Fabrication Quality Research Articles

Attenuated Total Reflection Fourier Transform Infrared Spectroscopy and Chemometrics for the Discrimination of Animal Hair Fibers for the Textile Sector.

Analyzing the composition of animal hair fibers in textiles is crucial for ensuring the quality of yarns and fabrics made from animal hair. Among others, Fourier transform infrared (FT-IR) spectroscopy is a technique that identifies vibrations associated with chemical bonds, including those found in amino acid groups. Cashmere, mohair, yak, camel, alpaca, vicuña, llama, and sheep hair fibers were analyzed via attenuated total reflection FT-IR (ATR FT-IR) spectroscopy and scanning electron microscopy techniques aiming at the discrimination among them to identify possible commercial frauds. ATR FT-IR, being a novel approach, was coupled with chemometric tools (partial least squares discriminant analysis, PLS-DA), building classification/prediction models, which were cross-validated. PLS-DA models provided an excellent differentiation among animal hair of both camelids and eight animal species. In addition, the combination of ATR FT-IR and PLS-DA was used to discriminate the cashmere hair from different origins (Afghanistan, Australia, China, Iran, and Mongolia). The model showed very good discrimination ability (accuracy 87%), with variance expression of 94.88% and mean squared error of cross-validation of 0.1525.

Enhancing textile quality control with the application of teachable machine and Raspberry Pi as machine learning-based image processing

The adoption of image processing-based technologies in the textile sector is rising. This technology is commonly utilized to replace traditional sensor systems that are limited to a single function while also improving product quality control functions. Defects during the manufacturing process are a common problem in the textile business, particularly with fabric products. This study created a fabric quality control system that detects fabric problems using machine learning-based picture classification techniques. A D320p web camera detects rare and slap flaws, which are classified using open-source Google teaching machine software and processed on a Raspberry Pi 3B device. The laboratory-scale measurement was carried out on a prototype cloth rolling machine using the confusion matrix method. The test results reveal an average inference speed of 143.5 milliseconds, a frame rate of 6.45 fps, and a 98.56% accuracy rate. These results demonstrate that the proposed system is effective and efficient for detecting fabric defects, offering a promising solution for enhancing quality control in the textile industry. Future research could focus on scaling the system for industrial use and enhancing real-time performance.

A Short Review on the Wire-Based Directed Energy Deposition of Metals: Mechanical and Microstructural Properties and Quality Enhancement

Wire-based directed energy deposition (WDED) is an emerging additive manufacturing process garnering significant attention due to its potential for fabricating metal components with tailored mechanical and microstructural properties. This study reviews the WDED process, focusing on fabrication techniques, mechanical behaviors, microstructural characteristics, and quality enhancement methods. Utilizing data from the Web of Science, the study identifies leading countries in WDED research and highlights a growing interest in the field, particularly in materials engineering. Stainless steel, titanium, aluminum, and copper-based alloys are prominent materials for WDED applications. Furthermore, the study explores post-processing techniques such as machining, heat treatment, and surface finishing as integral steps for quality enhancement in WDED components.

The role of the electricity grid in operation-induced greenhouse gas emissions by a residential building: A multi-year retrospective simulation study

In view of the growing shares of renewables in the electricity grid in combination with the electrification of hvac (heating, ventilation, air conditioning) systems in residential buildings, the grid intensity (in terms of carbon dioxide emissions per unit of electric energy) becomes increasingly sensitive to weather conditions, and synchronicity between weather and the grid becomes a more critical aspect in building performance assessment. Using building performance simulation techniques to seek robust building designs requires awareness about the uncertainties in circumstantial factors that affect performance. This 2016 – 2022 retrospective study highlights the effects of using low or high temporal resolution grid emissions intensity data on projected operation-induced carbon dioxide emissions for a terraced dwelling in the Netherlands. Building fabric quality, the occupant profile, and systems configurations (i.e., hvac and photovoltaics) are varied to investigate the effects of the applied grid model resolution. This study shows that ignoring high-resolution grid intensity data is getting increasingly problematic; applying low resolution (annual) instead of high-resolution (15-minute) grid intensity data leads to an increasingly unjustified optimistic assessment both for net and gross emissions (either or not allowing for carbon displacement by feeding locally generated electricity into the grid).

