Textile Manufacturing Processes Research Articles

Fabric Defect Detection Using Transfer Learning

Transfer learning in fabric defect detection involves utilizing pre-trained deep learning models on a large dataset, typically from a different domain, and fine-tuning them on a smaller dataset that is specific to fabric defects. By leveraging transfer learning, the limitations of limited annotated data for fabric defect detection can be overcome by utilizing the knowledge gained from a more extensive and diverse dataset. The pre-trained model's learned features are adjusted to recognize specific fabric defect patterns, resulting in more accurate and efficient defect detection. This approach reduces the reliance on a massive labelled dataset for training, which is particularly beneficial in industrial applications where obtaining a vast amount of annotated fabric defect images may be challenging. Ultimately, transfer learning enhances the model's ability to generalize and detect fabric defects with higher precision, thereby contributing to improved quality control in textile manufacturing processes.

Automated machine learning for fabric quality prediction: a comparative analysis.

The enhancement of fabric quality prediction in the textile manufacturing sector is achieved by utilizing information derived from sensors within the Internet of Things (IoT) and Enterprise Resource Planning (ERP) systems linked to sensors embedded in textile machinery. The integration of Industry 4.0 concepts is instrumental in harnessing IoT sensor data, which, in turn, leads to improvements in productivity and reduced lead times in textile manufacturing processes. This study addresses the issue of imbalanced data pertaining to fabric quality within the textile manufacturing industry. It encompasses an evaluation of seven open-source automated machine learning (AutoML) technologies, namely FLAML (Fast Lightweight AutoML), AutoViML (Automatically Build Variant Interpretable ML models), EvalML (Evaluation Machine Learning), AutoGluon, H2OAutoML, PyCaret, and TPOT (Tree-based Pipeline Optimization Tool). The most suitable solutions are chosen for certain circumstances by employing an innovative approach that finds a compromise among computational efficiency and forecast accuracy. The results reveal that EvalML emerges as the top-performing AutoML model for a predetermined objective function, particularly excelling in terms of mean absolute error (MAE). On the other hand, even with longer inference periods, AutoGluon performs better than other methods in measures like mean absolute percentage error (MAPE), root mean squared error (RMSE), and r-squared. Additionally, the study explores the feature importance rankings provided by each AutoML model, shedding light on the attributes that significantly influence predictive outcomes. Notably, sin/cos encoding is found to be particularly effective in characterizing categorical variables with a large number of unique values. This study includes useful information about the application of AutoML in the textile industry and provides a roadmap for employing Industry 4.0 technologies to enhance fabric quality prediction. The research highlights the importance of striking a balance between predictive accuracy and computational efficiency, emphasizes the significance of feature importance for model interpretability, and lays the groundwork for future investigations in this field.

Mechanically-enhanced structural composites yarns with multifilament-spreading technique using a modified ring spinning system and predicting modelling

To advance spinning technology for multifilament covered cotton fibers, a spreading apparatus was introduced to ring spinning. This innovation allowed the manufacturing of a composite yarn with a wrapped structure. However, an effective strategy for predicting the mechanical properties of multifilament spread composite structural yarns (FS-CSY) was urgently needed. In this study, researchers compared FS-CSY with bi-component composite yarn (b-CY) to determine if the addition of a spreading apparatus and twisting in the manufacturing process resulted in any improvements or enhancements. The FS-CSY structure was found to be novel and exhibited significant mechanical properties, including a 4.7% increase in tensile strength compared to b-CY. A strategy was developed to predict FS-CSY by considering the transfer impact of fiber enhancement within the yarn and by incorporating two-component interaction forces in the yarn-wrapped structure. Meanwhile, a modified three-element tensile constitutive model was established to effectively simulate the stress characteristics under different twist levels, which proved the composite yarn prediction theoretical model. Finally, the fracture morphology analysis shown the b-CY fracture surface was irregular, while FS-CSY exhibited a uniform fracture surface, and the 750TPM showed a more uniform and stable structure. By developing this predictive strategy, enhance existing structural composite yarn by maximizing the efficiency and quality of multi-filament covered cotton fibers. Ultimately, this research contributes to advancements in textile manufacturing processes and lays a foundation for future innovations.

