• 천문학회보
• /
• 제44권1호
• /
• pp.82.3-82.3
• /
• 2019

In this study, we generate future full disk magnetograms in 12, 24, 36 and 48 hours advance from SDO/HMI images using deep learning. To perform this generation, we apply the convolutional generative adversarial network (cGAN) algorithm to a series of SDO/HMI magnetograms. We use SDO/HMI data from 2011 to 2016 for training four models. The models make AI-generated images for 2017 HMI data and compare them with the actual HMI magnetograms for evaluation. The AI-generated images by each model are very similar to the actual images. The average correlation coefficient between the two images for about 600 data sets are about 0.85 for four models. We are examining hundreds of active regions for more detail comparison. In the future we will use pix2pix HD and video2video translation networks for image prediction.

• Journal of Astronomy and Space Sciences
• /
• 제21권4호
• /
• pp.361-370
• /
• 2004

본 연구에서는 행성간 탐사선의 정밀궤도결정에 필수적인 심우주 추적망(Deep Space Network, DSN) 관측모델을 개발하였다. DSN 관측모델은 DSN 관측시 발생하는 오차를 모델링하여 실제 DSN 관측값과 동일한 관측값을 생성하는 역할을 수행한다. 본 연구의 목적은 행성간 탐사선 정밀궤도결정 과정의 일환인 DSN 관측모델을 개발하는 것이다. DSN 관측모델에는 대류층, 이온층과 안테나 옵셋 오차 모델을 포함시켰으며 임무에 따라 변하는 파라미터 값도 적용하였다. 또한 DSN 관측모델을 3개의 DSN 지상국에서 방위각-고도 마운트를 사용하는 모든 안테나에 대해 구현하였다. 고려한 오차모델의 결과값과 JPL 결과값을 비교해 본 결과, 모든 오차모델 값이 JPL에서 제시한 허용오차 범위인 $10\%$ 내에 있음을 확인하였다. 오차모델과 파라미터를 고려하여 실제 관측과 동일한 DSN 관측값을 생성하였으며, 이를 통해 본 연구에서 개발된 관측모델이 향후 우리 나라 행성간 탐사 임무시 정밀궤도 결정을 위한 관측모델로 활용 가능함을 확인하였다.

• Journal of Astronomy and Space Sciences
• /
• 제34권3호
• /
• pp.213-223
• /
• 2017

The deep space orbit determination software (DSODS) is a part of a flight dynamic subsystem (FDS) for the Korean Pathfinder Lunar Orbiter (KPLO), a lunar exploration mission expected to launch after 2018. The DSODS consists of several sub modules, of which the orbit determination (OD) module employs a weighted least squares algorithm for estimating the parameters related to the motion and the tracking system of the spacecraft, and subroutines for performance improvement and detailed analysis of the orbit solution. In this research, DSODS is demonstrated and validated at lunar orbit at an altitude of 100 km using actual Lunar Prospector tracking data. A set of a priori states are generated, and the robustness of DSODS to the a priori error is confirmed by the NASA planetary data system (PDS) orbit solutions. Furthermore, the accuracy of the orbit solutions is determined by solution comparison and overlap analysis as about tens of meters. Through these analyses, the ability of the DSODS to provide proper orbit solutions for the KPLO are proved.

• Journal of Astronomy and Space Sciences
• /
• 제35권4호
• /
• pp.295-308
• /
• 2018

In this study, orbit determination (OD) simulation for the Korea Pathfinder Lunar Orbiter (KPLO) was accomplished for investigation of the observational arc-length effect using a sequential estimation algorithm. A lunar polar orbit located at 100 km altitude and $90^{\circ}$ inclination was mainly considered for the KPLO mission operation phase. For measurement simulation and OD for KPLO, the Analytical Graphics Inc. Systems Tool Kit 11 and Orbit Determination Tool Kit 6 software were utilized. Three deep-space ground stations, including two deep space network (DSN) antennas and the Korea Deep Space Antenna, were configured for the OD simulation. To investigate the arc-length effect on OD, 60-hr, 48-hr, 24-hr, and 12-hr tracking data were prepared. Position uncertainty by error covariance and orbit overlap precision were used for OD performance evaluation. Additionally, orbit prediction (OP) accuracy was also assessed by the position difference between the estimated and true orbits. Finally, we concluded that the 48-hr-based OD strategy is suitable for effective flight dynamics operation of KPLO. This work suggests a useful guideline for the OD strategy of KPLO mission planning and operation during the nominal lunar orbits phase.

• 한국항공우주학회지
• /
• 제49권3호
• /
• pp.197-204
• /
• 2021

유도탄의 비행 시험 중 고장 또는 비정상적인 기동이 발생하는 경우 비행을 계속하지 않도록 의도적으로 자폭한다. 이때 파편이 발생하며 안전 지역을 벗어났는지 여부를 실시간으로 추정하는 것이 중요하다. 본 논문에서는 Fully-Connected Neural Network(FCNN)를 이용하여 실시간으로 파편의 예상 낙하 영역 및 낙하 시간을 추정하는 방법을 제안한다. 많은 양의 학습 데이터 생성을 위해 Unscented Transform(UT)를 적용하였으며 신뢰도 확보를 위해 Monte-Carlo(MC) 시뮬레이션과 비교하여 파라미터를 선정하였다. 또한 제안한 방법의 추정 결과를 MC와 비교하여 성능을 분석하였다.

