检索结果-内蒙古大学图书馆

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Zhang, Yaowei Yin, Senlin Hu, Zhangming Bai, Kai Xiong, Ting College of Computer Science and Technology Yangtze University Hubei Jingzhou China Hubei Provincial Key Laboratory of Southern Complex Shale Oil and Gas Geology and Development Hubei Province Wuhan China Research Institute of Mud Logging Technology and Engineering Yangtze University Hubei Jingzhou China CNPC Xibu Drilling Engineering Company Limited Engineering and Technology Division Xinjiang Urumqi China Co. Ltd. Shenzhen China

ISBN: (纸本)9798331517021

The study of reservoir fractures has always been a key focus in oil and gas exploration and development, and the most intuitive method is to observe rock fractures in outcrop areas. Manual surveying has low efficiency and strong subjectivity, so identifying rock fractures in outcrop areas has always been a difficult task. In response to this difficulty, this article utilizes drone oblique photography technology to significantly improve surveying efficiency, and proposes an improved DeepLabv3+ semantic segmentation model to achieve accurate segmentation of rock fractures. The experimental results showed that the MAP (Mean Average Precision) of the improved DeepLabv3+ model reached 83.77%, which was 12.44% higher than the original DeepLabv3+ model;MIoU (Mean Intersection over Union) has increased from 68.21 % to 78.84%;The accuracy has increased from 74.83% to 91.66%;The parameter count is only 15.14M. The experimental results show that the improved DeepLabv3+ model in this paper exhibits superior segmentation performance in rock fracture segmentation tasks in field outcrop areas, and has good mobile deployment performance. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

CNN-LSTM Low-Resistivity Reservoir Fluid Identification Method Based on Attention Mechanism

CNN-LSTM Low-Resistivity Reservoir Fluid Identification Meth...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Chen, Xingyue Yin, Senlin Tao, Jiang Ting, Xiong Yonghua, Liu College of Earth Sciences Yangtze University Hubei China Research Institute of Mud Logging Technology and Engineering Yangtze University Hubei China Hubei Provincial Key Laboratory of Southern Complex Shale Oil and Gas Geology Development Hubei Province Hubei China Zhundong Oil Production Plant of Xinjiang Oilfield Xinjiang China Co. Ltd. Shenzhen China China France Bohai Geoservices Co. Ltd Tian Jing China

ISBN: (纸本)9798331517021

Low-resistivity reservoirs are becoming increasingly significant in oil and gas exploration due to their extensive distribution and substantial reserves. However, their complex characteristics often render traditional logging interpretations insufficient. This study focuses on the low-resistivity reservoir fluids of the Hanjiang Formation and Zhujiang Formation in the Enping Sag of the Pearl River Mouth Basin. By analyzing gas logging data, quantitative fluorescence, and geochemical logging from 32 wells in the study area, we propose a hybrid model. This model combines the strengths of the Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) and integrates an attention mechanism to enhance its ability to process small sample sizes of low-resistivity reservoir fluids, thereby improving recognition accuracy. The research findings show that the hybrid model significantly outperforms traditional single models in identifying low-resistivity reservoirs, achieving an accuracy rate of 88.43%, which surpasses single model performances by 2% to 8%. These results not only enhance the predictive accuracy of the model but also establish a new technical approach for identifying low-resistivity reservoirs. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Organic matter pores in the chang 7 lacustrine shales from the Ordos Basin and its effect on reflectance measurement

引用

Petroleum Science 2023年第1期20卷 60-86页

作者： Peng Pang Hui Han Xiu-Cheng Tan Shi-Meng Ren Chen Guo Lin Xie Ling-Li Zheng Hai-Hua Zhu Yuan Gao Yun-Hui Xie School of Geoscience and Technology Southwest Petroleum UniversityChengduSichuan610500China Natural Gas Geology Key Laboratory of Sichuan Province Southwest Petroleum UniversityChengduSichuan610500China Shale Gas Industry Development Institute of Sichuan Province ChengduSichuan610500China The First Branch Mud Logging Company CNPC Bohai Drilling Engineering Co.Ltd.Tianjin300457China State Key Laboratory of Oil and Gas Reservoir Geology and Exploration Southwest Petroleum UniversityChengduSichuan610500China Beijing Center for Physical and Chemical Analysis Beijing100089China Nursing College Guizhou University of Traditional Chinese MedicineGuiyangGuizhou520002China