VISUALIZING SPUN YARN DEFORMATION: INSIGHTS FROM OPTICAL INSTRUMENTATION

This article presents a comprehensive analysis of key quality indicators for spun yarns, focusing on yarns with a linear density of T=20 (Ne=30) tex produced on both simple and compact ring spinning machines. Through the utilization of optical instrumentation, various parameters including relative breaking strength (Rkm), strength, elongation at break (E %), and hairiness (H %) were meticulously examined to evaluate yarn quality. The study delves into the assessment of yarn unevenness (CV %) as a crucial quality metric, aiming to provide insights into the deformation characteristics of spun yarns. By employing advanced optical techniques, such as high-resolution imaging and precise measurements, the deformation behaviour of yarns under different spinning conditions is elucidated. The findings shed light on the influence of spinning machine type on yarn quality parameters, revealing nuanced differences in strength, elongation, and hairiness between simple and compact spinning processes. Additionally, the analysis highlights the correlation between yarn deformation and overall yarn quality, emphasizing the significance of understanding deformation mechanisms in optimizing textile manufacturing processes. Through a rigorous examination of these quality indicators, this research contributes valuable insights into the intricate dynamics of spun yarn deformation and its implications for textile production. The utilization of optical instrumentation offers a novel approach to visualize and quantify yarn deformation, providing a deeper understanding of the factors influencing yarn quality and performance in industrial settings.

Progress of air flow field and fiber motion analysis in textile manufacturing process: a review

The control of air flow fields generated in the textile manufacturing process is important to fiber motion. With the expansion of textile applications and the challenges brought by carbon emissions, a series of fundamental research has been conducted on the control of various forms of air flow fields in textile processes. This paper reviews the research on air flow fields and fiber motion in textile processes over the past few decades, focusing on both experimental and numerical studies. The air flow field characteristics, fiber motion patterns, and corresponding control methods for vortex, jet and shear flow fields in the textile process are summarized. The results show that the air flow field and fiber motion are major factors affecting textile structure. These fundamental studies are of great significance in improving product quality, reducing energy consumption, and exploring novel applications.

Efficiency of cotton and fiber wetting in cotton ginning plants

This article provides a comprehensive examination of humidification technologies and points within ginneries, with a specific focus on the moisture content of the produced fiber. Several key aspects are covered, ranging from the assessment of existing humidification technologies to the determination of moisture levels in the fiber across different ginneries. Additionally, the article delves into the changes in moisture content observed in various cotton components during technological processes, particularly in fiber bales utilized in production at the spinning factory "OSBORN TEXTILE," along with associated challenges. By examining these facets, the article provides valuable insights into the intricacies of managing moisture content in cotton processing, from ginneries to spinning factories. The findings contribute to a better understanding of the role of humidification technologies in maintaining optimal conditions for cotton fiber production and subsequent textile manufacturing processes. The identification of challenges and vices allows for targeted improvements and optimizations in the industry's practices.

Modeling anisotropic friction in triaxial overbraiding simulations

Triaxial overbraiding is a highly intricate textile manufacturing process that involves interlacing yarns in three directions, enhancing reinforcement of the final composite compared to biaxial braids. Predictive process simulation is a cost-effective approach to optimizing the manufacturing process. Previous research on biaxial overbraiding simulations indicates that yarn-yarn friction has a significant effect on the braid angle and convergence zone length. This study presents an extended yarn interaction model; it utilizes a fast frontal approach and a Eulerian on Lagrangian method to simulate the complex interlacing of multiple yarns in triaxial overbraiding, including yarn-yarn and yarn-ring friction. Experiments were conducted to evaluate the effect of UD yarn tension on the convergence zone length and braid angle, and to validate the simulations. The model validation shows that a recently proposed anisotropic yarn-yarn friction model predicts braid angle more accurately than an isotropic friction model.

