AUTHOR=Xu Hao , Xu Ji-Wei , Yi Long-Xiang , Yuan Yu-Ting , Cai Zheng-Qun 

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

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2023.1109371

DOI=10.3389/fncom.2023.1109371

ISSN=1662-5188

ABSTRACT=Meltblown nonwoven materials have been widely concerned by domestic and foreign enterprises because of their excellent filtration performance. The performance research of intercalation meltblown preparation process is complex, and it is also a research hotspot in the field of chemical production. Based on the data related to intercalated and unintercalated meltblown materials under given process conditions, the product performance prediction model of intercalated meltblown materials under different process parameters (receiving distance, hot air velocity) is established. Firstly, the structural variables (thickness, porosity, compressive resilience), the change law of product performance and the relationship between structural variables and product performance (filtration resistance, filtration efficiency, air permeability) after intercalation were studied. Secondly, the receiving distance and hot air velocity were taken as the independent variables, multiple regression analysis was used to analyze the structural variables, and R2, MSE, SSR and SST were used to evaluate the regression results. Then, on the basis of this experiment, a BP neural network prediction model for product performance is established. Finally, the BP neural network model is used to solve the maximum filtration efficiency, which provides theoretical support for regulating product performance.