Artificial neural network-based prediction of aesthetic and functional properties of worsted suiting fabrics

Purpose - The purpose of this paper is to investigate an alternative approach that can predict non-linear relations. Design/methodology/approach - An engineered approach to fabric development is described in which a radial basis function network is trained with worsted fabric constructional parameters to predict functional and aesthetic properties of fabrics. An objective method of fabric appearance evaluation with the help of digital image processing is introduced. The prediction of fabric properties by the network with changing basic fibre characteristics and fabric constructional parameters is found to have good correlation with the experimental values of fabric functional and aesthetic properties. Findings - The radial basis function network can successfully predict the fabric functional and aesthetic properties from basic fibre characteristics and fabric constructional parameters with considerable accuracy. The network prediction is in good correlation with the actual experimental data. There is some error in predicting the fabric proper-ties from the constructional parameters. The variation in the actual values and predicted values is because of small sample size. Moreover, the properties of worsted fabrics are greatly influenced by the finishing parameters which are not taken into consideration in the training of the network. Prediction performance can be further improved by including these parameters as input, during the training phase. In few cases, the network has predicted contradictory trends, which are found difficult to be explained. Originality/value - The paper describes a radial basis function neural network model that can be used for the prediction of the fabric appearance values and comfort properties using fabric constructional parameters and some primary fibre mechanical properties as input parameters of the network.