Treatability Study on Textile Wastewater using Water Hyacinth Bioadsorbent

Textile dye effluent consists of dye colour and other harmful organics has been a major problem to the Environment due to Industrial development. The most effective adsorption in textile dye wastewater is attained by using commercially activated carbon. The creation of adsorbent, which may be utilized as an alternative, inexpensive method of treating the dye produced during the textile manufacturing process, can benefit greatly from agricultural wastes. In this study, the characterization of the textile dye waste water sample was done and the adsorptive capacity of Water hyacinth biochar in the COD,TDS, TSS removal of textile dye wastewater was studied. Water hyacinth biochar is used as the adsorbent in investigations using batch adsorption. COD values were determined through back titration before adsorption process and after the adsorption process to ascertain whether water hyacinth biochar is helpful at lowering COD of wastewater from textile dyes. Adsorbent dose, contact time, and agitation speed were some of the adsorption parameters that were varied during the adsorption investigation. The reduction of COD, TSS and TDS due to adsorption was found to effective. Hence, the study demonstrated a successful application of Water hyacinth biochar as a promising long-lasting adsorbent for cleaning out impurities from effluent from textile dyeing.

Industrial Textile Wastewater Treatment by Crossflow NF Membrane Filtration

Ineffective dyeing procedures frequently lead to the release of approximately 10–50% of the dye applied, which does not adhere to the fabric and is consequently discharged into the environment along with the effluent. This situation is undesirable both for potential recycling within the textile manufacturing process and because of its adverse environmental pollution effects. This study thoroughly examines nanofiltration (NF) membrane characteristics and their performance in textile wastewater treatment. Pristine NF membrane surfaces were revealing a web-like structure with well-defined pores predominantly in the membrane active region. This assessment confirms the membrane initial cleanliness, free from any external contaminants, which is vital for effective membrane-based filtration. Additionally, the study investigates how different feed flow rates affect water flux during NF membrane filtration. The results demonstrate a clear relationship, where the increasing flow rates boost water flux. This can be attributed to heightened cross-flow velocity and shear force on the membrane surface due to the increased water flux, minimizing external concentration polarization and reducing membrane fouling. The impact of feed flow rate on membrane separation efficiency is also examined, showing consistent efficiency at feed flow rates between 2 LPM and 5 LPM (approximately 80.8% to 82.22%). However, efficiency drops as the feed flow rate increases from 5 LPM to 6 LPM, likely due to increased pressure drop across the membrane, affecting separation efficiency.

A Novel Elastic Conductive Yarn for Smart Textile Applications

Conductive yarns are crucial for electrical connections in electronic textiles. Challenges in conductive and elastic properties of conductive yarns, their durability, and compatibility with existing manufacturing processes limit mass production and affordability of conductive yarn. This work investigates elastic, shell‐conductive, and noncorrosive electroconductive yarns for textile‐based wearable electronics. The existing textile manufacturing processes (plaiting, coiling, and twisting) are used to fabricate elastic conductive yarn (ECY) using different blend ratios of stainless steel conductive yarn and elastomeric yarn. The ECY samples are inspected for structural uniformity, conductive coverage, ability to be woven, thickness, and extensibility. The most promising ECY exhibits a breaking force of 10.87 N, a tenacity of 2.04 cN tex−1, and an elongation at break of 61.1%, suitable for integration into e‐textiles where elasticity is required. The ECY with a conductive coverage of 85.36% provides better electrical connection points, while a thickness of 0.69 mm and linear density of 534 tex make it compatible with traditional textile manufacturing equipment. Findings demonstrate that the fabrication method and input parameters significantly impact the properties of ECY, including their elasticity and conductive coverage. Utilizing ECYs in fabric circuit boards can enable improved smart wearables for sustainable and modular integration of electronic components.

