• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2305-2314
• /
• 2023

The governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and enables rapid simulations, but it can be difficult to apply to situations with complex model parameters. Recently, a method of solving PDEs using artificial neural networks called physics-informed neural network (PINN) has been proposed. The PINN assumes the latent (hidden) solution of a PDE as an arbitrary neural network model and approximates the solution by optimizing the model. Unlike a Gaussian model, the PINN is intuitive in that it does not require special assumptions and uses the original equation without modifications. In this paper, we describe an approach to atmospheric dispersion modeling using the PINN and show its applicability through simple case studies. The results are compared with analytic and fundamental numerical methods to assess the accuracy and other features. The proposed PINN approximates the solution with reasonable accuracy. Considering that its procedure is divided into training and prediction steps, the PINN also offers the advantage of rapid simulations once the training is over.

• Advances in Computational Design
• /
• 제7권1호
• /
• pp.1-17
• /
• 2022

In this study, a new strategy is presented to transmit the fundamental elastic beam problem into the modern optimization platform and solve it by using artificial intelligence (AI) tools. As a practical example, deflection of Euler-Bernoulli beam is mathematically formulated by 2nd-order ordinary differential equations (ODEs) in accordance to the classical beam theory. This fundamental engineer problem is then transmitted from classic formulation to its artificial-intelligence presentation where the behavior of the beam is simulated by using neural networks (NNs). The supervised training strategy is employed in the developed NNs implemented in the heuristic optimization algorithms as the fitness function. Different evolutionary optimization tools such as genetic algorithm (GA) and particle swarm optimization (PSO) are used to solve this non-linear optimization problem. The step-by-step procedure of the proposed method is presented in the form of a practical flowchart. The results indicate that the proposed method of using AI toolsin solving beam ODEs can efficiently lead to accurate solutions with low computational costs, and should prove useful to solve more complex practical applications.

• 한국소음진동공학회논문집
• /
• 제12권8호
• /
• pp.598-608
• /
• 2002

This paper shows the optimal design methodology for the fluid engine mount by the artificial life algorithm. The design has been commonly modified by trial and error because there is many design parameters that can be varied in order to minimize transmissibility at the desired fundamental resonant and notch frequencies. The application of trial and error method to optimization of the fluid mount is a great work. Many combinations of parameters are possible to give us the desired resonant and notch frequencies, but the question is which combination Provides the lowest resonant peak and notch depth. In this study the enhanced artificial life algorithm is applied to get the desired fundamental resonant and notch frequencies of a fluid mount and to minimize transmissibility at these frequencies. The present hybrid algorithm is the synthesis of and artificial life algorithm with the random tabu (R-tabu) search method. The hybrid algorithm has some advantages, which is not only faster than the conventional artificial life algorithm, but also gives a more accurate solution. In addition, this algorithm can find all globa1 optimum solutions. The results show that the performance of the optimized mount compared with the original mount is improved significantly.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2004년도 춘계 학술발표회 제16권1호
• /
• pp.680-683
• /
• 2004

This study is to obtain basic data concerned with properties of foam for foamed concrete and foaming method. Main factors of this study are types of foaming agents, temperature of solution with foaming agents, and types of foam generator. Testing items are size distribution of foam, foaming ratio to solution, and stability of foam. The results of this study were shown as follow. It is optimum condition of foam generator that length/diameter of foaming tube is 2.0, bead size within foaming tube is $4\~6mm$, and nozzle size of foaming tube is 10mm. AES and AOS are good results to produce high quality foam, and stability of foam is good in foaming temperature of $20^{\circ}C$.

• 대한화학회지
• /
• 제6권2호
• /
• pp.133-142
• /
• 1962

This study was carried out to investigate the lead-bismuth-sodium ternary system which a basis of the Dittmer method as a part of "the fundamental study of pyrometallurgical debismuthizing of lead". Thermodynamic properties of each liquid Pb-Bi, Pb-Na binaries as well as liquid Pb-Bi-Na ternary solution were measured by e.m.f. of these concentration cells, and those of each component were also determined. Furthermore, iso-activity lines including Pb rich side composition of Pb-Bi-Na ternary solution were determined. The relationship between those thermodynamic characteristics and tendency of intermetallic compound formation was discussed through the above experiments.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2011년도 추계 학술논문 발표대회
• /
• pp.41-42
• /
• 2011

The purpose of this study is not only fixation of carbon dioxide using the cement-saturated solution by wet carbonating reaction but also evaluate the possibility of storage technology of Carbon dioxide. wet carbonation is reaction of CO₂ injection by CO₂ reactor. As a result of experiment, the carbon dioxide is fixed, and high-purity Calcium Carbonate is eluted.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2012년도 춘계 학술논문 발표대회
• /
• pp.71-72
• /
• 2012

The purpose of this study is not only fixation of carbon dioxide using the cement-Paste solution's calcium ion by wet carbonating reaction but also quantitatively evaluate the possibility of storage technology of Carbon dioxide. wet carbonation is reaction of CO₂ injection by CO₂ reactor. As a result of experiment, the carbon dioxide is fixed, and high-purity Calcium Carbonate is eluted.

• 한국산학기술학회논문지
• /
• 제16권11호
• /
• pp.8064-8073
• /
• 2015

편미분방정식 해를 위한 효율적인 방법 중의 하나는 미분구적법이다. 이방법은 복잡한 구조 및 하중에 따른 컴퓨터 용량의 과도한 사용뿐만 아니라, 컴퓨터 프로그래밍의 복합알고리즘 해석상의 어려움 피하기 위해 많은 분야에 적용되어왔다. 아크축의 비신장 및 신장을 고려한 곡선보의 내평면 진동을, 미분구적법 (DQM)을 이용하여 해석하였다. 다양한 경계조건과 열림각에 따른 진동수을 계산하였다. DQM의 해석결과는, 비교 가능한 정확한 수학적 해법을 다른 수치해석결과와 비교하였다. DQM은 적은 격자점을 사용하고도 정확한 해석을 보여주었고, 다양한 변화에 따른 새로운 결과를 제시하였다.

• 한국방사성폐기물학회:학술대회논문집
• /
• 한국방사성폐기물학회 2005년도 Proceedings of The 6th korea-china joint workshop on nuclear waste management
• /
• pp.214-221
• /
• 2005

Spent ion-exchanged resin generated from various purification systems in CANDU reactor is causing concern due to a limited storage capacity and safe disposal. As a suggestion for a proper treatment technology for the spent ion-exchanged resin containing a high activity of C­14 radionuclide which would be classified as Class A and C wastes, a fundamental study for the development of C-14 removal technology from a spent resin was performed. The adsorption characteristics of the inactive $HCO_3^-$ ion and other ions in a stripping solution on IRN-150 mixed resin was evaluated and the removal technology of the $HCO_3^-$ ion adsorbed on IRN-150 by an alkaline stripping method was proposed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 A
• /
• pp.217-219
• /
• 1999

This paper presents a study of 2-dimensional(2-D) eddy current problem using boundary element method(BEM). When compared with finite element method(FEM), there are only a few unknown variables in BEM because it implements numerical analysis only for the surface or boundary of a model. As a result, a lot of computational memory and time can be saved. In order to analyze 2-D eddy current problem, potentials and its derivatives(flux) in a boundary are used as variables. The Mantel function of the second kind of the zero order is used here as a fundamental solution. In order to remove singularity and to solve the integral equations in a boundary, Subtracting Singularity Method and Gauss Quadrature Formula are adopted in this paper.