Modeling the air permeability of pile loop knit fabrics using fuzzy logic and artificial neural network

Pile loop knit fabrics have attracted attention in biomedical applications particularly due to their unique porous three-dimensional structures. Since there is a close relationship between pore characteristics and air permeability of a textile structure, the control of air permeability property during production would improve production planning when designing new knitted fabrics. This study deals with the development of an Artificial Neural Network (ANN) model, and a Fuzzy Logic (FL) model for predicting the air permeability of pile loop knit fabrics. For this aim, pile loop knit structures with different areal densities were produced by using textured polyethylene terephthalate (PET) yarns from four different filament fineness. Multiple linear regression (MLR), FL, and ANN model analyses were done. The root mean square error of the MLR, FL, and ANN were found to be 14.934, 12.41, and 2.418, respectively. Thus, the ANN model provided superior performance over the MLR and FL model in predicting air permeability.

Automated summary

Pile loop knit fabrics with unique porous three-dimensional structures have gained attention in biomedical applications. In this study, an Artificial Neural Network (ANN) model and a Fuzzy Logic (FL) model were developed to predict the air permeability of pile loop knit fabrics. Experimental results showed that the ANN model outperformed the Multiple Linear Regression (MLR) and FL models in predicting air permeability.