Optimization of Fracturing Parameters by Modified Genetic Algorithm in Shale Gas Reservoir

Shale gas reservoirs have extremely low porosity and permeability, making them challenging to exploit. The best method for increasing recovery in shale is horizontal well fracturing technology. Hence, parameter optimization necessary enhance production. Traditional methods, however, cannot meet the requirements overall of parameters. As intelligent algorithms, most excellent global search capability but incur high computation costs, which limits their usefulness real-world engineering applications. Thus, a modified genetic algorithm combined based on Spearman correlation coefficient (SGA) proposed achieve rapid SGA determines crossover mutation rates by calculating instead randomly determining like GA does, so that it could quickly converge optimal solution. Within particular time, perform better than GA. In this study, production prediction model established XGBoost dataset obtained simulating multistage development. result shows performs predicting Based trained model, GA, SGA, SGD were used optimize parameters with 30-day cumulative as objective. This process has conducted nine tests under different permeability conditions. results show that, compared SGD, faster speed higher accuracy. study’s findings can help faster, resulting improving wells.