Optimizing Textile Manufacturing With Neural Network Decision Support: An Ornstein-Uhlenbeck Reinforcement Learning Approach

The textile sector makes a substantial contribution to the global economy. During the Industry 4.0 era, the textile production process is anticipated to become more adaptable and versatile. The complex interplay between the macroscopic factors in different textile processes may make decision-making challenging. To address these challenges and provide a viable answer to textile manufacturing companies, machine learning methods are suggested to develop decision support systems. It is possible for a model to correctly reflect the intricate relationships that exist between the parameters and performances of a textile manufacturing process. This representation serves as the foundation for a decision support system. Especially in this work, quality control can be improved by predicting the defects in fabrics using an effective Ornstein-Uhlenbeck reinforcement learning-based decision neural network (OU_RL_DNN), which can detect both local and global defects. The framework's approach effectively reduces the expense of manually annotating the dataset. It takes a few faulty samples mixed with reference samples to learn fault characteristics and properly locate them. The experiment, which comprised a data set that was available to the public and three private fabric data sets, demonstrated that the proposed method surpasses a number of cutting-edge methods in terms of detection and detection time.

Characterization of the Viscoelastic Properties of Yarn Materials: Dynamic Mechanical Analysis in Longitudinal Direction

Warp knitting is a highly productive textile manufacturing process and method of choice for many products. With the current generation of machines running up to 4400 min−1, dynamics become a limit for the production. Resonance effects of yarn-guiding elements and oscillations of the yarn lead to load peaks, resulting in breakage or mismatches. This limits material choice to highly elastic materials for high speeds, which compensate for these effects through their intrinsic properties. To allow the processing of high-performance fibers, a better understanding of the viscoelastic yarn behavior is necessary. The present paper shows a method to achieve this in longitudinal yarn direction using a dynamic mechanical analysis approach. Samples of high tenacity polyester and aramid are investigated. The test setup resembles the warp knitting process in terms of similar geometrical conditions, pre-loads, and occurring frequencies. By recording the mechanical load resulting from an applied strain, it is possible to calculate the phase shift and the dissipation factor, which is a key indicator for the damping behavior. It shows that the dissipation factor rises with rising frequency. The results allow for a simulation of the warp knitting process, including a detailed yarn model and representation of stitch-formation process.

Investigation of ring, airjet and rotor spun yarn structures on the fragmented fibers (microplastics) released from polyester textiles during laundering.

The release of fragmented fibers (FFs), including microplastics from textiles, during their service life is considered an established source of environmental pollution. The yarn structure is identified to affect the amount and length distribution profile of shed FFs from textiles. In the present work, the impact of yarn structures spun from 100% polyester staple fibers, using commercially relevant spun yarn technologies in the textile industry, on the release of FFs from textiles is studied. The bespoke woven fabric samples produced from three types of spun yarns, which include ring, airjet (air vortex) and rotor yarns, were subjected to an accelerated washing process, for up to five washes, to quantify shed FFs and their length distribution profile. The morphological shapes of FF ends associated with the nature of fiber damage were also investigated. The results demonstrated that airjet and rotor yarn structures had released 28% and 33% less mass of FFs, respectively, as compared to the ring yarn structure during the whole washing process. The length distribution profile identified that the ring yarn structure shed longer length FFs as compared to both airjet and rotor ones. The damaged ends highlight the importance of textile manufacturing processes on the generation of FFs. The results of this study give a better understanding of the yarn structural effect of commercially relevant technologies on shedding of FFs, which are released as a pollutant to the environment.

Statistical mapping and data collection of critical equipment failures in the weaving section of textile manufacturing

AbstractThe study's foundation was a scenario analysis of a textile mill's weaving department, with the goal of determining the necessity of a reliable and comprehensive plan for scheduling maintenance time. According to the background information and problem statement, incidents of Run failure maintenance and lengthy downtime (up to 60 days) undermine the machines' availability. The desired efficiency and production are 90% and 194.76 m, respectively; however, the preliminary results indicated less. This indicated a gap that must be closed by implementing regular and appropriate maintenance plans. Additionally, the incoherent and inconsistencies points at a lack of an efficient maintenance plan. It was established that the current strategy is not optimized and does not ensure machine availability because there are disparities and irregularities in the maintenance of crucial equipment. The objective of the study was to map out the critical equipment and collect data on the number and time between failures encountered in the weaving section of the textile manufacturing processes. Failure mode and effect analysis and fish‐bone diagram were used in the analysis of the data. Mapping results indicated downtime up to 60 days, the productivity was estimated at 194.76 m, and efficiency was 90%. The results showed that the critical equipment were the essential piece of machinery in the production line of a textile mill.

