In this work, polyvinyl alcohol/nylon6 hybrid nanofiber yarns were produced to achieve good properties of each component. The influence of the twist level in the range of 3000–14,666 tpm and take-up speed in the range of 2.5–8.5 cm/min of yarns on the tensile properties was investigated. The highest strength and elongation at break of yarns were achieved in twist level and take-up speed of about 11,000 tpm (8.13±0.72 cN/tex and 72.44±7.64%) and 6.5 cm/min (6.20±0.57 cN/tex and 70.23±7.95%), respectively. Excessive values over these amounts caused a drastic decrement in tensile properties. This could be due to the loss nanofiber arrangement in the yarn structure that was confirmed by the study of orientation of the nanofibers in the yarns by the SEM images. These yarns have the potential to be used in medical applications such as a non-absorbable suture due to the drug loading ability and bio-compatibility properties of PVA nanofibers.
Exploring relationships between characteristics of a yarn and influencing factors is momentous subject to optimize the selection of the variables. Different modelling methodologies have been used to predict spun yarn properties. Developing a prediction approach with higher degree of precision is a subject that has received attention by the researchers. In the last decade, Artificial Neural Network (ANN) has been developed successfully for textile nonlinear processes. In spite of the precision, ANN is a black box and does not indicate inter-relationship between input and output parameters. Hence, Gene Expression Programming (GEP) is presented here as an intelligent algorithm to predict breaking strength of rotor spun yarns based on draw frame parameters as one of the most important stages in spinning line. Forty eight samples were produced and different models were evaluated. Prediction performance of the GEP was compared with that of ANN using Mean Square Error (MSE) and correlation coefficient (R2-Value) parameters on test data. The results showed a better capability of the GEP model in comparison to the ANN model. The R2-value and MSE were 97% and 0.071 respectively which means desirable predictive power of GEP algorithm. Finally, an equation was extracted to predict breaking strength of the yarns with a high degree of accuracy using GEP algorithm.
This study compares capabilities of two different modelling methodologies for predicting breaking strength of rotor spun yarns. Forty eight yarn samples were produced considering variations in three drawing frame parameters namely break draft, delivery speed, and distance between back and middle rolls. Several topologies with different architectures were trained to get the best adaptive neuro-fuzzy inference system (ANFIS) and gene expression programming (GEP) models. Prediction performance of the GEP model was compared with that of ANFIS using root mean square error (RMSE) and correlation coefficient (R2-Value) parameters on the test data. Results show that, the GEP model has a significant priority over the ANFIS model in term of prediction accuracy. The correlation coefficient (R2-value) and root mean square error for the GEP model were 0.87 and 0.35 respectively, while these parameters were 0.48 and 0.53 for the ANFIS model. Also, a mathematical formula was developed with high degree of accuracy using GEP algorithm to predict the breaking strength of the yarns. This advantage is not accessible in the ANFIS model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.