|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Ma, Kuiqian (Tianjin Branch of CNOOC (China) Co., Ltd) | Chen, Cunliang (Tianjin Branch of CNOOC (China) Co., Ltd) | Zhang, Wei (Tianjin Branch of CNOOC (China) Co., Ltd) | Liu, Bin (Tianjin Branch of CNOOC (China) Co., Ltd) | Han, Xiaodong (CNOOC Ltd and China University of Petroleum, Beijing)
Abstract Performance prediction is one of the important contents of oilfield development. It is also an important content affecting investment decision-making, especially for offshore oilfields with large investment. At present, most oilfields in China have entered high water cut stage or even extra high water cut stage, which requires higher prediction accuracy. Water drive curve is an important method for predicting performance. Traditional methods are based on exponential formulas, but these methods have poor adaptability in high water cut period. Because traditional methods deviate from straight line in high water cut period. In this paper, a robust method for predicting performance of offshore oilfield in high water cut period based on big data and artificial intelligence is proposed. Firstly, the reasons for the "upward warping" phenomenon of traditional methods deviating from the straight line are analyzed. It is found that the main reason for the deviation is that the relationship between the relative permeability ratio of oil to water and the water saturation curve no longer conforms to the exponential relationship. So a new percolation characteristic characterization equation with stronger adaptability is proposed, which focuses on the limit of high water flooding development. On this basis, the equation of the new water drive characteristic curve is deduced theoretically, and the dynamic prediction method is established. What's more, the solution of the method is based on large data and AI algorithm. This method has been applied to many high water flooding phase permeability curves, and the coincidence rate is more than 95.6%. The new water drive characteristic curve can better reflect the percolation characteristics of high water cut reservoirs. At the same time, the performance of adjustment wells and measures on the curve of development dynamic image is analyzed. Curve warping indicates that adjustment wells or measures are effective. Field application shows that the prediction error of the new method is less than 6%, which is more in line with the needs of oilfield development. Because of the application of artificial intelligence algorithm, the application is more convenient and saves a lot of time and money. This is a process of self-learning and self-improvement. As the oil field continues over time, each actual data will be recalculated into the database. Then the fitting and correction are carried out, and then the solution is learned again. This method has been applied to several oil fields in Bohai. And the effect is remarkable, which provides a good reference for the development of other oil fields.
After long-term waterflooding, a number of mature oil fields in China have entered the high-water-cut stage, and abnormal production decline has become the primary problem for stable production. This paper describes an accurate, three-step, machine-learning-based early warning system (EWS) that has been used to monitor production and guide strategy in the Shengli field. Adding artificial samples to the training process improved the system's prediction accuracy greatly (Figure 1). For conventional Chinese oil fields that have entered the high-water-cut stage after decades of waterflooding, stabilizing production has become increasingly difficult. After stimulation treatments throughout the field's history, abnormal decline rates--that is, exceeding 5%--occurred more frequently.
This article, written by JPT Technology Editor Judy Feder, contains highlights of paper SPE 197365, “A Novel Early Warning System of Oil Production Based on Machine Learning,” by Kang Ma, Hanqiao Jiang, and Junjian Li, China University of Petroleum-Beijing, et al., prepared for the 2019 Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, 11–14 November. The paper has not been peer reviewed. After long-term waterflooding, a number of mature oil fields in China have entered the high-water-cut stage, and abnormal production decline has become the primary problem for stable production. This paper describes an accurate, three-step, machine-learning-based early warning system (EWS) that has been used to monitor production and guide strategy in the Shengli field. Adding artificial samples to the training process improved the system’s prediction accuracy greatly (Fig. 1). Introduction For conventional Chinese oil fields that have entered the high-water-cut stage after decades of waterflooding, stabilizing production has become increasingly difficult. After stimulation treatments throughout the field’s history, abnormal decline rates—that is, exceeding 5%—occurred more frequently. Production declined dramatically in 2004 and has not been maintained since then. To prevent future abnormal production declines, an effective EWS was needed that could release a production alarm to enable engineers to take preventive measures in advance. The complete paper includes a discussion of various early-warning models and their limitations. The paper discusses an EWS based on a neural network method using a previously established data set. Factors that can affect the abnormal decline were selected. The index sets of production composition and injected and produced water obtained from practical statistics were considered as the main assessment indicators. Grey relational analysis was used to evaluate the importance of the different indicators and to eliminate redundant parameters. Machine learning was adopted to build the EWS. Using the degree of deviation from normal as the input data for the prediction model provided the highest accuracy. However, the basic machine-learning model contains many input parameters that cannot be obtained easily. The number of input parameters was optimized on the basis of the variation of accuracy under different input parameter numbers. To improve prediction accuracy, artificial samples were added to the training process. The prediction accuracy of the final optimization model can reach 92%. The result reveals the possibility of the occurrence of anomalous decline in different reservoirs, which can guide oilfield production strategy effectively. The EWS was verified by oilfield production. Fundamentals of Neural-Network Classification Neural networks use existing data to determine the implicit model between input and output data. Classification and prediction are the most common applications. Neural networks are used in the industry to solve classification and regression problems.