Optical coherence tomography imaging can identify Merino lambs’ wool using automatic machine learning vision

Merino lambs’ wool fiber has a unique chemical structure that gives the wool many unique properties and technical benefits. For example, the small fiber diameters mean that Merino wool is soft, countering the scratchiness commonly associated with wool. It is also biodegradable, organic, and environmentally friendly, making it a popular choice of sustainable fabric material. Unfortunately, some fiber sellers unduly sell coarse wool tops to wool yarn factories as Merino wool tops. It is, therefore, an important task to identify the actual wool type for quality assurance in the textile manufacturing process. This paper describes applying the spectral-domain optical coherence tomography (OCT) imaging and automatic machine learning (AutoML) techniques for distinguishing Merino wool from coarse wool. We present the results of wool measurements that were performed by the OCT scans and AutoML algorithms. We conclude that OCT imaging and AutoML algorithms can be applied to distinguish Merino wool from coarse wool in a simple, non-destructive, and contactless manner.

Productivity and Quality Improvement by SCM in Textile and Apparel Industry - An Overview

Retailing, marketing, and merchandising in fibre production, yarn spinning, fabric manufacturing, wet processing, product distribution and disposal are coming under the textile manufacturing process. Any supply chain management consists of many deals such as money, goods, information, and services both inside and among different entities like suppliers, information processing, warehousing and customer dealing. India is one of the world’s few countries which works across the entire value chain process in the textile and apparel industry. Supply chain management in modern textile manufacturing is a crucial part. In the analysis of supply chain management, statistical techniques like factor analysis, structural equations, etc. are used. The three essential variants in the supply chain are such as push-pull chain, pull supply chains, and push/pull supply chains. Information is a major component of supply chain.

Chemical of concern for raising awareness to Indonesian textile sustainability

It is well known that textiles and textile products may contain hazardous compounds. Formally, all imported textiles and textile products must be registered through the Indonesian Custom. Ideally, the Indonesian Custom has the capability to detect chemicals of concern in textiles or textile products entering Indonesian territory. However, this is not the case, particularly for chemicals listed in the Stockholm Convention. The difficulties arise from the lack of identification regarding substances listed in the Stockholm Convention that might be present in textiles, textile products, and finished products. The Indonesian Government has initiated programs to assess the presence of persistent organic pollutants (POPs) in Indonesian territory. Results of the assessment were elaborated in the National Implementation Plan Document on POPs, which was updated recently. Not all substances listed in the Stockholm Convention can be described in depth. Some POPs such as short-chain chlorinated paraffins (SCCPs) and polychlorinated naphthalenes have not been included in Indonesian regulation, particularly in Indonesian Customs Tariff Book, making it extremely difficult to assess them. Nevertheless, a preliminary assessment of polybrominated diphenyl ethers and SCCPs has been carried out. Using the Tier 1 approach, it was revealed that 2,194 tonnes of SCCPs was imported from India to Indonesia, which was listed under HS code 38249090 that covered CP52 (containing 50–54% chlorinated paraffins). Furthermore, another prominent issue for chemicals of concern (CoC) in textiles was the use of lead-containing dyes, nonylphenols, and nonylphenol ethoxylates. The latter two compounds are known to be used in detergents and surfactants during textile manufacturing processes. At present, nonylphenols and nonylphenol ethoxylates are not listed in Indonesian laws for regulated chemicals in textiles and textile products, as well as in the wastewater quality standard for the textile industry. Therefore, to avoid circular economy obstacles of used textiles and textile products and support sustainable Indonesian textiles, a systematic inventory of CoC in textiles is very important.

3D Textiles Based on Warp Knitted Fabrics: A Review.

