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.

This study examined the effects of pre-soaking solvents and repeated steaming-drying (SD) cycles on the antioxidant activity and active compound content of Rehmanniae Radix Preparata(RRP), the processed root of Rehmannia glutinosa Libosch. SD treatments were conducted for 1 to 9 cycles using four different pre-soaking solvents: Takju (a traditional rice wine), Spirits, Honey, and Sugar solution. The results showed no significant differences in DPPH and ABTS radical scavenging activities or in total polyphenol and flavonoid contents among the pre-soaking treatments, although samples pre-soaked in honey and Takju exhibited slightly higher levels. Polyphenol and flavonoid contents increased progressively with the number of SD cycles, reaching levels 2–3 times higher after nine cycles. Catalpol content remained relatively constant regardless of treatment, whereas aucubin content increased in all groups, with the highest accumulation observed in the Takju treatment. Similarly, 5-hydroxymethylfurfural (5-HMF) content increased with the number of SD cycles, with the highest levels found in the honey group, followed by Takju, Sugar, and Spirits. In conclusion, while the type of pre-soaking solvent had minimal influence on antioxidant activities and catalpol content, both aucubin and 5-HMF contents increased with additional SD cycles, with Takju proving particularly effective in enhancing their accumulation.

본 연구는 펫푸드 제조업체의 품질 및 위생관리 수준을 파악하기 위해 펫푸드 및 식품 제조업체 27곳을 선정하여 점검을 진행하였다. 점검에는 17개 항목, 200개 문항으로 구성된 체크리스트가 사용되었으며, 이 중 유의미한 결과 가 도출된 41개 문항의 점검 결과만 연구 자료로 활용하 였다. 점검 결과, 펫푸드 제조업체 작업자는 출입 전 손 씻기, 위생복 착용 등 위생 절차 미 준수 비율이 식품 제 조업체에 비해 높았다(P<0.05). 또한, 펫푸드 제조 설비의 세척 관리 수준이 식품 제조업체보다 미흡한 것으로 나타 났다(P<0.05). 아울러 펫푸드 제조업체는 원료의 생물학적 안전성을 확보하기 위한 해동 기준이 미비하였으며, 환경 오염도 검사, critical control point (CCP) 유효성 평가 등 제품 안전성을 검증할 수 있는 자료도 충분히 보유하고 있지 않았다(P<0.05). 특히, 법규 위반에 해당될 수 있는 자가 품질검사 미 준수비율이 식품 제조업체에 비해 현저 하게 높아, 이에 대한 집중적인 관리와 개선이 요구되었 다(P<0.05). 종합적으로 분석해 볼 때, 펫푸드 제조업체의 품질 및 위생관리 운영관리가 식품 제조업체보다 낮은 수 준인 것으로 확인되었다. 이는 펫푸드 제조업체의 기반 시 설 및 인프라 부족에서 기인한 것으로 추정된다. 따라서 반려동물의 안전성 보호 및 품질 강화를 위해 펫푸드 제 조업체의 위생교육과 법적기준 강화, 정부 기관의 펫푸드 제조업체 지원 정책 마련 등의 개선 방안이 요구된다.

For experimental studies on the production of MR fluid for MR dampers, MR fluid with a viscosity of 506 cP and a density of 2.6 g/cc was produced. In order for MR fluid to have suitable performance for MR dampers, it is important to select surfactants, magnetic particles, base oil, and characteristic additives to obtain high damping force and maintain physical and chemical properties. In order to investigate the redispersibility of MR fluid, viscosity, density, saturation magnetic flux density, dispersibility, and temperature effects were evaluated. A particle size distribution meter and a vibrating magnetometer were used, and a yield stress and redispersion device were developed to obtain the yield stress of the MR fluid. The recovery rate of MR fluid was approximately 97% at 0.2% succinic acid coating and 8% anti-settling agent. And when current is applied, the viscosity increases by more than 90% due to magnetic properties.

본 연구는 시멘트 산업의 대체연료(폐합성수지 등) 사용량 증대에 따라 이를 활용한 탄소배출 저감 및 시멘트/콘크리트 제조 적용 기술 및 방안에 대해 검토하고자 했으며, 향후 시멘트 산업의 탄소중립 실현을 위한 기초 자료로써 활용하고자 한다. 시멘트 제조 에 있어 폐합성수지 사용은 경제적 장점과 높은 발열량으로 인해 연료로서의 가치가 높은 것으로 나타났으며, 열경화성 수지는 부가가 치가 높은 저탄소 시멘트 복합체의 비반응성 골재로 작용할 수 있는 것으로 확인되었으며, 감마선 조사는 다양한 폐플라스틱의 성능 평가에 적용되는 것으로 확인되었다.

