves. Based on this method, rock mechanical profiles were further established, enabling quantitative evaluation of brittleness. The results indicated that CNN-based predictions of rock mechanical parameters had good applicability for coal-bearing layers. The brittleness indices the main coal seams, 4+5^# and 8+9^#, in the Baode block were generally low. The brittleness index of the 4+5^# seam was slightly higher than that of the 8+9^# seam. Both seams exhibited similar spatial distributions, with low brittleness values in the central and southeastern parts of the study area. Differences in mineral composition affected rock brittleness. Higher quartz content was linearly correlated with greater elastic modulus and brittleness index.
- convolutional neural network /
- coal seam brittleness /
- Taiyuan-Shanxi formations /
- Permian /
- Baode block /
- Ordos Basin
注释:

利益冲突声明/Conflict of Interests

所有作者声明不存在利益冲突。

All authors declare no relevant conflict of interests.

作者贡献/Authors’Contributions

张庆丰、李子玲撰写论文初稿；郝帅、尚延洁、左运完成绘图；张继坤、孙晓光修改论文。所有作者均阅读并同意最终稿件的提交。

ZHANG Qingfeng and LI Ziling wrote the initial draft of the paper. HAO Shuai, SHANG Yanjie, and ZUO Yun completed the drawings. ZHANG Jikun and SUN Xiaoguang revised the paper. All authors have read the final version of the paper and consented to its submission.

HTML全文

图 1 鄂尔多斯盆地保德区块大地构造

据参考文献[17]修改。

Figure 1. Geotectonic map of Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 2 鄂尔多斯盆地保德区块典型井地层柱状图

Figure 2. Stratigraphic histogram of typical wells in Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 3 卷积神经网络结构

Figure 3. Structure of convolutional neural network

下载: 全尺寸图片幻灯片

图 4 鄂尔多斯盆地保德区块B38井二叠系太原组—山西组煤层及其顶底板脆性评价剖面

Figure 4. Brittleness evaluation profiles of coal seams and their roof and floor in Permian Taiyuan-Shanxi formations of well B38 in Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 5 鄂尔多斯盆地保德区块B19井二叠系太原组—山西组煤层及其顶底板脆性评价剖面

Figure 5. Brittleness evaluation profiles of coal seams and their roof and floor in Permian Taiyuan-Shanxi formations of well B19 in Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 6 鄂尔多斯盆地保德区块二叠系太原组—山西组主采煤层脆性评价结果

Figure 6. Brittleness evaluation results of main coal seams in Permian Taiyuan-Shanxi formations of Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 7 鄂尔多斯盆地保德区块砂泥岩层段岩石弹性模量、脆性指数与石英含量的关系

Figure 7. Relationship between elastic modulus, brittleness index, and quartz content of rocks in sand and mudstone layers of Baode block, Ordos Basin

下载: 全尺寸图片幻灯片

图 8 常规方法与卷积神经网络方法预测岩石力学参数精度统计

Figure 8. Accuracy statistics of rock mechanical parameter predictions using conventional method and convolutional neural network method

下载: 全尺寸图片幻灯片

表 1 基于岩石力学参数评价脆性常用公式

Table 1. Common formulas for evaluating brittleness based on rock mechanical parameters

脆性评价公式	参数含义	文献来源
B=(σ_c-σ_t)/(σ_c+σ_t)	σ_c为单轴抗压强度，σ_t为抗张强度	HUCKA等^[20]
B=45°+φ/2	φ为内摩擦角	HUCKA等^[20]
B=σ_cσ_t/2	σ_c为单轴抗压强度，σ_t为抗张强度	ALTINDAG^[21]
B=(E_b+μ_b)/2 E_b=(E_i-E_min)×100%/(E_max-E_min) μ_b=(μ_i-μ_max)×100%/(μ_min-μ_max)	E_b和μ_b为中间参数，E_max和E_min分别为最大和最小弹性模量，μ_max和μ_min分别为最大和最小泊松比	RICKMAN等^[22]
B=0.918σ_c-2.174σ_t-0.913ρ-3.807	σ_c为单轴抗压强度，σ_t为抗张强度，ρ为岩石密度	YAGIZ^[23]
B=Eρ/μ	E为岩石弹性模量，μ为泊松比，ρ为岩石密度	ZHANG等^[24]
B=(2G-2)/λ=1/λ-4	G为剪切模量，λ为拉梅常数	HUANG等^[25]

