Research on the Application of Integrated Learning Models in Oilfield Production Forecasting.

Forecasting oil production is crucially important in oilfield management. Currently, multifeature-based modeling methods are widely used, but such modeling methods are not universally applicable due to the different actual conditions of oilfields in different places. In this paper, a time series forecasting method based on an integrated learning model is proposed, which combines the advantages of linearity and nonlinearity and is only concerned with the internal characteristics of the production curve itself, without considering other factors. The method includes processing the production history data using singular spectrum analysis, training the autoregressive integrated moving average model and Prophet, training the wavelet neural network, and forecasting oil production. The method is validated using historical production data from the J oilfield in China from 2011 to 2021, and compared with single models, Arps model, and mainstream time series forecasting models. The results show that in the early prediction, the difference in prediction error between the integrated learning model and other models is not obvious, but in the late prediction, the integrated model still predicts stably and the other models compared with it will show more obvious fluctuations. Therefore, the model in this article can make stable and accurate predictions.

Optimization of Gel Flooding during the High Water Cut Stage in a Conglomerate Reservoir of the Xinjiang A Oilfield.

Influenced by water injection, a dominant flow channel is easily formed in the high water cut stage of a conglomerate reservoir, resulting in the inefficient or ineffective circulation of the injected water. With gel flooding as one of the effective development methods to solve the above problems, its parameter optimization determines its final development effect, which still faces great challenges. A new optimization method for gel flooding is proposed in this paper. Firstly, the gel flooding parameters were obtained through physical experiments; then, an experimental model of gel flooding was established according to the target reservoir, and parameter sensitivity analysis was carried out. Next, a history matching of the gel flooding experiment was carried out. Finally, history matching of the target reservoir was also carried out, and a gel flooding scheme was designed and optimized to determine the best parameters. The experimental results showed that the gelation time was 4 h and the gel viscosity was 6332 mPa·s; the breakthrough pressure, resistance factor (RF), and residual resistance factor (RRF) all decreased with the increase in permeability. The gel had a good profile control ability and improved oil recovery by 16.40%. The numerical simulation results illustrated that the porosity of the high permeability layer (HPL) had the greatest impact on the cumulative oil production (COP) of the HPL, and the maximum polymer adsorption value of the HPL had the largest influence on the COP of the low permeability layer (LPL) and the water cut of both layers. Benefiting from parameter sensitivity analysis, history matching of the gel flooding experiment and a conglomerate reservoir in the Xinjiang A Oilfield with less time consumed and good quality was obtained. The optimization results of gel flooding during the high water cut stage in a conglomerate reservoir of the Xinjiang A Oilfield were as follows: the gel injection volume, injection rate, and polymer concentration were 2000 m3, 50 m3/d, and 2500 mg/L, respectively. It was predicted that the water cut would decrease by 6.90% and the oil recovery would increase by 2.44% in two years. This paper not only provides a more scientific and efficient optimization method for gel flooding in conglomerate reservoirs but also has important significance for improving the oil recovery of conglomerate reservoirs.

Polymer Flooding in Heterogeneous Heavy Oil Reservoirs: Experimental and Simulation Studies.

Polymer flooding (PF) in heterogeneous heavy oil reservoirs is not only closely related to polymer degradation, but also to non-Newtonian flow. In this paper, both experimental and simulation methods are combined to investigate this type of flooding. Through experiments, the degradation of polymer, rheological properties of fluids, and flow of fluids in porous media were determined. Based on the experimental results, a novel mathematical model was established, and a new PF simulator was designed, validated, and further applied to study the effects of polymer degradation, polymer solution shear thinning, and non-Newtonian flow on PF in heterogeneous heavy oil reservoirs. These experimental results demonstrated that the polymer first-order static degradation rate constant was lower than the polymer first-order dynamic degradation rate constant; the polymer solution and heavy oil were non-Newtonian fluids, with shear thinning and Bingham fluid properties, respectively; and the heavy oil threshold pressure gradient (TPG) in low-permeability porous media was higher than that in high-permeability porous media. All comparison results showed that the designed simulator was highly accurate and reliable, and could well describe both polymer degradation and non-Newtonian flow, with special emphasis on the distinction between polymer static and dynamic degradation and heavy oil TPG. Furthermore, the simulation results verified that polymer degradation, polymer solution shear thinning, and heavy oil TPG all had negative effects on the efficiency of PF in heterogeneous heavy oil reservoirs.

