Bayesian techniques are vital in mechanical manufacturing for uncertainty quantification and process optimization. This review explores their diverse applications, highlighting advantages in handling small data and incorporating expertise for improved decision-making in quality control, reliability, and machining. It also discusses integration with machine learning and applications in specialized areas. Future research should focus on Industry 4.0 integration and user-friendly tools, emphasizing Bayesian methods' role in intelligent manufacturing.

This study examines the effects of additive manufacturing (AM) orientations and support structures on the compressive strength of lattice structures. Test specimens were fabricated using a selective laser melting (SLM) process with AlSi10Mg material under three conditions: horizontally aligned (0°), tilted at 45°, and supported. Compression tests were conducted using a universal testing machine (UTM) and Digital Image Correlation (DIC) to evaluate mechanical behavior. The results showed that the supported horizontal specimens exhibited the highest compressive strength, while the 45° tilted specimens had the lowest due to interlayer separation and localized failures. The findings highlight the significance of build orientation and support design in optimizing AM lattice structures. Future research should explore various lattice configurations, material selections, and post-processing effects to further enhance structural performance.

High-entropy alloys (HEAs) incorporating low-melting-point elements (Mg and Al) and high-melting-point elements (Ti, Cr, and V) were fabricated via mechanical alloying and spark plasma sintering. Sintering temperatures were varied to investigate phase behavior and microstructural evolution. X-ray diffraction was used to identify phase structures, scanning electron microscopy to analyze microstructures, X-ray fluorescence to determine elemental composition, and a gas pycnometer to measure density. Micro-Vickers hardness testing was conducted to evaluate mechanical properties. Mechanical-alloyed HEAs exhibited a body-centered cubic (BCC) phase and lamellar structures with element-enriched regions. Sintering introduced additional BCC and Laves phases, while higher temperatures promoted Mg liquid-phase sintering, increasing density and hardness. This study highlights the effects of sintering on HEAs containing elements with differing melting points to optimize their properties.

Ti-6Al-4V alloy is widely utilized in aerospace and medical sectors due to its high specific strength, corrosion resistance, and biocompatibility. However, its low machinability makes it difficult to manufacture complex-shaped products. Advancements in additive manufacturing have focused on producing high-performance, complex components using the laser powder bed fusion (LPBF) process, which is a specialized technique for customized geometries. The LPBF process exposes materials to extreme thermal conditions and rapid cooling rates, leading to residual stresses within the parts. These stresses are intensified by variations in the thermal history across regions of the component. These variations result in differences in microstructure and mechanical properties, causing distortion. Although support structure design has been researched to minimize residual stress, few studies have conducted quantitative analyses of stress variations due to different support designs. This study investigated changes in the residual stress and mechanical properties of Ti-6Al-4V alloy fabricated using LPBF, focusing on support structure design.

Ni-based superalloys are widely used for critical components in aerospace, defense, industrial power generation systems, and other applications. Clean superalloy powders and manufacturing processes, such as compaction and hot isostatic pressing, are essential for producing superalloy discs used in turbine engines, which operate under cyclic rotating loads and high-temperature conditions. In this study, the plasma rotating electrode process (PREP), one of the most promising methods for producing clean metallic powders, is employed to fabricate Ni-based superalloy powders. PREP leads to a larger powder size and narrower distribution compared to powders produced by vacuum induction melt gas atomization. An important finding is that highly spheroidized powders almost free of satellites, fractured, and deformed particles can be obtained by PREP, with significantly low oxygen content (approximately 50 ppm). Additionally, large grain size and surface inclusions should be further controlled during the PREP process to produce high-quality powder metallurgy parts.

The present study introduces a machine learning approach for designing new aluminum alloys tailored for directed energy deposition additive manufacturing, achieving an optimal balance between hardness and conductivity. Utilizing a comprehensive database of powder compositions, process parameters, and material properties, predictive models—including an artificial neural network and a gradient boosting regression model, were developed. Additionally, a variational autoencoder was employed to model input data distributions and generate novel process data for aluminum-based powders. The similarity between the generated data and the experimental data was evaluated using K-nearest neighbor classification and t-distributed stochastic neighbor embedding, with accuracy and the F1-score as metrics. The results demonstrated a close alignment, with nearly 90% accuracy, in numerical metrics and data distribution patterns. This work highlights the potential of machine learning to extend beyond multi-property prediction, enabling the generation of innovative process data for material design.

