Sparrow search algorithm optimized material pressure filtration process simulation model

For attaining a higher material pressure filtration efficiency and an improved dewatering result and obtaining optimum filtration process control parameters, it is required to develop a high-precision material filtration process model. Based on analysis of the special features of the support vector machine (SVM) and support vector regression (SVR), the SVR simulation model and the SSA-optimized SVR (SSA-SVR) simulation model are constructed respectively. Then, analysis is made of the model-simulated results based on mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), average percentage error (MAPE) and coefficient of determination (R²). As evidenced by experimental study, the SVR-model has a high accuracy in simulation of the industrial filter press as viewed from the data respect while the use of the SSA-optimized SVR-model can produce a relatively better result both in accuracy and veracity. With the use of the latter model, the control parameters of the pressure filtration system can get accurately optimized and rationally controlled.