• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.100-105
• /
• 2024

In this study, we propose an alternative approach using Artificial Neural Networks (ANN) for determining Mass Attenuation Coefficients (MAC) in various glass systems. This method takes into account the weights of glass compositions, density, and photon energy as input features. The ANN model was trained and tested on a dataset consisting of 650 data points and subsequently validated through a K-fold cross-validation procedure. Our findings demonstrate a high level of accuracy, with R² values ranging from 0.90 to 0.99. Additionally, the model exhibits robust extrapolation capabilities with an R² score of 0.87 for predicting MAC values in a new glass system. Furthermore, this approach significantly reduces the need for costly and time-consuming computations and experiments, making it a potential tool for selecting materials for effective radiation protection.

• Interaction and multiscale mechanics
• /
• v.6 no.4
• /
• pp.339-356
• /
• 2013

This paper investigates the optimized parameters of Tuned Mass Dampers (TMDs) for vibration control of high-rise structures including Soil Structure Interaction (SSI). The Artificial Bee Colony (ABC) method is employed for optimization. The TMD Mass, damping coefficient and spring stiffness are assumed as the design variables of the controller; and the objective is set as the reduction of both the maximum displacement and acceleration of the building. The time domain analysis based on Newmark method is employed to obtain the displacement, velocity and acceleration of different stories and TMD in response to 6 types of far field earthquakes. The optimized mass, frequency and damping ratio are then formulated for different soil types; and employed for the design of TMD for the 40 and 15 story buildings and 10 different earthquakes, and well results are achieved. This study leads the researchers to the better understanding and designing of TMDs as passive controllers for the mitigation of earthquake oscillations.

• Nuclear Engineering and Technology
• /
• v.49 no.7
• /
• pp.1555-1562
• /
• 2017

A loose part monitoring system is used to identify unexpected loose parts in a nuclear reactor vessel or steam generator. It is still necessary for the mass estimation of loose parts, one function of a loose part monitoring system, to develop a new method due to the high estimation error of conventional methods such as Hertz's impact theory and the frequency ratio method. The purpose of this study is to propose a mass estimation method using a Markov decision process and compare its performance with a method using an artificial neural network model proposed in a previous study. First, how to extract feature vectors using discrete cosine transform was explained. Second, Markov chains were designed with codebooks obtained from the feature vector. A 1/8-scaled mockup of the reactor vessel for OPR1000 was employed, and all used signals were obtained by impacting its surface with several solid spherical masses. Next, the performance of mass estimation by the proposed Markov model was compared with that of the artificial neural network model. Finally, it was investigated that the proposed Markov model had matching error below 20% in mass estimation. That was a similar performance to the method using an artificial neural network model and considerably improved in comparison with the conventional methods.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.8
• /
• pp.2403-2409
• /
• 2014

Absolute isotope ratio is a critical constituent in determination of atomic weight. To measure the absolute isotope ratio using a mass spectrometer, mass discrimination factor, $f_{MD}$, is needed to convert measured isotope ratio to real isotope ratio of gas molecules. If the $f_{MD}$ could be predicted, absolute isotope ratio of a chemical species would be measureable in absence of its enriched isotope pure materials or isotope references. This work employed gravimetrically prepared isotope mixtures of argon (Ar) to obtain $f_{MD}$ at m/z of 40 in the magnetic sector type gas mass spectrometer (gas/MS). Besides, we compare the nitrogen isotope ratio of nitrogen trifluoride ($NF_3$) with that of nitrogen molecule ($N_2$) decomposed from the same $NF_3$ thermally in order to identify the difference of $f_{MD}$ values in extensive m/z region from 28 to 71. Our result shows that $f_{MD}$ at m/z 40 was $-0.044%{\pm}0.017%$ (k = 1) from measurement of Ar artificial isotope mixtures. The $f_{MD}$ difference in the range of m/z from 28 to 71 is observed $-0.12%{\pm}0.14%$ from $NF_3$ and $N_2$. From combination of this work and reported $f_{MD}$ values by another team, IRMM, if $f_{MD}$ of $-0.16%{\pm}0.14%$ is applied to isotope ratio measurement from $N_2$ to $SF_6$, we can determine absolute isotope ratio within relative uncertainty of 0.2 %.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.5
• /
• pp.43-47
• /
• 2012

A evaluation for the strength of rock includes a lot of uncertainty due to existence of discontinuity surface and weakness plain in the rock mass, so essential test results and other data for the resonable strength analysis are absolutely insufficient. Therefore, a analytical technique to reduce such uncertainty can be required. A probabilistic analysis technique has mainly to make up for the uncertainty to investigate the strength of rock mass. Recently, a artificial neural networks, as a more newly analysis method to solve several problems in the existing analysis methodology, trends to apply to study on the rock strength. In this study the unconfined compressive strength from basic physical property values of sedimentary rock, black shale and red shale, distributed in Daegu metropolitan area is estimated, using the artificial neural networks. And the applicability of the analysis method is investigated. From the results, it is confirmed that the unconfined compressive strength of the sedimentary rock can be easily and efficiently predicted by the analysis technique with the artificial neural networks.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.99-107
• /
• 2021

