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

    A novel hybrid method of lithology identification based on k-means++ algorithm and fuzzy decision tree

    Quan RenHongbing zhangDailu Zhang
    13页
    查看更多>>摘要： Lithology identification methods based on conventional logging data are essential in reservoir geological evaluation. Due to the highly non-linear relationship between lithology and various logging parameters, conventional methods cannot meet the requirements. In recent years, machine learning methods such as Neural Networks and decision tree have been applied to the field of lithology identification and achieved good effects. However, there is no obvious difference in logging parameters for various types of lithology, and at the same time, there is a large amount of information redundancy between each logging curve. Therefore, its uncertainty and fuzziness are high, which interferes with the result of lithology identification. Combining fuzzy theory, decision tree and K-means++ algorithm, this paper proposes a novel hybrid technique of lithology identification which can better overcome the ambiguity and uncertainty of logging data. In the actual data test, we select six logging parameters: density (RHOB), neutron porosity (NPHI), natural gamma (GR), longitudinal wave velocity (VP), shallow formation resistivity (LLS), and deep formation resistivity (LLD). Then K-means++ clustering algorithm was used for clustering analysis on logging data. Finally, the triangular membership function is selected to fuzz the logging data according to the obtained clustering center points, and a fuzzy decision tree lithology identification model is constructed. The prediction accuracy of the model reached 93.92%. The fuzzy decision tree algorithm was also compared with five machine learning algorithms, including decision tree, extremely randomized trees (ET), Adaboost, random forest (RF) and gradient boosting decision tree (GBDT). The results show that the modeling results of fuzzy decision tree algorithm outperform other algorithms. In summary, the fuzzy decision tree model developed in the study is a practical and effective model for complex lithology identification, providing a new idea for lithology identification.
      原文链接:
    • NSTL

    A review of research on the dispersion process and CO2 enhanced natural gas recovery in depleted gas reservoir

    Changzhong ZhaoShezhan LiuLei Yuan
    13页
    查看更多>>摘要： The dispersion coefficient is a key physical parameter for enhanced gas recovery (EGR) and reflects the degree of mixing between the displacing-fluid CO2 and natural gas. However, no comprehensive overview of existing research on EGR dispersion characteristics has been conducted to date. In this review article, previous experimental and simulation studies are summarized to provide an overview of the current research progress and, hence, to elucidate the limitations of EGR and identify directions for future research. The literature analysis reveals that temperature and flow rate promote CO2-CH4 dispersion, whereas pressure and residual-water salinity inhibit dispersion under supercritical conditions. The CO2-CH4 dispersion coefficient is smaller in porous media with high permeability. However, on the core scale, the effects of residual water on the CO2 dispersion and breakthrough time are controversial and further verification is required. To date, only limited research has been conducted on the effects of impurities under supercritical conditions, such as considering CO2 containing N2, and CH4 containing CO2, N2 and ethane. Existing pilot EGR trials are insufficient to provide standardized field operation instructions, for example, with regard to the wellhead layout. Field-scale simulations have verified the feasibility of EGR technology and economy. However, factors such as the permeability heterogeneity, initial water saturation distribution, connate water salinity, gas-reservoir non-isothermal conditions, and vertical stratification should be considered in simulations of actual gas reservoirs. More in-depth experimental and simulation-based investigations of EGR should be performed on various scales to accurately assess the dispersion characteristics and natural-gas recovery efficiency under gas-reservoir conditions.
      原文链接:
    • NSTL

    One-step preparation of Cu/BC catalyzed the upgrading of heavy oil assisted by microwave

