A fuzzy logic based criterion for selecting relevant process parameters for design of nonwoven products

In this paper, we present a new fuzzy logic based selection criterion which takes into account both the conformity of human knowledge on nonwoven process technology and the sensitivity of measured data to the functional properties. This selection criterion permits to rank all process parameters (input variables) and select the most relevant parameters as input variables of the model for designing nonwovens products. Compared with the other relevant parameter selection criteria, the proposed method is more robust and less sensitive to measuring noises. This method has been validated using mathematical simulation and real data of a textile nonwoven process