Modeling and analysis of hydraulic fracture complexity index in sandy conglomerate reservoirs based on genetic expression programming—A case study in Xinjiang Oilfield

Abstract

The stimulation effect of oil wells is seriously affected by the complexity of hydraulic fractures, and the analysis of the factors that control the fracture complexity index has become the key to fracturing design in sandy conglomerate reservoirs. Based on the intrinsic relationship between geological engineering parameters and the fractures complexity index, a Genetic Expression Programming (GEP) method, which has broad advantages in solving multi-factor nonlinear fitting and black-box prediction problems, is proposed to analyze the hydraulic fracture complexity index. Combined with the geoengineering factors that affect the hydraulic fractures propagation, a comprehensive index calculation method is established to analyze the relative importance of these features and 18 reconstructed features were obtained by collecting the geoengineering parameter data of 118 fracturing sections in 8 fracturing wells in Jinlong oilfield. The principal component analysis was performed to eliminate the interaction between the features, and then a GEP-based fractures complexity index calculation model was developed. The partial dependence plot is used to analyze the influence of the main control feature (variable) on the hydraulic fracture complexity index. It showed that GEP model can achieve satisfactory performance (Training set: R = 0.861; Test set: R = 0.817) by statistical parameters. The results showed that the model can calculate the hydraulic fracture complexity index quickly and precisely. The influence of geological engineering control factors can be obtained. It proved that the GEP method can effectively analyze and evaluate the complexity in sandy conglomerate reservoirs.