    Xiaodong TangBin HeJingjing Li
    10页
    查看更多>>摘要： As a clean and efficient means to reduce the viscosity of heavy oil, microwave has broad research prospects in the field of heavy oil upgrading. For the microwave-assisted heavy oil upgrading process, the catalyst research has not made a breakthrough for a long time. In this study, a one-step method was used to load copper on biochar (BC) to prepare a catalyst (Cu/BC) in microwave, which can be used as a catalyst and microwave absorbing medium in the microwave-assisted upgrading process of heavy oil. The effect of the catalyst on the upgrading of heavy oil under different microwave reaction conditions was studied. The results show that the catalyst prepared by impregnation concentration of 0.15M metal salt has the best catalytic upgrading effect on heavy oil at a microwave temperature of 260 °C for 20 min, and the viscosity reduction rate of heavy oil reaches 78.55%. Under the action of the functional groups on the surface of the catalyst and the metal, the long-chain macro-molecular hydrocarbons in the heavy oil were cracked into small molecular hydrocarbons, resulting in a decrease in the viscosity of the heavy oil. The analysis results show that the catalyst also has a positive effect on promoting the breaking of C-S bonds in heavy oil. The application of metal-supported biochar catalyst provides a new idea for the study of the viscosity reduction reaction of heavy oil under microwave irradiation.
      原文链接:
    • NSTL

    Incorporating adaptive well conditions into numerical reservoir simulators constrained by well and reservoir performance data

    Suleiman AltaheiniPeyman MostaghimiStuart R. Clark
    15页
    查看更多>>摘要： Using fixed boundary conditions has always been the way wells are modelled in reservoir simulators for prediction runs. This commonly results in oil wells being shut-in due to increasing production of water or gas or triggering a workover option shutting-in a section of the wells perforated interval. These actions are late reactive actions instead of being proactive actions that can help prolong a wells life. In actual field operations, well flow rates and bottomhole pressures are often adjusted to better suit reservoir management strategies and control water and gas production. This paper introduces a novel yet simple implementation of adaptive well conditions that updates well boundary conditions based on wellbore or near-wellbore performance. This methodology can be executed using a commercial simulator alongside a small instructing application, or internally integrated as done here with an inhouse reservoir simulator built to present this work as proof of concept. Three case studies are presented in this paper with increasing complexity. We show that an improvement in the amount of recovered oil, an increase in the lifetime of assets, and a reduction of produced water and gas are all possible with adaptive well controls. In one of the three cases, adaptive well controls resulted in an oil recovery increase as high as 20%. We also discuss the differences between well-data and reservoir-data dependencies of the adaptive well-condition algorithms in terms of dynamic response and physical application. Implementing adaptive well controls can help in reconsidering business plans by reducing water and gas production and avoiding early abandonment of wells. It was also considered that one of the main advantages of adaptive well conditions is the potentially significant reduction in number of variables for future optimization studies due to the elimination of control steps.
      原文链接:
    • NSTL

    On the evaluation of permeability of heterogeneous carbonate reservoirs using rigorous data-driven techniques

    Aydin LarestaniMenad Nait AmarMehdi Mahdaviara
    17页
    查看更多>>摘要： This study probes the application of Cascade Forward Neural Network (CFNN), Least Square Support Vector Machine (LSSVM), Multilayer Perception (MLP), and Generalized Regression Neural Network (GRNN) techniques for modeling the absolute permeability of carbonate rocks in terms of pore specific surface area, porosity, and irreducible water saturation. The control parameters of the MLP and CFNN models were tuned through Levenberg Marquardt Algorithm (LMA) and Bayesian Regularization (BR) optimizers, and the LSSVM paradigm was optimized using Gravitational Search Algorithm (GSA). Accordingly, six intelligent schemes, viz. MLP-BR, MLP-LMA, LSSVM-GSA, CFNN-BR, CFNN-LMA, and GRNN were trained by utilizing 80% of a valuable set of core data compiled from reliable literature and were tested through the rest of the data points (20%). The accuracy of the proposed paradigms was evaluated using several statistical and graphical assessments. The overall results were fulfilling and fair enough for the scope of this study. The proposed MLP-BR, MLP-LMA, LSSVM-GSA, CFNN-BR, CFNN-LMA, and GRNN models were associated with the Root Mean Square Errors of 6.8019, 5.6225, 165.8852, 6.6841, 5.2136, and 11.1799, respectively. The results were endorsed through 3-fold cross-validation. Furthermore, outlier detection was carried out by means of the plot of standardized residuals versus Leverage values. For all models, the majority of the points were valid values distributing in the applicability domain of the models. In the end, the developed models were compared against two literature smart models and a traditional correlation. The results demonstrated that the recently generated models offer remarkably higher accuracy than other alternatives followed by the Gene Expression Programming (GEP) modeling approach.
      原文链接:
    • NSTL

