Romashkino oil field has large oilfield area, small formation dip, many reservoir layers, wide oil-water transition zone and complicated sedimentary environment. Since development, 3 overall development plannings and ...Romashkino oil field has large oilfield area, small formation dip, many reservoir layers, wide oil-water transition zone and complicated sedimentary environment. Since development, 3 overall development plannings and adjustments of individual block have been established. This achieves a high oil production. However, the recoverable reserves of major oil layer with high production become smaller and smaller and the water cut increases over time, the production ability of oil layer decreases. The development status of oil layer of mining siltstone, oil-water transition zone and oil layer with upswept injected water cannot be changed under present dilute well network condition, because there is no reinforced measurement to water well. This results the low oil production of Romashkino oil field. In order to improve oil production rate and reach the designed oil recovery, Romashkino oil field has been implemented many added cuttings since development. Resent researches about Romashkino oil field show: in later oilfield development stage, sidetrack and lateral drilling horizontal wells technology is very reasonable;formation hydraulic fracturing technology has been widely used in recent years;in tertiary oil recovery, sweep efficiency and flooding efficiency related technologies have been taken. This offers reference and guidance for the effective and reasonable oil field development in later period.展开更多
Feasibility of oil production predicting results influences the annual planning and long-term field development plan of oil field, so the selection of predicting models plays a core role. In this paper, three differen...Feasibility of oil production predicting results influences the annual planning and long-term field development plan of oil field, so the selection of predicting models plays a core role. In this paper, three different predicting models are introduced, they are neural network model, support vector machine model and GM (1, 1) model. By using these three different models to predict the oil production in XINJIANG oilfield in China, advantages and disadvantages of these models have been discussed. The predicting results show: the fitting accuracy by the neural network model or by the support vector machine model is higher than GM (1, 1) model, the prediction error is smaller than 10%, so neural network model and support vector machine model can be used to short-term forecast of oil production;predicting accuracy by GM (1, 1) model is not good, but the curve trend with GM (1, 1) model is consistent with the downward trend in oil production, so GM (1, 1) predicting model can be used to long-term prediction of oil production.展开更多
文摘Romashkino oil field has large oilfield area, small formation dip, many reservoir layers, wide oil-water transition zone and complicated sedimentary environment. Since development, 3 overall development plannings and adjustments of individual block have been established. This achieves a high oil production. However, the recoverable reserves of major oil layer with high production become smaller and smaller and the water cut increases over time, the production ability of oil layer decreases. The development status of oil layer of mining siltstone, oil-water transition zone and oil layer with upswept injected water cannot be changed under present dilute well network condition, because there is no reinforced measurement to water well. This results the low oil production of Romashkino oil field. In order to improve oil production rate and reach the designed oil recovery, Romashkino oil field has been implemented many added cuttings since development. Resent researches about Romashkino oil field show: in later oilfield development stage, sidetrack and lateral drilling horizontal wells technology is very reasonable;formation hydraulic fracturing technology has been widely used in recent years;in tertiary oil recovery, sweep efficiency and flooding efficiency related technologies have been taken. This offers reference and guidance for the effective and reasonable oil field development in later period.
文摘Feasibility of oil production predicting results influences the annual planning and long-term field development plan of oil field, so the selection of predicting models plays a core role. In this paper, three different predicting models are introduced, they are neural network model, support vector machine model and GM (1, 1) model. By using these three different models to predict the oil production in XINJIANG oilfield in China, advantages and disadvantages of these models have been discussed. The predicting results show: the fitting accuracy by the neural network model or by the support vector machine model is higher than GM (1, 1) model, the prediction error is smaller than 10%, so neural network model and support vector machine model can be used to short-term forecast of oil production;predicting accuracy by GM (1, 1) model is not good, but the curve trend with GM (1, 1) model is consistent with the downward trend in oil production, so GM (1, 1) predicting model can be used to long-term prediction of oil production.
