[해외논문] A Novel Hybrid Deep Neural Network Model to Predict the Refrigerant Charge Amount of Heat Pumps

구분 : 논문 | 저자 : Jun Kwon Hwang, Patrick Nzivugira Duhirwe , Geun Young Yun , Sukho Lee , Hyeongjoon Seo , Inhan Kim, Mat Santamouris

성과코드	2-양-A-11-1	연구기관	경희대학교
성과명	A Novel Hybrid Deep Neural Network Model to Predict the Refrigerant Charge Amount of Heat Pumps	버전
성과형식		연구기관 연락처	jungsikchoi@hanyang.ac.kr
다운로드	2-양-A-11-1-① 해외논문(SCI급)-A Novel Hybrid Deep Neural Network Model to Predict the Refrigerant Charge Amount of Heat Pumps.pdf,
다운로드 링크
URL 연결
성과정의
성과구성	Abstract: Improper refrigerant charge amount (RCA) is a recurring fault in electric heat pump (EHP) systems. Because EHP systems show their best performance at optimum charge, predicting the RCA is important. There has been considerable development of data-driven techniques for predicting RCA; however, the current data-driven approaches for estimating RCA su_er from poor generalization and overfitting. This study presents a hybrid deep neural network (DNN) model that combines both a basic DNN model and a thermodynamic model to counter the abovementioned challenges of existing data-driven approaches. The data for designing models were collected from two EHP systems with di_erent specifications, which were used for the training and testing of models. In addition to the data obtained using the basic DNN model, the hybrid DNN model uses the thermodynamic properties as a thermodynamic model. The testing results show that the hybrid DNN model has a prediction performance of 93%, which is 21% higher than that of the basic DNN model. Furthermore, for model training and model testing, the hybrid DNN model has a 6% prediction performance di_erence, indicating its reliable generalization capabilities. To summarize, the hybrid DNN model improves data-driven approaches and can be used for designing e_cient and energy-saving EHP systems. Keywords: building energy; energy use; energy efficiency; prediction model; deep neural network; electric heat pump; refrigerant charge amount
사용주체		사용단계
사용용도
사용환경
적용된 KBIMS

List of Articles
번호	구분	분류	제목	저자
23	소프트웨어	3세부	[소프트웨어]스캔투빔 반자동 객체 생성 프로그램	두올테크
22	국내학술발표	3세부	SBF(Scan-BIM-FM) 기반 스마트 시설물 관리	강태욱
21	국내논문	3세부	건축물 유지관리를 위한 COBie기반 건축정보교환체계 프레임웍 연구	강태욱
20	연구홍보	2세부	[연구홍보] 개방형BIM 기반의 건축설계 적법성 평가 자동화 기술 및 응용기술 개발 성과 홍보	연세대학교
19	논문	2세부	[해외논문(SCI급)] Deep learning-based extraction of predicate-argument structure (PAS) in building design rule sentences	Jaeyeol Song, Jin-Kook Lee, Jungsik Choi, Inhan Kim
18	논문	2세부	[국내논문] 기계학습활용 건축설계지침 문장 내 논리규칙 구성요소 자동추출과 설계품질 검토도구 연계방안(심사완료)	김진성, 송재열, 이진국
17	논문	2세부	[국내논문] 모바일 BIM기반 현장 품질관리 지원도구	송경욱, 유정호, 김경
16	논문	2세부	[해외논문 (SCI)] Longitudinal Study on Construction Organization’s BIM Acceptance	Seulki Lee, Jungho Yu
»	논문	2세부	[해외논문] A Novel Hybrid Deep Neural Network Model to Predict the Refrigerant Charge Amount of Heat Pumps	Jun Kwon Hwang, Patrick Nzivugira Duhirwe , Geun Young Yun , Sukho Lee , Hyeongjoon Seo , Inhan Kim, Mat Santamouris
14	논문	2세부	[국내논문] 배관 ISO도면 파일 기반 ARVR모델 생성 기법 연구	이정민, 이경호, 한영수