基于带梯度惩罚深度卷积生成对抗网络的页岩三维数字岩心重构方法

doi:10.11772/j.issn.1001-9081.2020091367

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1805-1811.DOI: 10.11772/j.issn.1001-9081.2020091367

所属专题：前沿与综合应用

基于带梯度惩罚深度卷积生成对抗网络的页岩三维数字岩心重构方法

王先武¹, 张挺¹, 吉欣¹, 杜奕²

1. 上海电力大学计算机科学与技术学院, 上海 200090;
2. 上海第二工业大学工学部, 上海 201209

收稿日期:2020-09-07 修回日期:2020-11-13 出版日期:2021-06-10 发布日期:2020-11-26
通讯作者: 张挺
作者简介:王先武(1997-),男,江苏宿迁人,硕士研究生,主要研究方向:深度学习、图像重构;张挺(1979-),男,安徽安庆人,教授,博士,主要研究方向:图像处理、机器学习;吉欣(1997-),男,江苏南通人,硕士研究生,主要研究方向:深度学习、图像重构;杜奕(1977-),女,江苏吴江人,副教授,博士,CCF会员,主要研究方向:数据挖掘。
基金资助:
国家自然科学基金面上项目（41672114）；国家自然科学基金青年基金资助项目（41702148）。

3D shale digital core reconstruction method based on deep convolutional generative adversarial network with gradient penalty

WANG Xianwu¹, ZHANG Ting¹, JI Xin¹, DU Yi²

1. College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China;
2. College of Engineering, Shanghai Polytechnic University, Shanghai 201209, China

Received:2020-09-07 Revised:2020-11-13 Online:2021-06-10 Published:2020-11-26
Supported by:
This work is partially supported by the Surface Program of National Natural Science Foundation of China (41672114), the Youth Program of National Natural Science Foundation of China (41702148).

摘要/Abstract

摘要： 针对传统数字岩心重构技术存在的成本高昂、复用性差和重构质量低等问题，提出了一种基于带梯度惩罚深度卷积生成对抗网络（DCGAN-GP）的三维页岩数字岩心重构方法。首先，利用神经网络参数来描述页岩训练图像的分布概率，并完成训练图像的特征提取；其次，保存训练后的网络参数；最后，利用生成器重构出页岩三维数字岩心。实验结果表明，相较于经典的数字岩心重构技术得到的图像，DCGAN-GP得到的图像在孔隙度、变差函数和孔隙大小及分布特征上都更接近训练图像，而且DCGAN-GP的CPU使用率不到经典算法的一半，内存峰值仅有7.1 GB，重构时间达到了每次42 s，体现出模型重构质量高、效率高的特点。

关键词: 重构, 数字岩心, 生成对抗网络, 深度卷积, 梯度惩罚

Abstract: Aiming at the problems of high cost, poor reusability and low reconstruction quality in traditional digital core reconstruction technology, a 3D shale digital core reconstruction method based on Deep Convolutional Generation Adversarial Network with Gradient Penalty (DCGAN-GP) was proposed. Firstly, the neural network parameters were used to describe the distribution probability of the shale training image, and the feature extraction of the training image was completed. Secondly, the trained network parameters were saved. Finally, the 3D shale digital core was constructed by using the generator. The experimental results show that, compared to the classic digital core reconstruction technologies, the proposed DCGAN-GP obtains the image closer to the training image in porosity, variogram, as well as pore size and distribution characteristics. Moreover, DCGAN-GP has the CPU usage less than half of the classic algorithms, the memory peak usage only 7.1 GB, and the reconstruction time reached 42 s per time, reflecting the characteristics of high quality and high efficiency of model reconstruction.

Key words: reconstruction, digital core, Generative Adversarial Network (GAN), deep convolution, gradient penalty

中图分类号:

TP399

王先武, 张挺, 吉欣, 杜奕. 基于带梯度惩罚深度卷积生成对抗网络的页岩三维数字岩心重构方法[J]. 计算机应用, 2021, 41(6): 1805-1811.

