首页期刊导航|Journal of Petroleum Science & Engineering
期刊信息/Journal information
Journal of Petroleum Science & Engineering
Elsevier Science B.V.
Journal of Petroleum Science & Engineering

Elsevier Science B.V.

0920-4105

Journal of Petroleum Science & Engineering/Journal Journal of Petroleum Science & Engineering
正式出版
收录年代

    The development of an AI-based model to predict the location and amount of wax in oil pipelines

    Juhyun KimSunlee HanYoungjin Seo
    12页
    查看更多>>摘要：The petroleum that flows within pipelines can contain impurities to form a solid wax which, when aggregated in sufficient qualities within the pipeline, can impair liquid flow and destabilize production. This material buildup is not constant, but rather may be exacerbated by various temperature and pressure conditions. In this study, we designed and tested a system that enables wax diagnosis in oil pipelines. An OLGA simulator was used to build learning data, and the RRR (Ryg, Rydahl, and Ronningen) model was used as a calculation model to describe the molecular diffusion and shear dispersion that most influence wax deposition. A SAE (Stacked Auto-Encoder) was used as the AI (Artificial Intelligence) model after analyzing training loss to select a suitable AI model. The Greedy Layer-Wise method was applied as a learning method to predict various information across all grid sections over time. Our AI model proved to be highly capable by the time a thick layer of wax had formed, with the location of maximum wax buildup being predictable with a great deal of accuracy. But the comparison of predicted wax thickness and actual data is not accurate, which may be the consequence of the small amount of data used for the initial learning. Ultimately, maximum wax volume and the location of maximum wax buildup were predicted with an accuracy of more than 90%. For the maximum wax location, an error of 650 m did appear, however this length corresponds to that of one grid, rendering the error insignificant. This study confirmed that flow assurance can be safeguarded with the application of AI technology, with is both more efficient in terms of time and cost than existing diagnostic methods.
      原文链接:
    • NSTL

    Research on wellbore temperature control and heat extraction methods while drilling in high-temperature wells

    Dong XiaoYifan HuYingfeng Meng
    17页
    查看更多>>摘要：During the drilling process, the downhole high-temperature problem has considerably limited the exploration and development of deep oil and gas reservoirs and geothermal resources in China. The aim of its oil and gas exploration and development has gradually shifted to deeper formations. In this study, a transient heat transfer model for high-temperature wells during the drilling process is built. Both heat sources and variations of thermophysical properties of drilling fluids and tubular string with temperature and pressure are considered. An iterative method is used to calculate annular temperature distributions by considering fluid composition, complex casing programs combination, and well structure. Based on the model in this study, a heat extraction-while-drilling technology approach is proposed by combining insulated pipe string and the phase-change heat storage drilling liquid. The results show that this method effectively reduces the bottom-hole temperature while using the geothermal energy of high-temperature wells. The study's results provide a theoretical foundation and technical support for resolving downhole high-temperature complications in deep oil and gas, as well as geothermal well drilling. The results will be a helpful supplement for the petroleum industry in achieving the national energy aim of carbon neutrality and peak carbon dioxide emissions.
      原文链接:
    • NSTL

    3D reconstruction of porous media by combining scaling transformation and multi-scale discrimination using generative adversarial networks

    Ting ZhangXin JiFangfang Lu
    23页
    查看更多>>摘要：The modeling and characterization of porous media is quite significant to explore and develop oil and natural gas resources. Traditional numerical simulation methods obtain reconstruction results through the statistical probability in training images (TIs), while the reconstruction process is lengthy and the probability information cannot be reused. The development of deep learning has provided reliable support for the reconstruction of porous media due to its strong ability of learning and extracting characteristics from TIs and the reuse of network parameters. As a common deep learning method, generative adversarial networks (GANs) can obtain images highly similar to the structural characteristics of the TI through adversarial training between the generator and the discriminator. Based on GAN, a three-dimensional multi-scale pattern generative adversarial network (3D-MSPGAN) that can achieve 3D super-resolution reconstruction of porous media is proposed in this paper. The use of scaling transformation allows 3D-MSPGAN to reconstruct super-resolution images of porous media that are much larger than the TI, while the multi-scale discrimination in the discriminator provides a guarantee for the generation of high-quality super-resolution images, by which the discriminator can retain the global structure and local characteristics of the TI simultaneously during the reconstruction process. In addition, due to the multi-scale patch information used in the discriminator, only a single TI is needed to complete the reconstruction of porous media. Experimental comparison with some typical methods proves that 3D-MSPGAN can achieve the reconstruction of 3D porous media with faster speed and higher quality.
      原文链接:
    • NSTL

