A New Productivity Prediction Hybrid Model for Multi-Fractured Horizontal Wells in Tight Oil Reservoirs

Single well productivity is an important index to evaluate the effect of volume fracturing. However, there are many factors affecting the productivity of Multi-fractured horizontal wells (MFHWs) in unconventional reservoirs and the relationship is complex, which makes productivity prediction very difficult. In this paper, taking the tight oil reservoir in Songliao Basin as the research object, a new mixed model of initial cumulative oil production of MFHWs was established, which can consider the geological factors and volume fracturing factors at the same time. Firstly, based on the big data, the multi-level evaluation system was established by using the analytic hierarchy process (AHP). Then, the weight factor was calculated to uncover key factors that dominate productivity of MFHWs. Finally, the fuzzy logic method was used to calculate the Euclidean distance and quantitatively predict the production of any horizontal wells. The simulation results shown that: the order of the main factors affecting production in the study area was horizontal section sandstone length, number of stages, formation pressure, proppant amount, net pay thickness, permeability, porosity, oil saturation, fracturing fluid volume. The hybrid model has been applied to the productivity prediction of 185 MFHWs in tight oil reservoirs in China, the prediction error was less than 5%. The new model can be used to predict production for MFHWs quickly and economically.