• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.27 no.1
• /
• pp.55-70
• /
• 2024

The loss of biodiversity poses a significant threat not only to business sustainability and investment risk but also to societal well-being. Nature serves as a crucial driver for long-term business viability and economic prosperity. The Task Force on Nature-related Financial Disclosures (TNFD), established in September 2023, mandates that companies assess and disclose their impacts on nature. Despite this, many businesses lack a full understanding of their reliance on and impact upon natural capital and ecosystem services, leading to insufficient disclosures. This study evaluates the applicability of TNFD's assessment methodologies and indicators within a domestic context, highlighting the condition of nature and ecosystem services, and exploring potential synergies with national biodiversity policies. Our analysis suggests that TNFD necessitates a unique approach to the spatial and temporal data and methodologies traditionally employed in environmental impact assessments. This includes assessing the reciprocal influences of corporate activities on natural capital and ecosystem services via the LEAP framework. Moreover, in industries where the choice of specific indicators depends on unique sectoral traits, developing a standardized strategy for data and assessment indicators-adapted to local conditions-is crucial due to the variability in the availability of assessment tools and data. The proactive engagement of the private sector in ecosystem restoration projects is particularly promising for contributing towards national biodiversity objectives. Although TNFD is in its nascent phase, its global adoption by numerous companies signifies its potential impact. Successful implementation of TNFD is anticipated to deepen businesses' and financial institutions' understanding of natural capital and ecosystem services, thereby reinforcing their commitment to sustainable development.

• Steel and Composite Structures
• /
• v.51 no.1
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.

• Nuclear Engineering and Technology
• /
• v.56 no.3
• /
• pp.973-979
• /
• 2024

In the framework of the Generation IV research and development project, in which the French Commission of Alternative and Atomic Energies (CEA) is involved, a main objective for the design of Sodium-cooled Fast Reactor (SFR) is to meet the safety goals for severe accidents. Among the severe ones, the Unprotected Transient OverPower (UTOP) accidents can lead very quickly to a global melting of the core. UTOP accidents can be considered either as slow during a Control Rod Withdrawal (CRW) or as fast. The paper focuses on fast UTOP accidents, which occur in a few milliseconds, and three different scenarios are considered: rupture of the core support plate, uncontrolled passage of a gas bubble inside the core and core mechanical distortion such as a core flowering/compaction during an earthquake. Several levels and rates of reactivity insertions are also considered and the thermal-mechanical behavior of an ASTRID fuel pin from the ASTRID CFV core is simulated with the GERMINAL code. Two types of fuel pins are simulated, inner and outer core pins, and three different burn-up are considered. Moreover, the feedback from the CABRI programs on these type of transients is used in order to evaluate the failure mechanism in terms of kinetics of energy injection and fuel melting. The CABRI experiments complete the analysis made with GERMINAL calculations and have shown that three dominant mechanisms can be considered as responsible for pin failure or onset of pin degradation during ULOF/UTOP accident: molten cavity pressure loading, fuel-cladding mechanical interaction (FCMI) and fuel break-up. The study is one of the first step in fast UTOP accidents modelling with GERMINAL and it has shown that the code can already succeed in modelling these type of scenarios up to the sodium boiling point. The modeling of the radial propagation of the melting front, validated by comparison with CABRI tests, is already very efficient.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1153-1164
• /
• 2024

In recent years, unmanned ground vehicles (UGVs) have been used to search for lost or stolen radioactive sources to avoid radiation exposure for operators. To achieve autonomous localization of radioactive sources, the UGVs must have the ability to automatically determine the next radiation measurement location instead of following a predefined path. Also, the radiation field of radioactive sources has to be reconstructed or inverted utilizing discrete measurements to obtain the radiation intensity distribution in the area of interest. In this study, we propose an effective source localization framework and method, in which UGVs are able to autonomously explore in the radiation area to determine the location of radioactive sources through an iterative process: path planning, radiation field reconstruction and estimation of source location. In the search process, the next radiation measurement point of the UGVs is fully predicted by the design path planning algorithm. After obtaining the measurement points and their radiation measurements, the radiation field of radioactive sources is reconstructed by the Gaussian process regression (GPR) model based on machine learning method. Based on the reconstructed radiation field, the locations of radioactive sources can be determined by the peak analysis method. The proposed method is verified through extensive simulation experiments, and the real source localization experiment on a Cs-137 point source shows that the proposed method can accurately locate the radioactive source with an error of approximately 0.30 m. The experimental results reveal the important practicality of our proposed method for source autonomous localization tasks.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.209-217
• /
• 2024

Recent years have seen a notable increase in fire incidents in university cafeterias, yet the social attention to these occurrences remains limited. Despite quick responses to these incidents preventing loss of life, the need for large-scale evacuation in such high foot traffic areas can cause significant disruptions, economic losses, and panic among students. The potential for stampedes and unpredictable damage during inadequate evacuations underscores the importance of fire safety and evacuation research in these settings. Previous studies have explored evacuation models in various university environments, emphasizing the influence of environmental conditions, personal characteristics, and behavioral patterns on evacuation efficiency. However, research specifically focusing on university cafeterias is scarce. This paper addresses this gap by employing Pathfinder software to analyze fire spread and evacuation safety in a university cafeteria. Pathfinder, an advanced emergency evacuation assessment system, offers realistic 3D simulations, crucial for intuitive and scientific evacuation analysis. The studied cafeteria, encompassing three floors and various functional areas, often exceeds a capacity of 1500 people, primarily students, during peak times. The study includes constructing a model of the cafeteria in Pathfinder and analyzing evacuation scenarios under different fire outbreak conditions on each floor. The paper sets standard safe evacuation criteria (ASET > RSET) and formulates three distinct evacuation scenarios, considering different fire outbreak locations and initial evacuation times on each floor. The simulation results reveal the impact of the fire's location and the evacuation preparation time on the overall evacuation process, highlighting that fires on higher floors or longer evacuation preparation times tend to reduce overall evacuation time.In conclusion, the study emphasizes a multifaceted approach to improve evacuation safety and efficiency in educational settings. Recommendations include expanding staircase widths, optimizing evacuation routes, conducting regular drills, strengthening command during evacuations, and upgrading emergency facilities. The use of information and communication technology for managing emergencies is also suggested. These measures collectively form a comprehensive framework for ensuring safety in educational institutions during fire emergencies.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.38 no.2
• /
• pp.49-58
• /
• 2024