    Reliable channel reservoir characterization and uncertainty quantification using variational autoencoder and ensemble smoother with multiple data assimilation

    Youngbin AhnJonggeun Choe
    17页
    查看更多>>摘要：Reservoir characterization is essential for reliable performance prediction and decision making. In this study, a reliable scheme is suggested for channel reservoir characterization and uncertainty quantification using variational autoencoder(VAE) and ensemble smoother with multiple data assimilation(ES-MDA). The scheme composes of three stages. First, rock facie s of channel reservoir models are used to train a VAE network. Second, the latent vectors in VAE are updated via ES-MDA by considering observation data. Finally, updated latent vectors are decoded to restore rock facies of the channel reservoir models. The proposed scheme shows superior capability of model calibration compared to ES-MDA algorithm for all three channel reservoirs cases analyzed. It successfully detects channel patterns of reference models and also prevents permeability from exceeding unreal value, which is a major problem of ES-MDA. On the top of that, more reliable future production forecast is achieved from the models updated by the proposed method.
      原文链接:
    • NSTL

    Fault characterization and flow barrier detection using capacitance-resistance model and diagnostic plots

    Oscar I.O. OgaliOyinkepreye D. Orodu
    32页
    查看更多>>摘要：Advantageous for its speed and far less data requirements, the Capacitance-Resistance Model has been successfully applied to waterflood performance prediction and optimization, gas flood optimization and reservoir characterization. In this study, a diagnostic plot and an iterative workflow that incorporates geological and well data with calibrated CRM results, were developed for depicting injector-producer communication, thereby characterizing a reservoir of interest. These were validated using three synfield cases. Thereafter, two selected faults in a Far East Oil Field (FEOF) were characterized and sealing baffles identified around these faults. Based on the results, one fault had several sections with varying degrees of communication and sealing baffles on either side of the fault. The second fault was mostly sealing with no sealing baffles on either side. The new diagnostic plot and workflow also quality-checked interwell connectivities from calibrated CRM, thereby substantially improving the fault characterization process. With far fewer and readily available data from oilfields, reduced physics models like CRM and the Diagnostic Plots are tools for cost-effective and speedy reservoir characterization, and to corroborate results of Interference and Tracer Tests, as well as 4D Seismic.
      原文链接:
    • NSTL

    A coupled geomechanics and reservoir simulator with a staggered grid finite difference method

    Chao GaoK E.Gray
    17页
    查看更多>>摘要：For a stress-sensitive reservoir, the constant rock compressibility term used in a conventional reservoir simulator (CRS), does not account for change of porosity and permeability. This paper develops a coupled geomechanics and reservoir simulator (CGRS) which accounts for changes in porosity and permeability related to deformation. The simulator in this paper adopts a staggered grid finite difference method for fluid flow and displacements. Displacements and pore pressures are placed at centers of faces and grid blocks, which increases numerical accuracy. Four types of nonlinear, coupled equations (porosity, permeability, displacements, and pressure equations) have been derived for use in CGRS. The Newton-Raphson method requires solving all the unknowns simultaneously, a computationally intensive procedure. An alternative is to use the Macro Gauss-Seidel method, which divides a huge nonlinear matrix into several smaller matrices, thus speeding up computations. Solutions from CGRS have been validated using two analytical solutions;; a one-dimensional consolidated reservoir and an idealized reservoir. This validated simulator is used to simulate a 3D reservoir with multiple vertical and horizontal wells. The comparison between CRS and CGRS shows that pressure depletes faster in CRS as compared to CGRS. CGRS results in higher bottom-hole pressure for a constant rate well. Constant rate wells yield a result of 1~(-1).26 times higher bottom-hole pressure than CRS. This shows that neglecting geomechanics effects in CRS can lead to an under prediction of reservoir/bottom hole pressures and production rates. Another powerful function of CGRS is the output of 3D displacements, which cannot be predicted by CRS. After producing for 1000 days, the maximum vertical displacement reaches 0.34 ft (0.085% of reservoir thickness). Maximum displacements in the x and y directions (lateral displacements) are 4 x 10 4 ft. and 0.015 ft, both of which are smaller than vertical displacement because of fixed lateral boundary conditions. Unlike traditional iterative coupled (IC) methods, fluid flow and geomechanics share the same mesh, which solves the problem of numerical instability in two discretization methods used in traditional IC. Also, the change of volumetric strain with respect to time (usually neglected in traditional IC) has been included in the fluid flow equation to better characterize the effects of solids movement on fluid flow. The Macro Gauss-Seidel method was adopted to increase computation efficiency of the simulations. The simulator introduced in this paper has its own data structure for geomechanics analysis which can be incorporated in single-phase, two-phase, three-phase or compositional reservoir simulators.
      原文链接:
    • NSTL

