BEMS 운영을 위한 인공신경망 기반 중앙공조시스템의 에너지 소비량 예측 소프트웨어 개발

성남철,김지헌,최원창 대한설비공학회 2019 설비저널 Vol.48 No.6

비주거 건축물의 그린 리트로핏 의사결정 지원을 위한 에너지 해석 및 비용분석 프로그램 개발

성남철,홍구표 대한설비공학회 2022 설비저널 Vol.51 No.7

PMV지표를 이용한 공동주택의 난방제어에 따른 온열환경 및 에너지소비량 시뮬레이션

성남철,윤동원,Seong, Nam-Chul,Yoon, Dong-Won 한국토지주택공사 토지주택연구원 2010 LHI journal of land, housing, and urban affairs Vol.1 No.1

최근 에너지 절약을 화두로 건물에서의 에너지 절약기술들이 크게 요구되어 지는 반면 재실자의 온열쾌적환경은 비교적 비중 있게 다루어지지 않고 있다. 실내공간의 쾌적성은 재실자의 만족감과 더불어 생산성을 향상시키는 등의 역할을 하며, 최근 삶의 질 향상 등에 따라 그 필요성이 크게 요구되고 있는 실정이다. 따라서 본 연구에서는 공동주택을 대상으로 겨울철 난방 시 쾌적지표를 통한 실내 온열환경 제어의 타당성을 검토하고자 시뮬레이션을 수행하였으며, 주거건물에서의 일상적인 실내온도와 에너지 절약 설계기준에서 제시한 실내 설정온도, 그리고 쾌적지표를 설정으로 한 각 제어조건의 온열환경과 에너지 소비량을 비교 분석 및 검토하였다. 본 연구결과에 따르면, 쾌적지표인 PMV로 실내환경을 제어했을 때 에너지 절약설계 기준인 $22^{\circ}C$로 실내온도를 설정하였을 때보다 에너지 소비량은 29% 증가하지만 주거용 건물에서 일반적으로 유지되는 실내온도인 $24^{\circ}C$ 보다는 에너지소비량은 11% 정도 감소하며, 온열쾌적감도 각 제어조건 중 가장 우수하게 나타났다. 따라서 여러 가지 제어변수들을 통한 연구가 지속된다면 주거용 건물에서도 쾌적지표를 활용한 실내 공간의 제어방법은 건물의 에너지를 절약하고 실내 환경의 쾌적성을 증대시키는 주요기술이 될 수 있을 것으로 기대된다. Thermal comfort provide satisfaction of thermal environment and affects productivity of occupants in residential building. However, temperature control can not provide the thermal comfort at all the time. because thermal comfort is influenced by many environmental variables such as temperature, relative humidity, air velocity, radiation temperature, activity level and clothing insulation. The purpose of this study is that predicted mean vote(PMV) index is used as control. And, Thermal comfort is evaluated both PMV control and temperature control by simulation. Each other cases were compared, in which set-point temperatures of $22^{\circ}C$ and $24^{\circ}C$ and, set-point PMV index through the respective heating season in the simulation. The results show that PMV control is better to maintain comfort state and save energy than temperature control.

재실 기반 설비제어에 따른 대학 건물의 에너지소비량 비교 분석

성남철,홍구표 한국건축친환경설비학회 2021 한국건축친환경설비학회 논문집 Vol.15 No.6

In this study, occupant information, one of the information that can be found in the operation stage of the building, was collected using an actual survey. After converting occupancy data to HVAC system operation schedule, it was analyzed and compared the change of energy consumption applied with occupancy-based HVAC control. As a result, the actual number of occupants was smaller than the case where the occupancy density per area was set, so the energy consumption of the total building decreased by 15.16%, and the energy consumption of the HVAC system decreased by 34.32%. When the occupanct-based HVAC control was applied, the energy consumption of the entire building decreased by 9.71%, and the energy consumption of the HVAC system decreased by 28.42%. As a result of analyzing energy consumption by system, the control of occupancy-based HVAC control has a greater energy saving effect on heating than cooling. The occupancy-based HVAC control is simpler than other controls and has a significant energy saving effect.

이코노마이저시스템의 제어 방법 및 설정 변화에 따른 운전 성능 평가

성남철,홍구표 한국건축친환경설비학회 2022 한국건축친환경설비학회 논문집 Vol.16 No.1

The economizer system may reduce cooling energy consumption by control the introduction of outside air. When controlling this system, the rate of outside air introduction is determined according to the introduction criteria and setpoints of outside air, and the operating performance varies. Therefore, in this study, the operation time and energy consumption were compared when the economizer system was controlled in four method: Fixed Dry Bulb Control, Different Dry Bulb Control, Fixed Enthalpy Control, and Differential Enthalpy Control. As a result, the operating time of the system also increased as the maximum limit value increased, but the operating time and energy consumption were not proportional. When the Maximum Limit was fixed, the energy consumption was the lowest when the Dry Bulb Temperature was 22°C, and when the Maximum Limit Enthalpy was 58.0 kJ/kg, the energy consumption was the lowest. The economizer system can save energy from at least 13.47% to 15.84% for each control method, and Differential Enthalpy Control has the largest energy saving among the control methods. Enthalpy control is more effective in reducing energy consumption thandry bulb temperature control.