Fibre-reinforced composites (FRCs) are already well established in several industrial sectors such as aerospace, automotive, plant engineering, shipbuilding and construction. The technical advantages of FRCs over metallic materials are well researched and proven. The key factors for an even wider industrial application of FRCs are the maximisation of resource and cost efficiency in the production and processing of the textile reinforcement materials. Due to its technology, warp knitting is the most productive and therefore cost-effective textile manufacturing process. In order to produce resource-efficient textile structures with these technologies, a high degree of prefabrication is required. This reduces costs by reducing the number of ply stacks, and by reducing the number of extra operations through final path and geometric yarn orientation of the preforms. It also reduces waste in post-processing. Furthermore, a high degree of prefabrication through functionalisation offers the potential to extend the application range of textile structures as purely mechanical reinforcements by integrating additional functions. So far, there is a gap in terms of an overview of the current state-of-the-art of relevant textile processes and products, which this work aims to fill. The focus of this work is therefore to provide an overview of warp knitted 3D structures.

A Self‐Powered Body Motion Sensing Network Integrated with Multiple Triboelectric Fabrics for Biometric Gait Recognition and Auxiliary Rehabilitation Training

AbstractGait analysis provides a convenient strategy for the diagnosis and rehabilitation assessment of diseases of skeletal, muscular, and neurological systems. However, challenges remain in current gait recognition methods due to the drawbacks of complex systems, high cost, affecting natural gait, and one‐size‐fits‐all model. Here, a highly integrated gait recognition system composed of a self‐powered multi‐point body motion sensing network (SMN) based on full textile structure is demonstrated. By combining of newly developed energy harvesting technology of triboelectric nanogenerator (TENG) and traditional textile manufacturing process, SMN not only ensures high pressure response sensitivity up to 1.5 V kPa−1, but also is endowed with several good properties, such as full flexibility, excellent breathability (165 mm s−1), and good moisture permeability (318 g m−2 h−1). By using machine learning to analyze periodic signals and dynamic parameters of limbs swing, the gait recognition system exhibits a high accuracy of 96.7% of five pathological gaits. In addition, a customizable auxiliary rehabilitation exercise system that monitors the extent of the patient's rehabilitation exercise is developed to observe the patient's condition and instruct timely recovery training. The machine learning‐assisted SMN can provide a feasible solution for disease diagnosis and personalized rehabilitation of the patients.

The Importance of Natural Indigo Dye and Its Revitalization and Ethiopian Potential for Indigo Growing

The recent increasing consciousness for environment sustainability and health hazards is the motive for looking for alternative environment-friendly materials and manufacturing processes. Therefore, environmental compatibility and safety to the health manufacturing process are a worldwide concern. The use of excessive and toxic synthetic dyes in textile and apparel manufacturing processes lineages environment pollution and health hazards to the surroundings where they are sited. Consequently, penetrating for alternative eco-friendly dyes has been initiated in recent times by researchers and development motivators in order to reduce the excessive use of synthetic dyes. In this regard, natural indigo dye from the indigo plant is getting attention, and thus, it is preferred as good as synthetic indigo dye, owing to its inherited dyeing property. With natural indigo dye, it can be achieved eco-friendly dyeing without the application of mordant attaining commercially acceptable fastness properties. Owing to the popularity of blue jeans around the world, especially those that are naturally dyed indigo blue, indigo dye consumption is now rising. Furthermore, currently, natural indigo dye is demanding for functional textile finishing, cosmetics and food colouration, UV protection and deodorizing agents, and other applications. In general, because of its increasing demand and wide applications, natural indigo has become an important cash crop and is traded in the international market with a price range of 35 to 40 USD per kilogram as per its purity level. Indigo dye has therefore been revived with more applications than it had before the advent of man-made colourants. The revival of indigo presents a chance for underdeveloped nations with incorporated economic and social benefits. Ethiopia as a developing country and situated in tropical Africa will benefit from indigo revival because of its potentials with having a suitable climate, a young workforce, enough land resource, and its booming textile and apparel industries.