A new path planning strategy driven by geometric features and tensile properties for 3D printing of continuous fiber reinforced thermoplastic composites

Three-dimensional (3D) printing technology for continuous fiber reinforced thermoplastic composites (C-FRTP), capable of rapid manufacturing of lightweight components with intricate geometric features, has emerged as one of the most promising technologies in the field of advanced composite manufacturing. Path planning is a crucial step for determining the fabrication quality of C-FRTP components. This study proposed a new 3D printing path planning strategy driven by the geometric features and tensile properties of C-FRTP components. The strategy employed the properties of the Euler graph to generate the continuous full-field filling paths, ensuring the geometric features of the target components. The intersections were scattered along the printing path to enhance the tensile strength. The feasibility and advantages of the new path planning strategy were validated by comparative experiments with different printing paths. The results indicated that the new strategy not only achieved the geometric features of the target components but significantly enhanced their tensile strength. Using the printing path generated by the new path planning strategy, the tensile strength of specimens featuring mounting holes reached 349.4 MPa, which was only about 4.1 % lower than the tensile strength of continuous fibers at straight paths. Compared to the existing contour-parallel path, the new strategy in this work improved the tensile properties by about 40.9 %. The new path planning strategy proposed in this study shows great potential to design and fabricate C-FRTP components with enhanced mechanical properties for practical applications.

A Systematic Review of AI-Driven Prediction of Fabric Properties and Handfeel

Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 899 papers initially identified, 39 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.

Optimizing textile dyeing and finishing for improved energy efficiency and sustainability in fleece knitted fabrics

In the industrial range, optimizing dyeing and finishing energy is important to control environmental pollution. In the Dyeing stage to finishing of textiles gas, electricity, steam, and water are used 260 m3/hour, 591 kWh, 1.2 pounds/hour, and 8.69 tons/hour respectively. If textile professionals do not match the desired shade and quality of fabrics with the use of minimal resources the energy cost will be multiple times higher. This study investigates the change in the shade of fleece knitted fabrics from the dyeing unload to the finish stage and assumes a dyeing recipe adjustment, focusing on the impact of optimized dyeing and finishing processes. Also, it focuses on qualitative changes in properties across various color variations. Identical dyeing recipes for light, medium, and dark shades of red, blue, and navy. Properties such as GSM (grams per square meter), width, color strength, shade (darker/lighter, red/green, blue/yellow), shrinkage, spirality, pilling, bursting strength, and color fastness were analyzed. Dyeing to post-finishing, an increase in color strength (K/S) values was observed, with examples including minimum increases from 2.9 to 3.18 for light red and maximum from 19.3 to 22.9 for dark navy shade. Darker shades (DL*) were observed after stenter 1st pass (among all variants, red: 1.2 % to 8.1 %, blue: 4.5 % to 6.7 %, navy: 1.6 % to 2 %), while lighter shades (DL*) were observed following sueding and napping (among all variants, red: 3.1 % to 19.7 %, blue: 11.8 % to 19.7 %, navy: 14.8 % to 27.6 %). Greenish (Da*) and yellowish (Db*) tones are prominent across all colors in the finishing stages. Besides, other properties shrinkage, spirality, pilling, bursting strength, and color fastness significantly changed. These findings offer valuable guidance for dyeing professionals aiming to achieve the desired adjustment of shades that match the quality standard and produce sustainable fleece fabrics. To compensate for the shade lightening that occurs during the finishing process, it is recommended to keep the fabric shade slightly darker (5.70 % to 23.10 %) at the dyeing stage.

Three-dimensional visualization of large-area, nanoscale topography measurements

High-resolution metrology is a critical area of development for nanoscale manufacturing, especially as it affects production throughput and fabrication quality. Atomic force microscopy (AFM) is one of the most popular tools for nanometrology, and high-resolution AFM often requires a significant time commitment and produces datasets of several million points. It is therefore critical for the development of data processing techniques to keep pace with the requirements of analyzing this type of data, and for these techniques to be portable as miniaturization in AFM is becoming more common. This work presents a data fitting algorithm designed for reducing the parameters of large-area data sets which utilizes well-established spline fitting techniques. In this paper we show that basis-spline fitting can be used to accurately represent large AFM data sets, including data sets with noisy data and sharp features, while achieving at least 90% parameter reduction in all test cases.

