SVM算法在渤海湾盆地南堡凹陷火山岩储层流体预测中的应用

doi:10.13809/j.cnki.cn32-1825/te.2023.02.006

Abstract

Abstract:

Volcanic rock reservoirs are affected by many factors such as lithofacies, lithology, and reservoir space types, and fluid identification is difficult, which is one of the difficulties in well logging interpretation. It is urgent to establish a convenient and quick identification method. For this reason, the SVM（Support Vector Machine） algorithm of machine learning is used to predict the fluids of unknown reservoirs for the volcanic rock reservoirs in the Nanpu Sag of the Bohai Bay Basin. The research shows that: ① Comprehensive application of core, well logging, mud logging and other data to optimize fluid sensitive characteristic parameters, single information sensitive parameters are acoustic time difference, compensation density, resistivity, multi-information fusion parameters are natural gamma relative value, total hydrocarbon Ratio, hydrocarbon gas density index, hydrocarbon gas humidity index, the above seven parameters participate in the model establishment; ②Using the SVM algorithm for volcanic fluid prediction, the reservoir fluid is divided into three types: oil layer, oil-water layer and water layer. Sensitive parameters of well logging and mud logging are selected, and a reliable sample library is trained. The correct judgment rate of the prediction library reaches 90 %. The prediction application of SVM algorithm shows that it has low calculation complexity and strong generalization ability, which can quickly identify the fluid properties of volcanic rocks and provide a reliable basis for the analysis of oil and gas accumulation rules and the production and development of geological reserves.

Key words: SVM algorithm, reservoir characteristics, fluid prediction, volcanic rocks, Nanpu Sag

CLC Number:

TE19

ZHANG Ying,QU Lili,ZHU Lu,ZHANG Yan,HAN Siyang,ZENG Cheng. Application of SVM algorithm in fluid prediction of volcanic reservoirs in Nanpu Sag, Bohai Bay Basin[J].Reservoir Evaluation and Development, 2023, 13(2): 181-189.

Figures/Tables 11

Fig. 1

Table 1

Fig. 2

Table 2

Fig. 3

Fig. 4

Table 3

Fluid prediction parameters of volcanic reservoir"

特征参数	$A C (μ s / f t ?)$	$D E N (g / c m 3 ?)$	$R L L D (Ω · m)$	$Δ G R$	全烃比值	烃气密度指数	烃气湿度指数
相关系数	0.43	0.48	0.36	0.38	0.48	0.55	0.42

Table 3

Table 4

Training database for SVM to identify fluid properties of volcanic rocks"

训练数据
井号	$A C (μ s / f t ?)$	$D E N (g / c m 3 ?)$	$R L L D (Ω · m)$	△GR	全烃比值	烃气湿度指数	烃气密度指数	试油结论
NP11-A1	91.72	2.57	12.30	0.18	12.12	36.16	6.11	油层
NP11-A2	88.56	2.41	14.50	0.25	13.47	52.59	4.47	油层
NP11-A3	88.20	2.26	11.30	0.32	25.70	45.51	5.31	油层
NP11-A4	96.00	2.30	25.00	0.31	26.43	43.53	4.74	油层
NP11-A5	82.40	2.40	20.00	0.14	43.94	31.84	3.83	油层
NP11-A6	84.30	2.47	9.80	0.29	110.41	40.22	3.78	油层
NP11-A7	78.70	2.48	4.10	0.22	5.55	51.81	6.08	油水同层
NP11-A8	95.66	2.14	4.80	0.16	6.00	86.65	10.00	油水同层
NP11-A9	73.40	2.64	8.80	0.23	11.50	23.44	5.50	油水同层
NP11-A10	83.33	2.39	7.80	0.30	7.04	34.52	5.77	油水同层
NP11-A11	87.00	2.30	10.50	0.29	10.50	79.08	9.25	油水同层
NP11-A12	88.81	2.54	7.60	0.16	9.73	33.44	5.43	油水同层
NP11-A13	85.23	2.35	6.50	0.31	8.16	87.39	7.57	油水同层
NP11-A14	90.29	2.48	3.50	0.24	4.42	39.20	7.53	水层
NP11-A15	80.05	2.59	3.50	0.18	2.62	45.24	9.00	水层
NP11-A16	71.54	2.70	6.50	0.25	3.96	50.69	8.33	水层
NP11-A17	87.32	2.35	5.20	0.32	5.16	35.72	6.33	水层
NP11-A18	101.59	2.20	2.50	0.31	4.91	32.87	7.74	水层
NP11-A19	95.18	2.20	6.50	0.22	6.28	24.33	7.28	水层
NP11-A20	100.24	2.33	6.00	0.16	7.68	33.41	7.77	水层

