• Composites Research
• /
• v.36 no.5
• /
• pp.329-334
• /
• 2023

The classical multiscale finite element (FE² ) method involves iterative calculations of micro-boundary value problems for representative volume elements at every integration point in macro scale, making it a computationally time and data storage space. To overcome this, we developed the data-driven multiscale analysis method based on the mean-field homogenization (MFH). Data-driven computational mechanics (DDCM) analysis is a model-free approach that directly utilizes strain-stress datasets. For performing multiscale analysis, we efficiently construct a strain-stress database for the microstructure of composite materials using mean-field homogenization and conduct data-driven computational mechanics simulations based on this database. In this paper, we apply the developed multiscale analysis framework to an example, confirming the results of data-driven computational mechanics simulations considering the microstructure of a hyperelastic composite material. Therefore, the application of data-driven computational mechanics approach in multiscale analysis can be applied to various materials and structures, opening up new possibilities for multiscale analysis research and applications.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.1
• /
• pp.13-21
• /
• 2020

Surrogate models have been used for the rapid estimation of six-DOF aerodynamic coefficients in the context of the design and control of a missile. For this end, we may generate highly accurate surrogate models with a multitude of aerodynamic data obtained from wind tunnel tests (WTTs); however, this approach is time-consuming and expensive. Thus, we aim to swiftly predict aerodynamic coefficients via co-Kriging using a few WTT data along with plenty of computational fluid dynamics (CFD) data. To demonstrate the excellence of co-Kriging models based on both WTT and CFD data, we first generated two surrogate models: co-Kriging models with CFD data and Kriging models without the CFD data. Afterwards, we carried out numerical validation and examined predictive trends to compare the two different surrogate models. As a result, we found that the co-Kriging models produced more accurate aerodynamic coefficients than the Kriging models thanks to the assistance of CFD data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.339-341
• /
• 2024

본 논문에서는 전기 자동차 배터리 팩 설계에서 성능 예측을 위해 전산유체해석 및 Long Short-Term Memory (LSTM)를 활용한다. 두 계산 모두의 예측이 상당한 유사성을 나타내며, 전산유체해석은 시스템 유체 역학을 고려한 상세한 물리 모델을 제공하고, LSTM은 시계열 데이터를 기반으로 한 딥러닝 모델로 효과적으로 패턴을 파악, 향후 온도 상승을 예측한다. 결과는 두 접근 모두가 효과적인 예측을 제공하며 향후 전기 자동차 배터리 팩 설계 및 최적화에서 종합적인 접근의 필요성을 강조한다. 특히, LSTM 기반 예측에 소요되는 시간은 계산 유체 역학의 약 25%로, 약 일주일 정도로 빠르게 확인 가능하다. 이는 현대 산업 환경에서 시간적 효율성이 중요한 측면을 강조하며, 계산 유체 역학의 상세한 물리 모델링과 LSTM의 빠른 예측 속도를 결합한 설계 방법론을 제안한다.

• Prospectives of Industrial Chemistry
• /
• v.22 no.4
• /
• pp.13-19
• /
• 2019

최근 가공할만한 성능의 슈퍼컴퓨터에 머신 러닝 기법을 연동한 인공 지능형 소재 정보학이 과학 기술 및 산업계에 새로운 연구개발 패러다임으로 급속히 확산되고 있다. 본 기고문에서는 이 기법의 성공에 핵심적 요소인 정확한 데이터베이스 구축을 위해 제일원리 전산을 적용하는 것과 이를 기반으로 소재를 구성하는 원소 간 인공 신경망 포텐셜을 만드는 방법을 소개하고자 한다. 이 연구 방법론은 나노 스케일 신소재 개발에 적용할 경우, 양자역학 수준의 정밀도로 순수 제일원리 전산 대비 100배 이상의 빠른 결과를 도출할 가능성이 있음을 예시한다. 이는 향후 다양한 산업계에 막대한 파급효과를 가져올 것으로 예상된다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.4
• /
• pp.263-272
• /
• 2021

In this study, aerodynamic coefficients obtained from Computational Fluid Dynamics (CFD) using wind tunnel test-like method is compared with coefficients obtained by actual wind tunnel test. Unsteady analysis has performed with using harmonic equation for motion of the external store. Aerodynamic database is generated based on CFD results to simulate 6 degree-of-freedom store separation analysis. Trajectory is obtained from simulation using both CFD-based and test-based database, and results are compared with trajectory from flight test result. It is concluded that generation of database based on CFD with wind tunnel test technique is valid from good agreement of the trajectory.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.41 no.2
• /
• pp.135-143
• /
• 2017

