Predicting the influence of seam design on formability and strength of nonwoven structures using artificial neural network

Formability which is also known as drapability is defined as the ability of a planar textile structure to be directly deformed to fit a three-dimensional surface without the formation of wrinkling, kinks or tears. According to human’s desire for comfortable and high quality clothing, formability has a specific place in the textile industry so many studies have been conducted on understanding and predicting formability of textiles. Artificial neural network method is used in this study order to predict the influence of seam design on formability and tensile behavior of nonwoven structures. Our findings and analysis showed that seam design, seam allowance and weight of nonwoven layers are three main parameters significantly affecting the formability and overall tensile of nonwoven structure. Predicted values obtained from the ANN methodology were compared with the experimental data proving very good correlation between examined and predicted values.     

Predicting tensile strength of yarns required for producing PET/Cotton blended woven fabrics of a pre-defined tensile strength

This study was aimed at developing statistical models for the prediction of tensile strength of warp and weft yarns required for attaining a pre-defined strength of PET/Cotton blended woven fabrics. The models were developed based on the empirical data obtained from carefully developed 234 fabric samples with different constructions using 15, 20, and 25 tex yarns in warp and weft directions. The prediction ability and accuracy of the developed models were assessed by correlation analyses of the predicted and actual warp and weft yarn strength values of another set of 36 fabric samples. The analyses showed a very strong ability and accuracy of the developed statistical prediction models.     

Predicting the tensile strength of polyester/cotton blended woven fabrics using feed forward back propagation artificial neural networks

Tensile strength plays a vital role in determining the mechanical behavior of woven fabrics. In this study, two artificial neural networks have been designed to predict the warp and weft wise tensile strength of polyester cotton blended fabrics. Various process and material related parameters have been considered for selection of vital few input parameters that significantly affect fabric tensile strength. A total of 270 fabric samples are woven with varying constructions. Application of nonlinear modeling technique and appreciable volume of data sets for training, testing and validating both prediction models resulted in best fitting of data and minimization of prediction error. Sensitivity analysis has been carried out for both models to determine the contribution percentage of input parameters and evaluating the most impacting variable on fabric strength.     

The study on the air volume fraction of electrospun nanofiber nonwoven mats

Electrospinning is an efficient method to produce polymer fibers with a diameter range from nanometers to a few microns using an electrically driven jet. Electrospun nanofiber nonwoven fabrics can be applied into different areas with higher air volume fraction, especially applied into textile materials with good warmth retention property. In this article, the air volume fraction in nonwoven mats made of electrospun nanofibers was verified by studying fiber volume fraction in the mats. Then the relationship between fiber volume fraction and fiber diameter was derived, and the fiber volume fraction is in direct ratio to the square of fiber radius. By experimental verification, to get electrospun PAN nanofiber nonwoven mats with high air volume fraction about 99 %, it can fix the polymer concentration on 8 %. The voltage fixed on 20 kV, the tip-to-collector distance on 15 cm. The experiment is in accordance with the theory excellently.     

Measuring tensile strength of nanofibers using conductive substrates and dynamic mechanical analyzer

Though the tensile strength of nanofibers is essential to determine their application fields, few studies have been conducted on this topic, due to the difficulties involved in the preparation of single nanofiber tensile specimens, the manipulation of the clamping device, and the sensing of the nano- force and strain. A bundle testing method was employed in this work to measure the tensile strength of nanofibers. For this purpose, a conductive substrate was designed to hold several thousand nanofibers extruded from a spinning nozzle and align them uniaxially during the electrospinning process. This substrate was designed for a dynamic mechanical analyzer (DMA), because most DMAs are equipped with fine sensors sensitive enough to measure a very small force and strain. Nylon 6 nanofibers were electrospun and collected on the substrate. Then, they were elongated simultaneously in the DMA until they were fractured, showing that the aligned nanofibers have superior tensile strength and modulus compared to their counterpart microfibers and thus suggesting that polymeric nanofibers have the potential to be used as reinforcement fibers for composite materials.     

