Tuba Alpyildiz

This study aims to investigate the impact performances of the monoaxial knitted fabric composites to evaluate the effect of straight yarns within the reinforcement knitted fabric. Monoaxial knitted fabric composites have enhanced in-plane properties and it is important to evaluate the effect of yarn insertion on the impact performances because knitted fabric composites are preferred due to their out-of-plane properties. Bending, impact and compression after impact (CAI) tests were performed on the composites reinforced with monoaxial rib knitted fabrics. The flexural properties, the peak force, the damage area and the energy absorption capabilities under drop weight impact loadings and the compression strength after impact of the composites were evaluated comparatively. The results indicated that the monoaxial rib knitted fabric reinforcement enhances the bending and CAI performances of the composites, but it causes detrimental effects on the impact performances of the composites. The use of yarn insertion for the enhancement of the composite performance necessitates considerate planning for an optimization between the in-plane and out-of-plane properties of the knitted fabric composites.

Data mining has been proven useful for knowledge discovery in many areas, ranging from marketing to medical and from banking to education. This study focuses on data mining and machine learning in textile industry as applying them to textile data is considered an emerging interdisciplinary research field. Thus, data mining studies, including classification and clustering techniques and machine learning algorithms, implemented in textile industry were presented and explained in detail in this study to provide an overview of how clustering and classification techniques can be applied in the textile industry to deal with different problems where traditional methods are not useful. This article clearly shows that a classification technique has higher interest than a clustering technique in the textile industry. It also shows that the most commonly applied classification methods are artificial neural networks and support vector machines, and they generally provide high accuracy rates in the textile applications. For the clustering task of data mining, a K‐means algorithm was generally implemented in textile studies among the others that were investigated in this article. We conclude with some remarks on the strength of the data mining techniques for textile industry, ways to overcome certain challenges, and offer some possible further research directions. WIREs Data Mining Knowl Discov 2018, 8:e1228. doi: 10.1002/widm.1228This article is categorized under: Application Areas > Business and Industry Application Areas > Industry Specific Applications Application Areas > Science and Technology

Neural network technique has been recently preferred in textile sector for the prediction task because the traditional mathematical and statistical methods can be inadequate to derive complex relations within textile datasets. Meanwhile ensemble learning has become a popular machine learning approach in recent years due to the high prediction performance it provides. Therefore, this study proposes an ensemble learning approach that combines neural networks with different parameter values (the number of hidden layers, learning rate and momentum coefficient) to improve prediction performance in textile sector. In the experimental studies, the proposed model was tested on ten different real-world textile datasets. The results show that ensemble neural networks usually achieve better prediction performance than an individual neural network in terms of correlation coefficient and relative absolute error measures.

The objective of this study is to enhance the out-of-plane tensile and compressive performances of foam core sandwich composite via structural core modifications considering the ease of application and time consumption. The performances of single core perforated, single core stitched, divided core perforated, and divided core stitched sandwich composites are compared with each other and reference plain foam core sandwich composites. Results indicate that “perforated and stitched core” sandwich composites have superior strength, and in terms of performance modification, dividing the core is found very efficient for plain (non-perforated and non-stitched) core sandwich composites.

The electromagnetic shielding effectiveness (SE) of various weft-knitted fabrics made of hybrid yarns is investigated by considering the anisotropy of the structures, which has not been analyzed in previous studies. The anechoic chamber with aperture method at different polarizations of electromagnetic waves within the frequency range of 30 MHz and 9.93 GHz is used to determine the SE of knitted fabrics manufactured on a circular weft knitting machine from siro-spun and siro core-spun yarns without and with a metal core. The results show that SE depends on the orientation of the fibers within the structure regarding the direction of the electrical field in addition to parameters such as metal content, loop length and frequency; these results can be used to outline the basic points in determining a knit structure with desired SE.

Geometrical modelling for tubular braids of different structures is studied and a simple versatile three-dimensional model is proposed after considering the crimp of the braiding yarn together with the tubular curvature of the tubular braid structure. The proposed model is versatile and suitable not only for different braid structures, but also, with the changes in the structural parameters such as braid angle, number of yarns in a set, yarn and mandrel diameter the model is still applicable. Application and 3D drawings of the model for diamond, regular and triaxial braids are given with the aid of Visual Basic and 3DSMax Studio.

A new double-face knitted structure has been developed which is composed of tuck stitches and has the same back and front faces. The newly derived structure, manufactured from p-aramid fibers with and without inlay yarns, has been compared with jersey and plush structures of these same fibers in terms of cut and stab performances. Not only have new structures been proposed, but the effect of the inlay yarns has been investigated also. In order to manufacture the plush structure on a V-bed Flat Knitting Machine instead of a traditional circular knitting machine a new design has been developed. The results show that the newly derived structure with inlay yarns has the best cut and stab performances when a comparison is made between samples of different structures with the same mass per unit area and thickness values.