Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm

doi:10.11772/j.issn.1001-9081.2017.10.3034

Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (10): 3034-3038.DOI: 10.11772/j.issn.1001-9081.2017.10.3034

Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm

ZHU Linqi^1,2, ZHANG Chong^1,2, ZHOU Xueqing^1,2, WEI Yang^1,2, HUANG Yuyang^1,2, GAO Qiming^1,2

1. Key Laboratory of Exploration Technologies for OH and Gas Resources of Ministry of Education (Yangtze University), Wuhan Hubei 430100, China;
2. School of Geophysics and Oil Resources, Yangtze University, Wuhan Hubei 430100, China

Received:2017-04-02 Revised:2017-05-20 Online:2017-10-16 Published:2017-10-10
Supported by:
This work is partially supported by the Natural Science Foundation of Hubei Province (2013CFB396), the Major Projects of China National Petroleum Corporation (2013E-38-09), the Open Found of Key Laboratory of Exploration Technologies for Oil and Gas Resources (Yangtze University), Ministry of Education (K201609).

融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法

朱林奇^1,2, 张冲^1,2, 周雪晴^1,2, 魏旸^1,2, 黄雨阳^1,2, 高齐明^1,2

1. 油气资源与勘探技术教育部重点实验室(长江大学), 武汉 430100;
2. 长江大学地球物理与石油资源学院, 武汉 430100

通讯作者: 张冲(1983-),男,湖北汉川人,副教授,博士,主要研究方向:复杂储层测井解释,E-mail:yzlogging@163.com
作者简介:朱林奇(1993-),男,湖北荆州人,博士研究生,CCF会员,主要研究方向:机器学习与数据挖掘方法的地球物理应用、核磁共振测井解释;张冲(1983-),男,湖北汉川人,副教授,博士,主要研究方向:复杂储层测井解释;周雪晴(1993-),女,山东东营人,硕士研究生,主要研究方向:测井地质、机器学习与数据挖掘方法的地球物理应用;魏旸(1991-),男,湖北孝感人,硕士研究生,主要研究方向:碳酸盐岩测井解释;黄雨阳(1994-),男,湖北鄂州人,硕士研究生,主要研究方向:页岩气测井解释;高齐明(1990-),男,山东泰安人,硕士,主要研究方向:测井解释.
基金资助:
湖北省自然科学基金资助项目（2013CFB396）；中国石油天然气集团公司重大专项（2013E-38-09）；长江大学教育部实验室开放基金资助项目（K2016-09）。

Abstract

Abstract: Duing to the complicated pore structure of low porosity and low permeability reservoirs, the prediction accuracy of the existing Nuclear Magnetic Resonance (NMR) logging permeability model for low porosity and low permeability reservoirs is not high. In order to solve the problem, a permeability prediction method based on Deep Belief Network (DBN) algorithm and Kernel Extreme Learning Machine (KELM) algorithm was proposed. The pre-training of DBN model was first carried out, and then the KELM model was placed as a predictor in the trained DBN model. Finally, the Deep Belief Kernel Extreme Learning Machine Network (DBKELMN) model was formed with supervised training by using the training data. Considering that the proposed model should make full use of the information of the transverse relaxation time spectrum which reflected the pore structure, the transverse relaxation time spectrum of NMR logging after discretization was taken as the input, and the permeability was taken as the output. The functional relationship between the transverse relaxation time spectrum of NMR logging and permeability was determined, and the reservoir permeability was predicted based on the functional relationship. The applications of the example show that the permeability prediction method based on DBN algorithm and KELM algorithm is effective and the Mean Absolute Error (MAE) of the prediction sample is 0.34 lower than that of Schlumberger Doll Researchcenter (SDR) model. The experimental results show that the combination of DBN algorithm and KELM algorithm can improve the prediction accuracy of low porosity and low permeability reservoir, and can be used to the exploration and development of oil and gas fields.