Study of the microstructure of durum wheat endosperm using X-ray micro-computed tomography

Durum wheat grains are used for producing food, such as pasta or couscous. The grain mechanical properties which are linked to its internal micro-structure (i.e. endosperm porosity) are known to determine its ability to produce semolina during milling. The proportion of grains having porous endosperm in a batch appears therefore as a critical quality factor for the durum wheat value chain. Our objective was to investigate the ability of X-ray micro-tomography (μCT) method to describe the porous or vitreous counterpart structures in the endosperm of durum wheat grains. We selected two different durum wheat samples displaying vitreous or partially porous endosperms. The grains were analyzed using μCT at two pixel sizes (1 μm or 7 μm). The μCT data collected at 7 μm pixel size were used for qualitative classification of grains according to apparent distribution curve of the porosity parameters. Analysis of μCT images at 1 μm pixel size allowed us to propose pore size classification in the vitreous and porous parts of the endosperm in three durum wheat grain. Results are used to better describe the durum-wheat endosperm microstructure, but requires long scanning periods.     

The effect of blend ratio and process parameters on tensile properties of polyester/viscose blended needle-punched nonwovens

In this study, the tensile strength and elongation of polyester/viscose blended needle-punched nonwovens were analyzed. For this purpose, five different blend ratios of polyester/viscose webs were produced, cross-lapped and needled in four different mass per unit areas and three different needling/punching densities. The tensile properties of the nonwovens were determined by performing the standard test methods and the data obtained from tests were statistically analyzed in Design Expert software. In addition, a mixture process crossed regression model with two mixture components (polyester and viscose blend ratios) and two process variables (fabric mass per unit area and needling density) was developed to analyze the tensile strength and elongation of polyester/viscose blended needled nonwovens. In conclusion, the regression model indicated that the tensile strength of the needle-punched nonwovens decreases with the increase of polyester proportion in the mixture and increases with the increase in mass per unit area and punching density.     

Fique fibers: Enhancement of the tensile strength of alkali treated fibers during tensile load application

Fique fibers were treated using Na(OH) solution at 5 w/v%, slack and under 1 N of tension, at room temperature, for 4 and 24 h respectively. Changes in their structure and composition were monitored using Fourier transform infrared spectroscopy (FTIR), thermogravimetric analysis (TGA) and X-ray diffraction (XRD). Additionally their mechanical properties were evaluated and analyzed. Results showed that tensile load application during alkali treatment improves their tensile strength and modulus. The most important change in mechanical properties was achieved in fibers treated for 24 h under tension. However, these fibers presented a high standard deviation; due to this treatment causing an important defibrillation. Moreover, fibers treated for 4 hours under tension, enhance their tensile strength around 56 %, while slack treated fibers improve only 38 %. When fibers were treated under tension, cellulose microfibrills were rearranged in the direction of tensile application and the spiral angle decreased, increasing the molecular orientation.     

Prediction of the water absorption capacity of VIS/PES needle-punched webs using genetic algorithms

Needle-punched webs for wet cleaning wipes were produced using a dry-laid method of web- forming. Fibrous webs with a different content of hydrophilic viscose and hydrophobic polyester fibers, as well as webs made from 100 % polyester fibers, were utilized during this study. The webs were compared in terms of their water absorption capacity on the basis of their basic construction parameters, such as fiber fineness, raw material (e.g. fiber density), and web density. The higher water absorption capacity of the viscose/polyester-blended needle-punched webs was achieved at higher content of viscose fibers which coincide with the higher fiber density, finer fibers, and lower web density. A prediction model regarding water absorption capacity of viscose/polyester needle-punched webs was developed on the basis of the mentioned construction parameters and a non-deterministic modelling method, e.g. genetic algorithms, and could provide a guideline for the engineering of nonwoven webs in order to fit the desired water absorption capacity.     

Predicting the unevenness of polyester/viscose blended open-end rotor spun yarns using artificial neural network and statistical models

In this study, an artificial neural network (ANN) and a statistical model are developed to predict the unevenness of polyester/viscose blended open-end rotor spun yarns. Seven different blend ratios of polyester/viscose slivers are produced and these slivers are manufactured with four different rotor speed and four different yarn counts in rotor spinning machine. A back propagation multi layer perceptron (MLP) network and a mixture process crossed regression model (simplex lattice design) with two mixture components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed) are developed to predict the unevenness of polyester/viscose blended open-end rotor spun yarns. Both ANN and simplex lattice design have given satisfactory predictions, however, the predictions of statistical models gave more reliable results than ANN.     