    Well performance prediction based on Long Short-Term Memory (LSTM) neural network

    Ruijie HuangChenji WeiBaohua Wang
    17页
    查看更多>>摘要： Fast and accurate prediction of well performance continues to play an increasingly important role in development adjustment and optimization. It is now possible to predict performance more accurately using neural networks thanks to the advancement of artificial intelligence. In this study, A Long Short-Term Memory (LSTM) neural network model which considered gas injection effect was established to forecast the production performance of a carbonate reservoir in the Middle East. Over 12 years of surveillance data from 17 producers and 11 injectors were selected as the dataset. A correlation analysis was performed to determine the input and output variables of the model before establishing the model. Using historical data from the first 4000 days, the model is trained and validated before it is used to predict the performance of the next 500 days. After that, the calculation results of this model and traditional reservoir numerical simulation (RNS) were compared under the same conditions. The results show that the average error of the LSTM method is 43.75% lower than that of traditional RNS. Moreover, the total CPU time and comprehensive computing power consumption of LSTM method only account for 10.43% and 36.46% of RNS's, respectively. Thus, it is clear that the LSTM approach has a significant advantage when it comes to calculating. In the end, we categorized all 17 producers into three groups based on GOR predictions for the next 500 days, and proposed optimization and adjustment techniques for each type. This study provides a new direction for the application of artificial intelligence in oil and gas development.
      原文链接:
    • NSTL

    Optimization of an in-situ polymerized and crosslinked hydrogel formulation for lost circulation control

    Fuat Campos PereiraKarl Jan ClinckspoorRosangela Barros Zanoni Lopes Moreno
    11页
    查看更多>>摘要： Lost circulation is a common problem during drilling and completion, and it contributes much to the nonproductive time of the operation. The Brazilian pre-salt is composed of highly heterogeneous carbonates and is highly susceptible to circulation loss. In this work, a removable, solid-free polymer gel formulation based on in-situ polymerization and gelation was proposed and optimized using design of experiments. The proposed gel contains acrylic acid (monomer), carboxymethylcellulose (thickener), ammonium persulfate (initiator), chromium (III) salt (crosslinking agent) and 240,000 NaCl brine as a solvent. The concentrations of these components, and the solution pH, were the variables considered in this study. The plateau modulus, maximum elastic modulus, gel stability, and gelation times were obtained and analyzed. The gelation time was obtained from oscillatory rheology time curves fitted by the Hill 5 model and from low-frequency nuclear magnetic resonance. Most of the studied gels presented elastic moduli from 1000 to 7000 Pa, close to and higher than the moduli of other gels for lost circulation. The gelation times ranged from 5 to 30 min, which could be improved by changing the initiator, protecting or inhibiting it. A pH of 9 led to faster gelation times, syneresis, and lower elastic moduli; therefore, pH values from 5 to 7 are ideal. Carboxymethylcellulose and the chromium salt increased slightly the gelation time, the elastic moduli, and the stability. Acrylic acid concentration controlled the overall elastic moduli, and higher concentrations led to shorter gelation times. Ammonium persulfate was able to both initiate the polymerization and also internally break the gel, depending on the concentration. Molecular explanations for these effects were provided. This proposed system is a promising candidate for lost circulation control for operations in the Brazilian pre-salt. Future steps involve studying the plugging and removable properties of the gels with optimized composition in high pressure and temperature settings.
      原文链接:
    • NSTL

    Experimental investigation into the development and evaluation of ionic liquid and its graphene oxide nanocomposite as novel pour point depressants for waxy crude oil