To quantify the pore characteristics of various macerals in Chang 7 lacustrine shales,macerals were effectively identified according to their optical and morphological characteristics,and the nanoscale pore structure of macerals was observed by scanning electron ***,the reflectances of different positions in the same pieces of vitrinite or solid bitumen with heterogeneous pores development were *** results showed that the average contents of sapropelinite,liptinite,vitrinite,inertinite and solid bitumen are 42.7%,8.7%,13.6%,13.8% and 21.2%,respectively,which suggests that the source of the organic matter of the Chang 7 shales is a mixed source *** organic pores of Chang 7 shales are enriched,and the pore shapes are mostly round or *** pore size of organic pores has a wide distribution,mainly concentrate in the range of 100-400 nm,and the average plane porosity of organic pores is 10.13%.The size order of the organic pores in various macerals is:solid bitumenfusinite>bituminite>solid bitumen>vitrinite>*** pores are mainly contributed by bituminite,solid bitumen and *** plane porosity of bituminite increases with *** the process of thermal evolution,the plane porosity of fusinite is distributed in the two ranges of 20%-28% and 1%-7%.The former is mainly the primary pores of the fusinite itself,and the latter is the secondary pores formed in the thermal *** for the organic pores of other macerals,no obvious thermal evolution law was ***,the surface imperfections of vitrinite or solid bitumen is enhanced by the enrichment of organic pores(an increase in pore size or pore number),which may result in the underestimation of their reflectances.

关键词： Ordos Basin Chang 7 member OM pore Macerals Differential developmental characteristics Reflectance

来源：评论

学校读者我要写书评

暂无评论

Lithology Identification of Improved Model based on DeepLabv3 + Deep Convolutional Neural Network

Lithology Identification of Improved Model based on DeepLabv...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Ju Wang Senlin Yin Zhangming Hu Kai Bai College of Computer Science and Technology Yangtze University Hubei China Research Institute of Mud Logging Technology and Engineering Yangtze University Hubei China Hubei Provincial Key Laboratory of Southern Complex Shale Oil and Gas Geology and Development Hubei Province Wuhan China Engineering and Technology Division of CNPC Xibu Drilling Engineering Company Limited

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

Aiming at the complexity of outcrop lithology identification, an improved outcrop lithology identification algorithm based on DeepLabv3 + is proposed. We use the Xception network replaced by the MobileNetV2 module to enhance the ability to extract lithologic features and make the model more lightweight. In order to segment pixels more accurately, the CA (Coordinate attention) attention mechanism is introduced, so that the improved backbone network can extract lithologic features more accurately in complex environments. The experimental results show that compared with the traditional DeepLabv3 +, the accuracy of the improved algorithm is increased by 1.08 percentage points, the MP A is increased by 2.4 percentage points, and the average classification accuracy is 94.86 %. Compared with other mainstream semantic segmentation models, all aspects of performance are more prominent.

关键词： Accuracy Attention mechanisms Computational modeling Semantic segmentation Feature extraction Market research Complexity theory Classification algorithms Convolutional neural networks Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Analysis of Transport and Deposition for Proppant in Rough Complex Fractures

SSRN

引用

SSRN 2023年

作者： Yin, Biao Lou, Yishan Liu, Shanyong Zhang, Yan School of Petroleum Engineering Yangtze University Wuhan430113 China National Engineering Research Center for Oil & Gas Drilling and Completion Technology Yangtze University Wuhan430100 China Institute of Mud Logging Technology and Engineering Yangtze University Hubei Jingzhou434023 China

To accurately characterize the proppant transport pattern in the rough and complex fracture and elucidate the interaction mechanism between the proppant and fractures, the study reconstructs a numerical model of the identical size fracture after fracturing the rock samples from the field. Based on Matlab, different auto-correlation Gaussian rough fracture models were established to precisely evaluate the roughness of cracks by using fractal dimension method. The article, innovatively combines Boolean operations to establish a 3D rough fracture model, which incorporates CFD-DEM with a bidirectional method for Co-Simulation. Further, these sensitive factors including fracture surface roughness, proppant particle sphericity, branch fracture inclination, and injection sequence of multi-size proppant on the law of proppant transport within the rough fracture are quantitatively analyzed. The study shows that the transport of proppant in the fracture is clearly divided into 3 zones with different turbulent kinetic energy. In addition, the roughness of the fracture walls formed by artificial fracturing increases the retention effect of the wall on the fluid, which leads to the phenomenon of plugging, causing only few of proppants flow into the branch fracture;the effect of sphericity is two-sided. Compared with spherical proppant (S3), proppant with low sphericity can transport farther under the driving of fracturing fluid. However, it can form more Pluuging effect near the intersection of fractures with greater curvature, which hinders the post-injection proppant. Whereas spherical proppant apparently form a better result of deposition with significant support effect;the variation of fracture inclination angle mainly affects the wall shear of the flow field in the fracture, showing that the smaller the inclination angle, the greater the shear energy at the fracture intersection (maximum 15.2 Pascal). Compared with the inclination angle of 30°, the height and area deposited