WANG Xianwu, ZHANG Ting, JI Xin, DU Yi. 3D shale digital core reconstruction method based on deep convolutional generative adversarial network with gradient penalty[J]. Journal of Computer Applications, 2021, 41(6): 1805-1811.

参考文献

[1] RANI S,PADMANABHAN E,PRUSTY B K. Review of gas adsorption in shales for enhanced methane recovery and CO2 storage[J]. Journal of Petroleum Science and Engineering,2019,175:634-643.
[2] WANG Q,LI R. Research status of shale gas:a review[J]. Renewable and Sustainable Energy Reviews,2017,74:715-720.
[3] 张泽毅, 杨淑莹, 范凯翔. 模拟退火的动态免疫克隆算法在聚类中的应用[J]. 计算机应用, 2018, 38(S2):27-33.(ZHANG Z Y, YANG S Y, FAN K X. Application of simulated annealing optimized dynamic immune cloning algorithm in clustering analysis[J]. Journal of Computer Applications,2018,38(S2):27-33.)
[4] ØREN P E,BAKKE S. Process based reconstruction of sandstones and prediction of transport properties[J]. Transport in Porous Media,2002,46(2/3):311-343.
[5] HUANG J,LIU W,ZENG G,et al. An exploration of spatial human health risk assessment of soil toxic metals under different land uses using sequential indicator simulation[J]. Ecotoxicology and Environmental Safety,2016,129:199-209.
[6] ORIANI F,BORGHI A,STRAUBHAAR J,et al. Missing data simulation inside flow rate time-series using multiple-point statistics[J]. Environmental Modelling and Software,2016,86:264-276.
[7] WU Y,LIN C,REN L,et al. Reconstruction of 3D porous media using multiple-point statistics based on a 3D training image[J]. Journal of Natural Gas Science and Engineering, 2018, 51:129-140.
[8] DAI M Y,LI S H,WANG Y B. Principle and application of filtersim algorithm[J]. Advanced Materials Research,2014,962/963/964/965:172-175.
[9] TALEBI H, MUELLER U, TOLOSANA-DELGADO R. Joint simulation of compositional and categorical data via direct sampling technique-application to improve mineral resource confidence[J]. Computers and Geosciences,2019,122:87-102.
[10] 陈杰, 张挺, 杜奕. 基于自适应深度迁移学习的多孔介质重构[J]. 计算机应用, 2020, 40(4):1231-1236.(CHEN J,ZHANG T,DU Y. Reconstruction of porous media using adaptive deep transfer learning[J]. Journal of Computer Applications,2020,40(4):1231-1236.)
[11] GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition,2018, 77:354-377.
[12] ZHANG H, GOODFELLOW I, METAXAS D, et al. Selfattention generative adversarial networks[C]//Proceedings of the 2019 36th International Conference on Machine Learning. New York:JMLR. org,2019:7354-7363.
[13] SAGAWA Y,HAGIWARA M. Face image generation system using attribute information with DCGANs[C]//Proceedings of the 20182nd International Conference on Machine Learning and Soft Computing. New York:ACM,2018:109-113.
[14] LUO Y,LU B. EEG data augmentation for emotion recognition using a conditional Wasserstein GAN[C]//Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway:IEEE, 2018:2535-2538.
[15] GULRAJANI I,AHMED F,ARJOVSKY M,et al. Improved training of Wasserstein GANs[C]//Proceedings of the 201731st International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc.,2017:5769-5779.
[16] HEUSEL M,RAMSAUER H,UNTERTHINER T,et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium[C]//Proceedings of the 201731st International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc.,2017:6629-6640.
[17] BJORCK N,GOMES C,SELMAN B,et al. Understanding batch normalization[C]//Proceedings of the 201832nd International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc.,2018:7705-7716.
[18] ZHANG X,ZOU Y,SHI W. Dilated convolution neural network with LeakyReLU for environmental sound classification[C]//Proceedings of the 201722nd International Conference on Digital Signal Processing. Piscataway:IEEE,2017:1-5.
[19] SHANG W,SOHN K,ALMEIDA D,et al. Understanding and improving convolutional neural networks via concatenated rectified linear units[C]//Proceedings of the 2016 33rd International Conference on Machine Learning. New York:JMLR. org,2016:2217-2225.
[20] ABADI M,ISARD M,MURRAY D G. A computational model for TensorFlow:an introduction[C]//Proceedings of the 20171st ACM SIGPLAN International Workshop on Machine Learning and Programming Languages. New York:ACM,2017:1-7.
[21] LI Z,ZHANG X,CLARKE K C,et al. An automatic variogram modeling method with high reliability fitness and estimates[J]. Computers and Geosciences,2018,120:48-59.
[22] WILLIAMS B M,DURVASULA P K,BROWN D E. Urban freeway traffic flow prediction:application of seasonal autoregressive integrated moving average and exponential smoothing models[J]. Transportation Research Record,1998, 1644(1):132-141.