    Catalytic combustion of heavy oil using y-Fe2O3 nanocatalyst in in-situ combustion process

    Chengdong YuanNikolay RodionovSeyedsaeed Mehrabi-Kalajahi
    8页
    查看更多>>摘要：In this work, γ-Fe2O3 nanoparticles were synthesized by co-precipitation method and characterized by Fourier transform infrared spectroscopy, transmission electron microscopy, dynamic light scattering, X-ray diffraction, and Mossbauer spectroscopy techniques. By co-precipitation method, ultrafine γ-Fe2O3 quasi-spherical individual nanoparticles with the average diameter of 9.1 nra and the surface free of capping ligands were successfully synthesized. The catalytic effect of the synthesized γ-Fe2O3 nanoparticles upon the combustion performance and kinetic of heavy oil combustion was studied by porous medium thermo-effect cell (PMTEC) together with isoconversional kinetic analysis using Ozawa-Flynn-Wall method. The results show that the combustion performance of heavy oil was substantially increased by y-Fe2O3 nanoparticles. The reaction intervals of low temperature oxidation (LTO) and high temperature oxidation (HTO) were shifted to lower temperature with an obvious increase in temperature caused the exothermic oxidation reactions. In addition, the fingerprint of the dependence of effective activation energy on conversion degree shows that the effective activation energy was reduced by about 20-35 kj/mol during the whole combustion process. These observed improvements make γ-Fe2O3 nanoparticle a promising catalyst for catalyzing heavy oil combustion.
      原文链接:
    • NSTL

    Evaluation of saturation changes during gas hydrate dissociation core experiment using deep learning with data augmentation

    Sungil KimKyungbook LeeMinhui Lee
    18页
    查看更多>>摘要：This study proposes a reliable evaluation method for three-phase saturation (water, gas hydrate (GH), and gas) evaluation during the GH dissociation core experiment using deep learning. A convolutional neural network (CNN) takes computed tomography (CT) images obtained during the GH core experiment as an input and provides three-phase saturation as an output. Although machine/deep learning methods have been applied to the saturation evaluation from CT images in previous research, they were not reliable due to the lack of adequate amount of training data where the model could not fnd appropriate parameters. Besides, non-zero gas hydrate saturation showed where it was supposed to be zero. This study improved the evaluation of three-phase saturation and solved the non-zero GH saturation problem by acquirement of extra data and application of data augmentation with CNN. The results of CNN and CNN with data augmentation presented 34% and 29% error compared to those of random forest. CNN with data augmentation brought 85% and 44% of error and its variance compared to those of CNN without data augmentation, respectively. Consequently, based on domain knowledge for GH, when it comes to the robustness of random data composition and consistency of performance, the evaluation of three-phase saturation can be boosted using CNN with data augmentation.
      原文链接:
    • NSTL

    Investigation on the microscopic damage mechanism of fracturing fluids to low-permeability sandstone oil reservoir by nuclear magnetic resonance