Key words: Deep Learning (DL), Nuclear Magnetic Resonance (NMR) logging, permeability, Deep Belief Network (DBN), Deep Belief Kernel Extreme Learning Machine Network (DBKELMN)

摘要： 由于低孔低渗储层孔隙结构较为复杂，现有核磁共振（NMR）测井渗透率模型对于低孔低渗储层预测精度不高。为此，提出一种融合深度置信网络（DBN）算法与核极限学习机（KELM）算法的渗透率预测方法。该方法首先对DBN模型进行预训练，然后将KELM模型作为预测器放置在训练好DBN模型后，利用训练数据进行有监督的训练，最终形成深度置信-核极限学习机（DBKELMN）模型。考虑到该模型需充分利用反映孔隙结构的横向弛豫时间谱信息，将离散化后的核磁共振测井横向弛豫时间谱作为输入，渗透率作为输出，确定NMR测井横向弛豫时间谱与渗透率的函数关系，并基于该函数关系对储层渗透率进行预测。实例应用表明，融合DBN算法与KELM算法的渗透率预测方法是有效的，预测样本的平均绝对误差（MAE）较斯伦贝谢道尔研究中心（SDR）模型降低了0.34。融合DBN算法与KELM算法的渗透率预测方法可提高低孔渗储层渗透率预测精度，可应用于油气田勘探开发。

关键词: 深度学习, 核磁共振测井, 渗透率, 深度置信网络, 深度置信-核极限学习机

CLC Number:

TP18
P631.8

ZHU Linqi, ZHANG Chong, ZHOU Xueqing, WEI Yang, HUANG Yuyang, GAO Qiming. Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm[J]. Journal of Computer Applications, 2017, 37(10): 3034-3038.

朱林奇, 张冲, 周雪晴, 魏旸, 黄雨阳, 高齐明. 融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法[J]. 计算机应用, 2017, 37(10): 3034-3038.

References

[1] 邵维志, 解经宇, 迟秀荣, 等.低孔隙度低渗透率岩石孔隙度与渗透率关系研究[J]. 测井技术, 2013, 37(2): 149-153. (SHAO W Z, XIE J Y, CHI X R, et al. On the relation of porosity and permeability in low porosity and low permeability rock [J]. Well Logging Technology, 2013, 37(2): 149-153.)
[2] PETROBRAS T W, PETROBRAS C B, PETROBRAS N P, et al. Magnetic Resonance (NMR) approach for permeability estimation in carbonate rocks [EB/OL]. [2017-01-10]. https://www.onepetro.org/conference-paper/OTC-26338-MS.
[3] XIAO L, ZOU C C, MAO Z Q, et al. Tight-gas-sand permeability estimation from Nuclear-Magnetic-Resonance (NMR) logs based on the Hydraulic-Flow-Unit (HFU) approach [EB/OL]. [2017-01-10]. https://www.onepetro.org/journal-paper/SPE-167255-PA.
[4] XIAO L, LIU X P, ZOU C C, et al. Comparative study of models for predicting permeability from Nuclear Magnetic Resonance (NMR) logs in two Chinese tight sandstone reservoirs [J]. Acta Geophysica, 2014, 62(1): 116-141.
[5] RIOS E H, AZEREDO R B V, MOSS A K, et al. Estimating the permeability of carbonate rocks by principal component regressions of NMR and MICP data [C]//Proceedings of the SPWLA 56th Annual Logging Symposium. Long Beach, CA: [s.n.], 2015.
[6] WEI D F, LIU X P, HU X X, et al. Estimation of permeability from NMR logs based on formation classification method in tight gas sands [J]. Acta Geophysica, 2015, 63(5): 1316-1338.
[7] 成志刚, 罗少成, 杜支文, 等.基于储层孔喉特征参数计算致密砂岩渗透率的新方法[J]. 测井技术, 2014, 38(2): 185-189. (CHENG Z G, LUO S C, DU Z W, et al. The method to calculate tight sandstone reservoir permeability using pore throat characteristic parameters [J]. Well Logging Technology, 2014, 38(2): 185-189.)
[8] RUSH D, LINDSAY C, ALLEN M. Combining electrical measurements and mercury porosimetry to predict permeability [J]. Petrophysics, 2013, 54(6): 531-537.
[9] 朱林奇, 张冲, 何小菊, 等.基于动态孔隙结构效率的核磁共振测井预测渗透率方法[J]. 新疆石油地质, 2015, 36(5): 607-611. (ZHU L Q, ZHANG C, HE X J, et al. NMR logging permeability prediction method based on dynamic pore structure efficiency [J]. Xinjiang Petroleum Geology, 2015, 36(5): 607-611.)
[10] 朱林奇, 张冲, 胡佳, 等.基于单元体模型的核磁共振测井渗透率评价方法[J]. 石油钻探技术, 2016, 44(5): 120-126. (ZHU L Q, ZHANG C, HU J, et al. An NMR logging permeability evaluation method based on the representative elementary volume model [J]. Petroleum Drilling Techniques, 2016, 44(5): 120-126.)
[11] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.
[12] HINTON G E. Training products of experts by minimizing contrastive divergence [J]. Neural Computation, 2002, 14(8): 1771-1800.
[13] HUANG G B, ZHOU H M, DING X J. Extreme learning machine for regression and multiclass classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, 2013, 43(2): 513-529.
[14] 江沸菠, 戴前伟, 董莉.基于主成分-正则化极限学习机的超高密度电法非线性反演[J]. 地球物理学报, 2015, 58(9): 3356-3369. (JIANG F B, DAI Q W, DONG L. Ultra-high density resistivity nonlinear inversion based on principal component-regularized ELM [J]. Chinese Journal of Geophysics, 2015, 58(9): 3356-3369.)