Table 4

Table 5

SVM identifies volcanic rock fluid properties prediction database"

预测数据
井号	$A C (μ s / f t ?)$	$D E N (g / c m 3)$	$R L L D (Ω · m)$	△GR	全烃比值	烃气湿度指数	烃气密度指数	试油结论	预测结果	对比
NP11-B1	100.00	2.26	9.80	0.11	15.57	27.61	5.45	油层	油层	正确
NP11-B2	97.00	2.22	15.00	0.26	19.60	49.71	5.92	油层	油层	正确
NP11-B3	83.20	2.47	10.90	0.19	13.92	40.70	5.06	油层	油层	正确
NP11-B4	93.06	2.38	13.20	0.21	36.33	30.13	4.10	油层	油层	正确
NP11-B5	83.12	2.48	21.30	0.28	104.96	23.56	4.89	油层	油层	正确
NP11-B6	74.50	2.42	6.50	0.35	5.25	32.30	6.34	油水同层	油水同层	正确
NP11-B7	80.45	2.42	5.10	0.34	5.64	131.54	7.54	油水同层	油水同层	正确
NP11-B8	85.74	2.50	8.10	0.09	6.22	161.15	11.22	油水同层	油层	错误
NP11-B9	86.73	2.39	10.50	0.24	7.02	73.04	6.56	油水同层	油水同层	正确
NP11-B10	82.12	2.45	6.50	0.17	7.42	65.82	8.50	油水同层	油水同层	正确
NP11-B11	77.37	2.50	5.80	0.23	8.94	17.44	4.92	油水同层	油水同层	正确
NP11-B12	91.64	2.35	9.60	0.30	5.09	119.40	10.00	油水同层	油水同层	正确
NP11-B13	81.58	2.26	3.50	0.37	2.66	38.53	7.14	水层	水层	正确
NP11-B14	91.06	2.59	4.50	0.36	3.56	25.60	8.58	水层	水层	正确
NP11-B15	71.23	2.65	3.60	0.11	3.29	52.00	9.00	水层	水层	正确
NP11-B16	75.23	2.55	5.30	0.26	4.56	34.87	6.84	水层	水层	正确
NP11-B17	98.76	2.39	5.50	0.19	5.21	43.03	11.20	水层	油水同层	错误
NP11-B18	91.53	2.11	3.50	0.25	5.29	30.05	8.38	水层	水层	正确
NP11-B19	101.01	2.44	4.10	0.35	6.54	30.78	9.00	水层	水层	正确
NP11-B20	96.13	2.34	3.66	0.29	4.35	29.50	6.32	水层	水层	正确