Early prediction of fabric quality using machine learning to reduce rework in manufacturing processes

The increasing competition and rapid technological advancements in today's business world have raised customer expectations. People now expect quick delivery, low prices, and high-quality products. As a result, companies must adapt to this competitive environment to survive. Rework, which is a significant cost in production, increases expenses, reduces production efficiency, and can lead to customer attrition. Research shows various efforts across different sectors to reduce rework, although there is still a gap in the textile sector's fabric dyeing units. Common problems in these units include non-retentive colors, customer dissatisfaction with shades, and repeated dyeing due to environmental factors or dye vat issues. This study uses logistic regression and artificial neural networks models from machine learning to predict which fabrics will need rework, using data from a textile company in Bursa. The analysis indicates that artificial neural networks models perform better.

A novel drying process for knitted fabrics based on heat-wet coupling model

The characteristics of high elasticity and easy deformation of knitted fabrics present challenges for traditional continuous flat drying processes. Shrinkage, uneven drying and dye migration are common problems with these processes. To address those problem, a novel dual-heat-supply drying process for knitted fabrics is proposed, which combines the characteristics of hot air drying and cylinder drying. By establishing a mechanical model of the fabric microelement, the force conditions of the fabric during the drying process are analyzed to prevent the occurrence of shrinkage. Consider the structural attributes of knitted fabrics and the diverse forms of water, a foundational unit model for single-sided weft knitted fabrics is proposed. The effective thermal conductivity of wet knitted fabrics in three directions is calculated through numerical simulation, and the validity of this method is preliminarily verified by comparison with literature experiments. The thermal-humidity coupling model is utilized to develop finite element models of cylinder drying and dual-heat-supply drying, which are then employed to conduct a comparative analysis of the two drying processes. The accuracy of the simulation results is verified through experiments, with the maximum deviation being less than 3.3 %. The results demonstrate that in comparison to cylinder drying, the temperature differential between the upper and lower surfaces of the fabric(ΔT) in dual-heat-supply drying is diminished by approximately 5 K. Additionally, the critical saturation point is reached approximately 10 s earlier, which effectively reduces the proclivity of dye migration and enhances the efficiency of the drying process. Finally, three process parameters (v, Tout and Th) is optimized for the dual-heat-supply drying process, 63.68 % reduction in ΔT, thereby further enhancing the quality of the drying process. The dual-heat-supply drying process represents an effective and significant improvement in the quality of knitted fabrics.

Effects of finishing processes on physical properties of knitted fabrics produced by recycled cotton fibers

This study examines conventional wet-finishing processes applicable to fabrics containing recycled cotton fibers. The knitted fabrics were produced using open-end and compact yarns, with up to 80% of the cotton fibers being obtained from mechanical recycling of pre-consumer textile wastes. The study evaluated the effects of these finishing processes on the physical properties of the fabrics based on the recycled fiber ratio, yarn type, and yarn count. After determining the parameters for enzymatic bio-polishing, scouring, and color removal processes, two sequential finishing routes were designed: using the fabrics as mélange without a dyeing process (F1) or coloring them with color stripping and subsequent dyeing (F2). The resulting fabrics were tested for bursting strength, pilling resistance, weight, thickness, air permeability, and abrasion resistance, and the results were evaluated statistically. The study demonstrated that compact yarns provide superior strength, particularly when the F2 process was employed. The F2 process resulted in high pilling resistance and increased breathability of recycled knitted fabrics. The study concluded that the quality of fabrics containing recycled cotton fibers could be optimized by the selection of the appropriate finishing processes.