다층신경망 학습 알고리즘 변화에 따른 건물 냉방부하 예측 모델의 성능 비교 평가

성남철,홍구표 한국생태환경건축학회 2022 한국생태환경건축학회 논문집 Vol.22 No.4

Purpose: In this study, among the methods of applying machine learning when predicting the load of a building, the cooling load of a building was predicted using a neural network model. To investigate the appropriateness of the learning algorithm of the multi-layer neural network model, the main purpose is to compare the predictive performance according to the change in the learning algorithm. Method: Among the learning algorithms applicable to multilayer neural networks, a total of 16 algorithms were used to predict the cooling load and compare the prediction results. The input variables of the input layer of the neural network model are outdoor dry bulb temperature, outdoor humidity, and Seasonally Data. The training period is 70% and the test period was 30%. The number of layers in the hidden layer is 3, the number of neurons is 20, and Epochs is 100. CvRMSE and MBE are used as performance index of the prediction model. The maximum, minimum, average, and standard deviation of the 20 prediction results are calculated, and the prediction performance according to the change in the learning algorithm was compared. Result: As a result of analyzing the predictive performance for each learning algorithm, the predictive performance according to the learning algorithm was different. Considering the results and deviations of the two indicators of predictive performance comprehensively, the model using the Levenberg-Marquardt (LM) learning algorithm is judged to have the best predictive performance.

데이터 전처리 과정이 다층신경망을 이용한 건물 부하 예측 모델의 성능에 미치는 영향 분석

성남철,홍구표 한국건축친환경설비학회 2022 한국건축친환경설비학회 논문집 Vol.16 No.4

Data preprocess affects the performance improvement of predictive models using neural networks. However, previous studies have not analyzed the effects of data preproces. Therefore, in this study, the effect of data preprocess in a load prediction model using a multilayer neural network was analyzed. After constructing a multilayer neural network and generating learning data using a reference building, the performance of the predictive model was evaluated and compared through index of ASHRAE Guideline 14. As a result of the study, it was confirmed that the prediction results were improved through data preprocess. Compared to non-data preprocess models, the CvRMSE of models that performed data preprocess was improved from 21.47% to 10.74%, and MBE from 7.71% to 4.11%. It was found that the predictive performance improvement effect of data cleaning that removes missing values of data was greater than that of data transformation that converts the form of data.

수도권지역을 중심으로 한 소규모 국내 보육시설 실내공기질 관리현황과 실태조사에 관한 연구

성남철,홍용석,윤동원 한국생활환경학회 2012 한국생활환경학회지 Vol.19 No.3

Indoor Air Quality deterioration due to various environmental causes of disease that has already been identified by many case studies. In particular, children are easily exposed to danger on indoor air contamination. So, the indoor air quality management of the living space of children is very important. However, the indoor air quality management guideline of daycare facilities is insufficient to guarantee the health of children. The purpose of this study, child day-care facilities in 73 locations in the metropolitan area, indoor air quality survey and analysis to identify the status and aims to provide data to improve Indoor Air Quality. As a result, 47 percent of facilities in the mechanical ventilation systems and air cleaners were installed. Known only to 26% for indoor air quality by responding to the survey that appeared to be a lack of awareness. as the following measuring result, contaminant of concentrations of the measured facilities are against the regulations which CO2(carbon dioxide) by 29%, PM10(particulate matter) by 42%, TVOC(total volatile organic compound) by 19%, HCHO(formaldehyde) by 6% and 37% for TBC(total bacteria colony) was measured. Therefore, indoor air quality in child care through the improvement of the active response and sustained efforts are required.

그린 리트로핏 프로그램을 이용한 소규모 공공 건축물의 리모델링 전후 에너지 성능분석

성남철,홍구표 한국건축친환경설비학회 2022 한국건축친환경설비학회 논문집 Vol.16 No.6

Energy performance evaluation before and after gree remodeling is important for effective green remodeling, and analysis tools and programs are used for this. This study aims to develop programs and verify performance that can be easily used by users without expertise, can be applied to non-residential buildings, and can support accurate energy performance analysis and decision-making during green remodeling. For accurate energy analysis, EnergyPlus, a verified energy analysis program, was installed inside the program as an analysis engine. The user mode may be divided into a general user mode and a professional user mode. In addition, the input method was optimized using a database. The energy analysis performance was verified by comparing the simulation results of the program developed for buildings that have been actually remodeled with the simulation results of EnergyPlus. As a result, there was an error of 4.7% in annual energy use before green remodeling and 8.9% in annual energy use after green remodeling. It is suitable for evaluating energy usage before and after actual green remodeling. However, it seems that there is an error in energy performance analysis due to differences in the process of modeling the shape of a building. Therefore, it is necessary to supplement and improve the program by conducting verification on buildings of various sizes and shapes in the future.

BEMS 환경에서 유전 알고리즘을 이용한 중앙 집중식 공조시스템의 에너지 최적화 운전방안

성남철,김지헌,최원창 대한설비공학회 2018 설비저널 Vol.47 No.11