A Soft Computing Model for Predicting Yarn Tenacity

A soft computing model for predicting yarn tenacity from fiber properties and yarn parameters is developed. Because the number of samples is limited, the artificial neural network to be established must be a small-scale one. This soft computing model includes two stages. Firstly, the fiber properties and yarn parameters were selected by utilizing a ranking method for identifying the most relevant fiber properties and yarn parameters as the input variables to fit the small-scale artificial neural network model. The first part of this method takes human knowledge of yarn tenacity into account. The second part utilizes a data sensitivity criterion based on a distance method. Secondly, the artificial neural network model of the relationship between fiber properties, yarn parameters and yarn tenacity is established. The results show that the artificial neural network model yields an accurate prediction, and a reasonably effective artificial neural network model can be achieved with relatively few data points integrated with the input variable selecting method developed in this research. The results also show that there is great potential for this research in the field of computer-assisted design in spinning technology.