Explore the vast range of titles available.

As the need for quickly exploring a textile manufacturing process is increasingly costly along with the complexity in the process. The development of manufacturing process modeling has attracted growing attention from the textile industry. More and more researchers shift their attention from classic methods to the intelligent techniques for process modeling as the traditional ones can hardly depict the intricate relationships of numerous process factors and performances. In this study, the literature investigating the process modeling of textile manufacturing is systematically reviewed. The structure of this paper is in line with the procedure of textile processes from yarn to fabrics, and then to garments. The analysis and discussion of the previous studies are conducted on different applications in different processes. The factors and performance properties considered in process modeling are collected in comparison. In terms of inputs’ relative importance, feature selection, modeling techniques, data distribution, and performance estimations, the considerations of the previous studies are analyzed and summarized. It is also concluded the limitations, challenges, and future perspectives in this issue on the basis of the summaries of more than 130 related articles from the point of views of textile engineering and artificial intelligence.

Nowadays, the demand of small-series production and quick response become more and more important in textile supply chains. To meet the increasing trend of customization in garment production, forecast based supply chain model is not suitable any more. Demand-driven garment supply chain is developed and employed more and more. However, there are still many defects in current model for demand-driven supply chains, e.g. long lead time, low efficiency etc. Therefore, in this study we proposed a new collaborative model with central order processing system (COPS) to optimize current demand-driven garment supply chain and improve multiple supply chain performances. Common and important supply chain collaboration strategies, including resource sharing, information sharing, joint-decision making and profit sharing, were merged into this system. Discrete-event simulation technology was utilized to experiment and evaluate the new collaborative model under different conditions based on a real case in France. Multiple key performance indicators (KPIs) were examined for the whole supply chain and also for individual companies. Based on the simulation experiment results, we found that new proposed collaborative model gain improvements in all examined KPIs. New model with COPS performed better under high workload condition than under low workload condition. It can not only increase overall profit level of the whole supply chain but also individual profit level of each company.

The quick development of mass customization in the apparel industry leads to an exponential increase of garment size combinations for markers, which induces a heavy and complex workload of marker making. In this context, due to the complexity of the problem, the classical marker making methods using the existing commercialized software are less performant in terms of efficiency and accuracy. Therefore, machine learning techniques, usually taken as efficient tools for extracting relevant information from data measured in uncertain and complex scenarios, are considered much simpler and faster. In this study, we apply the methods of multiple linear regression (MLR) and radial basis function neural network (RBF NN) to estimate marker lengths that are used in various garment production modes by considering various sets of garment sizes and different marker types. The experimental results show that the proposed approach leads to a good performance in estimating marker lengths of different types of markers (mixed marker and group marker) with diverse size combinations taken from various sets of garment sizes in both mass production and mass customization conditions.

In this paper, we present a mass customization (MC)-oriented garment production planning system using mathematical optimization methods to generate the most efficient size chart and cutting order plan. It is composed of two subsystems, i.e., the fit-oriented garment sizing system and the cost-oriented garment cutting-order-planning (COP) system. In the fit-oriented sizing system, additional sizes are generated based on classical standard sizes, where a genetic algorithm (GA) is used to find the global optimum within an acceptable computation time. The comprehensive fit (CF), an overall garment fit evaluation of the target population, is taken as the objective function of the GA. In the cost-oriented COP system, under the hypothesis that fabric-cutting markers vary greatly (regarding the marker length and the cutting length) with various size combinations, an expanded integer programming (IP) model is developed to generate a cutting order plan with the lowest overall cutting cost (including the costs of fabric, spreading operation, and cutting operation) for the proposed sizing system. This MC-oriented production planning system has been validated with the performance of personalization (fit) and economy (cutting cost) through a case study on a women’s basic straight skirt. The experimental results show that the proposed system enables a considerable improvement of custom-fit at the expense of a very limited amount of extra cutting cost. Nevertheless, the cutting cost can fluctuate with the increasing number of extra sizes rather than increase monotonically with it. This study illustrates that these optimization approaches which support the garment sizing and COP for MC can help to gain a high customer satisfaction in terms of the garment fit and the cutting cost. More precisely, a GA is capable of rapidly finding the globally optimal sizing scenario, and an IP is able to work out the corresponding best cutting order plan. Furthermore, these proposed approaches can ultimately facilitate the evolution of garment production from mass production (MP) to MC.

Few studies on supply location decisions focus on enhancing triple bottom line (TBL) sustainability in supply chains; they rarely employ objective quantifiable measurements which help ensure consistent and transparent decisions or reveal relationships between business and environmental trade-off criteria. Therefore, we propose a decision-making approach for objectively selecting multi-tier supply locations based on cost and carbon dioxide equivalents (CO2e) from manufacturing, logistics, and sustainability-assurance activities, including certificate implementation, sample-checking, living wage and social security payments, and factory visits. Existing studies and practices, logic models, activity-based costing, and feedback from an application and experts help develop the approach. The approach helps users in location decisions and long-term supply chain planning by revealing relationships among factors, TBL sustainability, and potential risks. This approach also helps users evaluate whether supplier prices are too low to create environmental and social compliance. Its application demonstrates potential and flexibility in revealing both lowest- and optimized-cost and CO2e supply chains, under various contexts and constraints, for different markets. Very low cost/CO2e supply chains have proximity between supply chain stages and clean manufacturing energy. Considering sustainability-assurance activities differentiates our approach from existing studies, as the activities significantly impact supply chain cost and CO2e in low manufacturing unit scenarios.