    Xuejiao LiQingjiu ZhangPeng Liu
    13页
    查看更多>>摘要：Hydraulic fracturing has become an essential stimulation treatment for improving the development efficiency of low-permeability oil reservoirs. However, fracturing fluid inevitably causes reservoir damage. This study proposed a combined method of microscopic and macroscopic experiments to investigate the nature of formation damage of fracturing fluid by quantifying its influence on porosity, permeability, and pore structure. Nuclear magnetic resonance technology combined with core flooding test and parallel sample comparison method was applied to quantitatively evaluate the damage degree and identify the main damage types of hydroxypropyl guar (HPG) fracturing fluid and slickwater fracturing fluid. The microscopic damage mechanisms of these fracturing fluids were analyzed by thin section petrography, X-ray diffraction, rate-controlled mercury intrusion, scanning electron microscopy, and wettability tests. The results show that the total permeability damage degree of HPG fracturing fluid filtrate is 30.43%, of which water sensitivity, water lock, and macromolecule adsorption account for 6.06%, 23.26%, and 1.11%, respectively. Water lock is the major damage factor. Regarding the damage of slickwater fracturing fluid filtrate, water sensitivity causes the severest damage, corresponding to 39.08% of core permeability loss, whereas macromolecule adsorption and water lock contribute 13.21% and 0.97%, respectively. Water sensitivity damage causes reduced porosity, decreased permeability, and narrower pores, resulting from hydration, swelling, dispersion and migration of clay minerals. Water lock damage increases the movable pore volume, decreases the permeability, increases the pore radius, decreases the throat radius, and increases the pore throat ratio, which increases the flow resistance to the oil phase. The magnitude of water lock damage is closely related to the surfactant content and performance, rock wettability, and pore throat radius ratio. Macromolecule adsorption damage leads to a decrease in permeability, a reduction in the number of large pores, an increase in the number of small throats, and an increase in the pore throat radius ratio due to the absorption and retention of macro molecules on the surfaces of the pores and throats. Increasing the flowback volume of slickwater fracturing fluid can recover part of the macromolecule absorption damage. This research can provide a reliable reference for the optimization of fracturing fluid performance, enhancement of the fracturing effect and reservoir protection of low-permeability reservoirs.
      原文链接:
    • NSTL

    Evaluation of unsupervised machine learning frameworks to select representative geological realizations for uncertainty quantification

    Seyed Kourosh MahjourLufs Otavio Mendes da SilvaLuis Augusto Angelorti Meira
    15页
    查看更多>>摘要：Ensembles of geological realizations (GR) are normally processed by numerical simulators to evaluate geological uncertainty during the decision-making process. Although different stochastic spatial algorithms can quickly generate hundreds to thousands of GR to capture the full uncertainty range, the simulation process applied to this number of realizations is computationally expensive. Hence, a small subset of representative geological realizations (RGR) that statistically represent the features of the full ensemble can be used for uncertainty quantification. In this study, unsupervised machine learning (UML) is applied by considering different (1) adjacency matrix construction, (2) dimensionality reduction, and (3) clustering and sampling algorithms to generate several RGR sets. Then, the mismatches between the distribution of different field and well indicators obtained from the RGR sets and the whole ensemble are measured using the Kolmogorov-Smirnov (KS) test to compare the uncertainty space of the subsets and the full set. Furthermore, to measure the pairwise adjacency between the realizations, we use a static reservoir feature called reservoir quality index (RQI). We performed extensive computational analyses to appraise the performance of the UML in two benchmark cases. Each case contains 500 GR. This study can provide a comprehensive assessment of the UML for the RGR selection due to the application of different algorithms. The results showed that the RGR set can be successfully selected without previous flow simulation runs, if an appropriate UML method is employed. This leads to a reduction in the computational cost during uncertainty quantification and risk analysis. Furthermore, we observed that the optimal number of RGR should be chosen due to the geological complexity of each case study. We also found that the type of recovery mechanism has no impact on the optimal number of RGR and on UML methods. The appropriate RGR set can be used for production forecasts and development planning support.
      原文链接:
    • NSTL