Zhao, Pingqi (Petrochina DaGang Oilfield Company, Tianjin, China) | He, Shumei (Petrochina DaGang Oilfield Company, Tianjin, China) | Cai, Mingjun (Petrochina DaGang Oilfield Company, Tianjin, China) | Tao, Ziqiang (Petrochina DaGang Oilfield Company, Tianjin, China) | Zhao, Ming (Petrochina DaGang Oilfield Company, Tianjin, China) | Wu, Xi (Petrochina DaGang Oilfield Company, Tianjin, China) | Ni, Tianlu (Petrochina DaGang Oilfield Company, Tianjin, China) | Guo, Qi (Petrochina DaGang Oilfield Company, Tianjin, China) | Wei, Pengpeng (Petrochina DaGang Oilfield Company, Tianjin, China) | Wang, Quanguo (Petrochina DaGang Oilfield Company, Tianjin, China) | Ren, Ruichuan (Petrochina DaGang Oilfield Company, Tianjin, China) | Cuo, Guan (State Key Laboratory of Petroleum Resources and Prospecting, China Petroleum University, Beijing, China)
In this paper, the flow field distribution of reservoir was calculated by commercial numerical simulation software, and the concept of streamline cluster was proposed. By extracting the spatial coordinates and attribute parameters of streamline particles, the vector flow field characterization parameters of streamline cluster potential, streamline cluster flow rate and oil content of streamline cluster are formed respectively. The Lorentz curve is introduced to evaluate the seepage velocity of the grid and to form a characterization method of reservoir flow heterogeneity. Based on the idea of balanced seepage field, the reconstruction methods of "building flow field", "planting flow field", "compensating flow field", "transferring flow field", "steadying flow field" and "controlling flow field" are established for different seepage field characteristic regions, and it is proved by an example. The results show that the property of streamline cluster between injection and production wells can effectively measure the horizontal and vertical development potential and displacement intensity of the reservoir, and the flow heterogeneity coefficient represents the fluid distribution difference in different development stages of the reservoir. The vector flow field characterization method is applied to a block in GD oilfield and its development status is evaluated. The vector reconstruction method established in this study is adopted to adjust the characteristics of different flow field regions. After the implementation of the adjustment scheme, the injection-production correspondence rate increased from 78.6% to 92.4%, the water drive control degree increased from 69.2% to 89.7%, and the EOR increased by 5.16%. The effect was obviously improved.
Technology Focus The bulk of the literature on enhanced oil recovery (EOR) from the past year has been devoted to an improved understanding of trends started more than a decade ago with physical and numerical modeling. A quick review of the basics will be helpful for putting these developments in perspective. The concept of displacement in an EOR method requires bringing the mobility ratio of displacing fluid to that of displaced oil under unity [Kw µ o / Ko µw less than 1; Ko, Kw being relative permeabilities of displaced oil and displacing fluid (e.g., water), respectively, and µ o, µw being their respective viscosities], and increasing sweep efficiency (Es) of the displacement process. Various established EOR methods try to accomplish this in different ways, depending on the formation and oil types, aiming to keep costs and environmental impact down while obtaining high and quick recovery. Thus, polymers or foams have been used traditionally to increase viscosity of displacing fluids (µw). To reduce Kw/Ko, surfactant; alkaline; microbes, which create in-situ surfactants; or low-salinity water, which changes wettability to water, were used. Steam or hot water have also been used to reduce both Kw and µo. Miscible gas or solvent displacements were used to attack µo. Quite frequently, a combination of these mechanisms has been applied, alkaline/surfactant/ polymer being a good example. Similarly, to address improvement in sweep, blocking agents such as polymers, microgels, or microbes, or a combination of a couple of these mechanisms, have been applied. While the underlying mechanisms remain the same, major developments in EOR in recent years center on the use of engineered water or nanoparticles to reduce Kw, on the experimental development of chemicals that are less susceptible to high-temperature and high-salinity environments, or on the use of novel computational techniques and machine learning to design and monitor the flood operations better. The literature of the last year is an important reflection of that evolution, as the selected papers reflect. Recommended additional reading at OnePetro: www.onepetro.org. SPE 195553 Investigation of Pore-Scale Mechanisms of Microbial Enhanced Oil Recovery Using Microfluidics by Calvin Gaol, Clausthal University of Technology, et al. SPE 192110 Polymers and Their Limits in Temperature, Salinity, and Hardness: Theory and Practice by Eric Delamaide, IFP Technologies Canada, et al. SPE 192651 Performance Evaluation and Field Trial of Self-Adaptive Microgel Flooding Technology by Zhe Sun, China National Offshore Oil Corporation, et al.