scispace - formally typeset
Search or ask a question
Author

Angang Zhang

Bio: Angang Zhang is an academic researcher from PetroChina. The author has contributed to research in topics: Water injection (oil production) & Phase (matter). The author has an hindex of 3, co-authored 8 publications receiving 37 citations.

Papers
More filters
Journal ArticleDOI
01 Oct 2015-Fuel
TL;DR: In this article, a three-layered (7-19-1) ANN trained with the Levenberg-Marquardt back propagation algorithm was used to estimate the gas/water interfacial tension.

23 citations

Journal ArticleDOI
Angang Zhang1, Zifei Fan1, Lun Zhao1
15 May 2020-Fuel
TL;DR: In this paper, the phase behavior of condensate oil in the formation mixed with various gas (CO2, N2, CH4, C2H6 and re-injected gas) has been analyzed.

22 citations

Journal ArticleDOI
TL;DR: In this paper, the authors evaluated the sensitivity of profile control by clay particles after polymer flooding, including the permeability ratio, formation oil viscosity, injection timing, injection volume and injection concentration of clay particles solution.

6 citations

Journal ArticleDOI
Angang Zhang1, Zifei Fan1, Lun Zhao1
TL;DR: In this paper, the effect of CO2/CH4 solvent and N2/Ch4 solvent injection on phase behaviors of condensate in DZT reservoir was investigated.
Abstract: This work is aimed to investigate the effect of CO2/CH4 solvent and N2/CH4 solvent injection on phase behaviors of condensate in DZT reservoir. The results indicate that CO2/CH4 flooding is vaporiz...

2 citations

Patent
26 Jun 2020
TL;DR: In this paper, an effective water injection amount determination method and device for strong edge-water reservoir outer edge water injection development is presented, which comprises the steps of obtaining a reservoir geologic feature and development dynamic parameter; judging whether a set stratum pressure meets a preset precision or not according to the reservoir geology feature and dynamic parameter and a matter balance equation; and determining an effective injection amount according to determined stratumpressure meeting the preset precision.
Abstract: The invention provides an effective water injection amount determination method and device for strong edge-water reservoir outer edge water injection development. The method comprises the steps of obtaining a reservoir geologic feature and development dynamic parameter; judging whether a set stratum pressure meets a preset precision or not according to the reservoir geologic feature and development dynamic parameter and a matter balance equation; and determining an effective water injection amount according to the determined stratum pressure meeting the preset precision. The effective water injection amount calculation method for building strong edge-water reservoir outer edge water injection development quantitatively evaluates the effective injection amount of the outer edge water injection development, and reasonably optimizes injection allocation amounts of different stages of outer edge water injection well drainage to implement efficient development of a strong edge-water reservoir.

2 citations


Cited by
More filters
Journal ArticleDOI
01 Jan 2018-Fuel
TL;DR: In this article, a particle swarm optimization (PSO) was employed to optimize the parameters of support vector regression (SVR) model to predict the temperature of coal spontaneous combustion based on the gases concentration in the gob and distance from the measuring points to the working face.

97 citations

Journal ArticleDOI
TL;DR: The integrated workflow followed in this study is quite innovative as it has not been employed before for surfactant adsorption studies, and the utilization of ANN for such prediction procedure can minimize the experimental time, operating cost and give feasible predictions compared to other computational methods.

71 citations

01 Jan 1972
TL;DR: In this article, a multicell equilibrium flash separation model has been developed which can predict the composition necessary to develop miscibility in linear systems, which can compute the compositional changes which occur in the transition zone between the in-place oil and injected fluid.
Abstract: A multicell equilibrium flash separation model has been developed which can predict the composition necessary to develop miscibility in linear systems. The model computes the compositional changes which occur in the transition zone between the in-place oil and injected fluid and can also compute effluent volumes and compositions. Furthermore, it has the capability of incorporating phase mobilities for determination of flowing fluid compositions. This model has been run with both 3-component and real system phase equilibria data. Results show that in some cases more enrichment may be required to develop miscibility than predicted by the Benham correlation. The model has proved to be much faster computationally than a more sophisticated model that was recently described in the literature. In addition, the model compares favorably with the predictions of this more sophisticated model. The model being presented shows mathematically the effect that phase mobilities have on the eventual development of miscibility. (11 refs.)

51 citations

Journal ArticleDOI
TL;DR: In this article, the authors used feed forward artificial neural network (ANN) to accurately estimate CO 2 -brine interfacial tension (IFT) based on a database acquired from previous literature, which consists of a total of 1716 CO 2-brine IFT datasets that cover relatively large ranges of pressure (0.1-60.05 MPa), temperature (5.25-175 °C), total salinity (0−5 ǫ kg −1 ) and mole fractions (0-80%) of impure components.
Abstract: Experimental determination of CO 2 –brine interfacial tension (IFT) usually requires expensive apparatus and sophisticated interpretation procedure and is time-consuming. Hence, it is of practical importance to develop an accurate and reliable model for determining the CO 2 –brine IFT. This paper presents the use of feed forward artificial neural network (ANN) to accurately estimate CO 2 –brine IFT based on a database acquired from previous literature. The database consists of a total of 1716 CO 2 –brine IFT datasets that cover relatively large ranges of pressure (0.1–60.05 MPa), temperature (5.25–175 °C), total salinity (0–5 mol kg −1 ) and mole fractions (0–80%) of impure components. Six independent variables were considered to develop the IFT estimation model: pressure, temperature, monovalent cation (Na + and K + ) molality, bivalent cation (Ca 2+ and Mg 2+ ) molality in brine, and mole fractions of N 2 and CH 4 in injected CO 2 streams. The ANN topology was optimized by trial-and-error in order to enhance its capability of generalization and the optimal one was determined to be 6-10-20-1 (10 and 20 neurons in the first and second hidden layers, respectively). The accuracy of the proposed ANN model was highlighted by four evaluation matrices, namely mean absolute error (MAE), mean absolute relative error (MARE), mean squared error (MSE), and determination coefficient ( R 2 ) between the measured and estimated IFT. The ANN model was further compared against four empirical IFT correlations developed in previous studies. It was observed that the ANN model outperforms significantly the empirical correlations and provides the most accurate IFT reproduction with respect to pure CO 2 –pure water, pure CO 2 –brine and impure CO 2 systems.

31 citations

Journal ArticleDOI
15 Dec 2020-Fuel
TL;DR: A novel supervised learning (SL) method is proposed, namely the eXtreme gradient boosting (XGBoost) trees, for the fast estimation of (gas + n-alkane) IFT, which demonstrated that the new model outperforms the multi-layer perceptron (MLP), support vector regression (SVR) and existing correlations in terms of accuracy and robustness.

28 citations