Predicting bending rigidity of woven fabrics using adaptive neuro-fuzzy inference system (ANFIS)

Predictability of the bending rigidity of cotton plain-woven fabrics from their structural parameters has been investigated using an adaptive neuro-fuzzy inference system (ANFIS) approach. A set of cotton grey fabrics meant for apparel end use was desized, scoured, and relaxed. The fabrics were then conditioned and tested for bending properties. Fabric weight, fabric thickness, and fabric cover constituted the input parameters for the model, whereas overall bending rigidity of the fabric was the single output parameter. Fabric data-set has been modeled using ANFIS and its prediction potential is compared with that of an artificial neural network (ANN) model. A sensitivity analysis was also carried out to investigate the robustness of developed model. Results show that the learning capability of the ANFIS model is superior and its generalization ability is slightly better than that of a standalone ANN model.