关键词： Proppants

来源：评论

学校读者我要写书评

暂无评论

Identification of Rock Cracks in Outcrop Areas Based on Improved DeepLab V3+

Identification of Rock Cracks in Outcrop Areas Based on Impr...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Yaowei Zhang Senlin Yin Zhangming Hu Kai Bai Ting Xiong College of Computer Science and Technology Yangtze University Jingzhou Hubei China Hubei Provincial Key Laboratory of Southern Complex Shale Oil and Gas Geology and Development Wuhan Hubei Province China Research Institute of Mud Logging Technology and Engineering Yangtze University Jingzhou Hubei China Engineering and Technology Division CNPC Xibu Drilling Engineering Company Limited Xinjiang Urumqi China Shenzhen Branch of CNOOC (China) Co. Ltd. Shenzhen China

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

The study of reservoir fractures has always been a key focus in oil and gas exploration and development, and the most intuitive method is to observe rock fractures in outcrop areas. Manual surveying has low efficiency and strong subjectivity, so identifying rock fractures in outcrop areas has always been a difficult task. In response to this difficulty, this article utilizes drone oblique photography technology to significantly improve surveying efficiency, and proposes an improved DeepLabv3+ semantic segmentation model to achieve accurate segmentation of rock fractures. The experimental results showed that the MAP (Mean Average Precision) of the improved DeepLabv3+ model reached 83.77%, which was 12.44% higher than the original DeepLabv3+ model; MIoU (Mean Intersection over Union) has increased from 68.21 % to 78.84%; The accuracy has increased from 74.83% to 91.66%; The parameter count is only 15.14M. The experimental results show that the improved DeepLabv3+ model in this paper exhibits superior segmentation performance in rock fracture segmentation tasks in field outcrop areas, and has good mobile deployment performance.

关键词： Performance evaluation Training Accuracy Convolution Semantic segmentation Rocks Reservoirs Stability analysis Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

CNN-LSTM Low-Resistivity Reservoir Fluid Identification Method Based on Attention Mechanism

CNN-LSTM Low-Resistivity Reservoir Fluid Identification Meth...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Xingyue Chen Senlin Yin Jiang Tao Xiong Ting Liu Yonghua College of Earth Sciences Yangtze University Hubei China Research Institute of Mud Logging Technology and Engineering Yangtze University Hubei China Hubei Provincial Key Laboratory of Southern Complex Shale Oil and Gas Geology and Development Hubei Province Hubei China Zhundong Oil Production Plant of Xinjiang Oilfield Xinjiang China Shenzhen Branch of CNOOC (China) Co. Ltd. Shenzhen China China France Bohai Geoservices Co. Ltd Tian Jing China

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

关键词： Fluids Accuracy Attention mechanisms Geology Soft sensors Predictive models Reservoirs Data models Convolutional neural networks Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Factors Controlling Hydrocarbon Accumulation in Jurassic Reservoirs in the Southwest Ordos Basin, NW China

引用

Acta Geologica Sinica(English Edition) 2020年第2期94卷 467-484页

作者： LIU Xin WANG Feng LIU Baojun TIAN Jingchun SHANG Ting MA Jiong ZHANG Zhongyi ZHANG Xiaolei Institute of Sedimentary Geology Chengdu University of TechnologyChengdu 610059Chino Exploration&Development Research Institute of PetroChina Changqing Oilfield Company Xi'an 710018China National Engineering Laboratory for Exploration and Development of Low Permeability Oil&Gas Fields Xi'an 710018China Key Laboratory of Nuclear Resource and Environment(Ministry of Education) East China University of TechnologyXanchang 330013China Production Logging Center China Petroleum Logging Co.Xi'an 710200China

The sedimentary, paleogeomorphological and reservoir characteristics of the Jurassic Yan’an Formation in the southwestern Ordos Basin, northwestern China, were studied by means of casting thin sections, scanning electron microscopy, inclusion analysis and identification of low-amplitude structures. A model for reservoir formation is established, and the controlling effects of sedimentary facies, paleotopography, low-amplitude structures and formation water on oil reservoirs are revealed. There are significant differences in the sedimentary characteristics, structural morphology and paleowater characteristics between the reservoirs above the Yan 10 Member and those in the Yan 9 to Yan 7 Members. The Yan 10 Member contains fluvial sediments, whereas the Yan 9 to Yan 7 members contain delta-plain anastomosing-river deposits. The distribution of high-permeability reservoir is controlled by pre-Jurassic paleogeomorphology and sedimentary facies. Some of these facies exhibit high porosity and high permeability in a lowpermeability background. The main hydrocarbon accumulation period was the late Early Cretaceous, filling was continuous, and the charging strength altered from weak to strong and then from strong to weak. The Yan 10 reservoir is mainly controlled by the paleogeomorphology: hydrocarbons migrated upward at a high speed through the unconformity surface, and accumulated in the favorable traps formed by paleogeomorphic structural units, such as gentle slopes or channel island. Furthermore, groundwater alternation in these areas was relatively stagnant, providing good reservoir preservation conditions. The reservoirs in the Yan 9 and higher members are controlled by the sedimentary facies, lowamplitude structure and paleowater characteristics. Hydrocarbons migrated through the three-dimensional delivery system, influenced by favorable sedimentary facies and high-salinity groundwater, then accumulated in the favorable low-amplitude structural traps that formed duri

