Study the Effect of Fabrics’ Parameters on Particles Filtration Efficiency of Cloth Mask Using Artificial Neural Network

Exposure to air pollutants has diverse health impacts on humans, particularly through inhalation, commonly encountered in workplaces. Respiratory masks are employed, to control respiratory aerosols, and offer some wearer protection, especially in the absence of adequate control measures. Evaluation of masks typically involves metrics like filtration efficiency, airflow resistance, and fit factors, yet these do not directly measure how effectively masks block coughed and exhaled aerosols. This study aims to identify criteria for selecting face masks. Using an artificial neural network (A.N.N.) system, the effects of fabric parameters and air permeability on the filtration efficiency of 3 µm particles by cloth masks were investigated. 70 cloth masks were analyzed, revealing the influence of parameters like surface wetting on filtration efficiency. This suggests the A.N.N. could aid the textile industry in understanding the nonlinear relationship between fabric parameters and mask filtration performance, ultimately enhancing protection against airborne pathogens and pollutants.