下载: 导出CSV

表 2 卷积神经网络分析弹性模量、泊松比数据及误差统计

Table 2. Convolutional neural network analysis of elastic modulus, Poisson's ratio, and errors

序号	GR/ API	AC/ (μm/s)	DEN/ (g/cm³)	CNL/ %	实测E/ GPa	预测E/ GPa	误差/ %	实测μ	预测μ	误差/ %
1	130.78	227.52	2.60	22.19	34.00	29.39	13.55	0.25	0.23	8.90
2	129.37	262.97	2.45	23.22	30.00	26.52	11.61	0.27	0.23	16.24
3	176.70	282.47	2.44	20.90	16.35	16.55	1.22	0.20	0.20	0.76
4	73.68	270.20	2.51	14.85	15.39	13.07	15.05	0.19	0.22	13.36
5	72.30	222.49	2.65	15.26	27.42	26.31	4.06	0.36	0.33	8.19
6	89.07	322.11	2.10	76.75	17.32	18.72	8.08	0.27	0.28	2.23
7	129.60	214.02	2.73	23.99	29.11	26.65	8.45	0.25	0.23	8.19
8	83.15	410.30	1.52	60.21	4.18	4.58	9.49	0.43	0.34	20.19
9	108.68	318.67	2.12	40.69	22.10	19.37	12.36	0.22	0.24	11.22
10	153.26	231.97	2.60	46.30	18.72	20.84	11.31	0.21	0.18	12.09
11	126.72	256.61	2.33	21.53	16.24	14.74	9.21	0.24	0.22	9.63
12	142.40	218.46	2.73	24.89	33.88	32.23	4.86	0.28	0.25	10.02
13	119.79	212.46	2.70	18.92	38.90	34.24	11.97	0.25	0.24	2.62
14	146.22	226.91	2.75	21.78	27.62	29.27	5.98	0.20	0.18	11.78
15	87.57	282.79	2.34	21.94	20.00	20.54	2.71	0.19	0.22	18.31
16	127.79	220.18	2.62	20.65	30.00	31.78	5.92	0.16	0.17	3.54
17	103.24	262.79	2.48	30.08	35.00	29.93	14.48	0.17	0.17	0.52
18	85.36	244.21	2.57	16.63	19.40	19.38	0.12	0.33	0.27	17.43
19	132.81	235.85	2.60	45.09	17.40	19.74	13.46	0.37	0.28	24.68
20	143.32	266.80	2.39	28.33	18.00	20.06	11.43	0.25	0.23	9.35
21	101.96	340.12	1.99	31.41	16.00	17.16	7.23	0.27	0.28	4.86
22	83.07	242.83	2.54	16.14	18.00	19.19	6.61	0.25	0.23	7.51
23	105.95	309.07	2.07	29.00	24.00	22.14	7.73	0.25	0.26	5.26
24	143.17	282.50	2.26	24.15	20.00	19.96	0.19	0.23	0.25	7.21
25	126.39	354.55	1.89	34.43	31.00	28.65	7.59	0.22	0.24	11.19
26	124.28	240.55	2.36	26.76	37.00	35.38	4.38	0.24	0.21	10.89
27	92.30	308.08	2.16	27.51	22.00	24.06	9.38	0.26	0.25	2.72
28	44.45	379.29	1.45	55.84	2.56	2.64	3.10	0.39	0.31	20.37
29	100.30	237.43	2.48	17.00	29.00	26.95	7.07	0.30	0.27	9.17
30	91.50	262.08	2.47	17.39	19.00	21.45	12.87	0.19	0.21	9.40
31	132.58	296.92	2.43	25.22	31.00	30.59	1.32	0.20	0.24	22.08
32	144.45	353.38	1.64	65.49	14.29	16.60	16.13	0.37	0.37	1.35
33	46.81	393.85	1.25	62.70	4.68	4.51	3.68	0.39	0.33	16.34
注：E为弹性模量，μ为泊松比；误差计算方法：预测与实测之差的绝对值与实测值的比值。