In addition to the 4th Industrial Revolution and Industry 4.0, the recent megatrends in the ICT field are Big-data, IoT, Cloud Computing, and Artificial Intelligence. Therefore, rapid digital transformation according to the convergence of various industrial areas and ICT fields is an ongoing trend that is due to the development of technology of AI services suitable for the era of the 4th industrial revolution and the development of subdivided technologies such as (Business Intelligence), IA (Intelligent Analytics, BI + AI), AIoT (Artificial Intelligence of Things), AIOPS (Artificial Intelligence for IT Operations), and RPA 2.0 (Robotic Process Automation + AI). This study aims to integrate and advance various machine learning services of infrastructure-side GPU, CDA (Connected Data Architecture) framework, and AI based on mass distributed Abyss storage in accordance with these technical situations. Also, we want to utilize AI business revenue model in various industries.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.45 no.4
• /
• pp.234-242
• /
• 2009

To develop the artificial spawning seaweeds of the sandfish, Arctoscopus japonicus, the effects by the material type of artificial spawning seaweeds were investigated at Dongsan port in Gangwon-do from December 2006 to March 2007. Sargassum fulvellum, S. horneri, rope and net were used as materials for artificial spawning seaweeds, and the most effective thing among them was S. fulvellum. A. japonicus began to attach the egg mass to artificial spawning seaweeds when sea temperature dropped below 10${^{\circ}C}$ in December, spawned heavily when it was around 8${^{\circ}C}$ in January, and completed the behavior when it started to increase over 10${^{\circ}C}$ in February. The hatching period of eggs was estimated to be about 60 days. The middle position in artificial spawning seaweed had the highest number of egg masses and the diameter of the egg mass ranged from 25mm to 62mm. Based on the result for the effects, the artificial spawning seaweeds of A. japonicus were developed and it is possible to use them to form seaweed forests or spawning grounds of other species.

• Tunnel and Underground Space
• /
• v.3 no.1
• /
• pp.63-79
• /
• 1993

The design of tunnels in rock masses often demands more informations on geologic features and rock mass properties than acquired by usual field survey and laboratory testings. In practice, the situation that a perfect set of geological and mechanical input data is given to geomechanics design engineer is rare, while the engineers are asked to achieve a high level of reliability in their design products. This study presents an artificial neural network which is developed to resolve the difficulties encountered in conventional design techniques, particulary the problem of deteriorating the confidence of existing numerical techniques such as the finite element, boundary element and distinct element methods due to the incomplete adn vague input data. The neural network has inferring capabilities to identify the possible failure modes, support requirements and its timing for underground openings, from previous case histories. Use of the neural network has resulted in a better estimate of the correlation between systems of rock mass classifications such as the RMR and Q systems. A back propagation learning algorithm together with a multi-layer network structure is adopted to enhance the inferential accuracy and efficiency of the neural network. A series of experiments comparing the results of the neural network with the actual field observations are performed to demonstrate the abilities of the artificial neural network as a new tunnel design assistance system.

• Journal of Mechanical Science and Technology
• /
• v.14 no.7
• /
• pp.705-714
• /
• 2000

The formulation of Smoothed Particle Hydrodynamics (SPH) and a shortcoming of traditional SPH in contact simulation are presented. A contact algorithm is proposed to treat contact phenomenon between two objects. We describe the boundary of the objects with non-mass artificial particles and set vectors normal to the contact surface. Contact criterion using non-mass particles is established in this study. In order to verify the contact algorithm, an algorithm is implemented in to an in-house program; elastic wave propagation is an analysed under low velocity axial impact of two rods. The results show that the contact algorithm eliminates the undesirable phenomena at the contact surface; numerical result with the contact algorithm is compared with theoretical one.

• Korean journal of applied entomology
• /
• v.62 no.4
• /
• pp.287-293
• /
• 2023

A lot of individuals of Mythimna loreyi have been attracted to the sex-pheromone traps of Spodoptera frugiperda during recent few years. However, there is no information about this pest. Thus, an efficient mass-rearing method of M. loreyi is demanded to study this pest. In this study, we compared the effects of artificial diets and rearing methods on its larval development and oviposition to suggest an efficient mass-rearing method of M. loreyi. Between S. frugipera and Agrotis ipsilon artificial diets, A. ipsilon diet showed more rapid larval development with higher survivorship, and decreased pupa weights and oviposition numbers compared to S. frugipera diet. Moreover, a grouping rearing caused more rapid larva development, decreased pupa weight and survivorship compared to an individual rearing. Therefore, for mass-rearing of M. loreyi, it is considered efficient to rear the newly emerged larvae in groups using A. ipsilon artificial diet and then rearing them individually after second or third larval stadium.