• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.2
• /
• pp.103-110
• /
• 2009

We are witnessing rapid increase of the number of wireless devices available today such as cell phones, PDAs, Wibro enabled devices. Because of the inherent limitation of the bandwidth available for wireless channels, broadcast systems have attracted the attention of the research community. The main problem in this area is to develop an efficient broadcast program. In this paper, we propose a dynamic broadcast method that overcomes the limitations of static broadcast programs. It optimizes the scheduling based on the probabilistic model of user requests. We show that dynamic broadcast system can indeed improve the quality of service using user requests. This paper extends our previous work in [1] to include more thorough explanation of the proposed methodology and diverse performance evaluation models.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• Journal of fish pathology
• /
• v.37 no.1
• /
• pp.97-110
• /
• 2024

The Serranidae is high-quality fish species with good meat quality and is traded at high price, and is attracting attention in South Korea as a cultured species that creates high added value. However, the high-density fish farming for mass production increases the risk of mass mortality due to infectious diseases, leading to enormous economic losses. Therefore, in order to safely prevent and protect farmed fish from serious infectious diseases, it is necessary to conduct disease monitoring on a regular basis. In this study, Hyporthodus septemfasciatus, Epinephelus moara, and the hybrid longtooth grouper (E. moara ♀×E. lanceolatus ♂) were collected once a month from fish farm of Garorim and Aquabiotech Co., Ltd for a total of six months, from July to December 2023. We investigated infections of five species of bacterial diseases, including Flavobacterium columnare, six species of viral diseases, including LCDV (lymphocystis disease virus), and parasitic pathogens in grouper farms. As the result, Vibrio vulnificus and V. harveyi were detected in H. septemfasciatus in August, in the case of viral diseases, NNV was detected in H. septemfasciatus from July to August using RT-PCR or PCR. Finally, In the case of parasitic diseases, Tricodina sp. was detected in E. moara and the hybrid longtooth grouper from August to December.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.65-74
• /
• 2024

In recent years, image processing technology has played a critical role in the field of autonomous driving. Among them, image recognition technology is essential for the safety and performance of autonomous vehicles. Therefore, this paper aims to develop a hybrid image recognition system to enhance the safety and performance of autonomous vehicles. In this paper, various image recognition technologies are utilized to construct a system that recognizes and tracks objects in the vehicle's surroundings. Machine learning and deep learning algorithms are employed for this purpose, and objects are identified and classified in real-time through image processing and analysis. Furthermore, this study aims to fuse image processing technology with vehicle control systems to improve the safety and performance of autonomous vehicles. To achieve this, the identified object's information is transmitted to the vehicle control system to enable appropriate autonomous driving responses. The developed hybrid image recognition system in this paper is expected to significantly improve the safety and performance of autonomous vehicles. This is expected to accelerate the commercialization of autonomous vehicles.

• Ocean Systems Engineering
• /
• v.13 no.4
• /
• pp.349-365
• /
• 2023

Targeting a floating wave and offshore wind hybrid power generation system (FWWHybrid) designed in the Republic of Korea, this study examines the impact of the interaction, with multiple wave energy converters (WECs) placed on the platform, on platform motion. To investigate how the motion of WECs affects the behavior of the FWWHybrid platform, it was numerically compared with a scenario involving a 'single-body' system, where multiple WECs are constrained to the platform. In the case of FWWHybrid, because the platform and multiple WECs move in response to waves simultaneously as a 'multi-body' system, hydrodynamic interactions between these entities come into play. Additionally, the power take-off (PTO) mechanism between the platform and individual WECs is introduced for power production. First, the hydrostatic/dynamic coefficients required for numerical analysis were calculated in the frequency domain and then used in the time domain analysis. These simulations are performed using the extended HARP/CHARM3D code developed from previous studies. By conducting regular wave simulations, the response amplitude operator (RAO) for the platform of both single-body and multi-body scenarios was derived and subsequently compared. Next, to ascertain the difference in response in the real sea environment, this study also includes an analysis of irregular waves. As the floating body maintains its position through connection to a catenary mooring line, the impact of the slowly varying wave drift load cannot be disregarded. To assess the influence of the 2^nd-order wave exciting load, irregular wave simulations were conducted, dividing them into cases where it was not considered and cases where it was included. The analysis of multi-degree-of-freedom behavior confirmed that the action of multiple WECs had a substantial impact on the platform's response.

• Journal of ILASS-Korea
• /
• v.29 no.3
• /
• pp.105-111
• /
• 2024

Although the classic Kelvin-Helmholtz model of aerodynamically driven jet breakup(primary breakup) has been widely employed in engine CFD codes for the last three decades, the model is not generally predictive. This lack of predictive capability points to the likelihood of an incorrect physical basis for the model formulation. As such, there have been more recent spray-model development efforts that incorporate additional sources of jet instability and breakup, including nozzle-generated turbulence and cavitation but predictive capabilities have remained elusive. Meanwhile, it should be noted that modern combustors increasingly operate under low-temperature combustion(LTC) conditions, where ambient densities and aerodynamic forces are much lower than under classical operating conditions. Therefore, further consideration of physical model formulation is needed. The previous literature introduced a new primary atomization modeling approach premised on experimental measurements by the Faeth group, which demonstrate that breakup is governed by nozzle-generated turbulence under low ambient density conditions. In this new modeling approach, termed the KH-Faeth model, two different primary breakup models are combined to allow the hybrid breakup modeling approach, i.e. Kelvin- Helmholtz instability breakup mechanism and turbulence-induced breakup are competed via dominant breakup rate evaluation. In the current work, we implement this hybrid KH-Faeth model within the open-source CFD framework OpenFOAM and validate the model against detailed drop sizing measurements stemming from collaborative experiments between Georgia Tech and Argonne National Laboratory.