下载: 导出CSV

参考文献(30)

[1]	陈天, 易远元, 李甜甜, 等. 中国煤层气勘探开发现状及关键技术展望[J]. 现代化工, 2023, 43(9): 6-10. CHEN Tian, YI Yuanyuan, LI Tiantian, et al. Current situation of CBM exploration and development in China and prospects on key technologies[J]. Modern Chemical Industry, 2023, 43(9): 6-10.
[2]	刘大锰, 李俊乾. 我国煤层气分布赋存主控地质因素与富集模式[J]. 煤炭科学技术, 2014, 42(6): 19-24. LIU Dameng, LI Junqian. Main geological controls on distribution and occurrence and enrichment patterns of coalbed methane in China[J]. Coal Science and Technology, 2014, 42(6): 19-24.
[3]	吴国代, 桑树勋, 杨志刚, 等. 地应力影响煤层气勘探开发的研究现状与展望[J]. 中国煤炭地质, 2009, 21(4): 31-34. doi: 10.3969/j.issn.1674-1803.2009.04.007 WU Guodai, SANG Shuxun, YANG Zhigang, et al. Current research status and prospect of geo-stress impact on CBM exploration and exploitation[J]. Coal Geology of China, 2009, 21(4): 31-34. doi: 10.3969/j.issn.1674-1803.2009.04.007
[4]	秦勇, 申建, 史锐. 中国煤系气大产业建设战略价值与战略选择[J]. 煤炭学报, 2022, 47(1): 371-387. QIN Yong, SHEN Jian, SHI Rui. Strategic value and choice on construction of large CMG industry in China[J]. Journal of China Coal Society, 2022, 47(1): 371-387.
[5]	何建华, 李勇, 邓虎成, 等. 基于多元力学实验的深层页岩气储层脆性影响因素分析与定量评价[J]. 天然气地球科学, 2022, 33(7): 1102-1116. HE Jianhua, LI Yong, DENG Hucheng, et al. Quantitative evaluation and influencing factors analysis of the brittleness of deep shale reservoir based on multiple rock mechanics experiments[J]. Natural Gas Geoscience, 2022, 33(7): 1102-1116.
[6]	王濡岳, 胡宗全, 赖富强, 等. 川东北地区下侏罗统自流井组大安寨段陆相页岩脆性特征及其控制因素[J]. 石油与天然气地质, 2023, 44(2): 366-378. WANG Ruyue, HU Zongquan, LAI Fuqiang, et al. Brittleness features and controlling factors of continental shale from Da'anzhai Member of the Lower Jurassic Ziliujing Formation, northeastern Sichuan Basin[J]. Oil & Gas Geology, 2023, 44(2): 366-378.
[7]	孔令运, 宋广朋, 蒋恕, 等. 深层页岩微观力学特征及控制机理: 以涪陵地区平桥区块JYA井深层页岩为例[J]. 石油实验地质, 2024, 46(4): 683-697. doi: 10.11781/sysydz202404683 KONG Lingyun, SONG Guangpeng, JIANG Shu, et al. Micromechanical characteristics and controlling mechanism of deep shale: a case study of well JYA in Pingqiao block, Fuling area[J]. Petroleum Geology & Experiment, 2024, 46(4): 683-697. doi: 10.11781/sysydz202404683
[8]	徐珂, 鞠玮, 张辉, 等. 塔里木盆地库车坳陷白垩系巴什基奇克组致密砂岩力学性质影响因素及其变化规律[J]. 石油实验地质, 2024, 46(4): 823-832. doi: 10.11781/sysydz202404823 XU Ke, JU Wei, ZHANG Hui, et al. Factors affecting the mechanical properties of tight sandstone and their patterns of variation in Cretaceous Bashijiqike Formation of Kuqa Depression in Tarim Basin[J]. Petroleum Geology & Experiment, 2024, 46(4): 823-832. doi: 10.11781/sysydz202404823
[9]	魏海峰. 非均质性页岩水力压裂裂缝扩展形态研究进展[J]. 油气地质与采收率, 2023, 30(4): 156-166. WEI Haifeng. Research progress on fracture propagation patterns of hydraulic fracturing in heterogeneous shale[J]. Petroleum Geology and Recovery Efficiency, 2023, 30(4): 156-166.