Nuclear magnetic resonance logging reservoir permeability prediction method based on deep belief network and kernel extreme learning machine algorithm

融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 13

Recommended Articles

Metrics

[1]	Junyan LIU, Feibo JIANG, Yubo PENG, Li DONG. Multi-objective optimization model for unmanned aerial vehicles trajectory based on decomposition and trajectory search [J]. Journal of Computer Applications, 2023, 43(12): 3806-3815.
[2]	XIANG Jinyong, YANG Wenzhong, SILAMU·Wushouer. Text sentiment classification algorithm based on feature selection and deep belief network [J]. Journal of Computer Applications, 2019, 39(7): 1942-1947.
[3]	ZHOU Xiangyu, CHENG Yong, WANG Jun. Agricultural greenhouse temperature prediction method based on improved deep belief network [J]. Journal of Computer Applications, 2019, 39(4): 1053-1058.
[4]	SHEN Xueli, QIN Shujuan. Anomaly detection based on synthetic minority oversampling technique and deep belief network [J]. Journal of Computer Applications, 2018, 38(7): 1941-1945.
[5]	LI Fang, ZHANG Ting. Deep belief network-based matching algorithm for abnormal point sets [J]. Journal of Computer Applications, 2018, 38(12): 3570-3573.
[6]	QIU Meng, YIN Haoyu, CHEN Qiang, LIU Yingjian. Automatic cloud detection algorithm based on deep belief network-Otsu hybrid model [J]. Journal of Computer Applications, 2018, 38(11): 3175-3179.
[7]	YANG Jian, ZHOU Tao, GUO Lifang, ZHANG Feifei, LIANG Mengmeng. Lung tumor image recognition algorithm based on cuckoo search and deep belief network [J]. Journal of Computer Applications, 2018, 38(11): 3225-3230.
[8]	WANG Yining, QIN Pinle, LI Chuanpeng, CUI Yuhao. Improved algorithm of image super resolution based on residual neural network [J]. Journal of Computer Applications, 2018, 38(1): 246-254.
[9]	ZENG An, ZHANG Yinan, PAN Dan, Xiao-wei SONG. Deep belief networks based on sparse denoising auto encoders [J]. Journal of Computer Applications, 2017, 37(9): 2585-2589.
[10]	CHEN Hong, WAN Guangxue, XIAO Zhenjiu. Intrusion detection method of deep belief network model based on optimization of data processing [J]. Journal of Computer Applications, 2017, 37(6): 1636-1643.
[11]	CHEN Qiuju, LI Ying. Sound recognition based on optimized orthogonal matching pursuit and deep belief network [J]. Journal of Computer Applications, 2017, 37(2): 505-511.
[12]	LI Meng, QIN Pingle, LI Chuanpeng. Deep belief network algorithm based on multi-innovation theory [J]. Journal of Computer Applications, 2016, 36(9): 2521-2525.
[13]	KANG Xiaodong, WANG Hao, GUO Jun, YU Wenyong. Unsupervised deep learning method for color image recognition [J]. Journal of Computer Applications, 2015, 35(9): 2636-2639.