제올라이트, 특히 ZSM-5는 독특한 구조와 분자 체 특성으로 인해 산업적으로 매우 유용하며, 우수한 가스 분리 및 투과 증발 성능으로 높은 평가를 받고 있다. 그러나 ZSM-5 막의 제조 공정을 일관되게 재현하는 것은 여전히 도전 과제 로 남아 있다. 본 연구는 수열합성 조건(합성 시간: 24~72 h, 온도: 180~220°C)을 제어하고, 다양한 알루미나 지지체 비교하 며, 수열 처리 시 유기 구조유도체의 영향 분석을 통해 ZSM-5 막 제조의 신뢰성 향상을 목표로 하였다. 연구 결과, 합성 온 도 및 시간의 변화는 막 두께나 결정 크기에 큰 영향을 미치지 않았으나, 180°C에서 48 h 합성 조건에서 가장 우수한 가스 투과 성능이 나타났다. 다양한 알루미나 지지체 중에서는 N5 α-알루미나 모세관 지지체가 가장 높은 투과도를 나타내었다. 또한, 유기 구조유도체인 테트라프로필 암모늄 브로마이드(tetrapropylammonium bromide, TPABr)의 존재는 합성의 신뢰성에 상당한 영향을 미치는 것으로 확인되었다. 가스 투과 성능 평가 결과, 본 ZSM-5 막은 SF₆에 비해 N2 및 CO2에 대해 선택적 인 투과 특성을 보였으며, TPABr을 사용하여 합성한 막은 CO2/N2 선택도(α)가 약 4.6으로 나타났다.

Fault detection in electromechanical systems plays a significant role in product quality and manufacturing efficiency during the transition to smart manufacturing. Because collecting a sufficient number of datasets under faulty conditions of the system is challenging in practical industrial sites, unsupervised fault detection methods are mainly used. Although fault datasets accumulate during machine operation, it is not straightforward to utilize the information it contains for fault detection after the deep learning model has been trained in an unsupervised manner. However, the information in fault datasets is expected to significantly contribute to fault detection. In this regard, this study aims to validate the effectiveness of the transition from unsupervised to supervised learning as fault datasets gradually accumulate through continuous machine operation. We also focus on experimentally analyzing how changes in the learning paradigm of the deep learning model and the output representation affect fault detection performance. The results demonstrate that, with a small number of fault datasets, a supervised model with continuous outputs as a regression problem showed better fault detection performance than the original model with one-hot encoded outputs (as a classification problem).

Small and medium-sized manufacturing enterprises(SMEs) have traditionally relied on skilled labor to support multi-variety, small-batch production. However, demographic changes such as low birth rates and aging populations have led to severe labor shortages, prompting increased interest in collaborative robots(cobots) as a viable alternative. Despite this necessity, many SMEs continue to face significant challenges in implementing such technologies due to technical, organizational, and environmental(TOE) constraints. While prior research has mainly focused on technology adoption from the perspective of user organizations, this study adopts a differentiated approach by analyzing adoption factors from the perspective of smart factory experts—specifically, evaluators/mentors and solution providers—who play a critical role in Korea’s policy-driven smart manufacturing environment. Using the Analytic Hierarchy Process(AHP), the study evaluates the relative importance and prioritization of adoption factors across three dimensions: technology, organization, and environment. Survey data collected from 20 smart factory experts indicate that top management support, relative advantage, and safety are key determinants in cobot adoption. Furthermore, the findings reveal that organizational readiness and technical effectiveness have greater influence on implementation decisions than external pressures such as partner pressure. This study provides new insights by incorporating expert perspectives into the adoption framework and offers practical policy and managerial implications to support cobots implementation in the SMEs.

Zinc oxide has attracted attention due to its high functionality, including chemical stability, high biocompatibility, and excellent optical properties. In particular, when the particles are nano-sized, they exhibit new characteristics, making them suitable for application in UV-filters, photo-catalysts and cosmetics. This paper provides an overview of nano zinc oxide used for UV filters, and summarizes domestic and international production technology and the industrial status of zinc oxide nano-powder. First, the concept and principle of the nano-sized zinc oxide manufacturing process is provided, and various types of manufacturing methods are analyzed, namely, wet process, dry process, and powder process. Next, the results of an analysis of the domestic sunscreen market size and company status are provided. The production processes of major domestic companies and their product characteristics, such as particle size, purity, surface treatment, and transparency of the zinc oxide powder being produced, are analyzed and provided. The characteristics of zinc oxide produced for use in sunscreens, both domestically and internationally, can be summarized as follows. Manufactured zinc oxide powder is white or transparent, and particle size typically ranges from 30 to 200 nm on average, although non-nano sized powders have also been developed in recent years. When used as a coating, the surface to be coated is typically treated with substances such as silicone oil or silane, and the powder is formulated into products by dispersing it in oil- or water-based systems.