    Barasha DekaVikas MahtoRohit Sharma
    16页
    查看更多>>摘要： Wax deposition in pipelines transporting crude oil is a serious problem as wax tends to precipitate under low temperature conditions observed during pipeline flow. The current research work embarks on the development of novel nanocomposite pour point depressant (PPD) for waxy crude oils. Two additives were synthesized in the laboratory: 1-octyl 3-methylimidazolium chloride [(OMIM)Cl], and a novel class of nanocomposite PPD: PPDR-GO. These additives were tested on an Indian waxy crude oil and proved to be acting as PPDs and flow improvers. Pour point reduction occurred from 39 °C to 21 °C with [(OMIM)Cl], while the depression occurred from 39 °C up to 9 °C with nanocomposite PPDR-l%GO, suggesting significant improvement in the flow ability of the crude oil. The PPDs also induced reduction in the apparent viscosities of crude oil significantly from 7 Pa s down to 0.04 Pa s by (OMIM)Cl and 0.02 Pa s (at higher shear rates and temperatures) by PPDR-l%GO respectively. Apart from the pour point and viscosity tests, the effectiveness of the additives were tested by cold finger, gelation point and aging tests and they produced encouraging set of results. The characterization of the two PPDs performed using spectroscopic analytical techniques FTIR, Proton NMR, XRD and Raman helped identifying the presence of different components and confirm their structure. The purpose of this work is to develop new pour point depressants which are highly effective for providing flow assurance of waxy crude oils. This research also aimed at improving the synthesized PPDs in important areas such as improving dispersion of VGO nanosheets in nanocomposite matrix, enhanced pour point depression ability, low dosage requirement of PPDs, eliminating the need of solvent for PPDs. The action mechanism of the PPDs develops theoretical insights on interactions of ionic liquids, graphene oxide sheets and asphaltenes with the wax structures, which would be highly beneficial for future research.
      原文链接:
    • NSTL

    Accelerating reservoir production optimization by combining reservoir engineering method with particle swarm optimization algorithm

    Zhibin AnKang ZhouJian Hou
    8页
    查看更多>>摘要： Generally, the optimization of injection and production parameters in oilfields are carried out by using reservoir engineering method or mathematical algorithm individually, which limits the optimization efficiency and accuracy. To deal with this problem, the paper tries to improve production optimization performance by introducing reservoir engineering method into conventional particle swarm optimization (PSO) in three ways: the preprocessing result by reservoir engineering method is used respectively as population initialization, the search space constraint and the particle velocity guide item in PSO. Results show that all the three improved optimization methods can speed up the convergence rate of PSO algorithm while keeping similar convergence results at the same time. Furthermore, the use of the reservoir engineering preprocessing scheme as the search space constraint obtains the best convergence performance and reduces the iteration calculations by 24.14%, providing an effective way to reduce calculation cost for reservoir production optimization in commercial oilfields.
      原文链接:
    • NSTL

    Artificial neural networks-based correlation for evaluating the rate of penetration in a vertical carbonate formation for an entire oil field

    Ahmad Al-AbdulJabbarAhmed Abdulhamid MahmoudSalaheldin Elkatatny
    13页
    查看更多>>摘要： The rate of penetration (ROP) is a critical factor affecting the process of oil well drilling optimization and the total drilling cost. This work introduces an empirical correlation extracted from the learned artificial neural networks (ANN) to assess the ROP across a vertical carbonate formation from five surface drilling parameters measurable through real-time sensors. The ANN was built based on real 220 datasets obtained from eight wells. The data from five of these wells were used to train the ANN model. Several sensitivity analyses were conducted on the model's parameters to achieve the best combination of these parameters. To enable real-time assessment of the ROP, a correlation from the leaned ANN model was extracted, which was tested on 92 datasets from the same training wells while unseen datasets from another three wells were used for validating the empirical correlation. The results showed that the ANN was effectively predicted the ROP with an average absolute percentage error (AAPE) of only 4.34% for the training data. Using the developed equation, the ROP was assessed for the validation data with an average AAPE of 6.75%.
      原文链接:
    • NSTL