scholarly journals Pore Space Reconstruction of Shale Using Improved Variational Autoencoders

Geofluids ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yi Du ◽  
Hongyan Tu ◽  
Ting Zhang

Pore space reconstruction is of great significance to some fields such as the study of seepage mechanisms in porous media and reservoir engineering. Shale oil and shale gas, as unconventional petroleum resources with abundant reserves in the whole world, attract extensive attention and have a rapid increase in production. Shale is a type of complex porous medium with evident fluctuations in various mineral compositions, dense structure, and low hardness, leading to a big challenge for the characterization and acquisition of the internal shale structure. Numerical reconstruction technology can achieve the purpose of studying the engineering problems and physical problems through numerical calculation and image display methods, which also can be used to reconstruct a pore structure similar to the real pore spaces through numerical simulation and have the advantages of low cost and good reusability, casting light on the characterization of the internal structure of shale. The recent branch of deep learning, variational auto-encoders (VAEs), has good capabilities of extracting characteristics for reconstructing similar images with the training image (TI). The theory of Fisher information can help to balance the encoder and decoder of VAE in information control. Therefore, this paper proposes an improved VAE to reconstruct shale based on VAE and Fisher information, using a real 3D shale image as a TI, and saves the parameters of neural networks to describe the probability distribution. Compared to some traditional methods, although this proposed method is slower in the first reconstruction, it is much faster in the subsequent reconstructions due to the reuse of the parameters. The proposed method also has advantages in terms of reconstruction quality over the original VAE. The findings of this study can help for better understanding of the seepage mechanisms in shale and the exploration of the shale gas industry.

2021 ◽  
Vol 9 ◽  
Author(s):  
Jia Wang ◽  
Xianfeng Tan ◽  
Jingchun Tian ◽  
Long Luo ◽  
Xuanbo Gao ◽  
...  

Diagenetic evolution is an important controlling factor of shale gas reservoirs. In this study, based on field outcrop and drilling core data, analytical techniques including X-ray diffraction (XRD), field emission scanning electron microscope combined with a focused ion beam (FIB-FESEM), and energy-dispersive spectroscopy (EDS) analyses were performed to determine the diagenetic evolution of the Longmaxi Formation shale and reveal the effect of diagenetic evolution on the shale gas exploration and development in the Sichuan Basin, Southwest China. The eodiagenesis phase was subdivided into two evolution stages, and the mesodiagenesis phase was subdivided into three evolution stages in the basin margin and center. Absorbed capacity and artificial fracturing effect of the Longmaxi Formation shale gas were related to mineral composition, which was influenced by sedimentary characteristics and diagenetic evolution. The diagenetic system in the basin margin was more open than that in the basin center due to a different burial history. The more open diagenetic system, with more micro-fractures and soluble constitute (e.g., feldspar), was in favor for the formation and preservation of secondary dissolved pores and organic pores in the basin margin. The relatively closed diagenetic system with stronger compaction resulted in deformation of pore space in the central basin.


2015 ◽  
Vol 55 (2) ◽  
pp. 406
Author(s):  
Vishnu Nair

Moving from conventional to unconventional gas project development requires a significant shift in approach. This presents challenges for operators making this transition, including standards and specifications being mis-matched to functional requirements, the need for robust surface and subsurface field development planning, lack of infrastructure, high construction and procurement costs and the scarcity of supply chain and logistics support. In their need to prove up sufficient reserves in time for downstream LNG plant operations, coal seam gas (CSG) players have neglected the development of appropriate standards, specifications and contracting and procurement strategies that consider how upstream costs can be minimised. This can impact project viability in a high-cost, low-productivity environment. The requirement of shale gas development for continual expansion also presents challenges compared to conventional project development. Adopting a factory approach can ensure a smooth and economic transition through the phase of continual shale gas production across the life of individual wells and through field expansion. Using case studies, this extended abstract describes how innovation can be applied across the gas-gathering development phase of unconventional projects to achieve significant cost savings. Key innovative opportunities include: Maximising modularise construction and operation to reduce the construction schedule and maximise onsite productivity Relocatable, interchangeable, standardised skid designs (design kit approach). Standard modules sized to maximise container volumes (and they minimise freight costs) Low-cost design Asian and Australian fabrication. Fit-for-purpose technology and packages to lower operating costs. Design and fabrication to minimise environmental impacts.