Table 5

Fig. 5

Fig.6

References 27

[1]	邹才能, 候连华, 王京红, 等. 火山岩风化壳地层型油气藏评价预测方法研究——以新疆北部石炭系为例[J]. 地球物理学报, 2011, 54(2): 388-400.
	ZOU Caineng, HOU Lianhua, WANG Jinghong, et al. Evaluation and forecast methods of stratigraphic reservoir of volcanic weathering crust: An example from Carboniferous formation in northern Xinjiang[J]. Chinese Journal of Geophysics, 2011, 54(2): 388-400.
[2]	庄圆, 杨凤丽. 春风油田石炭系火山岩油气层综合判识研究[J]. 新疆地质, 2019, 37(2): 231-236.
	ZHUANG Yuan, YANG Fengli. Study on hydrocarbon reservoir synthesize distinguish of carboniferous volcanic rock from Chunfeng Oil Field[J]. Xinjiang Geology, 2019, 37(2): 231-236.
[3]	张艺, 李道清, 仇鹏, 等. 基于岩性分类的火山岩储层流体识别方法——以克拉美丽气田石炭系火山岩为例[J]. 西安石油大学学报(自然科学版), 2020, 35(6): 22-28.
	ZHANG Yi, LI Daoqing, QIU Peng, et al. Study on fluid identification method of volcanic reservoir based on lithology classification: A case study of carboniferous volcanic rocks in Kelamei Gasfield[J]. Journal of Xi'an Shiyou University(Natural Science Edition), 2020, 35(6): 22-28.
[4]	吴煜宇, 谢冰, 伍丽红, 等. 四川盆地二叠系基性火山岩测井评价技术——以永探1井区火山岩为例[J]. 天然气工业, 2019, 39(2): 37-45.
	WU Yuyu, XIE Bing, WU Lihong, et al. Logging based lithology identification of Permian mafic volcanic rocks in the Sichuan Basin: A case study from the well Yongtan 1[J]. Natural Gas Industry, 2019, 39(2): 37-45.
[5]	李想, 金萍, 石艳. 火山岩储层含油性预测方法——以克拉玛依油田九区石炭系油藏为例[J]. 石油天然气学报, 2014, 36(6): 59-62.
	LI Xiang, JIN Ping, SHI Yan. Oiliness prediction method for volcanic rock reservoirs: Taking Carboniferous reservoirs in block 9 of Karamay Oilfield as an example[J]. Journal of Oil and Gas Technology, 2014, 36(6): 59-62.
[6]	张丽华, 张国斌, 齐艳萍, 等. 准噶尔盆地西泉地区石炭系火山岩岩性测井识别[J]. 新疆石油地质, 2017, 38(4): 427-431.
	ZHANG Lihua, ZHANG Guobin, QI Yanping, et al. Lithology identification of Carboniferous volcanic rocks in Xiquan area, Junggar Basin[J]. Xinjiang Petroleum Geology, 2017, 38(4): 427-431.
[7]	SHI F, WANG X L, LIU C, et al. An XFEM-based method with reduction technique for modeling hydraulic fracture propagation in formations containing frictional natural fractures[J]. Engineering Fracture Mechanics, 2017, 173: 64-90. doi: 10.1016/j.engfracmech.2017.01.025
[8]	NGUYEN T T, YVONNET J, ZHU Q Z, et al. A phase-field method for computational modeling of interfacial damage interacting with crack propagation in realistic microstructures obtained by microtomography[J]. Computer Methods in Applied Mechanics & Engineering, 2016, 312(6): 567-595.
[9]	LIANG X, YVONNET J, GHABEZLOO S. Phase field modeling of hydraulic fracturing with interfacial damage in highly heterogeneous fluid-saturated porous media[J]. Engineering Fracture Mechanics, 2017, 186(6): 158-180. doi: 10.1016/j.engfracmech.2017.10.005
[10]	洪一鸣, 王璞珺, 李瑞磊, 等. 基于常规测井数据的火山岩岩性神经网络识别: 以松辽盆地南部长岭断陷为例[J]. 世界地质, 2021, 40(2): 409-417.
	HONG Yiming, WANG Pujun, LI Ruilei, et al. Neural network recognition of volcanic rock lithology based on conventional logging data: A case study of Changling fault depression, southern Songliao Basin[J]. Global Geology, 2021, 40(2): 409-417.
[11]	陈跃, 王丽雅, 李国富, 等. 基于随机森林算法的低煤阶煤层气开发选区预测[J]. 油气藏评价与开发, 2022, 12(4): 596-603.
	CHEN Yue, WANG Liya, LI Guofu, et al. Prediction of favorable areas for low-rank coalbed methane based on random forest algorithm[J]. Petroleum Reservoir Evaluation and Development, 2022, 12(4): 596-603.
[12]	董月霞, 周海民, 夏文臣. 南堡凹陷火山活动与裂陷旋回[J]. 石油与天然气地质, 2000, 21(4): 304-307.
	DONG Yuexia, ZHOU Haimin, XIA Wenchen. Volcanic activity and rift-subsidence cycles in Nanpu Sag[J]. Oil and Gas Geology, 2000, 21(4): 304-307.
[13]	林伟强, 曲丽丽, 朱璐, 等. 井震藏结合判定井间砂体联通性研究及应用——以南堡油田M区中深层为例[J]. 油气藏评价与开发, 2022, 12(2): 373-381.
