All Issue

2021 Vol.15, Issue 4 Preview Page

Research Article

Sensitivity Analysis and Bayesian MCMC based on Artificial Neural Network Surrogate Model for Input Variable Uncertainty Calibration

입력변수의 불확실성 보정을 위한 인공신경망 대리모델 기반의 민감도 분석 및 베이지안 MCMC

Seong-Cheol Park1
,
Ju-Wan Ha1
,
Kyung-Soon Park2
,
Young-Hak Song3*
박 성철1
,
하 주완1
,
박 경순2
,
송 영학3*
1Graduate School, Department of Architectural Engineering, Gyeongsang National University, Jinju, Korea
2Associate Professor, Architectural Engineering Major, Division of Urban, Architecture and Civil Engineering, Dong-eui University, Busan, Korea
3Associate Professor, Department of Architectural Engineering, ERI, Gyeongsang National University, Jinju, Korea
1경상대학교 건축공학과 대학원 과정
2동의대학교 건설공학부 건축공학전공 부교수
3경상대학교 건축공학과 부교수
*Corresponding Author
30 August 2021. pp. 326-337
PDF XML Citation
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.

Keywords
Input Variable
uncertainty
Sensitivity analysis
Surrogate model
Bayesian calibration
Monte-carlo Markov-chain
키워드
입력변수
불확실성
민감도 분석
대리모델
베이지안 보정
MCMC
References
1
Calama-Gonzalez, C.M., Symonds, P., Petrou, G., Suarez, R., Leon-Rodriguez, A.L. (2021). Bayesian Calibration of Building Energy Models for Uncertainty Analysis through Test Cells Monitoring. Applied Energy, 282, 116118. 10.1016/j.apenergy.2020.116118
2
Gelman, A., Rubin, D.B. (1992). Inference from Iterative Simulation using Multiple Sequences (with Discussion). Statistical Science, 7, 457-511. 10.1214/ss/1177011136
3
Kim, Y.J., Ahn, K.U., Park, C.S. (2014). Decision making of HVAC System using Bayesian Markov Chain Monte Carlo Method. Energy and Buildings, 72, 112-121. 10.1016/j.enbuild.2013.12.039
4
Kong, D.S., Chang, Y.S., Huh, J.H. (2015). Selecting of the Energy Performance Diagnosis Items through the Sensitivity Analysis of Existing Buildings. The Society of Air-Conditioning and Refrigerating Engineers of Korea, 27(7), 354-361. 10.6110/KJACR.2015.27.7.354
5
Oh, J.H., Kwon, S.J., Kim, S.S. (2017). A Study on Envelope Design Variables for Energy Conservation of General Hospital Ward Area by Sensitivity Analysis. Korea Institute of Healthcare Architecture, 23(1), 7-14.
6
Tian, W. (2013). A Review of Sensitivity Analysis Methods in Building Energy Analysis. Renewable and Sustainable Energy Reviews, 20, 411-419. 10.1016/j.rser.2012.12.014
7
Tian, W., de Wilde, P., Li, Z.Y., Song, J., Yin, B. (2018). Uncertainty and Sensitivity Analysis of Energy Assessment for Office Buildings based on Dempster-Shafer theory. Energy Conversion and Management, 174(15), 705-718. 10.1016/j.enconman.2018.08.086
8
Yoon, S.M. (2020). 건물에너지시스템의 가상센싱기술과 커미셔닝 자동화 방안. Korean Institute of Architectural Sustainable Environment and Building Systems, 14(3), 31-40.
9
Youn, S.H., Kim, Y.J., Park, C.S. (2014). Bayesian Calibration of Energy Model for Existing Buildings. Architectural Institute of Korea, 30(10), 189-197. 10.5659/JAIK_PD.2014.30.10.189
10
Yu, Y.S., Yi, D.H., Kim, S.S., Park, C.S. (2020). Rational Building Energy Assessment using Global Sensitivity Analysis. Journal of the Architectural Institute of Korea Structure & Construction, 36(5), 177-185.
11
Saltelli, A., Ratto, M., Andres, T., Campolongo, F., Cariboni, J., Gatelli, D., Trantola, S. (2008). Global Sensitivity Analysis: the Primer. New Jersey: John Wiley & Sons. 10.1002/9780470725184
12
de Wit, S., Augenbroe, G. (2002). Analysis of Uncertainty in Building Design Evaluations and its Implications. Energy and Buildings. 34(9), 951-958. 10.1016/S0378-7788(02)00070-1
13
Kim, W.H. (2013). Fault Detection and Diagnosis for Air Conditioners and Heat Pumps based on Virtual Sensors. Ph.D. Thesis. University of Purdue.
14
Macdonald, I.A. (2002). Quantifying the Effects of Uncertainty in Building Simulation. Ph.D. Thesis. University of Strathclyde Scotland.
15
Youn, S.H. (2015). Uncertainty Quantification in Bayesian Calibration of Building Energy Model for Decision-Making. Ph.D Thesis, SungKyunKwan University.
16
PyMC3. (2018). About PyMC3. PyMC Development Team. https://docs.pymc.io.
Information
  • Publisher :Korean Institute of Architectural Sustainable Environment and Building Systems
  • Publisher(Ko) :한국건축친환경설비학회
  • Journal Title :Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
  • Journal Title(Ko) :한국건축친환경설비학회논문집
  • Volume : 15
  • No :4
  • Pages :326-337
  • Received Date : 2021-06-03
  • Revised Date : 2021-08-06
  • Accepted Date : 2021-08-20
  • DOI :https://doi.org/10.22696/jkiaebs.20210028
Journal Informaiton Journal of Korean Institute of Architectural Sustainable Environment and Building Systems Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
Manuscript Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close