Reconstructing hyperspectral images of textiles from a single RGB image utilizing the multihead self-attention mechanism

Hyperspectral images possess abundant information and play a pivotal role in enhancing the accuracy of color difference detection in textiles. However, traditional hyperspectral imaging methods necessitate costly equipment and intricate operational procedures. A novel deep learning model based on a multihead attention mechanism was proposed in this article to facilitate the extensive application of hyperspectral imaging technology in textile quality inspection. This model enabled the reconstruction of the hyperspectral information of plain weave textiles from a single RGB image. In this model, encoder-decoder architecture and pyramid pooling convolutional operations were employed to integrate multiscale features of plain weave cotton-linen textiles. This could capture details and contextual information in textile images more precisely, enhancing the accuracy of hyperspectral image reconstruction. Simultaneously, an attention mechanism was introduced to increase the model’s receptive field and improve its focus on key regions in the input image and feature maps. This resulted in a reduced weighting of redundant information during network learning, leading to an improved feature extraction capability of the network. Through these methods, successful reconstructions of plain weave textiles hyperspectral information from a single RGB image was achieved. Quantitative and qualitative tests were conducted on two datasets, namely, the NTIRE 2020 dataset and a self-made textile dataset, to evaluate the performance of the proposed method. The approach proposed in this article exhibited promising results on both datasets. Specifically, the reconstructed textile hyperspectral images achieved a root mean square error of 0.0344, a peak signal-to-noise ratio of 29.945, a spectral angle mapper of 3.753, and a structural similarity index measure of 0.955 on the textile dataset. In the reconstructed hyperspectral colorimetric experiment, the maximum value of average color difference was 2.641. These results demonstrate that the method can meet the requirements for textile color measurement applications.

Enhancing Fire Safety and Softness: Efficacy of Ethanolamine Polyphosphate as a Fire Retardant for Textiles.

The rising awareness of fire safety among consumers has driven the demand for fire retardants (FRs) that are both cost-effective and efficient across various industries, particularly in textiles. Traditional FRs often compromise fabric softness, resulting in undesirable tactile texture and stiffness changes. While the external addition of softeners can mitigate the stiffness, it may introduce issues such as a greasy texture and increased flammability. This study introduces ethanolamine polyphosphate (EAPP), an innovative organic polyphosphate, as an effective fire retardant that preserves the softness of textiles. Comprehensive evaluations are conducted on EAPP-treated textiles, revealing significant improvements in fire retardancy without compromising fabric quality. EAPP treatment (15wt.% aqueous solutions) increases the limiting oxygen index (LOI) of pure cotton textiles from 17% to 36% and significantly reduces the peak heat release rate (pHRR) and total smoke rate (TSR) as measured by cone calorimetry. Unlike conventional FR products that form FR-salt crystal particles on the fabric surface after drying, EAPP forms a smooth FR protective layer on the fabric, enhancing mechanical fastness and maintaining tactile qualities. These findings highlight EAPP's potential as a non-washing durable, spray-on fire retardant solution for textiles, combining safety with user comfort.

Optimization of Combined Pre-Treatment Process for Bleaching of Cotton Woven Fabric Using Box–Behnken Design

ABSTRACT The conventional bleaching process for cotton woven fabrics is characterized by high consumption of chemicals, water, and energy, resulting in significant environmental impact through elevated energy use and wastewater discharge. To address these concerns and align with sustainable development goals, there is an urgent need for eco-friendly alternatives that minimize environmental footprint while maintaining fabric quality. This study presents the development and optimization of a novel one-bath pre-treatment process for cotton bleaching, employing the Box-Behnken design to enhance sustainability. The optimized process utilizes 32% hydrogen peroxide and 12% sodium hydroxide based on fabric weight, operating at 90°C. The application of the Box-Behnken design facilitated substantial reductions in chemical usage, energy consumption, and wastewater output. The results demonstrated notable improvements in fabric properties, with a whiteness index of 139.5, weight loss of 7.9%, and tensile strengths of 404.9 N (warp) and 259.5 N (weft). Moreover, fabric absorbency increased by 9.3% compared to conventional methods. The findings underscore the efficacy of the Box-Behnken design in optimizing a more sustainable and eco-friendly bleaching process, which not only significantly enhances fabric performance but also offers considerable environmental benefits. This approach presents a promising solution for the textile industry to achieve greener practices while maintaining high-quality standards.