This study develops a machine learning-based tool life prediction model using spindle power data collected from real manufacturing environments. The primary objective is to monitor tool wear and predict optimal replacement times, thereby enhancing manufacturing efficiency and product quality in smart factory settings. Accurate tool life prediction is critical for reducing downtime, minimizing costs, and maintaining consistent product standards. Six machine learning models, including Random Forest, Decision Tree, Support Vector Regressor, Linear Regression, XGBoost, and LightGBM, were evaluated for their predictive performance. Among these, the Random Forest Regressor demonstrated the highest accuracy with R2 value of 0.92, making it the most suitable for tool wear prediction. Linear Regression also provided detailed insights into the relationship between tool usage and spindle power, offering a practical alternative for precise predictions in scenarios with consistent data patterns. The results highlight the potential for real-time monitoring and predictive maintenance, significantly reducing downtime, optimizing tool usage, and improving operational efficiency. Challenges such as data variability, real-world noise, and model generalizability across diverse processes remain areas for future exploration. This work contributes to advancing smart manufacturing by integrating data-driven approaches into operational workflows and enabling sustainable, cost-effective production environments.

MES(manufacturing execution system) plays a critical role in improving production efficiency by managing operations across the entire manufacturing system. Conventional manufacturing systems employ a centralized control structure, which has limitations in terms of the flexibility, scalability and reconfigurability of the manufacturing system. Agent-based manufacturing systems, on the other hand, are better suited to dynamic environments due to their inherent high autonomy and reconfigurability. In this study, we propose an agent-based MES and present its collaboration model between agents along with a data structure. The agent-based MES consists of three types of core agents: WIPAgent, PAgent(processing agent), and MHAgent(material handling agent). The entire manufacturing execution process operates through collaboration among these core agents, and all collaboration is carried out through autonomous interactions between the agents. In particular, the order-by-order dispatching process and the WIP(work-in-process) routing process are represented as respective collaboration models to facilitate understanding and analyzing the processes. In addition, we define data specifications required for MES implementation and operation, and their respective structures and relationships. Moreover, we build a prototype system employing a simulation model of an exemplary shop-floor as a simulation test bed. The framework proposed in this study can be used as a basis for building an automated operating system in a distributed environment.

This study explores the utilization level of smart manufacturing systems in the value chain processes of manufacturing and empirically examines the effect of the utilization level of these systems on manufacturing competitiveness in SMEs. Smart manufacturing systems in the value chain processes are categorized into Sales, Purchasing, Production & Logistics, and Support systems. By analyzing the research model using structural equation modeling, this study identifies that Sales systems, Purchasing systems, Production & Logistics systems, and Support systems have a significant impact on manufacturing process efficiency. Additionally, Production & Logistics systems and manufacturing process efficiency positively and significantly influence manufacturing competitiveness. The findings suggest that the utilization of information is directly and positively related to manufacturing process efficiency, including reducing lead-time, decreasing work performance man-hours (M/H), and improving work accuracy. These improvements ultimately have a significant impact on manufacturing competitiveness. In conclusion, the use of smart manufacturing systems is becoming an integral part of the manufacturing industry. To gain a competitive edge, it will be necessary to introduce and utilize optimal smart manufacturing systems, taking into account the size of manufacturing firms.

Recently, in the manufacturing industry, changes in various environmental conditions and constraints appear rapidly. At this time, a dispatching system that allocates work to resources at an appropriate time plays an important role in improving the speed or quality of production. In general, a rule-based static dispatching method has been widely used. However, this static approach to a dynamic production environment with uncertainty leads to several challenges, including decreased productivity, delayed delivery, and lower operating rates, etc. Therefore, a dynamic dispatching method is needed to address these challenges. This study aims to develop a reinforcement learning-based dynamic dispatching system, in which dispatching agents learn optimal dispatching rules for given environmental states. The state space represents various information such as WIP(work-in-process) and inventory levels, order status, machine status, and process status. A dispatching agent selects an optimal dispatching rule that considers multiple objectives of minimizing total tardiness and minimizing the number of setups at the same time. In particular, this study targets a multi-area manufacturing system consisting of a flow-shop area and a cellular-shop area. Thus, in addition to the dispatching agent that manages inputs to the flow-shop, a dispatching agent that manages transfers from the flow-shop to the cellular-shop is also developed. These two agents interact closely with each other. In this study, an agent-based dispatching system is developed and the performance is verified by comparing the system proposed in this study with the existing static dispatching method.