Design for longevity is known as an eco-design opportunity and could help to reduce the environmental footprint of energy-free items. However, extending the lifespan of products is not always desirable and the focus should be on achieving an optimal lifespan. Operationally, recommendations for design for longevity usually refer to durability, repairability, upgradability or emotional attachment. The use of high-quality and robust material is frequently stated, although it is not obvious what high-quality material is. Based on a quality by design approach, this study aims to propose a methodology to design for optimal longevity with a consumer-oriented approach. To do so, it includes data collection of product quality and manufacturing processes and then embeds consumers’ knowledge. These are combined into data analysis to help to highlight relationships and the most appropriate quality contributors. This methodology relies on three-steps: first, a single quality score which includes consumers’ knowledge; secondly, a multi-scale reverse-engineering process; and finally a data analysis using principal component analysis. The originality of such a proposal is that it enables the consumers’ knowledge to be considered in the identification of appropriated quality contributors. The proposed methodology is implemented in the fashion sector as it is said to be the second most polluting one. Moreover, given the huge variety of materials and production processes available in textiles, the selection of the most suitable recommendations to support a longer lifespan is very complex. The presented case study involves 29 T-shirts and reveals the mechanical-related strengths to be the main quality contributors.

In the fashion market, the lack of historical sales data for new products imposes the use of methods based on Stock Keeping Unit (SKU) attributes. Recent works suggest the use of functional data analysis to assign the most accurate sales profiles to each item. An application of siamese neural networks is proposed to perform long-term sales forecasting for new products. A comparative study using benchmark models is conducted on data from a European fashion retailer. This shows that the proposed application can produce valuable item level sales forecasts.

Accurate demand forecasting has always been essential for retailers in order to be able to survive in the highly competitive, volatile modern market. However, anticipating product demand is an extremely difficult task in the context of short product life cycles in which consumer demand is influenced by many heterogeneous variables. During the COVID-19 pandemic in particular, with all its related new constraints, the fashion industry has seen a huge decline in sales, which makes it difficult for existing sales forecasting methods to accurately predict new product sales. This paper proposes an original sales forecasting framework capable of considering the effect of the COVID-19 related crisis on sales. The proposed framework combines clustering, classification, and regression. The main goals of this framework are (1) to predict a sales pattern for each item based on its attributes and (2) to correct it by modelling the impact of the crisis on sales. We evaluate our proposed framework using a real-world dataset of a French fashion retailer with Omnichannel sales. Despite the fact that during the lockdown period online sales were still possible, consumer purchases were significantly impacted by this crisis. Experimental analysis show that our methodology learns the impact of the crisis on consumer behavior from online sales, and then, adapts the sales forecasts already obtained.

PurposeWe propose a machine learning based methodology to deal with data collected from a mobile application asking users their opinion regarding fashion products. Based on different machine learning techniques, the proposed approach relies on the data value chain principle to enrich data into knowledge, insights and learning experience.Design/methodology/approachOnline interaction and the usage of social media have dramatically altered both consumers’ behaviors and business practices. Companies invest in social media platforms and digital marketing in order to increase their brand awareness and boost their sales. Especially for fashion retailers, understanding consumers’ behavior before launching a new collection is crucial to reduce overstock situations. In this study, we aim at providing retailers better understand consumers’ different assessments of newly introduced products.FindingsBy creating new product-related and user-related attributes, the proposed prediction model attends an average of 70.15% accuracy when evaluating the potential success of new future products during the design process of the collection. Results showed that by harnessing artificial intelligence techniques, along with social media data and mobile apps, new ways of interacting with clients and understanding their preferences are established.Practical implicationsFrom a practical point of view, the proposed approach helps businesses better target their marketing campaigns, localize their potential clients and adjust manufactured quantities.Originality/valueThe originality of the proposed approach lies in (1) the implementation of the data value chain principle to enhance the information of raw data collected from mobile apps and improve the prediction model performances, and (2) the combination consumer and product attributes to provide an accurate prediction of new fashion, products.

Growing use of social media such as Twitter, Instagram, Facebook, etc., by consumers leads to the vast repository of consumer generated data. Collecting and exploiting these data has been a great challenge for clothing industry. This paper aims to study the impact of Twitter on garment sales. In this direction, we have collected tweets and sales data for one of the popular apparel brands for 6 months from April 2018 – September 2018. Lexicon Approach was used to classify Tweets by sentence using Naïve Bayes model applying enhanced version of Lexicon dictionary. Sentiments were extracted from consumer tweets, which was used to map the uncertainty in forecasting model. The results from this study indicate that there is a correlation between the apparel sales and consumer tweets for an apparel brand. “Social Media Based Forecasting (SMBF)” is designed which is a fuzzy time series forecasting model to forecast sales using historical sales data and social media data. SMBF was evaluated and its performance was compared with Exponential Forecasting (EF) model. SMBF model outperforms the EF model. The result from this study demonstrated that social media data helps to improve the forecasting of garment sales and this model could be easily integrated to any time series forecasting model.