Analyzing the Factors by One-Way ANOVA Associated with Plain Weft Knitted Fabrics’ Production

Bangladesh has achieved a significant reputation for RMG exporting over the last three decades, particularly in knitwear. The knitwear sector is one of the self-supporting sectors of Bangladesh, which could meet 90% of the fabric requirements. However, there is an empirical relationship between machine diameter and fabric diameter. It’s assumed that the machine diameter determines the fabric diameter. Therefore, the objectives of the study were to test the significance of average shifting in fabric diameter from machine diameter and the overall effect of machine diameter on fabric diameter. Empirical research has been conducted for such an investigation. This study was carried out with a few factories and a full lot of each factory was inspected. Based on the collected data, diameters of machines were grouped into three levels to understand the variation of fabric diameters. Then, SPSS software was used to analyze the collected data, applying one sample t test and one-way ANOVA. However, the result of the analysis revealed that machine diameter has no effect but indicative means reduction were found in fabric diameters. In the future, more comprehensive studies could be done by including larger data. But now, these findings will help all the personnel related to the quality and production of knitted fabric.

From Waste to Wonder: Leveraging Rust Dyeing and Eco-Printing for Modern Sustainable Textiles

In rust dyeing, rusted objects are repurposed to transfer unique patterns and earthy tones onto fabric, transforming what might be considered waste into beautiful, sustainable works of art. This study investigates the combined effects of rust dyeing and eco-printing on different fabric types—cotton, modal, viscose, and polyester. Rust dyeing was performed using rusted iron nails to impart earthy tones of brown and orange to the fabrics. Following the dyeing process, eco-printing was carried out using Psidium guajava (guava) leaves that were pre-mordanted with a ferrous sulphate solution. The colourfastness, pattern quality, and overall appearance of the rust-dyed fabrics post eco-printing was assessed. Results revealed that rust dyeing produced distinct shades on each fabric type, with cotton and modal showing the most pronounced colour retention and eco-print detail. Viscose exhibited moderate colour absorption, while polyester showed limited dye adhesion and eco-print definition. The study concludes that while rust dyeing and subsequent eco-printing can effectively enhance the aesthetic qualities of natural and regenerated cellulosic fabrics, polyester's synthetic nature poses challenges in achieving vibrant and durable impressions. The findings provide insights into optimizing eco-printing techniques for diverse fabric types and contribute to the broader understanding of sustainable textile processes. By embracing the unpredictability of nature, artists and designers can create one-of-a-kind designs that reflect the textures, shapes, and hues found in the environment. These eco-friendly approaches not only reduce reliance on synthetic dyes but also transform everyday materials, often considered waste, into beautiful works of art.

Simple methodology to score micropattern quality and effectiveness.

Micropatterns (MPs) are widely used as a powerful tool to control cell morphology and phenotype. However, methods for determining the effectiveness of how well cells are controlled by the shape of MPs have been inconsistently used and studies rarely report on this topic, indicating lack of standardization. We introduce an evaluation score that quantitatively assesses the MP fabrication quality and effectiveness, which can be broadly used in conjunction with all currently available MP design types. This score uses four simple and quick steps: (i) scoring MP and (ii) background fabrication quality, (iii) defining the type(s) of MP of interest, and (iv) assigning so-called efficiency descriptors describing cell behavior. These steps are based on visual inspection and quick categorization of various aspects of MP fabrication quality and cell behaviour, presented in illustrations and microscopy image examples intended to serve as a reference "atlas". To illustrate the advantage of using this score, we determined differences in cell morphology and F-actin intensity between scored vs. non-scored cells. These measurements, which could be different in other studies, were chosen because both are understood as markers of cell phenotype and function. We combined intensity-calibrated immunofluorescence microscopy and image-based single cell protein analysis. Importantly, significant differences in cell morphology and cytoskeletal protein content between scored vs. non-scored cells were noted: the unconditional inclusion of all experimental read-outs (i.e., all MP data regardless of MP quality and effectiveness) into the final results significantly misjudged the experimental readouts vs. only including experimental read-outs of quality-controlled and effective MPs, identified by scoring. Specifically, non-scoring underestimated the F-actin intensity per cell and quantitative cellular morphometric descriptors circularity and solidity and overestimated aspect ratio. Scoring improved the precision of cellular readouts, advocating the use of a MP quality and efficiency score as a quantitative decision-supporting tool in deciding whether or not particular MPs should be used for experiments, saving time and money. This simple scoring methodology can be used for improving MP fabrication, comparing results across studies, benefiting basic science studies and potential future clinical use of MPs by introducing standardization.