A customized CFD simulator to perform thermo-fluid dynamic simulations of an HVAC for an indoor space is presented. This simulation system has been developed for engineers studying architectural engineering, as the HVAC mechanical systems used in housings and buildings. Hence, all functions and options are so designed to be suitable that they are suitable for non-CFD experts as well as CFD engineers. A Computational mesh is generated by open-source libraries, FEMM (Finite Element Method Magnetics), and OpenFOAM. Once the boundary conditions are set, the fluid dynamic calculations are performed using the OpenFOAM solver. Numerical results are validated by comparing them with the experimental data for a simple indoor air flow case. In this paper, an entirely new calculation process is introduced, and the flow simulation results for a sample office room are also discussed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1274-1280
• /
• 2022

The resistance performance evaluation of general ships using computational fluid dynamics requires a lot of time and cost, and various methods are being studied to reduce the time and cost. Existing methods using main particulars or cross sections of ships have limitations in estimating resistance performance that is greatly dependent on the shape of the ship. In this paper, we propose a deep neural network model that can quickly predict the resistance performance of the hull surface by inputting the geometric information of the hullform mesh. The proposed deep neural network model based on Perceiver IO can immediately predict resistance performance, unlike computational fluid dynamics techniques that require calculation in each time step. It shows the result of estimating the resistance performance with an average error of less than 1% in the data set for a 50 K tanker ship, a type of low-speed full ship.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.339-346
• /
• 2023

The uncertainties of microstructural features affect the properties of materials. Numerous pores that are randomly distributed in materials make it difficult to predict the properties of the materials. The distribution of pores in cementitious materials has a great influence on their mechanical properties. Existing studies focus on analyzing the statistical relationship between pore distribution and material responses, and the correlation between them is not yet fully determined. In this study, the mechanical response of cementitious materials is predicted through an image-based data approach using a convolutional neural network (CNN), and the correlation between pore distribution and material response is analyzed. The dataset for machine learning consists of high-resolution micro-CT images and the properties (tensile strength) of cementitious materials. The microstructures are characterized, and the mechanical properties are evaluated through 2D direct tension simulations using the phase-field fracture model. The attributes of input images are analyzed to identify the spot with the greatest influence on the prediction of material response through CNN. The correlation between pore distribution characteristics and material response is analyzed by comparing the active regions during the CNN process and the pore distribution.

• Journal of KIISE
• /
• v.43 no.4
• /
• pp.419-429
• /
• 2016

Generating a 3D surface model from coronary artery segmentation helps to not only improve the rendering efficiency but also the diagnostic accuracy by providing physiological informations such as fractional flow reserve using computational fluid dynamics (CFD). This paper proposes a method to generate a triangular surface mesh using vessel structure information acquired with coronary artery segmentation. The marching cube algorithm is a typical method for generating a triangular surface mesh from a segmentation result as bit mask. But it is difficult for methods based on marching cube algorithm to express the lumen of thin, small and winding vessels because the algorithm only works in a three-dimensional (3D) discrete space. The proposed method generates a more accurate triangular surface mesh for each singular vessel using vessel centerlines, normal vectors and lumen diameters estimated during the process of coronary artery segmentation as the input. Then, the meshes that are overlapped due to branching are processed by mesh merging and merged into a coronary mesh.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.06a
• /
• pp.182.1-182.1
• /
• 2010

현재 전 세계적으로 가장 널리 개발하고 보급되어지고 있는 풍력산업의 시장 규모는 매년 확대되고 있다. 특히 소형 풍력발전 시스템은 낙도 등의 전력 공급이 어려운 지역에 경제성 있는 전력 보급을 가능하게 한다. 국내의 미전화 지역과 일반 가정에서 풍력 에너지 자원을 적극 활용 개발하기 위해서 보다 우수한 성능의 풍력발전기용 블레이드를 설계하고자, 공기역학적인 최적설계에 대해 연구함으로써 추후 보급형 풍력발전 시스템의 개발에 필요한 설계 기술을 확립하고자한다. 본 연구는 설계된 블레이드의 유동해석 및 성능예측을 위하여 경제적으로 많은 지원이 필요한 대규모 풍동실험이 아닌 상용 CFD를 사용하여 보다 효율적으로 우수한 성능을 가지는 풍력 터빈을 설계함에 있다. Reynolds Averaged Navier-Stokes 방정식에 기반을 둔 CFD의 경우 이론적으로 명확한 해석이 가능하고, 실제 터빈의 운전 환경과 동일한 다양한 물리적 변수를 입력 데이터로서 활용할 수 있는 장점이 있기 때문에 풍력 터빈의 설계 과정에서 반영된 미소한 블레이드 형상변화 및 운전 조건의 변화에 따른 유동장의 변화 및 풍력터빈 성능을 정확히 예측할 수 있는 장점을 가지고 있다.