http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
화재방호 설비 설계 자동화를 위한 선행연구 및 기술 분석
홍성협,최두찬,이광호,Hong, Sung-Hyup,Choi, Doo Chan,Lee, Kwang Ho 한국토지주택공사 토지주택연구원 2020 LHI journal of land, housing, and urban affairs Vol.11 No.4
This paper presents the recent research developments identified through a review of literature on the application of artificial intelligence in developing automated designs of fire protection facilities. The literature review covered research related to image recognition and applicable neural networks. Firstly, it was found that convolutional neural network (CNN) may be applied to the development of automating the design of fire protection facilities. It requires a high level of object detection accuracy necessitating the classification of each object making up the image. Secondly, to ensure accurate object detection and building information, the data need to be pulled from architectural drawings. Thirdly, by applying image recognition and classification, this can be done by extracting wall and surface information using dimension lines and pixels. All combined, the current review of literature strongly indicates that it is possible to develop automated designs for fire protection utilizing artificial intelligence.
아파트 건물에서 재실자 활동량이 고려된 PMV제어에 따른 연간 국가 차원의 1차 에너지 및 온실가스 감축량 분석
홍성협(Hong, Sung-Hyup),도성록(Do, Sung-Lok),이광호(Lee, Kwang Ho) 대한건축학회 2018 大韓建築學會論文集 : 構造系 Vol.34 No.10
In this study, the effects of considering hourly metabolic rate variations for predicted mean vote (PMV) control on the heating and cooling energy and greenhouse gas emission were investigated. The case adopting PMV control taking the hourly metabolic rate into account was comparatively analyzed against the conventional dry-bulb air temperature control, using a detailed simulation technique. Under the assumption that all the apartments in Korea adopt the PMV control incorporating real-time metabolic rate measurements, nationwide reductions of primary energy and greenhouse gas emission were analyzed. As a result, PMV control considering hourly metabolic rate variations is expected to reduce national primary energy by 6.2% compared to conventional dry-bulb air temperature control, corresponding to reduction of 10,342 GWh. In addition, it turned out that 6.6% of tCO2 emission can be reduced by adopting PMV control, corresponding to nationwide reduction of greenhouse gas emission by approximately 1,720,000 tCO2.
실시간 MET 변화를 고려한 PMV 제어에 따른 동절기 부하 및 쾌적성 평가
홍성협(Sung Hyup Hong),이종만(Jong Man Lee),문진우(Jin Woo Moon),이광호(Kwang Ho Lee) 대한설비공학회 2018 대한설비공학회 학술발표대회논문집 Vol.2018 No.6
Recently, Korean Government is regulating indoor heating and cooling set-point temperatures to minimize the energy consumption, which is not well-considered policy without properly taking the actual thermal comfort into account. A variety of factors affect thermal comfort such as dry-bulb air temperature, humidity, air velocity, radiation, clothing insulation and activity level. In this study, the space is controlled based on PMV index considering real-time metabolic rate(MET) variations and the performance was compared against the conventional dry-bulb temperature based control. As a result, when the space was controlled based on PMV, occupants were more within comfort condition compared to conventional control and 10.6% of heating load reduction could be achieved. Economic analysis of the PMV index based control will be performed in the subsequent research.
기상 데이터를 활용한 LSTM 기반 일사량 예측모델 개발
박지원(Jiwon Park),홍성협(Sung Hyup Hong),전호성(Ho Seong Jeon),연상훈(Sang Hun Yeon),이광호(Kwang Ho Lee) 대한설비공학회 2022 대한설비공학회 학술발표대회논문집 Vol.2022 No.6
To stably operate EMS(Energy Management System) that systematically manages energy in the building, there is a need for predicting energy consumption and production in advance. In this study, we used hourly observed meteorological data from January, 2018 to December, 2020 provided by the Seoul branch of the Korea Meteorological Administration. The solar altitude data are calculated through the solar angle calculator provided by One Energy. The collected data are converted into available data set by data processing strategy. The correlation analysis between each meteorological data type and solar radiation after one hour proceeded to select the input parameters on the developed model. Selected meteorological data sets are used in the learning stage of the developed LSTM structure prediction model. The predictive performance of each model were analyzed through MAE(Mean Average Error), NMBE(Normalized Mean Bias Error), CV(RMSE)(Coefficient of Variation of Root Mean Square Error), R²(Coefficient of Determination) and computational time. The model with a window size of 24 was selected by performance evaluation criteria. Valid predictive performance of solar radiation after one hour in Busan was derived also from the selected model.
사무소의 하계 슬랫각도 최적제어를 위한 ANN 모델 개발 및 부하저감 효과
이종만(Jong Man Lee),홍성협(Sung Hyup Hong),연상훈(Sang Hoon Yeon),김홍욱(Hong Wook Kim),이광호(Kwang Ho Lee) 대한설비공학회 2018 대한설비공학회 학술발표대회논문집 Vol.2018 No.6
Windows are the only part of a building that can directly penetrate the solar radiation into the space and thus the shading devices are needed to control the solar penetration. A variety of research have been conducted to develop the optimized slat angle control in the existing literature, but the research incorporating artificial intelligence technique with slat angle control to consider dynamic operating conditions is limited thus far. Therefore, in this study, the ANN (Artificial Neural Network) model was applied to minimize the combined total load consisting of lighting and cooling loads through automatic slat angle control of venetian blinds. A three-story rectangular office building was simulated using EnergyPlus, and dimming control was applied to control the lighting. The interlocked simulation between Matlab and EnergyPlus was conducted through BCVTB. As a result of comparing automatic blind control via the ANN to fixed blind slat angle, the automatic blind control via the ANN showed 10.8% lower total load than the blind angle fixed at 40°. It was confirmed that the cooling and lighting load could be reduced by real-time automatic control via the ANN under various operating conditions, rather than fixing the blinds at one angle.
실내 열환경 쾌적 조성 및 에너지 효율 극대화를 위한 지능형 재실자 활동량 산출모델 개발
최은지(Eun Ji Choi),이광호(Kwang-Ho Lee),박보랑(Bo Rang Park),최영재(Young Jae Choi),홍성협(Sung-Hyup Hong),문진우(Jin Woo Moon) 대한설비공학회 2019 대한설비공학회 학술발표대회논문집 Vol.2019 No.-
본 연구는 실내 열환경의 쾌적 요소 중 하나인 재실자의 활동량(Metabolic rate, MET)을 산출하기 위한 지능형 MET 산출모델을 개발하는 것을 목적으로 한다. MET 산출모델 개발을 위해 딥러닝을 적용하였으며 재실자의 실내 활동 이미지 상의 인체 관절 좌표를 학습하여 MET를 출력한다. MET 산출모델 개발은 총 3단계로 진행되었다. 1) 학습 이미지 데이터 구축, 2) 모델 구조 설정 및 학습, 3) 학습 성능 평가. 학습 결과, MET 산출모델의 최적 구조는 14개의 인체 주요 관절 좌표 (x,y) 값을 입력 받는 입력층, 4개의 은닉층 및 1개의 출력층으로 구성되며 최적 모델의 MET 산출 정확도는 82.03%이다. 결과적으로 MET 산출모델의 개발을 통해 실내 재실자의 MET 측정 가능성 확인 및 PMV 제어 기반을 마련하였다.