Search

Sand production and sand control studies in non-diagenetic reservoirs are the weak point in the conventional petroleum industry. However, natural gas hydrate (NGH) mainly exists in non-diagenetic strata, and sand production occurs during exploitation, which restricts the safe and sustainable production of NGH. To study the microcosmic characteristics of sand production, the hydrate decomposition behaviours in the sediments were captured by the Cryo-SEM method. The micromorphology of different particle sizes of sand samples containing NGH (the sand median diameter d50 is 150, 87, 55, 38, 24, and 13 µm) and the microcosmic processes of NGH decomposition were observed. Then, the microcosmic characteristics of sand production, during the decomposition process, were analysed. (1) The gas hydrate decomposition increases pore space and reduces reservoir strength; the expansion action of the decomposition of water and gas, the softening action of the decomposition of water, and the compression action by overlying stress (crustal stress) promoted sand production, deformation, and subsidence of the NGH reservoirs in the mining process. (2) The decomposition of NGH has a more significant impact on sediments with smaller particle sizes. (3) The particle size of NGH may be larger than the particle size of the mud in the reservoirs, and acting as “gravel” plays a particular role in sand control. Therefore, the particle size of NGH cannot be ignored in the design of sand control. (4) It has been revealed, and verified, that sputtering (splashing) is a unique process of sand production caused by NGH decomposition. In other words, the rapid expansion of the volume of the decomposed gas and water from NGH leads to the eruption and sputtering of hydrate particles, providing the driving force for sand migration, which is a different process of sand production than in conventional oil and gas.

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.