Modeling and optimization for curing of polymer flooding using an artificial neural network and a genetic algorithm

An artificial neural network model was adopted to investigate the relationships between polymer curing process parameters (polymer concentration, agitation speed, and paddle type) and viscosity and curing time. The adequacy of established mathematical models was checked by analysis of variance (ANOVA). The interaction effects of process parameters on the mixing performance were investigated. The desirability function integrated with genetic algorithm was used to determine the optimum conditions of maximum viscosity and minimum curing time. The polymer concentration of 3798 mg/L, the double helical ribbon-screw impeller I, and the agitation speed of 115r/min were optimal for the polymer curing process. The results showed that the optimal results predicted by the genetic algorithm were in good agreement with the experimental results, so this study provided an effective method to enhance the curing process of polymer flooding.