Study of the Effect of Rock Type and Treatment Parameter on Acid Fracture Conductivity Using an Intelligent Model

One of the fundamental ways to stimulate and increase the production rate of a well completed in a carbonate reservoir is acid fracturing. The amount of rock dissolved, fracture surface etching patterns, rock strength, and closure stress impacts the conductivity of the resulting acid fracture. A model of acid fracturing conductivity must accurately anticipate fracture conductivity versus closure stress. There are two parts for an acid fracture model: fracture conductivity at zero closure stress and the rate of conductivity change with closure stress. The fracture conductivity is substantially influenced by rock type. A serious challenge in recent studies has been to predict behaviour of different formations under various closure stresses. Furthermore, treatment parameters like acid injection rate and acid strength have different effects on fracture conductivity, depending on formation type. This study develops artificial neural network models to precisely predict fracture conductivity by incorporating experimental data from various formations, thereby resulting in a good match between model predictions and experimental data. The effects of rock type and treatment parameters on fracture conductivity are investigated and show that different formations have different responses under various closure stresses. There is an optimum point at which maximum fracture conductivity is achieved, but finding this point is difficult because it is distinct for different formations.