Prediction of Yarn Properties Using Evaluation Programing

Abstract

This article proposes prediction approaches for the determination of the breaking strength of the yarn properties by using evaluation programing. Gene expression programing (GEP) and neural networks are the evaluation programings that are used for the prediction of physical properties of yarn. In addition to these methods, multiple linear regression analysis is also used to examine the predictive power of the evaluation programings in comparison to classical statistical approach. The implementation of the genetic programing technique in GEP to the prediction of physical properties of yarn is indicated for the first time in this paper. The results obtained from the computational tests clearly show that GEP is a promising technique in terms of precision and computation time for the prediction of yarn properties (98.88 %).

Artificial Neural Network Prosperities in Textile Applications

“…The statistical method showed very much worse performance than genetic and neural network since physical properties of yarn depends on many various factors and the relations between these factors are highly nonlinear and complex. Performance of genetic model (98.88%) was better than artificial neural network (94.00%) in his research (Dayik, 2009). The effects of splicing parameters, fiber and yarn properties on the tenacity and elongation of spliced yarns were investigated by Unal et al, 2010 using artificial neural network (ANN) and response surface model (RSM).…”

“…It takes a long time for the yarn producer to get the experimental results for the physical properties of yarn. Therefore, faster determination of yarn physical properties is needed (Dayik, 2009). Generally, modeling and prediction of yarn properties based on fiber properties and process parameters have been considered by many researchers such as mechanistic models, statistical regression models (Gharehaghaji et al, 2007).…”

“…The difference between the MSE value of two models for predicting breaking elongation and breaking strength of testing data were 0.119 and 0.365 respectively (Gharehaghaji et al, 2007). Dayik, 2009 determined the breaking strength of 100% cotton yarn properties by using Gene expression programming, neural network and classical statistical approach (multiple regression algorithms) and compared the predictive power of them by correlation coefficient (R-square) and mean square error (MSE). The inputs were included foreign matter, micronaire, uniformity, elongation, strength of fiber, length of fiber, short fiber index and neps which were collected for a three month period data.…”

Processing parameters optimization of draw frame for rotor spun yarn strength using gene expression programming (GEP)

“…Un-like the ANN method, GEP is not a black box and explores the inter-relationship between input and output variables. This approach is better than ANN in term of precision [18].…”

Artificial Neural Networks and Their Applications in the Engineering of Fabrics

“…The spinning process and its role on the prediction of the cotton-polyester yarn properties were examined using ANNs (Lu et al, 2007;JackowskaStrumiłło et al, 2008). The effect of the fibres properties on the yarn characteristics is a topic of great interest for many researchers, with different points of view or dealing with specific fibres or spinning method cases (Dayik, 2009;Jayadeva et al, 2003;Majunmdar et al, 2006). A method based on a combination of Genetic Algorithms and Neural Networks has been used for the prediction and optimization of the yarns properties (Subramanian et al, 2007).…”