http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
공공건물의 BEMS데이터를 활용한 설비시스템의 운영 실태 분석
라선중(Seon Jung Ra),손진웅(Jin Woong Son),엄태윤(Tae Yun Aum) 대한설비공학회 2019 대한설비공학회 학술발표대회논문집 Vol.2019 No.-
As BEMS is usually focused on monitoring functions rather than control, HVAC systems are operated as heuristic rules by the building manager. This can be difficult to control HVAC systems in response to real-time changing load. We analyzed the operation of HVAC systems and reviewed effective function of the BEMS for energy saving in the public office building. First, it found that several BEMS data sensor is not working normally. So operator was not able to perform effective control through BEMS monitoring. Second, it found that the HVAC systems are controlled by monitering realtime indoor-temperature. And then, the control method could lead to inefficient operation and unpleasant indoor environment. As a result, operator will be able to perform the efficient operation through the guideline that presenting the normal physical values of HVAC systems with the analysis results about the operation status.
기존 건물 HVAC 시스템에 대한 다섯 가지 기계학습 모델 개발
라선중(Ra, Seon-Jung),신한솔(Shin, Han-Sol),서원준(Suh, Won-Jun),추한경(Chu, Han-Gyeong),박철수(Park, Cheol-Soo) 대한건축학회 2017 大韓建築學會論文集 : 構造系 Vol.33 No.10
The first principles-based simulation model, e.g. dynamic simulation, is influenced by model uncertainty, simplification of the reality, lack of information, a modeler’s subjective assumptions, etc. Recently, a data-driven machine learning model has received a growing attention for simulation of existing buildings. The data-driven model is advantageous that it is simpler and requires less inputs than the first principles based model. In this study, the authors applied five different machine learning techniques (Artificial Neural Network, Support Vector Machine, Gaussian Process, Random Forest, and Genetic Programming) to HVAC systems (chiller, cooling tower, pump, ice thermal storage system and air handling unit) installed in an existing office building. It was found that the five machine learning models are good enough to predict the dynamic behavior of the HVAC systems. The machine learning model made by Genetic Programming is most accurate among the five machine learning models. The models made by Support Vector Machine and Gaussian Process Model require significant computation time and thus are limited in terms of the number of inputs. The accuracy of the model made by Random Forest is dependent on the set of inputs.
집중 시뮬레이션 모델을 활용한 건물의 실시간 냉방 예측 제어
라선중(Ra, Seon-Jung),김진홍(Kim, Jin-Hong),김영섭(Kim, Young-Sub),조형곤(Jo, Hyeong-Gon),신한솔(Shin, Han-Sol),박철수(Park, Cheol-Soo) 대한건축학회 2021 대한건축학회 학술발표대회 논문집 Vol.41 No.2
This paper presents a Model-Predictive Control (MPC) study applied to a cooling system in a large open-space building. The authors developed the MPC that uses minimal inputs based on a set of machine learning models for direct-expansion air handling unit (DX-AHU). For this study, the authors developed an DX-AHU supply air temperature prediction model and indoor temperature prediction models for 9 air conditioning zones. The prediction time horizon was set to 20-minute. The control objective is to minimize the energy consumption by DX-AHUs while keeping an average indoor temperature less than 27℃. It was found that the developed simulation models are accurate enough and the could save significant energy by 21.4% compared to the existing control.