Neural model of the spinning process for predicting selected properties of flax/cotton yarn blends

This article describes the design of a yarn spinning model based on the use of artificial neural networks, as well as the measurements aimed at collecting the data necessary for this model. Partial models of the spinning process were designed for selected essential yarn quality parameters, such as tenacity, yarn hairiness, and yarn faults. Feed-forward neural networks were used for modelling. Yarns manufactured from flax/cotton blended slivers and from a pure cotton sliver with the use of a BD 200S rotor-spinning machine were analysed The flax content in the blended slivers was 10, 20, 30, 40, and 50% Yarns of linear density of 20, 30, 40, 50, and 60 rev were manufactured from as silver of linear density of 3 knex.