[10]	丁然, 张峰, 王勇, 等. 准中深层砂岩脆性及其对岩石破裂模式的影响规律[J]. 油气地质与采收率, 2024, 31(3): 54-62. DING Ran, ZHANG Feng, WANG Yong, et al. Brittleness of deep sandstone in central Junggar Basin and its influence on fracture modes of rocks[J]. Petroleum Geology and Recovery Efficiency, 2024, 31(3): 54-62.
[11]	王芙蓉, 何生, 郑有恒, 等. 江汉盆地潜江凹陷潜江组盐间页岩油储层矿物组成与脆性特征研究[J]. 石油实验地质, 2016, 38(2): 211-218. WANG Furong, HE Sheng, ZHENG Youheng, et al. Mineral composition and brittleness characteristics of the inter-salt shale oil reservoirs in the Qianjiang Formation, Qianjiang Sag[J]. Petroleum Geology & Experiment, 2016, 38(2): 211-218.
[12]	LI Yuwei, LONG Min, ZUO Lihua, et al. Brittleness evaluation of coal based on statistical damage and energy evolution theory[J]. Journal of Petroleum Science and Engineering, 2019, 172: 753-763. doi: 10.1016/j.petrol.2018.08.069
[13]	REN Bo, WANG Shaohua, XUE Junhua, et al. Quantitative evaluation methods of brittle failure characteristics of coal: a case study of hard coal in China[J]. Geotechnical and Geological Engineering, 2019, 37(3): 1421-1434. doi: 10.1007/s10706-018-0696-3
[14]	孙彪, 刘小平, 舒红林, 等. 湖相泥页岩储层脆性评价及影响因素分析: 以苏北盆地海安凹陷曲塘次凹泥页岩为例[J]. 石油实验地质, 2021, 43(6): 1006-1014. https://xueshu.baidu.com/usercenter/paper/show?paperid=1w5f0jq0eq1b0tg0gt520ag0bc654091&site=xueshu_se&hitarticle=1 SUN Biao, LIU Xiaoping, SHU Honglin, et al. Evaluation and influencing factors for brittleness of lacustrine shale reservoir: a case study of Qutang Sub-Sag, Subei Basin[J]. Petroleum Geology & Experiment, 2021, 43(6): 1006-1014. https://xueshu.baidu.com/usercenter/paper/show?paperid=1w5f0jq0eq1b0tg0gt520ag0bc654091&site=xueshu_se&hitarticle=1
[15]	徐凤银, 张伟, 李子玲, 等. 鄂尔多斯盆地保德区块煤层气藏描述与提高采收率关键技术[J]. 天然气工业, 2023, 43(1): 96-112. doi: 10.3787/j.issn.1000-0976.2023.01.010 XU Fengyin, ZHANG Wei, LI Ziling, et al. Coalbed methane reservoir description and enhanced recovery technologies in Baode block, Ordos Basin[J]. Natural Gas Industry, 2023, 43(1): 96-112. doi: 10.3787/j.issn.1000-0976.2023.01.010
[16]	孟文辉, 张文, 王博洋, 等. 保德区块煤粉产出特征及其影响要素剖析[J]. 油气藏评价与开发, 2023, 13(4): 441-450. MENG Wenhui, ZHANG Wen, WANG Boyang, et al. Analysis of characteristics of coal fine production and its influence factors in Baode block[J]. Reservoir Evaluation and Development, 2023, 13(4): 441-450.
[17]	李建新, 胡博文, 方杰, 等. 保德煤矿8号煤瓦斯赋存规律及主控因素研究[J]. 能源与环保, 2022, 44(12): 291-296. LI Jianxin, HU Bowen, FANG Jie, et al. Study on gas occurrence law and main control factors of No. 8 coal seam in Baode Coal Mine[J]. China Energy and Environmental Protection, 2022, 44(12): 291-296.
[18]	赵欣. 煤层气产能主控因素及开发动态特征研究[D]. 徐州: 中国矿业大学, 2017. ZHAO Xin. The study of main influence factors on productivity of coalbed methane well and the development performance[D]. Xuzhou: China University of Mining and Technology, 2017.