Effect of Polymer Degradation on Polymer Flooding in Heterogeneous Reservoirs.

Polymer degradation is critical for polymer flooding because it can significantly influence the viscosity of a polymer solution, which is a dominant property for polymer enhanced oil recovery (EOR). In this work, physical experiments and numerical simulations were both used to study partially hydrolyzed polyacrylamide (HPAM) degradation and its effect on polymer flooding in heterogeneous reservoirs. First, physical experiments were conducted to determine basic physicochemical properties of the polymer, including viscosity and degradation. Notably, a novel polymer dynamic degradation experiment was recommended in the evaluation process. Then, a new mathematical model was proposed and an in-house three-dimensional (3D) two-phase polymer flooding simulator was designed to examine both polymer static and dynamic degradation. The designed simulator was validated by comparison with the simulation results obtained from commercial software and the results from the polymer flooding experiments. This simulator further investigated and validated polymer degradation and its effect. The results of the physical experiments showed that the viscosity of a polymer solution increases with an increase in polymer concentration, demonstrating their underlying power law relationship. Moreover, the viscosity of a polymer solution with the same polymer concentration decreases with an increase in the shear rate, demonstrating shear thinning. Furthermore, the viscosity of a polymer solution decreased with an increase in time due to polymer degradation, exhibiting an exponential relationship. The first-order dynamic degradation rate constant of 0.0022 day-1 was greater than the first-order static degradation rate constant of 0.0017 day-1. According to the simulation results for the designed simulator, a 7.7% decrease in oil recovery, after a cumulative injection volume of 1.67 pore volume (PV) was observed between the first-order dynamic degradation rate constants of 0 and 0.1 day-1, which indicates that polymer degradation has a detrimental effect on polymer flooding efficiency.

Effect of Non-Newtonian Flow on Polymer Flooding in Heavy Oil Reservoirs.

The flow of polymer solution and heavy oil in porous media is critical for polymer flooding in heavy oil reservoirs because it significantly determines the polymer enhanced oil recovery (EOR) and polymer flooding efficiency in heavy oil reservoirs. In this paper, physical experiments and numerical simulations were both applied to investigate the flow of partially hydrolyzed polyacrylamide (HPAM) solution and heavy oil, and their effects on polymer flooding in heavy oil reservoirs. First, physical experiments determined the rheology of the polymer solution and heavy oil and their flow in porous media. Then, a new mathematical model was proposed, and an in-house three-dimensional (3D) two-phase polymer flooding simulator was designed considering the non-Newtonian flow. The designed simulator was validated by comparing its results with those obtained from commercial software and typical polymer flooding experiments. The developed simulator was further applied to investigate the non-Newtonian flow in polymer flooding. The experimental results demonstrated that the flow behavior index of the polymer solution is 0.3655, showing a shear thinning; and heavy oil is a type of Bingham fluid that overcomes a threshold pressure gradient (TPG) to flow in porous media. Furthermore, the validation of the designed simulator was confirmed to possess high accuracy and reliability. According to its simulation results, the decreases of 1.66% and 2.49% in oil recovery are caused by the difference between 0.18 and 1 in the polymer solution flow behavior indexes of the pure polymer flooding (PPF) and typical polymer flooding (TPF), respectively. Moreover, for heavy oil, considering a TPG of 20 times greater than its original value, the oil recoveries of PPF and TPF are reduced by 0.01% and 5.77%, respectively. Furthermore, the combined effect of shear thinning and a threshold pressure gradient results in a greater decrease in oil recovery, with 1.74% and 8.35% for PPF and TPF, respectively. Thus, the non-Newtonian flow has a hugely adverse impact on the performance of polymer flooding in heavy oil reservoirs.