Radial Basis Function Neural Network and Response Surface Methodology-Based Optimization of Glue Breakage in Waste Drilling Fluids

This paper aims to solve the problems of difficult breakage and low water yield of wastewater-based drilling fluids. The effects of breakage agent dosage, reaction temperature, stirring speed, and pumping time on the water yield of wastewater-based drilling fluids were analyzed through one-way experiments, and these parameters were optimized by Response Surface Methodology (RSM). A Radial Basis Function Neural Network (RBF) model was also introduced to compare its performance with that of RSM in predicting optimal process conditions. To further improve the accuracy of the model, a combination of Genetic Algorithm (GA) and RBF was used for optimization. The results show that both RSM and RBF models can predict the water yield of wastewater-based drilling fluids with high accuracy, in which the coefficient of determination of the RSM model is 0.9939, which is better than that of the RBF model (0.9778). The optimal operating conditions are determined through numerical optimization: the amount of glue breaker added is 3.97 kg/m3, the reaction temperature is 51 °C, the stirring speed is 419 rpm, and the maximum water yield is 62.37%, which is the best-predicted water yield. The GA-RBF coupled model performed better in terms of root mean square error (RMSE), coefficient of determination (R2 = 0.998), and mean absolute error (MAE), and the t-test verified that there was no significant difference between the predicted and actual values. The maximum value of the water yield of the waste mud could reach 61.97% when the gum breaker was added at 3.83 kg/m3, the reaction temperature was 53 °C, and the stirring speed was 424 rpm, which provided an accurate and reliable theoretical basis and technical support for the harmless treatment of deep and complex drilling fluids.