Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

입력변수의 불확실성 보정을 위한 인공신경망 대리모델 기반의 민감도 분석 및 베이지안 MCMCSensitivity Analysis and Bayesian MCMC based on Artificial Neural Network Surrogate Model for Input Variable Uncertainty Calibration

Other Titles
Sensitivity Analysis and Bayesian MCMC based on Artificial Neural Network Surrogate Model for Input Variable Uncertainty Calibration
Authors
박성철하주완박경순송영학
Issue Date
2021
Publisher
한국건축친환경설비학회
Keywords
입력변수; 불확실성; 민감도 분석; 대리모델; 베이지안 보정; MCMC; Input Variable; uncertainty; Sensitivity analysis; Surrogate model; Bayesian calibration; Monte-carlo Markov-chain
Citation
한국건축친환경설비학회 논문집, v.15, no.4, pp.326 - 337
Indexed
KCI
Journal Title
한국건축친환경설비학회 논문집
Volume
15
Number
4
Start Page
326
End Page
337
URI
https://scholarworks.bwise.kr/gnu/handle/sw.gnu/5089
DOI
10.22696/jkiaebs.20210028
ISSN
1976-6483
Abstract
To have a precise simulation of building and quantitative performance evaluation, it is necessary to have high accuracy of input variables to implement a simulation. Inherent uncertainties (unknown fault or rapid error generation, etc.) in input variables can have a significant impact on energy performance evaluation. To solve this, this study conducted Artificial Neural Network (ANN) surrogate model-based Sobol sensitivity analysis using data of water-cooled variable refrigerant flow air conditioning system and Bayesian Markov chain Monte Carlo (MCMC) using no-U-turn sampler (NUTS) algorithm was performed. The main results showed that the Coefficient of the Variation of the Root Mean Square Error of the ANN surrogate model was 23.4%, and the top 6 variables that affected the energy usage through the sensitivity analysis results were selected. Then, the prior and posterior probability distributions were plotted through Bayesian MCMC. The convergence verification result of MCMC verified that the mean R-hat value was 1.0, which ensured the accuracy of MCMC. For future study, a virtual sensor will be developed to detect and diagnose faults in building heating, ventilation, and air conditioning based on the study results.
Files in This Item
There are no files associated with this item.
Appears in
Collections
공과대학 > School of Architectural Engineering > Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Song, Young Hak photo

Song, Young Hak
공과대학 (건축공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE