For stress-sensitive reservoirs, understanding the characteristics of the inflow performance relationship is vital for evaluating the performance of a well and designing an optimal stimulation. In this study, a reservoir simulator was used to establish the inflow performance relationship of a well for a wide variety of reservoirs and wellbore conditions. First, a base case was simulated using typical reservoir, wellbore, and fluid parameters. Subsequently, variations from the base case were investigated. The results of the simulation indicate that the dimensionless inflow performance relationship in the stress-sensitive reservoir is similar to the Vogel-type inflow performance relationship, which is used for evaluating the productivity of a vertical well in a solution-gas-drive reservoir. Unlike the two-phase flow in a solution-gas-drive reservoir, the nonlinear characteristic of the inflow performance relationship in stress-sensitive reservoirs is caused by stress-dependent permeability. Furthermore, the stress sensitivity level is the only parameter that affects the nonlinearity coefficient of the dimensionless inflow performance relationship equation. The nonlinearity coefficient was plotted against the stress sensitivity index, and the nonlinearity coefficient was found to be linearly proportional to the stress sensitivity index. This study provides a realistic and less expensive methodology to evaluate the reservoir productivity of stress-sensitive reservoirs when the reservoir stress sensitivity level is known and to predict the reservoir stress sensitivity level when the inflow performance relationship of the stress-sensitive reservoirs is known.

In the design of oilfield development plans, specific productivity index plays a vital role. Especially for offshore oilfields, affected by development costs and time limits, there are shortcomings of shorter test time and fewer test sampling points. Therefore, it is very necessary to predict specific productivity index. In this study, a prediction model of the specific productivity index is established by combining the principle of least squares support vector machine (LS-SVM) with the calculation method of the specific productivity index. The model uses logging parameters, crude oil experimental parameters and the specific productivity index of a large number of test well samples as input and output items respectively, and finally predicts the specific productivity index of non-test wells. It reduces the errors caused by short training time, randomness of training results and insufficient learning. A large number of sample data from the Huanghekou Sag in Bohai Oilfield were used to verify the prediction model. Comparing the specific productivity index prediction results of LS-SVM and artificial neural networks (ANNs) with actual well data respectively, the LS-SVM model has a better fitting effect, with an error of only 3.2%, which is 12.1% lower than ANNs. This study can better reflect the impact of different factors on specific productivity index, and it has important guiding significance for the evaluation of offshore oilfield productivity.