Weibull distribution analysis of the tensile strength of the kenaf bast fiber

This paper presents the influence of the gage length on the kenaf fiber Young’s modulus and the tensile strength characterization. Four different gage lengths of 10 mm, 15 mm, 20 mm and 25.4 mm are selected in this study and the tensile testing is performed at a quasi-static loading rate of 1 mm/min. The cross-sectional area of the fiber after failure is considered for the stress calculations. Weibull probability distribution is used to characterize the tensile strength of the kenaf fiber. The Weibull parameters are obtained for the two parameter, three parameter and Weibull of Weibull models and the average tensile strength of the fibers are evaluated. The predicted average tensile strength from all the three approaches are in good agreement with the experimental results for the obtained parameters.     

Image inspection of nonwoven defects using wavelet transforms and neural networks

Image inspection of nine kinds of nonwoven defects by the wavelet transform and neural network is presented. The defects include black yarn, hole, needle streak, oil stain, stripe, corrugation, white spot, folding mark, and wrinkle mark. The wavelet transform decomposes an original image into four subimages in different frequency bands. Four texture measures, the energy, contrast and correlation with gray-level co-occurrence matrices as well as the energy with wavelet coefficients, are selected as defect features and computed based on the low-frequency subimage at resolution level one. The feature values are distributed in groups by the categories of defects throughout the feature space, accounting for suitability of the four features for inspecting nonwoven defects. The subimage is a downsized approximation of the original image; thus, in this manner, feature extraction can not only consume less computation time but also maintain the classification accuracy. The neural network acts as a classifier, which is trained by forty-five samples. The experimental results demonstrate that among forty-five testing samples, the classification accuracy is 100 %.     

Selection of yarn for the predefined tensile strength of cotton woven fabrics

In order to meet the required strength of a fabric, selection of yarn is difficult because tensile strength of woven fabric depends upon a number of factors. Still, the manufacturers have to use hit and trial method in order to select the yarn for the required tensile strength of fabric. This study was carried out to develop regression equations for the prediction of yarn tensile strength suitable for the predefined strength of cotton woven fabrics. These equations were developed by using empirical data obtained from two hundred and thirty four fabric samples prepared under a systematic plan with different constructions. Prediction proficiency and precision of these regression equations were evaluated by correlation analysis of the predicted and actual warp and weft yarn strength values of another set of thirty six fabric samples. The results show a very strong prediction precision of the equations.     

Analysis and construction of a quality prediction system for needle-punched non-woven fabrics

In this study, polyester and polypropylene staple fibers were selected as the raw material, and then processed through roller-carder, cross-lapper and needle-punching machine to produce needle-punched non-woven fabrics. First, the experiment was planned using the Taguchi method to select processing parameters that affect the quality of the needle-punched non-woven fabric to act as the control factors for this experiment. The quality characteristics were the longitudinal and transverse tensile strength of the non-woven fabric as well as longitudinal and transverse tear strength. The L₁₈ (2¹×3⁷) orthogonal array was selected for the experiment as it offered an improvement on the traditional method that wastes a lot of time, effort and cost. By using the analysis of variance (ANOVA) technique at the same time, the effect of significant factors on the production process of needle-punched non-woven fabrics could be determined. Finally, the processing parameters were set as the input parameters of a back-propagation neural network (BPNN). The BPNN consists of an input layer, a hidden layer and an output layer where the longitudinal/transverse tensile and tear strength of the non-woven fabric were set as the output parameters. This was used to construct a quality prediction system for needle-punched non-woven fabrics. The experimental results indicated that the prediction system implemented in this study provided accurate predictions.     

