All Issue

2025 Vol.19, Issue 6 Preview Page

Research Article

Hamiltonian Monte Carlo-Based Automated Fault Detection, Diagnosis, and Correction of Outlet Water Temperature Sensor in Heat Pump System

Hamiltonian Monte Carlo 기반 히트펌프 출수온도 센서 자동 고장 감지 진단 및 보정

Seok-Jin Hong1
,
Hyo-Jun Kim2
,
Jin-Hyun Lee3
,
Young-Hum Cho4*
홍 석진1
,
김 효준2
,
이 진현3
,
조 영흠4*
1Master’s Course, Architecture Engineering, Graduate School of Yeungnam University, Gyeongsan, Korea
2Director, BETECH, Daegu, Korea
3Research Professor, Architecture Research Institute Yeungnam University, Gyeongsan, Korea
4Professor, School of Architecture, Yeungnam University, Gyeongsan, Korea
1영남대학교 일반대학원 건축학과 석사과정
2비텍 대표
3영남대학교 건축연구소 연구교수
4영남대학교 공과대학 건축학부 교수
*Corresponding Author
30 December 2025. pp. 311-318
PDF XML Citation
Abstract

This study proposes a model based on the Hamiltonian Monte Carlo (HMC) method to automatically detect, diagnose, and correct various errors that may occur in the outlet water temperature sensor of a heat pump system. To identify factors influencing the formation of the outlet water temperature, experimental data were collected through the Building Automation System (BAS), and the most influential variables were selected using Standardized Regression Coefficient (SRC) analysis. Based on these variables, a heat balance equation was formulated and integrated into the HMC model. Modeling results for steady-state data showed that the proposed model satisfied the ASHRAE Guideline 14 criteria, with a Normalized Mean Bias Error (NMBE) of –0.45% and a Coefficient of Variation of the Root Mean Square Error (CvRMSE) of 0.67%. The coefficient of determination (R²) was 0.9987, confirming a high level of agreement between the measurement and prediction. For performance verification, random errors ranging from –3 to +3℃ in 1℃ increments were introduced, and the posterior distribution were found to closely match the specified errors. In addition, when offset error, random noise error, and drift error were applied to actual operating data, the improvement rates were 84.95%, 81.87%, and 85.67%, respectively.

Keywords
Heat Pump
Sensor
FDD (Fault Detection and Diagnostics)
Correction
키워드
히트펌프
센서
고장 감지 진단
보정
References
1

Chua, K.J., Chou, S.K., Yang, W.M. (2010). Advances in heat pump systems: A review. Applied energy, 87(12), 3611-3624.

10.1016/j.apenergy.2010.06.014
2

Girolami, M., Calderhead, B. (2011). Riemann manifold langevin and hamiltonian monte carlo methods. Journal of the Royal Statistical Society Series B: Statistical Methodology, 73(2), 123-214.

10.1111/j.1467-9868.2010.00765.x
3

Jin, S., Kim, D.S., Do, S.L. (2023). Evaluation of Influence on Cooling System by Faulty Temperature Sensor of Supply Chilled Water. Journal of the Architectural Institute of Korea, 39(8), 207-213.

10.5659/JAIK.2023.39.8.207
4

Wang, P., Li, J., Yoon, S., Zhao, T., Yu, Y. (2020a). The detection and correction of various faulty sensors in a photovoltaic thermal heat pump system. Applied Thermal Engineering, 175, 115347.

10.1016/j.applthermaleng.2020.115347
5

Wang, X., Xia, L., Bales, C., Zhang, X., Copertaro, B., Pan, S., Wu, J. (2020b). A systematic review of recent air source heat pump (ASHP) systems assisted by solar thermal, photovoltaic and photovoltaic/thermal sources. Renewable Energy, 146, 2472-2487.

10.1016/j.renene.2019.08.096
6

Yoon, S., Yu, Y., Wang, J., Wang, P. (2019). Impacts of HVACR temperature sensor offsets on building energy performance and occupant thermal comfort. Building Simulation, 12, 259-271.

10.1007/s12273-018-0475-3
7

Chen, T., Fox, E., Guestrin, C. (2014, June). Stochastic gradient hamiltonian monte carlo. In International Conference on Machine Learning. PMLR, 1683-1691.

8

Betancourt, M. (2017). A conceptual introduction to Hamiltonian Monte Carlo. arXiv preprint arXiv:1701.02434.

9

International Energy Agency (IEA). (2022). The Future of Heat Pump. International Energy Agency.

10

Carlsson, F. (2024). Regression models for heat pump performance: Exploring statistical and machine learning techniques for estimating heat pump COP and Carnot efficiency. Master’s degree, KTH Royal Institute of Technology, Sweden.

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 : 19
  • No :6
  • Pages :311-318
  • Received Date : 2025-09-30
  • Revised Date : 2025-11-04
  • Accepted Date : 2025-12-02
  • DOI :https://doi.org/10.22696/jkiaebs.20250027
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