Yarn strength modelling and prediction has remained as the cynosure of research for the textile engineers although the investigation in this domain was first reported around one century ago. Several mathematical, statistical and empirical models have been developed in the past only to yield limited success in terms of prediction accuracy and general applicability. In recent years, soft computing tools like artificial neural networks and neural-fuzzy models have been developed, which have shown remarkable prediction accuracy. However, artificial neural network and neural-fuzzy models are trained using enormous amount of noise free input-output data, which are difficult to collect from the spinning industries. In contrast, fuzzy logic based models could be developed by using the experience of the spinner only and it gives good understanding about the roles played by various inputs on the outputs. This paper deals with the modelling of ring spun cotton yarn strength using a simple fuzzy expert system. The prediction accuracy of the model was found to be very encouraging.
The phenomenon of spun yarn failure is strongly dependent on the yarn structure namely, the configuration, alignment and packing of the constituent fibers in the yarn cross-section. The structure of yarn is solely determined by the methods of consolidating the fibers into yarns. In the present study, ring, rotor, air-jet and open-end friction spun yarns were produced from identical fibers and their structural parameters; namely, mean fiber extent, spinning-in-coefficient, helix angle of the fibers, percentage of different hooks and their extents, number of fibers in yarn cross-section and yarn diameter were measured. These yarns were subjected to uniaxial loading on the tensile testers with a large range of gauge lengths (0 to 500 mm) and strain rates (5 to 400 m/min). The results showed that the strength of yarns largely depends on the structure of the yarns, gauge lengths and strain rates. A combined effect of fiber extent in the yarn and gauge length influences the yarn strength. At high strain rates the yarn failure is dominated by the breakage of fibers rather than the slippage of fibers. Furthermore, the analysis of the region of yarn failure provides more direct evidences of the influence of yarn structure and testing parameters on the strength of different spun yarns.OCTOBER 2005 731
Aesthetic properties of fabrics have been considered as the most important fabric attribute for years. However, recently there has been a paradigm shift in the domain of textile material applications and consequently more emphasis is now being given on the mechanical and functional properties of fabrics rather than its aesthetic appeal. Moreover, in certain woven fabrics used for technical applications, strength is a decisive quality parameter. In this work, tensile strength of plain woven fabrics has been predicted by using two empirical modelling methods namely artificial neural network (ANN) and linear regression. Warp yarn strength, warp yarn elongation, ends per inch (EPI), picks per inch (PPI) and weft count (Ne) were used as input parameters. Both the models were able to predict the fabric strength with reasonably good precision although ANN model demonstrated higher prediction accuracy and generalization ability than the regression model. The warp yarn strength and EPI were found to be the two most significant factors influencing fabric strength in warp direction.
Purpose -The purpose of this paper is to address a solution to the problem of defect recognition from images using the support vector machines (SVM). Design/methodology/approach -A SVM-based multi-class pattern recognition system has been developed for inspecting commonly occurring fabric defects such as neps, broken ends, broken picks and oil stain. A one-leave-out cross validation technique is applied to assess the accuracy of the SVM classifier in classifying fabric defects. Findings -The investigation indicates that the fabric defects can be classified with a reasonably high degree of accuracy by the proposed method. Originality/value -The paper outlines the theory and application of SVM classifier with reference to pattern classification problem in textiles. The SVM classifier outperforms the other techniques of machine learning systems such as artificial neural network in terms of efficiency of calculation. Therefore, SVM classifier has great potential for automatic inspection of fabric defects in industry.
This article presents the results from a study of yarn-to-yarn (YY) and yarn-to-metal (YM) frictions conducted on ring, rotor, air-jet, and open-end friction (OE friction) spun yarns at different relative speeds and input tensions. The results indicate that the behavior of frictions for YY is different than that of YM. In case of YY friction, OE friction yarn shows maximum friction followed by rotor, air-jet, and ring spun yarns; however, a reverse order is noticed for YM friction. The relative speed and input tension have significant influence on the frictional behavior of spun yarns.
Ranking and selection of textile fabrics for a particular end-use requirement is a complex task. In this article, an attempt has been made to develop a simple index of handloom fabric quality, which can be used for selecting fabrics for a specified end use. The Analytic Hierarchy Process (AHP) and Multiplicative Analytic Hierarchy Process (MAHP) of multi-criteria decision making (MCDM) have been used for ranking 25 handloom cotton fabrics in terms of their overall quality value considering their applicability as summer clothing materials. The rank correlation between the rankings elicited from two MCDM methods was found to be 0.926 which implies that the rankings given by AHP and MAHP are in high degree of agreement with each other and any of the two methods can be chosen for ranking of fabrics.
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.