The Experts below are selected from a list of 96 Experts worldwide ranked by ideXlab platform

Duru Baykal P. - One of the best experts on this subject based on the ideXlab platform.

  • Comparison of the neural network model and linear regression model for predicting the intermingled Yarn breaking strength and elongation
    'Informa UK Limited', 2014
    Co-Authors: Kuvvetli Y., Duru Baykal P., Erol R.
    Abstract:

    In this study, the effects of selected intermingling process parameters on Yarn breaking strength and elongation were predicted using artificial neural network. For this aim, partially oriented Polyester Yarn with 283 dtex linear density and three different numbers of filaments (34, 68, and 100) were used for producing interlaced Yarn under different process parameters (speed and pressure). Yarns' elongation and strength values measured with Uster Tensorapid test device and the number of filaments are input variables of the artificial neural networks. Feed forward neural network (FFNN) is used as the network structure. All FFNN computations were performed by MATLAB software package. The comparison results show that the FFNN has a better prediction performance than linear regression. © 2014 © 2013 The Textile Institute

  • The effects of intermingling process parameters and number of filaments on intermingled Yarn properties
    'Informa UK Limited', 2013
    Co-Authors: Duru Baykal P.
    Abstract:

    The aim of this study is to evaluate many parameters in intermingling process and to determine the effects of these parameters on Yarn properties statistically. For this purpose, POY (partially oriented Polyester Yarn) filaments, which have 283 dtex linear density and four different filament numbers (34, 47, 68, 100) in cross-section, were used as raw material. Samples were produced at speeds of 150, 300, 450 m/min and pressures of 3, 5, 6 bar, respectively. Intermingled Yarn's strength, elongation, and the number of nips were tested and these features were evaluated as response (dependent) variables. Number of filaments in cross-section, intermingling speed, and intermingling pressure were taken as independent variables. General factorial design was applied by using Design Expert 6.0.1 and SPSS 15.0 software package, and therefore, the effects of selected independent variables on response variables were evaluated statistically. Results showed that the intermingling pressure and number of filaments have statistically significant effects on all the response variables. Moreover, it is observed that there is an interaction between pressure and the number of filaments. The intermingling speed on the other hand has no statistically significant effect. © 2013 The Textile Institute

Kuvvetli Y. - One of the best experts on this subject based on the ideXlab platform.

  • Predicting the intermingled Yarn number of nips and nips stability with neural network models
    National Institute of Science Communication and Information Resources (NISCAIR), 2015
    Co-Authors: Özka İ., Kuvvetli Y., Aykal P.d., Sahi C.
    Abstract:

    This study aims at predicting the effects of selected process parameters on nips stability and number of nips by using different artificial intelligence methods. Partially oriented Polyester Yarn with 283 dtex linear density and different numbers of filaments are intermingled with different speed and pressure levels. The feed forward neural network with multi-hidden layers (ML-FFNN) and general regression neural networks (GRNN) have been selected as artificial intelligence methods. The number of filaments, intermingling speed and pressure values are used as input variables on the artificial neural networks. The effects of number of hidden layers on the ML-FFNN and number of nodes in the hidden layer are investigated. Based on comparative results, the ML-FFNN is found to give better performance (at most 6%) than by GRNN in terms of prediction accuracy on train and test data sets. It can be concluded from this study that the neural networks has great ability to predict intermingling process parameters. © 2015, National Institute of Science Communication and Information Resources (NISCAIR). All rights reserved

  • Comparison of the neural network model and linear regression model for predicting the intermingled Yarn breaking strength and elongation
    'Informa UK Limited', 2014
    Co-Authors: Kuvvetli Y., Duru Baykal P., Erol R.
    Abstract:

    In this study, the effects of selected intermingling process parameters on Yarn breaking strength and elongation were predicted using artificial neural network. For this aim, partially oriented Polyester Yarn with 283 dtex linear density and three different numbers of filaments (34, 68, and 100) were used for producing interlaced Yarn under different process parameters (speed and pressure). Yarns' elongation and strength values measured with Uster Tensorapid test device and the number of filaments are input variables of the artificial neural networks. Feed forward neural network (FFNN) is used as the network structure. All FFNN computations were performed by MATLAB software package. The comparison results show that the FFNN has a better prediction performance than linear regression. © 2014 © 2013 The Textile Institute

Rizva Erol - One of the best experts on this subject based on the ideXlab platform.

