Optimization of engineering parameters of deflagration fracturing in shale reservoirs based on hybrid proxy model

Abstract

Engineering parameter optimization of deflagration fracturing in shale reservoirs is operated with single factor analysis and orthogonal experimental design analysis. There are problems of the difficulty to search the global optimal solution, time-consuming optimization and low computation efficiency. To resolve these problems, a method of optimizing engineering parameters of deflagration fracturing based on the hybrid proxy model was proposed in this paper. The parameters with significant effects on deflagration fracturing were selected as variables, and the models for prediction of reservoir burst degree and stimulated area were established based on Radial Basis Function model, Kriging interpolation model and eXtreme Gradient Boosting regression model respectively. A hybrid proxy model based on the roulette method was established by integrating the priorities of these three models. Then, a multi-objective optimization method of deflagration fracturing based on the hybrid proxy model and was established by integrating the Nondominated Sorting Genetic algorithm II with the engineering parameters as variables and the maximum stimulated area and minimum burst degree as objectives. Optimal design of the deflagration fracturing scheme was achieved. The results show that the hybrid proxy model can accurately predict the evaluation index of the fracturing results in vertical and horizontal wells, and the prediction accuracy is maintained at about 0.9. At the same time, compared with numerical model, the proposed method greatly saves the calculation time. The method proposed by this paper provides the solution to the problem of multi-objective optimization of deflagration fracturing engineering parameters, weighs the reservoir failure degree and the stimulation range, and provides guidance for field operation.