Mathematical model for relationship between grafting ratio and variation of air permeability of linen fabric

Modification of linen fabric is performed via UV initiated photografting of acrylic acid.BP neural network and least squares regression modeling methods are used to predict the relationship between grafting ratio and air permeability under different conditions such as photografting time,photoinitiator amount and concentration of acrylic acid.A three-layer BP network model with architecture of 1-10-1 is established after extensive discussion,including one node in one input layer representing the grafting ratio,one node in one output layer representing the variation of air permeability,and ten nodes in one hidden layer.The activation function of sigmoid is selected.The optimum parameters,training step of 100 and training goal of 0.001,are determined.The BP neural network model has higher correlation coefficient between simulated output and targeted output and lower percentage error than least squares regression model.BP neural network as such has higher simulation precision,and provides an effective predictive model for the relationship between graft ratio and air permeability.