[19]	张雷, 徐凤银, 李子玲, 等. 煤层气田单/合层开发影响因素分析及应用: 以保德区块为例[J]. 煤田地质与勘探, 2022, 50(9): 68-77. ZHANG Lei, XU Fengyin, LI Ziling, et al. Analysis on influencing factors of single/multi-layer development of coalbed methane field: a case study of Baode block[J]. Coal Geology & Exploration, 2022, 50(9): 68-77.
[20]	HUCKA V, DAS B. Brittleness determination of rocks by different methods[J]. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 1974, 11(10): 389-392. http://download.xuebalib.com/xuebalib.com.12304.pdf
[21]	ALTINDAG R. The evaluation of rock brittleness concept on rotary blast hold drills[J]. Journal of the Southern African Institute of Mining and Metallurgy, 2002, 102(1): 61-66. http://journals.co.za/deliver/fulltext/saimm/102/1/2770.pdf?itemId=/content/saimm/102/1/AJA0038223X_2763&mimeType=pdf&containerItemId=content/journal/saimm
[22]	RICKMAN R, MULLEN M, PETRE E, et al. A practical use of shale petrophysics for stimulation design optimization: all shale plays are not clones of the Barnett shale[C]//SPE Annual Technical Conference and Exhibition. Denver: SPE, 2008.
[23]	YAGIZ S. Assessment of brittleness using rock strength and density with punch penetration test[J]. Tunnelling and Underground Space Technology, 2009, 24(1): 66-74. doi: 10.1016/j.tust.2008.04.002
[24]	ZHANG Bo, ZHAO Tao, JIN Xiaochun, et al. Brittleness evaluation of resource plays by integrating petrophysical and seismic data analysis[J]. Interpretation, 2015, 3(2): T81-T92. doi: 10.1190/INT-2014-0144.1
[25]	HUANG Xinrui, HUANG Jianping, LI Zhenchun, et al. Brittleness index and seismic rock physics model for anisotropic tight-oil sandstone reservoirs[J]. Applied Geophysics, 2015, 12(1): 11-22. doi: 10.1007/s11770-014-0478-0
[26]	LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
[27]	吴正阳, 莫修文, 柳建华, 等. 裂缝性储层分级评价中的卷积神经网络算法研究与应用[J]. 石油物探, 2018, 57(4): 618-626. doi: 10.3969/j.issn.1000-1441.2018.04.017 WU Zhengyang, MO Xiuwen, LIU Jianhua, et al. Convolutional neural network algorithm for classification evaluation of fractured reservoirs[J]. Geophysical Prospecting for Petroleum, 2018, 57(4): 618-626. doi: 10.3969/j.issn.1000-1441.2018.04.017
[28]	鲁朋, 宋保业, 许琳. 基于一维卷积神经网络的多工况轴承故障诊断[J]. 山东科技大学学报(自然科学版), 2023, 42(5): 88-96. LU Peng, SONG Baoye, XU Lin. Bearing fault diagnosis in multiple working conditions based on one dimensional convolutional neural network[J]. Journal of Shandong University of Science and Technology(Natural Sciences), 2023, 42(5): 88-96.
[29]	张岩, 赵蒙蒙, 孙英伟, 等. 基于卷积神经网络和混合注意力机制的书标检测算法[J]. 山东科技大学学报(自然科学版), 2023, 42(3): 94-102. ZHANG Yan, ZHAO Mengmeng, SUN Yingwei, et al. Title label detection using convolutional neural network and hybrid attention mechanism[J]. Journal of Shandong University of Science and Technology(Natural Sciences), 2023, 42(3): 94-102.
[30]	周文. 裂缝性油气储集层评价方法[M]. 成都: 四川科学技术出版社, 1998: 294. ZHOU Wen. Evaluation methods of fracture reservoir in oil and gas pool[M]. Chengdu: Sichuan Publishing House of Science & Technology, 1998: 294.