基于带梯度惩罚深度卷积生成对抗网络的页岩三维数字岩心重构方法

3D shale digital core reconstruction method based on deep convolutional generative adversarial network with gradient penalty

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张成, 万源, 强浩鹏. 基于知识蒸馏的深度无监督离散跨模态哈希[J]. 计算机应用, 2021, 41(9): 2523-2531.
[2]	王丹, 梁家敏, 刘金枝, 张友寿. 6G可重构智能表面的相移模型设计[J]. 计算机应用, 2021, 41(9): 2694-2698.
[3]	管其杰, 张挺, 李德亚, 周绍景, 杜奕. 基于多分辨率生成对抗网络的空间数据不确定性重建方法[J]. 计算机应用, 2021, 41(8): 2306-2311.
[4]	孙潇, 徐金东. 基于级联生成对抗网络的遥感图像去雾方法[J]. 计算机应用, 2021, 41(8): 2440-2444.
[5]	石雪松, 李宪华, 孙青, 宋韬. 基于人工蜂群与模糊C均值的自适应小波变换的噪声图像分割[J]. 计算机应用, 2021, 41(8): 2312-2317.
[6]	汤桂花, 孙磊, 毛秀青, 戴乐育, 胡永进. 基于深度对齐网络的生成对抗网络伪造人脸检测[J]. 计算机应用, 2021, 41(7): 1922-1927.
[7]	李衍志, 范勇, 高琳. 基于形态流的石油钻井水流异常检测[J]. 计算机应用, 2021, 41(6): 1842-1848.
[8]	井贝贝, 郭嘉, 王丽清, 陈静, 丁洪伟. 结合降噪卷积神经网络和条件生成对抗网络的图像双重盲降噪算法[J]. 计算机应用, 2021, 41(6): 1767-1774.
[9]	蒋林, 施佳琪, 李远成. 可重构结构下合成视点失真变化算法并行设计与实现[J]. 计算机应用, 2021, 41(6): 1734-1740.
[10]	郭茂祖, 杨倩楠, 赵玲玲. 基于条件Wassertein生成对抗网络的图像生成[J]. 计算机应用, 2021, 41(5): 1432-1437.
[11]	孙鹤立, 孙玉柱, 张晓云. 基于生成对抗网络的事件描述生成[J]. 计算机应用, 2021, 41(5): 1256-1261.
[12]	段友祥, 张含笑, 孙歧峰, 孙友凯. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J]. 计算机应用, 2021, 41(4): 1020-1026.
[13]	欧莉莉, 邵峰晶, 孙仁诚, 隋毅. 基于半监督方法的脑梗死图像识别[J]. 计算机应用, 2021, 41(4): 1221-1226.
[14]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[15]	高世伟, 张长柱, 王祝萍. 基于可分离金字塔的轻量级实时语义分割算法[J]. 计算机应用, 2021, 41(10): 2937-2944.