• Restorative Dentistry and Endodontics
• /
• v.34 no.1
• /
• pp.51-60
• /
• 2009

The purpose of this study was to perform quantitative comparisons of water permeable zones in both the adhesive and the hybrid layer before and after thermo cycling in order to assess the integrity of the bonding interface. Twenty eight flat dentin surfaces were bonded with a light-cured composite resin using one of four commercial adhesives [OptiBond FL (OP), AdheSE (AD), Clearfil SE Bond (CL). and Xeno III (XE)]. These were sectioned into halves and subsequently cut to yield 2-mm thick specimens; one specimen for control and the other subjected to thermocycling for 10,000 cycles. After specimens were immersed in ammoniacal silver nitrate for 24 h and exposed to a photo developing solution for 8 h, the bonded interface was analyzed by scanning electron microscopy (SEM) and wavelength dispersive spectrometry (WDS) at five locations per specimen. Immediately after bonding. the adhesive layer of OP showed the lowest silver uptake, followed by CL, AD. and XE in ascending order (p < 0.0001); the hybrid layer of CL had the lowest silver content among the groups (p = 0.0039). After thermocycling, none of the adhesives manifested a significant increase of silver in either the adhesive or the hybrid layer. SEM demonstrated the characteristic silver penetrated patterns within the interface. It was observed that integrity of bonding was well maintained in OP and CL throughout the thermocycling process. Adhesive-tooth interfaces are vulnerable to hydrolytic degradation and its permeability varies in different adhesive systems, which may be clinically related to the restoration longevity.

• Journal of Wetlands Research
• /
• v.25 no.2
• /
• pp.145-158
• /
• 2023

Constructed wetlands (CWs) are effective technologies for urban wastewater management, utilizing natural physico-chemical and biological processes to remove pollutants. This study employed a bibliometric analysis approach to investigate the progress and future research trends in the field of CWs. A comprehensive review of 100 most-recently published and open-access articles was performed to analyze the performance of CWs in treating wastewater. Spain, China, Italy, and the United States were among the most productive countries in terms of the number of published papers. The most frequently used keywords in publications include water quality (n=19), phytoremediation (n=13), stormwater (n=11), and phosphorus (n=11), suggesting that the efficiency of CWs in improving water quality and removal of nutrients were widely investigated. Among the different types of CWs reviewed, hybrid CWs exhibited the highest removal efficiencies for BOD (88.67%) and TSS (95.67%), whereas VSSF, and HSSF systems also showed high TSS removal efficiencies (83.25%, and 78.83% respectively). VSSF wetland displayed the highest COD removal efficiency (71.82%). Generally, physical processes (e.g., sedimentation, filtration, adsorption) and biological mechanisms (i.e., biodegradation) contributed to the high removal efficiency of TSS, BOD, and COD in CW systems. The hybrid CW system demonstrated highest TN removal efficiency (60.78%) by integrating multiple treatment processes, including aerobic and anaerobic conditions, various vegetation types, and different media configurations, which enhanced microbial activity and allowed for comprehensive nitrogen compound removal. The FWS system showed the highest TP removal efficiency (54.50%) due to combined process of settling sediment-bound phosphorus and plant uptake. Phragmites, Cyperus, Iris, and Typha were commonly used in CWs due to their superior phytoremediation capabilities. The study emphasized the potential of CWs as sustainable alternatives for wastewater management, particularly in urban areas.

• Advances in aircraft and spacecraft science
• /
• v.5 no.1
• /
• pp.1-19
• /
• 2018

The present work shows many aspects concerning the use of a numerical wave-based methodology for the computation of the structural response of periodic structures, focusing on cylinders. Taking into account the periodicity of the system, the Bloch-Floquet theorem can be applied leading to an eigenvalue problem, whose solutions are the waves propagation constants and wavemodes of the periodic structure. Two different approaches are presented, instead, for computing the forced response of stiffened structures. The first one, dealing with a Wave Finite Element (WFE) methodology, proved to drastically reduce the problem size in terms of degrees of freedom, with respect to more mature techniques such as the classic FEM. The other approach presented enables the use of the previous technique even when the whole structure can not be considered as periodic. This is the case when two waveguides are connected through one or more joints and/or different waveguides are connected each other. Any approach presented can deal with deterministic excitations and responses in any point. The results show a good agreement with FEM full models. The drastic reduction of DoF (degrees of freedom) is evident, even more when the number of repetitive substructures is high and the substructures itself is modelled in order to get the lowest number of DoF at the boundaries.