  • comparison of the neural network model and linear regression model for predicting the intermingled Yarn breaking strength and elongation
    Journal of The Textile Institute, 2014
    Co-Authors: Ilka Ozka, Yusuf Kuvvetli, Pinar Duru Aykal, Rizva Erol
    Abstract:

    In this study, the effects of selected intermingling process parameters on Yarn breaking strength and elongation were predicted using artificial neural network. For this aim, partially oriented Polyester Yarn with 283 dtex linear density and three different numbers of filaments (34, 68, and 100) were used for producing interlaced Yarn under different process parameters (speed and pressure). Yarns’ elongation and strength values measured with Uster Tensorapid test device and the number of filaments are input variables of the artificial neural networks. Feed forward neural network (FFNN) is used as the network structure. All FFNN computations were performed by MATLAB software package. The comparison results show that the FFNN has a better prediction performance than linear regression.

Erol R. - One of the best experts on this subject based on the ideXlab platform.

  • Comparison of the neural network model and linear regression model for predicting the intermingled Yarn breaking strength and elongation
    'Informa UK Limited', 2014
    Co-Authors: Kuvvetli Y., Duru Baykal P., Erol R.
    Abstract:

    In this study, the effects of selected intermingling process parameters on Yarn breaking strength and elongation were predicted using artificial neural network. For this aim, partially oriented Polyester Yarn with 283 dtex linear density and three different numbers of filaments (34, 68, and 100) were used for producing interlaced Yarn under different process parameters (speed and pressure). Yarns' elongation and strength values measured with Uster Tensorapid test device and the number of filaments are input variables of the artificial neural networks. Feed forward neural network (FFNN) is used as the network structure. All FFNN computations were performed by MATLAB software package. The comparison results show that the FFNN has a better prediction performance than linear regression. © 2014 © 2013 The Textile Institute

Özka İlka - One of the best experts on this subject based on the ideXlab platform.

  • Investigation of electromagnetic shielding properties of metal composite tufted carpets
    'Informa UK Limited', 2019
    Co-Authors: Özka İlka, Aykal, Pına Duru, Karaasla Muharrem
    Abstract:

    WOS: 000477541300001In this research, it is aimed to develop tufted carpets with electromagnetic shielding (EMSE) effectiveness. For this purpose, stainless steel, copper, silver wires, and metalized silver PA filaments were commingled with textured Polyester Yarn to produce composite Yarn. Composite Yarns were used in tufted carpet backing fabric with different densities and directions. The EMSE of carpet samples was measured in the frequency range of 0.8-5.2 GHz by free space technique. The effects of metal type, composite Yarn density, and placement direction on the EMSE were statistically analyzed in 0.8-3.0 and 3.0-5.2 GHz frequency ranges separately. Stainless steel and silver wires provided better EMSE in the range of 0.8-3.0 GHz. Stainless steel showed better EMSE in lower frequencies than 3 GHz. The metallized silver was more effective above 3 GHz. The increase in metal density significantly increased EMSE for all metal types. Carpets containing metal in two directions provided multidirectional shielding and maximum EMSE reached up to 44 dB level. As a result of the study, tufted carpets which can provide multi-axial protection were produced successfully

  • Predicting the intermingled Yarn number of nips and nips stability with neural network models
    Indian Journal of Fibre & Textile Research (IJFTR), 2015
    Co-Authors: Özka İlka, Kuvvetli Yusuf, Aykal, Pına Duru, Şahi Cenk
    Abstract:

    This study aims at predicting the effects of selected process parameters on nips stability and number of nips by using different artificial intelligence methods. Partially oriented Polyester Yarn with 283 dtex linear density and different numbers of filaments are intermingled with different speed and pressure levels. The feed forward neural network with multi-hidden layers (ML-FFNN) and general regression neural networks (GRNN) have been selected as artificial intelligence methods. The number of filaments, intermingling speed and pressure values are used as input variables on the artificial neural networks. The effects of number of hidden layers on the ML-FFNN and number of nodes in the hidden layer are investigated. Based on comparative results, the ML-FFNN is found to give better performance (at most 6%) than by GRNN in terms of prediction accuracy on train and test data sets. It can be concluded from this study that the neural networks has great ability to predict intermingling process parameters