Predicting adoption of double cropping in paddy fields of northern Iran: a comparison of statistical methods

Factors affecting the adoption of double cropping were explored in rice farms of Fouman County of Guilan Province in northern Iran using artificial neural networks (ANNs), linear discriminant analysis (LDA), and logistic regression (LGR). Eleven factors (age, education, occupation, family size, type of farm ownership, distance to the agricultural service center, attending agricultural extension courses, use of financial resources and bank loans, number of domestic animals, area under cultivation, and social participation) were examined. An additional objective was to compare the ability of the three models in predicting the adoption of double cropping. ANNs showed an overall predictive power of 89.8%. LDA showed an overall predictive power of 83.2%, with seven of the eleven independent variables being effective on the adoption of double cropping. LGR indicated an overall predictive power of 87.6%, with eight of the eleven independent variables being effective on the adoption of double-rice cropping. ANNs showed higher power than LGR and LDA in predicting the adoption of double cropping. Based on all three methods used for analysis, the most important independent variables were social participation and area under cultivation (positive factors) as well as distance to the agricultural service center and family members (negative factors). Establishment of cooperatives or other kinds of farmers’ associations to foster social participation could motivate adoption of double cropping, particularly among small-scale farmers. To increase agricultural services, more local centers should be created in rural areas. The government should promote double cropping through effective incentives and technology transfer to small-scale farmers.     

Relationship between chemical composition,crystallinity, orientation and tensile strength of kenaf fiber

The physical properties of natural growth fibers such as chemical composition content and fiber diameter are highly affected by environmental issues such as environmental changes and fiber extraction methods. These irregularities of the natural fibers seriously affect its utilization in composite as reinforcements. In this study, taking into account the importance of the fiber tensile strength, the correlation degrees between the kenaf fiber tensile strength and the fiber chemical composition, crystallinity, orientation degree were analyzed by the grey relational analysis method. Both the kenaf single fiber and fiber bundle were used as XRD and tensile strength test sample. The chemical composition content and the FTIR were carried out to obtain a correct result of the chemical composition content. It found that for the different XRD and tensile strength test samples, the single fiber showed lower crystallinity, higher orientation degree and tensile strength compared with the fiber bundle. The cellulose content and the orientation degree got the higher correlation degree with single fiber tensile strength, which was 0.674 and 0.640. The highest factor associated with the fiber bundle tensile strength was the orientation degree, the correlation degree was 0.747. The hemicellulose content and the crystallinity also got high correlation degree with the fiber bundle strength, which was 0.687 and 0.640.     

Characterizing the tensile properties of spun yarns using bivariate normal distribution

The tensile properties of spun yarns decisively influence its performance in various mechanical processing stages. This study is primarily aimed at simultaneous analysis of two tensile properties of spun yarns namely tenacity and breaking strain, which play crucial role in determining the frequency of warping breaks. The threshold values of yarn tenacity and breaking strain required for 20’s Ne carded cotton yarn to sustain the imposed stresses and strains during warping process have been determined using a bivariate normal distribution model. This study opens up the possibility of minimizing end breakage rate in various manufacturing processes of textile industry by engineering of spun yarns devoid of potential weak spots which are responsible for breaks.     

Fast X-ray tomography analysis of bubble growth and foam setting during breadmaking

The use of fast X-ray computed microtomography (CMT) shows that the development of gas cell structures during fermentation first depends on a critical time, t₁, determined by overall expansion and before which bubbles grow freely according to a simple exponential law. Afterwards, coalescence rapidly prevails and then leads to a heterogeneous structure, for t≥t₂, characterized by a continuous void phase likely to be stabilized by liquid film walls. This result confirms the involvement of minor components in addition to gluten protein for obtaining a desirable bread texture and suggests that their interfacial properties need to be investigated. The use of fast in situ CMT with careful 3D image analysis also provides data for the validation of numerical models of bubble growth. These small scale experiments could be extended to follow the rheological properties of expanding doughs and the temperature-state changes of wheat flour biopolymers which govern bread baking.     

Influence of the core-sheath weight ratio and twist on the tensile strength of the ring core yarns with high tenacity filaments

Core spun yarns are applied for various purposes that especially require the multi-functional performance. This research reports on the core spinning effect on the yarn strength. We prepared various core yarns by combining different kinds of high tenacity filaments in core with cotton staples in sheath with various twist levels in the ring spin system. And the tensile strength was tested to investigate the contribution of the core-sheath structure to the core yarn strength. The influence of the twist level was also checked up on the relationship between the core-sheath structure and the yarn strength. Results turned out that the core-sheath weight ratio had influence on the tensile properties of the ring core-spun yarns in different ways according to the core filaments used for the yarn. Increasing the twists yielded a monotone decreasing strength for the aramid and the basalt core yarns, while the PET core yarns showed almost unchanged strength, which could be ascribed to the extensional property of the filaments.