A rapid and low-cost method to fabricate well of the well (WOW) dishes with arbitrary 3D microwell shapes for improved embryo culture

Despite its high cost, the success rate for in vitro fertilization (IVF) remains < 33% in humans, driving the need for new techniques to improve embryo culture outcomes. The well-of-the-well (WOW) culture system is a platform for in-vitro mammalian embryo culture that has been shown to enhance the developmental competence of embryos and clinical pregnancy rates in humans. However, discovery and testing of the best design for optimal embryo culture quality is hindered by the lack of a method to flexibly produce WOW dishes of various designs. Here, we present a low-cost and simple method to fabricate WOW dishes with microwells of arbitrary shapes and dimensions. We use a low-cost 3D printing service to fabricate a poly(dimethylsiloxane) (PDMS)-based WOW insert that can be paired with a standard in vitro fertilization (IVF) dish to create WOW dishes with new microwell shapes, including pyramidal and hemispherical designs. We validate the fabrication quality of the WOW inserts and demonstrate the utility of the assembled WOW dishes for observation and grading of mouse embryo quality. Moreover, our results indicate that WOW dishes with hemispherical microwells result in better culture outcomes than traditional flat-bottomed IVF dishes and those with other microwell shapes, including the semi-elliptical microwells used in commercial WOW dishes. The proposed fabrication strategy thus provides a way to rapidly fabricate and test new WOW dishes that may bolster IVF success rates.

An approach to automatic fault detection in four-point system for knitted fabric with our benchmark dataset Isl-Knit

Knit fabric is one of the dominating fabric types for wearable textile across the whole world and during the production of knit fabric, faults created by different reasons cause difficulties in the subsequent process. The existing fault detection process in the knitting industry is done manually by the human naked eye. To detect faults automatically, deep learning-based models are very efficient and can reduce the workload for fabric inspection. However, implementing a deep learning-based model for fabric fault detection needs a large number of images with different types of knit fabric faults from real-world scenarios to train and for better performance. Most of the existing fabric fault datasets are based on woven fabric, which cannot be used for training because the faults of woven fabric and knit fabrics are completely different. In this research, we propose a new dataset named ISL-Knit. It is a benchmark dataset for knit fabric faults collected from different knit dyeing industries in Bangladesh. Our dataset contains high-resolution images of grey fabric and dyed fabric annotated with 7 types of faults. To provide correct annotation, all images of faults are annotated and verified with the proper reference which can be a great tool for boosting up deep learning-based models for automatic knit fabric fault detection in the textile field. A comparison of the accuracy of the deep learning-based model by training with our proposed dataset and existing knit fabric fault dataset is also done. To develop an automatic fault detection system, we trained the YOLOv5 models with our dataset, considering different image sizes. For real-world implementation, the best models are selected considering mAP and inference time. YOLOv5 models are implemented in Raspberry Pi with a Raspberry Pi camera, a laptop with no dedicated GPU, and a laptop with a dedicated GPU with a web camera to observe the performance. Finally, an automated four-point inspection system is developed by calibrating the camera to generate the score representing the quality of fabrics. The implementation represents the feasibility of a deep learning-based model in knit fabric fault detection, considering the cost and accuracy.

Fabric Defect Detection in Real World Manufacturing Using Deep Learning

Defect detection is very important for guaranteeing the quality and pricing of fabric. A considerable amount of fabric is discarded as waste because of defects, leading to substantial annual losses. While manual inspection has traditionally been the norm for detection, adopting an automatic defect detection scheme based on a deep learning model offers a timely and efficient solution for assessing fabric quality. In real-time manufacturing scenarios, datasets lack high-quality, precisely positioned images. Moreover, both plain and printed fabrics are being manufactured in industries simultaneously; therefore, a single model should be capable of detecting defects in all kinds of fabric. So training a robust deep learning model that detects defects in fabric datasets generated during production with high accuracy and lower computational costs is required. This study uses an indigenous dataset directly sourced from Chenab Textiles, providing authentic and diverse images representative of actual manufacturing conditions. The dataset is used to train a computationally faster but lighter state-of-the-art network, i.e., YOLOv8. For comparison, YOLOv5 and MobileNetV2-SSD FPN-Lite models are also trained on the same dataset. YOLOv8n achieved the highest performance, with a mAP of 84.8%, precision of 0.818, and recall of 0.839 across seven different defect classes.