SPE Journal ◽  
2011 ◽  
Vol 17 (01) ◽  
pp. 219-229 ◽  
Author(s):  
Ray J. Ambrose ◽  
Robert C. Hartman ◽  
Mery Diaz-Campos ◽  
I. Yucel Akkutlu ◽  
Carl H. Sondergeld

Summary Using focused-ion-beam (FIB)/scanning-electron-microscope (SEM) imaging technology, a series of 2D and 3D submicroscale investigations revealed a finely dispersed porous organic (kerogen) material embedded within an inorganic matrix. The organic material has pores and capillaries having characteristic lengths typically less than 100 nm. A significant portion of total gas in place appears to be associated with interconnected large nanopores within the organic material. Thermodynamics (phase behavior) of fluids in these pores is quite different; gas residing in a small pore or capillary is rarefied under the influence of organic pore walls and shows a different density profile. This raises serious questions related to gas-in-place calculations: Under reservoir conditions, what fraction of the pore volume of the organic material can be considered available as free gas, and what fraction is taken up by the adsorbed phase? How accurately is the shale-gas storage capacity estimated using the conventional volumetric methods? And finally, do average densities exist for the free and the adsorbed phases? We combine the Langmuir adsorption isotherm with the volumetrics for free gas and formulate a new gas-in-place equation accounting for the pore space taken up by the sorbed phase. The method yields a total-gas-in-place prediction. Molecular dynamics simulations involving methane in small carbon slit-pores of varying size and temperature predict density profiles across the pores and show that (a) the adsorbed methane forms a 0.38-nm monolayer phase and (b) the adsorbed-phase density is 1.8–2.5 times larger than that of bulk methane. These findings could be a more important consideration with larger hydrocarbons and suggest that a significant adjustment is necessary in volume calculations, especially for gas shales high in total organic content. Finally, using typical values for the parameters, calculations show a 10–25% decrease in total gas-storage capacity compared with that using the conventional approach. The role of sorbed gas is more important than previously thought. The new methodology is recommended for estimating shale gas in place.


Author(s):  
Harry Miller ◽  
Anders T. Johnson ◽  
Markus Ahrens ◽  
T. Kenton Flanery

A team forms to address the challenge of low cost, low maintenance gas compression that can be quickly ramped up to meet peak demands. The Natural Gas Industry recognizes the importance of efficient, flexible compression equipment for the transmission of gas. In the early 1900s the Gas Industry met its compression objectives with many small reciprocating compressor units. As competition increased, Gas Companies began employing more cost effective larger units 3.7 MW (5,000 bhp) and eventually gas turbines 11+ MW (15,000+ bhp) became the prime mover of choice. While gas fired engine driven compressors are convenient for gas companies; they are becoming increasingly difficult to install. Environmental restrictions have tightened making permitting difficult. The larger gas turbine units seemed a solution because they were the low capital cost prime mover and clean burning. However, gas turbines have not yet achieved the high degree of flexibility and fuel efficiency gas transporters hoped. Flexibility has become an increasingly important issue because of the new “Peaking Power Plants” that are coming online. Gas companies are trying to solve the problem of low cost, low maintenance compression that can be quickly ramped up to meet peak demands. The idea of using electric motors to drive compressors to minimize the environmental, regulatory, and maintenance issues is not new. The idea of installing an electrically powered, highly flexible, efficient, low maintenance compressor unit directly into the pipeline feeding the load, possibly underground where it won’t be seen or heard, is a new and viable way for the gas and electric industries to do business together. This paper examines the application of totally enclosed, variable speed electric motor driven gas compressors to applications requiring completely automated, low maintenance, quick response gas pressure boosters. In this paper we will describe how a natural gas transporter, compressor manufacturer, motor manufacturer, and power company have teamed up to design the world’s first gas compressor that can be installed directly in the pipeline. We will discuss methodologies for installing the proposed compressor, the environmental benefits — no emissions, a small footprint, minimal noise — and the benefit of being able to install compression exactly where it is needed to meet the peaking requirements of today’s new loads.


Author(s):  
Viviani C. Onishi ◽  
Juan A. Reyes-Labarta ◽  
José A. Caballero
Keyword(s):  

2019 ◽  
Vol 59 (2) ◽  
pp. 824
Author(s):  
David Walker

The ability to measure large amounts of data at high frequency, and the increasing ability to process these data close to the source at the edge, has opened up a new frontier in asset management. Until now, analysis of high-frequency data in real time has been the domain of a few, very expensive devices. However, this is rapidly changing, with the increasing capabilities of sensors and edge devices providing flexible, low-cost solutions that can be deployed across all site machinery to provide predictive and detailed information about these assets. All machinery vibrates at multiple frequencies when running. If you listen to this vibration, it can tell you a lot about the condition of the machine and its components. In fact, it is surprising how rich and detailed this information can be. Cavitation, insufficient lubrication, failing bearings and faulty impellers all have different vibration signatures, and by listening for these signatures it is possible to identify issues before they occur, and even predict when they will occur. It is also possible to feed this information (e.g. cavitation) to the control system so that process decisions can be made to avoid machine damage. This paper discusses solutions that are available now and currently being developed in terms of edge computing devices and advances in the algorithms that analyse the vibration data, and how they can be applied in the oil and gas industry to ensure assets are optimised and downtime is minimised.


Sign in / Sign up

Export Citation Format

Share Document