The rapid advancement of generative large language models has revolutionized various real-life domains, emphasizing the importance of exploring their applications in healthcare. This study aims to examine how generative large language models are implemented in the medical domain, with the specific objective of searching for the possibility and potential of integration between generative large language models and East Asian medicine. Through a comprehensive current state analysis, we identified limitations in the deployment of generative large language models within East Asian medicine and proposed directions for future research. Our findings highlight the essential need for accumulating and generating structured data to improve the capabilities of generative large language models in East Asian medicine. Additionally, we tackle the issue of hallucination and the necessity for a robust model evaluation framework. Despite these challenges, the application of generative large language models in East Asian medicine has demonstrated promising results. Techniques such as model augmentation, multimodal structures, and knowledge distillation have the potential to significantly enhance accuracy, efficiency, and accessibility. In conclusion, we expect generative large language models to play a pivotal role in facilitating precise diagnostics, personalized treatment in clinical fields, and fostering innovation in education and research within East Asian medicine.

• Smart Structures and Systems
• /
• v.33 no.3
• /
• pp.189-199
• /
• 2024

To properly extract the strain components under varying operational conditions is very important in bridge health monitoring. The abnormal sensor readings can be correctly identified and the expected operational performance of the bridge can be better understood if each strain components can be accurately quantified. In this study, strain components under varying load conditions, i.e., temperature variation and live-load variation are evaluated based on field strain measurements collected from a real concrete box-girder bridge. Temperature-induced strain is mainly regarded as the trend variation along with the ambient temperature, thus a smoothing technique based on the wavelet packet decomposition method is proposed to estimate the temperature-induced strain. However, how to effectively extract the vehicle-induced strain is always troublesome because conventional threshold setting-based methods cease to function: if the threshold is set too large, the minor response will be ignored, and if too small, noise will be introduced. Therefore, an autoencoder framework is proposed to evaluate the vehicle-induced strain. After the elimination of temperature and vehicle-induced strain, the left of which, defined as the model error, is used to assess the operational performance of the bridge. As empirical techniques fail to detect the degraded state of the structure, a clustering technique based on Gaussian Mixture Model is employed to identify the damage occurrence and the validity is verified in a simulation study.

• Herbal Formula Science
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2024

Objective : This study aims to assess the potential of utilizing large language models in pattern identification education by developing a simulated patient with fatigue and dual deficiency of the heart-spleen pattern. Methods : A simulated patient dataset was constructed using the clinical practice examination module provided by the National Institute for Korean Medicine Development. The dataset was divided into patient characteristics, sample questions, and responses, and utilized to design the system, assistant, and user prompts, respectively. A web-based interface was developed using the Django framework and WebSocket. Results : We developed a simulated fatigue patient representing dual deficiency of the heart-spleen pattern through prompt engineering. To make practical tools, we further implemented web-based interfaces for the examinee's and evaluator's roles. The interface for examinees allows one to examine the simulated patient and provides access to a personalized number for future access. In addition, the interface for evaluators included a page that provided an overview of each examinees' chat history and evaluation criteria in real-time. Conclusion : This study is the first development of an educational tool integrated with a large language model for pattern identification education, which is expected to be widely applied to Korean medicine education.

• Ocean Systems Engineering
• /
• v.14 no.2
• /
• pp.171-210
• /
• 2024

This paper focuses on the rigorous and holistic fatigue analysis of mooring chains for a deep draft semi-submersible platform in the challenging environment of the central Gulf of Mexico (GoM). Known for severe hurricanes and strong loop/eddy currents, this region significantly impacts offshore structures and their mooring systems, necessitating robust designs capable of withstanding extreme wind, wave and current conditions. Wave scatter and current bin diagrams are utilized to assess the probabilistic distribution of waves and currents, crucial for calculating mooring chain fatigue. The study evaluates the effects of Vortex Induced Motion (VIM), Out-of-Plane-Bending (OPB), and In-Plane-Bending (IPB) on mooring fatigue, alongside extreme single events such as 100-year hurricanes and loop/eddy currents including ramp-up and ramp-down phases, to ensure resilient mooring design. A detailed case study of a deep draft semi-submersible platform with 16 semi-taut moorings in 2,500 meters of water depth in the central GoM provides insights into the relative contributions of wave scatter diagram, VIMs from current bin diagram, the combined stresses of OPB/IPB/TT and extreme single events. By comparing these factors, the study aims to enhance understanding and optimize mooring system design for safety, reliability, and cost-effectiveness in offshore operations within the central GoM. The paper addresses a research gap by proposing a holistic approach that integrates findings from various contributions to advance current practices in mooring design. It presents a comprehensive framework for fatigue analysis and design optimization of mooring systems in the central GoM, emphasizing the critical importance of considering environmental conditions, OPB/IPB moments, and extreme single events to ensure the safety and reliability of mooring systems for offshore platforms.