关键词： inclusion analysis low-amplitude structure hydrocarbon accumulation Jurassic Yan'an Formation southwestern Ordos Basin

来源：评论

学校读者我要写书评

暂无评论

An unsupervised clustering method for nuclear magnetic resonance transverse relaxation spectrums based on the Gaussian mixture model and its application

引用

Petroleum Exploration and development 2022年第2期49卷 339-348页

作者： GE Xinmin XUE Zong’an ZHOU Jun HU Falong LI Jiangtao ZHANG Hengrong WANG Shuolong NIU Shenyuan ZHAO Ji’er School of Geosciences China University of PetroleumQingdao 266580China CNPC Key Well Logging Laboratory Xi’an 710077China Laboratory for Marine Mineral Resources Qingdao National Laboratory for Marine Science and TechnologyQingdao 266071China Oil and Gas Survey Center of China Geological Survey Beijing 100083China China Petroleum Logging Co.Ltd. Xi’an 710077China PetroChina Research Institute of Petroleum Exploration&Development Beijing 100083China PetroChina Qinghai Oilfield Company Dunhuang 736202China Zhanjiang Branch of CNOOC Ltd. Zhanjiang 524057China Sinopec Research Institute of Petroleum Engineering Beijing 100101China

To make the quantitative results of nuclear magnetic resonance(NMR) transverse relaxation(T;) spectrums reflect the type and pore structure of reservoir more directly, an unsupervised clustering method was developed to obtain the quantitative pore structure information from the NMR T;spectrums based on the Gaussian mixture model(GMM). Firstly, We conducted the principal component analysis on T;spectrums in order to reduce the dimension data and the dependence of the original variables. Secondly, the dimension-reduced data was fitted using the GMM probability density function, and the model parameters and optimal clustering numbers were obtained according to the expectation-maximization algorithm and the change of the Akaike information criterion. Finally, the T;spectrum features and pore structure types of different clustering groups were analyzed and compared with T;geometric mean and T;arithmetic mean. The effectiveness of the algorithm has been verified by numerical simulation and field NMR logging data. The research shows that the clustering results based on GMM method have good correlations with the shape and distribution of the T;spectrum, pore structure, and petroleum productivity, providing a new means for quantitative identification of pore structure, reservoir grading, and oil and gas productivity evaluation.

关键词： NMR T2 spectrum Gaussian mixture model expectation-maximization algorithm Akaike information criterion unsupervised clustering method quantitative pore structure evaluation

来源：评论

学校读者我要写书评

暂无评论

A decomposition method of nuclear magnetic resonance T2 spectrum for identifying fluid properties

引用

Petroleum Exploration and development 2020年第4期47卷 740-752页

作者： ZHONG Jibin YAN Ronghui ZHANG Haitao FENG Yihan LI Nan LIU Xingjun Exploration and Development Research Institute of PetroChina Changqing Oilfield Company Xi'an 710018China National Engineering Laboratory for Exploration and Development of Low-Permeability Oil&Gas Fields Xi'an 710018China PetroChina Changqing Oilfield Company Xi'an 710018China Changqing Branch China Petroleum Logging Co.Ltd.Xi'an 710201China Technology Center China Petroleum Logging Co.Ltd.Xi'an 710077China

Based on analysis of NMR T2 spectral characteristics,a new method for identifying fluid properties by decomposing T2 spectrum through signal analysis has been *** T2 spectrum satisfies lognormal distribution on transverse relaxation time axis,the T2 spectrum can be decomposed into 2 to 5 independent component spectra by fitting the T2 spectrum with Gauss *** analyzing the free relaxation response characteristics of crude oil and formation water,the dynamic response characteristics of the core mutual drive between oil and water,the petrophysical significance of each component spectrum is clarified.T2 spectrum can be decomposed into clay bound water component spectrum,capillary bound fluid component spectrum,micropores fluid component spectrum and macropores fluid component *** to the nature of crude oil in the target area,the distribution range of T2 component spectral peaks of oil-bearing reservoir is 165-500 ms on T2 time *** range can be used to accurately identify fluid *** method has high adaptability in identifying complex oil and water layers in low porosity and permeability reservoirs.

关键词： nuclear magnetic resonance free relaxation T2 spectrum decomposition method fitted T2 spectrum component spectrum fluid identification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：