Fabric Sewability Prediction with Kernel PCA Based on SFC-RBFNN

Abstract

By extracting five kernel principal components of fabric FAST (Fabric Assurance by Simple Testing) low mechanical data, this paper proposed a supervised fuzzy clustering radial basis function neural network to construct fabric sewability prediction system. Our experimental results demonstrate that the proposed system could efficiently be used as an objective seam pucker evaluation system with high accuracy and is robust for various structures and mechanical properties of middle-thickness woolen fabric.