This study optimized the gelling agent and rice protein ratio for developing elderly friendly jelly using a response surface methodology. Response surface analysis was conducted with a gelling agent (0.1, 0.2, and 0.3%) and rice protein (3, 6, and 9%) set as independent variables. Increasing the gelling agent and rice protein ratio raised the pH while lowering the total acidity. The sugar content decreased nonlinearly with a higher gelling agent ratio. The lightness (L) and yellowness (b) differed according to the addition ratios of each ingredient, and the hardness peaked at 0.3% gelling agent and 6% rice protein, but excessive rice protein addition led to a decrease in hardness. Response surface analysis indicated an optimal formulation of 0.16% gelling agent and 6.41% rice protein, with all response variables aligning within the predicted ranges, validating the model.

This study was conducted to verify the impact of hazardous risk factors in manufacturing workplaces on worker safety behaviors, focusing on the mediating effect of safety climate, and to establish safety management strategies in manufacturing workplaces and to suggest practical measures to improve worker safety. For this study, the results of the ‘10th Occupational Safety and Health Survey’ conducted by the Korea Occupational Safety and Health Agency’s Occupational Safety and Health Research Institute in 2021 were used as analysis data for 3,255 manufacturing workplaces with 20 or more regular workers. The data were analyzed using the SPSS 24.0 program for descriptive statistical analysis, validity and reliability verification, correlation and multiple regression analysis, and hierarchical regression analysis. As a result of the study, first, hazardous risk factors were confirmed to have a negative effect on workers' safety behaviors. Second, hazardous risk factors were confirmed to have a negative effect on safety climate. Third, safety climate was confirmed to have a positive effect on workers' safety behaviors. Fourth, it was verified that the safety climate had a partial mediating effect in the relationship between hazardous risk factors and workers’ safety behavior in the workplace. Through this study, it was found that hazardous risk factors had a negative effect on workers’ safety behavior. This emphasizes that efforts to systematically manage and minimize hazardous risk factors in the workplace are important in promoting workers’ safety behavior. In addition, it was confirmed that the safety climate had an important mediating effect in the relationship between hazardous risk factors and workers’ safety behavior. In other words, it can be seen that the safety climate can alleviate the negative effect of hazardous risk factors on workers’ safety behavior. These research results suggest that reducing hazardous risk factors in the workplace and improving the safety climate can have a positive effect on workers’ safety behavior practice, thereby preventing industrial accidents.

Organic-inorganic hybrid coating films have been used to increase the transmittance and enhance the physical properties of plastic substrates. Sol-gel organic-inorganic thin films were fabricated on polymethylmethacrylate (PMMA) substrates using a dip coater. Metal alkoxide precursor tetraethylsilicate (TEOS) and alkoxy silanes including decyltrimethoxysilane (DTMS), 3-glycidoxypropyltrimethoxysilane (GPTMS), phenyltrimethoxysilane (PTMS), 3-(trimethoxysilyl)propyl methacrylate (TMSPM) and vinyltrimethoxysilane (VTMS) were used to synthesize sol-gel hybrid coating solutions. Sol-gel synthesis was confirmed by the results of FT-IR. Cross-linking of the Si-O-Si network during synthesis of the sol-gel reaction was confirmed. The effects of each alkoxy silane on the coating film properties were investigated. All of the organicinorganic hybrid coatings showed improved transmittance of over 90 %. The surface hardness of all coating films on the PMMA substrate was measured to be 4H or higher and the average thickness of the coating films was measured to be about 500 nm. Notably, the TEOS/DTMS coating film showed excellent hydrophobic properties, of about 97°.

In this paper, we aim to improve the output quality of a food 3D printer through optimized component design and implementation. Existing 3D printers produce customized outputs according to consumer needs, but have problems with output speed and poor quality. In this paper, we aim to solve this problem through optimized design of unit parts such as the extruder, nozzle, guide, and external case. Fusion 360 was used for element design, and in the performance evaluation of the implemented system, the average precision was 0.06mm, which is higher than the non-repeatable precision of ±0.1㎜ of other products, and the feed speed of the existing system was evaluated to be more than twice as fast, from 70mm/s to 140mm/s. In the future, we plan to continuously research output elements that can produce texture and color and device control methods for convenience.