• Energy Research

Accurately predicting oilfield development indicators (such as oil production, liquid production, current formation pressure, water cut, oil production rate, recovery rate, cost, profit, etc.) is to realize the rational and scientific development of oilfields, which is an important basis to ensure the stable production of the oilfield. Due to existing oilfield development index prediction methods being difficult to accurately reflect the complex nonlinear problem in the oil field development process, using the artificial neural network, which can predict the oilfield development index with the function of infinitely close to any non-linear function, will be the most ideal prediction method at present. This article summarizes four commonly used artificial neural networks: the BP neural network, the radial basis neural network, the generalized regression neural network, and the wavelet neural network, and mainly introduces their network structure, function types, calculation process and prediction results. Four kinds of artificial neural networks are optimized through various intelligent algorithms, and the principle and essence of optimization are analyzed. Furthermore, the advantages and disadvantages of the four artificial neural networks are summarized and compared. Finally, based on the application of artificial neural networks in other fields and on existing problems, a future development direction is proposed which can serve as a reference and guide for the research on accurate prediction of oilfield development indicators.

Heat-injection production is a common technique for gas-hydrate development, and the mechanism needs further in-depth study, particularly of the decomposition characteristics of natural-gas hydrate, which are important fundamental issues. The natural gas-hydrate-reservoir model is based on a mathematical description of reservoir properties that considers the effects of hydrate decomposition and reservoir stress conditions. The aim of our investigation was to analyze the production and decomposition characteristics of natural-gas hydrates based on the results of numerical simulations of heat-injection production. The effects of different heat-injection temperatures and heat-injection rates on production were compared, and the decomposition characteristics of hydrates were evaluated qualitatively and characterized quantitatively by temperature distribution, saturation distribution, and the decomposition front in the process of heat-injection production of natural-gas hydrate. The results showed that, with the increase in the heat-injection temperature, the decomposition front moved faster, the area share of decomposition zone increased, but the increase extent decreased. The high heat-injection rate had a more significant effect than the heat-injection temperature in promoting the decomposition of natural-gas hydrate.

With the rapid growth of energy consumption, enhanced oil recovery (EOR) methods are continually emerging, the most effective and widely used was polymer flooding. However, the shortcomings were gradually exposed. A novel decorated polyacrylamide might be a better alternative than polymer. In this work, the molecular structure and the properties reflecting the viscosity of decorated polyacrylamide, interfacial tension, and emulsification were examined. In order to better understand the interactions between decorated polyacrylamide and oil as well as the displacement mechanism, the displacement experiment were conducted in the etched-glass microscale model. Moreover, the coreflooding comparison experiments between decorated polyacrylamide and polymer were performed to investigate the displacement effect. The statistical analysis showed that the decorated polyacrylamide has excellent characteristics of salt tolerance, viscosity stability, and viscosification like polymer. Besides, the ability to reduce the interfacial tension in order 10−1 and emulsification, which were more similar to surfactant. Therefore, the decorated polyacrylamide was a multifunctional polymer. The displacement process captured by camera illustrated that the decorated polyacrylamide flooded oil mainly by means of ‘pull and drag’, ‘entrainment’, and ‘bridging’, based on the mechanism of viscosifying, emulsifying, and viscoelasticity. The results of the coreflooding experiment indicated that the recovery of decorated polyacrylamide can be improved by approximately 11–16% after water flooding when the concentration was more than 800 mg/L, which was higher than that of conventional polymer flooding. It should be mentioned that a new injection mode of ‘concentration reduction multi-slug’ was first proposed, and it obtained an exciting result of increasing oil production and decreasing water-cut, the effect of conformance control was more significant.