Comparison of artificial intelligence methods for predicting tensile properties of multifilament polyester woven fabrics

The filament fineness, weave type and weave density have a great influence on the mechanical properties of multifilament woven fabrics. In this study, the previously determined breaking strength and breaking elongation values of multifilament woven fabrics were estimated using Artificial Neural Networks (ANN), Fuzzy Logic (FL), and Genetic Algorithms (GA) Artificial Intelligence (AI) techniques. The fabric samples used in the study have three different microfilament fineness and two different conventional filament fineness. Fabric samples with plain, twill and satin weave types were produced with four different weft setts. High accuracy rates were obtained with applied AI techniques. The mean absolute percentage error was lower than 6%. The minimum regression coefficient values (R^2) of linear regression analysis for each method were 0.80, 0.90 and 0.92 by ANN, BM and ANN-GA hybrid methods, respectively. As a conclusion, it was proved that the breaking strength and breaking elongation properties of multifilament woven fabrics can be estimated with high success rates.