	LIN Weiqiang, QU Lili, ZHU Lu, et al. Evaluation of inter-well sand body connectivity by combination of well, seismic, and reservoir and its application: Taking the middle and deep layers of M area of Nanpu Oilfield as an example[J]. Petroleum Reservoir Evaluation and Development, 2022, 12(2): 373-381.
[14]	董月霞, 夏文臣, 周海民. 南堡凹陷第三系火山岩演化序列研究[J]. 石油勘探与开发, 2003, 30(2): 24-26.
	DONG Yuexia, XIA Wenchen, ZHOU Haimin. Evolvement sequence of tertiary volcanic rocks in the Nanpu sag, Eastern China[J]. Petroleum Exploration and Development, 2003, 30(2): 24-26
[15]	庄东志, 谢伟彪. 南堡凹陷5号构造东部深层火山岩储层流体性质识别方法[J]. 石油天然气学报, 2014, 36(5): 73-76.
	ZHUANG Dongzhi, XIE Weibiao. A method for identifying fluid properties of deep volcanic reservoirs in the east of No. 5 structure in Nanpu Sag[J]. Journal of Oil and Gas Technology, 2014, 36(5): 73-76.
[16]	李昌年. 火成岩微量元素岩石学[M]. 武汉: 中国地质大学出版社, 1992.
	LI Changnian. Trace element petrology of igneous rocks[M]. Wuhan: China University of Geosciences Press, 1992.
[17]	梁新平, 金之钧, 刘全有, 等. 火山灰对富有机质页岩形成的影响——以西西伯利亚盆地中生界巴热诺夫组为例[J]. 石油与天然气地质, 2021, 42(1): 201-211.
	LIANG Xinping, JIN Zhijun, LIU Quanyou, et al. Impact of volcanic ash on the formation of organic-rich shale: A case study on the Mesozoic Bazhenov Formation, West Siberian Basin[J]. Oil & Gas Geology, 2021, 42(1): 201-211.
[18]	程希, 任战利. 利用地球化学元素与矿物关系识别GS油田下干柴沟组地层岩性[J]. 地球物理学进展, 2008, 23(6): 1903-1908.
	CHENG Xi, REN Zhanli. Identification of Ganchaigou group rock lithology in the GS Oilfield by relationship between elements and minerals using geochemical logging technology[J]. Progress in Geophysics, 2008, 23(6): 1903-1908.
[19]	张明学, 吴杰, 胡玉双. 松辽盆地丰乐地区营城组火山岩储层预测[J]. 地球物理学进展, 2009, 24(6): 2145-2150.
	ZHANG Mingxue, WU Jie, HU Yushuang. Prediction of reservoirs in volcanic rocks of the Yingcheng formation in the Fengle area north of the Songliao basin[J]. Progress in Geophysics, 2009, 24(6): 2145-2150.
[20]	支东明, 贾春明, 姚卫江, 等. 准噶尔盆地车排子地区火山岩油气成藏主控因素[J]. 石油天然气学报, 2010, (2): 166-169.
	ZHI Dongming, JIA Chunming, YAO Weijiang, et al. The major control factors of volcanic reservoir forming law in Chepaizi area of Junggar Basin[J]. Journal of Petroleum and Natural Gas, 2010, (2): 166-169.
[21]	刘双莲. 常规测井技术识别火山岩裂缝方法研究——以松南火山岩为例[J]. 非常规油气, 2022, 9(4): 16-22.
	LIU Shuanglian. Study on method of identifying volcanic rock fractures by conventional logging technology: A case study on Songnan volcanic rock[J]. Unconventional Oil & Gas, 2022, 9(4): 16-22.
[22]	刘双莲. 页岩气“双甜点”参数测井评价方法[J]. 石油与天然气地质, 2022, 43(4): 1005-1012.
	Liu Shuanglian. Logging evaluation of “double sweet spot” in shale gas reservoirs[J]. Oil & Gas Geology, 2022, 43(4): 1005-1012.
[23]	张建民, 李超炜, 张继业, 等. 长深1井区火成岩岩性识别方法及应用[J]. 吉林大学学报(地球科学版), 2008, 38(S1): 106-109.
	ZHANG Jianmin, LI Chaowei, ZHANG Jiye, et al. A lithologic identification method of igneous rocks and its application in changling area[J]. Journal of Jilin University(Earth Science Edition), 2008, 38(S1): 106-109.
[24]	张莹, 潘保芝, 印长海, 等. 成像测井图像在火山岩岩性识别中的应用[J]. 石油物探, 2007; 46(3): 288-293.
	ZHANG Ying, PAN Baozhi, YIN Changhai, et al. Application of imaging logging maps in lithologic identification of volcanics[J]. Geophysical Prospecting for Petroleum, 2007, 46(3): 288-293.
[25]	王满, 薛林福, 潘保芝. FMI图像纹理统计方法识别火成岩岩性[J]. 测井技术, 2009, 33(2): l10-114.
	WANG Man, XUE Linfu, PAN Baozhi. Lithology identification of igneous rock using FMI texture analysis[J]. Well Logging Technology, 2009, 33(2): l10-114.
[26]	赵建, 高福红. 测井资料交会图法在火山岩岩性识别中的应用[J]. 世界地质, 2003, 22(2): 136-140.
	ZHAO Jian, GAO Fuhong. Application of crossplots based on well log data in identifying volcanic lithology[J]. Global Geology, 2003, 22(2): 136-140.
[27]	张丽华, 潘保芝, 单刚义, 等. 长岭地区火山岩储层流体性质测井预测[J]. 地球物理学进展, 2009, 24(6): 2151-2155.
	ZHANG Lihua, PAN Baozhi, SHAN Gangyi, et al. Fluid property logging prediction of volcanic reservoirs in the Changling area[J]. Progress in Geophysics, 2009, 24(6): 2151-2155.

