Neural Model of the Permeability Features of Woven Fabrics

摘要

A method of modeling woven fabric permeability features by means of neural nets is presented. The experiment is based on a steady-system design. A formal dependence is found, describing the relationship of the integral of a function that is a real pressure impulse formed on the woven fabric under impact air flow conditions, with its apparent density, warp twist, and weft twist. The model is assessed by verifying the structure of the neural net.