• 한국항공우주학회지
• /
• 제50권5호
• /
• pp.317-323
• /
• 2022

본 논문에서는 c-스파 단면을 갖는 복합재 로터 블레이드에 대해 co-rotational(CR) 이론 기반 비선형 쉘 요소를 사용하는 In-house code를 통해 고유진동수를 구하고, 이를 이용하여 블레이드의 진동특성을 예측하는 심층신경망 모델을 개발하였다. 심층신경망 모델은 무작위 두께 분포를 갖는 데이터와 스팬 방향으로 두께 감소 경향성을 보이는 데이터를 통해 심층신경망 모델의 정확성을 평가하였다.

• 한국항공우주학회지
• /
• 제45권9호
• /
• pp.794-806
• /
• 2017

지속적으로 우주파편이 증가하고 있는 상황에서 국가 우주자산을 안전하게 보호하고 우주개발국으로서 우주환경 보호에 관심을 가지는 것은 중요하다. 우주파편의 급격한 증가를 막기 위한 효과적인 방법 중 하나는 충돌위험이 큰 우주파편들, 그리고 임무가 종료된 폐기위성을 직접 제거해 나가는 것이다. 본 논문에서는 영상기반 우주파편 추적시스템의 안정적인 인식모델을 위해 인공신경망을 적용한 연구에 대해 다루었다. 한국항공우주연구원에서 개발한 지상기반 우주쓰레기 청소위성 테스트베드인 KARICAT을 활용하여 우주환경이 모사된 영상을 획득하였고, 깊이불연속성에 기인한 영상분할 후 각 객체에 대한 구조 및 색상 기반 특징을 부호화한 벡터를 추출하였다. 특징벡터는 3차원 표면적, 점군의 주성분 벡터, 2차원 형상정보, 색상기반 정보로 구성되어있으며, 이 범주를 기반으로 분리한 특징벡터를 입력으로 하는 인공신경망 모델을 설계하였다. 또한 인공신경망의 성능 향상을 위해 입력되는 특징벡터의 범주에 따라 모델을 분할하여 각 모델 별 학습 후 앙상블기법을 적용하였다. 적용 결과 앙상블 기법에 따른 인식 모델의 성능 향상을 확인하였다.

• 천문학회보
• /
• 제42권2호
• /
• pp.82.2-82.2
• /
• 2017

Korea Microlensing Telescope Network (KMTNet) is one of powerful tools for investigating primordial objects in the inner solar system in that it covers a large area of the sky ($2{\times}2$ degree2) with a high observational cadence. The Deep Ecliptic Patrol of the Southern sky (DEEP-South) survey has been scanning the southern sky using KMTNet for non-bulge time (45 full nights per year) [1] since 2015 for examining color, albedo, rotation, and shape of the solar system bodies. Since 2017 January, we have launched a new collaborative group between Korea Astronomy and Space Science Institute (KASI) and Seoul National University (SNU) with support from KASI to reinforce mutual collaboration among these institutes and further to enhance human resources development by utilizing the KMTNet/DEEP-South data. In particular, we focus on the detection of comets and asteroids spontaneously scanned in the DEEP-South for (1) investigating the secular changes in comet's activities and (2) analyzing precovery and recovery images of objects in the NASA's NEOWISE survey region. In this presentation, we will describe our scientific objectives and current status on using KMTNet data, which includes updating the accuracy of the world coordinate system (WCS) information, finding algorithm of solar system bodies in the image, and doing non-sidereal photometry.

• Architectural research
• /
• 제26권1호
• /
• pp.1-12
• /
• 2024

This study introduces a deep reinforcement learning (DRL)-based methodology for optimizing apartment space arrangements, addressing the limitations of human capability in evaluating all potential spatial configurations. Leveraging computational power, the methodology facilitates the autonomous exploration and evaluation of innovative layout options, considering architectural principles, legal standards, and client re-quirements. Through comprehensive simulation tests across various apartment types, the research demonstrates the DRL approach's effec-tiveness in generating efficient spatial arrangements that align with current design trends and meet predefined performance objectives. The comparative analysis of AI-generated layouts with those designed by professionals validates the methodology's applicability and potential in enhancing architectural design practices by offering novel, optimized spatial configuration solutions.

• 천문학회보
• /
• 제44권2호
• /
• pp.43.1-43.1
• /
• 2019

In this study, we apply a deep learning model to denoising solar magnetograms. For this, we design a model based on conditional generative adversarial network, which is one of the deep learning algorithms, for the image-to-image translation from a single magnetogram to a denoised magnetogram. For the single magnetogram, we use SDO/HMI line-of-sight magnetograms at the center of solar disk. For the denoised magnetogram, we make 21-frame-stacked magnetograms at the center of solar disk considering solar rotation. We train a model using 7004 paris of the single and denoised magnetograms from 2013 January to 2013 October and test the model using 1432 pairs from 2013 November to 2013 December. Our results from this study are as follows. First, our model successfully denoise SDO/HMI magnetograms and the denoised magnetograms from our model are similar to the stacked magnetograms. Second, the average pixel-to-pixel correlation coefficient value between denoised magnetograms from our model and stacked magnetogrmas is larger than 0.93. Third, the average noise level of denoised magnetograms from our model is greatly reduced from 10.29 G to 3.89 G, and it is consistent with or smaller than that of stacked magnetograms 4.11 G. Our results can be applied to many scientific field in which the integration of many frames are used to improve the signal-to-noise ratio.