层位	SiO₂	TiO₂	Al₂O₃	Fe₂O₃	FeO	MnO	MgO	CaO	Na₂O	K₂O	P₂O₅	CO₂	H₂O
馆陶组	47.69	2.26	14.29	7.94	3.95	0.16	8.55	6.27	3.15	1.25	0.34	0.66	3.60
	45.64	2.72	15.91	6.42	4.24	0.19	8.75	7.68	3.15	1.45	0.66	0.66	2.89
	46.71	1.92	15.98	4.54	5.87	0.14	4.91	10.21	2.74	0.72	0.35	3.36	2.50
	46.02	2.23	14.86	5.00	7.74	0.09	5.25	8.51	2.30	0.42	0.27	3.60	3.86
	48.67	1.82	14.97	4.01	6.93	0.10	4.71	9.10	2.29	0.51	0.32	3.26	3.12
	45.91	1.85	15.50	2.69	7.28	0.12	4.11	9.05	3.80	0.56	0.35	5.14	3.51

岩性分类		电性响应
岩性分类		自然伽马(API)	声波时差(μs/ft)	密度(g/cm³)
火山熔岩	玄武岩	（30~45）/41	（55~70）/60	（2.3~2.8）/2.55
火山碎屑岩	凝灰岩	（70~90）/82	（68~72）/71	（2.2~2.5）/2.33
火山碎屑沉积岩	凝灰质砂岩	（68~102）/72	（69~96）/79	（2.3~2.6）/2.47

Application of SVM algorithm in fluid prediction of volcanic reservoirs in Nanpu Sag, Bohai Bay Basin

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 27

Related Articles 4

Metrics

Comments

Recommended 10

[1]	WANG Tong,XIONG Liang,DONG Xiaoxia,XIANG Keman,ZHOU Hua,ZHONG Wenjun,LUO Haijin,GUO Weixing,ZHOU Jing. Characteristics of shale reservoir in new strata of Qiongzhusi Formation in southern Sichuan [J]. Petroleum Reservoir Evaluation and Development, 2021, 11(3): 443-451.
[2]	ZHOU Guangzhe. Practice of progressive exploration-development integration in SD Oil Field [J]. Reservoir Evaluation and Development, 2021, 11(2): 261-268.
[3]	Ge Zhongwei,Ouyang Jiasui,Wang Tong,Zhou Jing,Guo Weixingi,Jin Lichao. Reservoir characteristics and enrichment rule of Yongchuan Deep Shale Gas Field [J]. Reservoir Evaluation and Development, 2021, 11(1): 29-37.
[4]	HE Shun,QIN Qirong,FAN Cunhui,ZHOU Jiling,ZHONG Cheng,HUANG Wei. Shale Reservoir characteristics and influencing factors of Wufeng-Longmaxi formation in Dingshan area, Southeast Sichuan [J]. Reservoir Evaluation and Development, 2019, 9(4): 61-67.