In a previous paper, a description was given of how the spinnability o
f a given fibre quality on a rotor- or a ring-spinning machine can be
predicted with a reliability of 95% by means of a neural network. This
paper goes further. It describes how yam properties can be deduced fr
om fibre properties and spinning-machine settings. In other words, a d
escription is given of how to construct, train, and use a neural netwo
rk in order to simulate the spinning process (predict yarn properties)
on both rotor- and ring-spinning machines with an accuracy of over 95
%.