Performance control study of interleaved meltblown non-woven materials based on statistical analysis and predictive modeling.

Meltblown nonwoven materials have gained attention due to their excellent filtration performance. The research on the performance of the intercalation meltblown preparation process is complex and a current research focus in the field of chemical production. Based on data related to intercalated and unintercalated meltblown materials under given process conditions, a product performance prediction model of intercalated meltblown materials was established under different process parameters (receiving distance, hot air velocity). The structural variables (thickness, porosity, and compressive resilience), the change in product performance, and the relationship between structural variables and product performance (filtration resistance, efficiency, air permeability) after intercalation were studied. Multiple regression analysis was used to analyze the structural variables, and evaluation of the regression results were made using R2, MSE, SSR, and SST. A BP neural network prediction model for product performance was established. The BP neural network model was used to find the maximum filtration efficiency. The study provides theoretical support for regulating product performance by solving the maximum filtration efficiency using BP neural network model.