Key Engineering Materials Vol. 1004

Abstract: Investigating the microstructures of materials with microscopy is a key task in quality assurance, the development of new materials, and the optimization of manufacturing processes. However, conventional image analysis often demands significant time for analysis and a large volume of images, and the predictions produced are commonly constrained. Applying deep learning, models can be trained to analyze material microstructures quickly and with greater accuracy. The objective of this study is to provide a method for the automatic segmentation of microstructural images obtained from microscopes or scanning electron microscopes using Convolutional Neural Networks. For this purpose, two software scripts were developed in Python employing OpenCV and the fastai library. The first script is designed to generate reference images, while the second is utilized for training a model and predicting the microstructure in an image. The test of the microstructural analysis using the developed software tools demonstrates that robust prediction results are attainable by using high-quality reference images. This tool has been made available as an open-source on GitHub for public use in materials analysis and can be enhanced and further developed if required.

Abstract: Ultraviolet (UV) radiation from sunlight changes constantly and depends on environmental conditions such as geographical location, season, time of day, weather, clouds, wind, humidity, etc. Therefore, the impact of UV radiation on the properties of textiles, food, or other products during production also varies greatly. This poses challenges for experimental studies on traditional processing conditions like sun drying outdoors. In this study, a compact measuring device using a simple Arduino board and a commercially available UV sensor with embedded software has been developed to measure UV doses (with an error of ± 0.05 UVI). Daily UV dose values measured over 30 days at a location in Ho Chi Minh City (Vietnam) with this device were evaluated and compared with values observed on a smartphone. The results showed that the average DUVD values of the two methods were almost identical, and their coefficients of variation did not differ much (12.30% compared to 14.86%). This device is being tested and upgraded for further research on accumulated UV doses over a period of time to check the UV resistance characteristics of textiles.

Abstract: The Fourth Industrial Revolution, or Industry 4.0, integrates advancements in physics, digital technology, and biology to create new production capabilities and significantly impact economic, political, and social systems. Textile and garment production, a labor-intensive industry, faces particular challenges from Industry 4.0. In this context, the trend toward digitized and automated equipment—utilizing the Internet of Things (IoT), cloud computing, 3D printing, big data analytics, and artificial intelligence (AI)—is gradually replacing human labor in garment factories and throughout supply chains. To keep pace with global trends, Vietnam's textile and garment industry must adopt Industry 4.0 technologies to boost productivity, with sewing line balance being a crucial aspect of this effort. In this article, the authors present research findings on 3D simulation techniques applied to sewing lines for women’s shirts and jackets, using Tecnomatix software. They evaluate and compare the effectiveness of traditional methods for balancing sewing lines and propose improvements based on 3D simulation results. Applying these simulation techniques to real-world production is expected to enhance productivity and labor efficiency in industrial sewing lines, contributing to the development of smart garment factories in Vietnam in the Industry 4.0 era.