Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Chen, Yimin; Wen, Jin; Pradhan, Ojas; Lo, L. James; Wu, Teresa

doi:10.1016/j.apenergy.2022.120050

Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Journal Article · Mon Oct 10 00:00:00 EDT 2022 · Applied Energy

DOI:https://doi.org/10.1016/j.apenergy.2022.120050· OSTI ID:2248026

Chen, Yimin ^[1]; Wen, Jin ^[2]; Pradhan, Ojas ^[2]; Lo, L. James ^[2]; Wu, Teresa ^[3]

Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Drexel Univ., Philadelphia, PA (United States)
Drexel Univ., Philadelphia, PA (United States)
Arizona State Univ., Tempe, AZ (United States)

Fault detection and diagnosis (FDD) technologies are critical to ensure satisfactory building performance, such as reducing energy wastes and negative impacts on occupant comfort and productivity. Existing FDD technologies mainly focus on component-level FDD solutions, which could lead to mis-diagnosis of cross-level faults in heating, ventilating, and air-conditioning (HVAC) systems. Cross-level faults are those faults that occur in one component or subsystem, but cause operational abnormalities in other components or subsystems, and result in a building level performance degradation. How to effectively diagnose the root cause of a cross-level fault is the focus of this study. Here, this paper presents a novel discrete Bayesian Network (DisBN)-based method for diagnosing cross-level faults in an HVAC system commonly used in commercial buildings. A two-level DisBN structure model is developed in this study. The parameters used in the DisBN model are obtained either from expert knowledge or through machine-learning strategies from normal system operation data. Meanwhile, the probability parameters are discretized to incorporate the uncertainties associated with typical expert knowledge. Thus, the developed DisBN method addresses the challenges many other BN based FDD methods face, i.e., the lack of fault data for BN parameter training. The developed DisBN represents causal relationships between a fault and its cross-level system impacts (i.e., fault symptoms or fault indicators) by considering how fault impacts propagate across different levels in an HVAC system. A weather and schedule information-based Pattern Matching (WPM) method is employed to automatically create WPM baseline data sets for each incoming real time snapshot data from the building systems. Consequently, BN inference and real-time diagnostics are achieved by comparing incoming snapshot data and the WPM baseline data set. The proposed method is evaluated using experimental fault data collected in a campus building. Fault diagnosis results demonstrate that the WPM-DisBN method is effective at locating the root causes of cross-level faults in an HVAC system.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE)

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 2248026

Journal Information:: Applied Energy, Journal Name: Applied Energy Vol. 327; ISSN 0306-2619

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (45)

Bayesian belief networks for system fault diagnostics Lampis, M.; Andrews, J. D. Quality and Reliability Engineering International, Vol. 25, Issue 4 https://doi.org/10.1002/qre.978	journal	June 2009
Backward Inference in Bayesian Networks for Distributed Systems Management Ding, Jianguo; Krämer, Bernd; Bai, Yingcai Journal of Network and Systems Management, Vol. 13, Issue 4 https://doi.org/10.1007/s10922-005-9003-8	journal	December 2005
Analysis of an information monitoring and diagnostic system to improve building operations Piette, Mary Ann; Kinney, Sat Kartar; Haves, Philip Energy and Buildings, Vol. 33, Issue 8 https://doi.org/10.1016/S0378-7788(01)00068-8	journal	October 2001
Application of machine learning in the fault diagnostics of air handling units Najafi, Massieh; Auslander, David M.; Bartlett, Peter L. Applied Energy, Vol. 96 https://doi.org/10.1016/j.apenergy.2012.02.049	journal	August 2012
Fault detection and diagnosis of chillers using Bayesian network merged distance rejection and multi-source non-sensor information Wang, Zhanwei; Wang, Zhiwei; He, Suowei Applied Energy, Vol. 188 https://doi.org/10.1016/j.apenergy.2016.11.130	journal	February 2017
Bayesian network-based early-warning for leakage in recovery boilers Widarsson, Björn; Dotzauer, Erik Applied Thermal Engineering, Vol. 28, Issue 7 https://doi.org/10.1016/j.applthermaleng.2007.06.016	journal	May 2008
Diagnostic Bayesian networks for diagnosing air handling units faults – Part II: Faults in coils and sensors Zhao, Yang; Wen, Jin; Wang, Shengwei Applied Thermal Engineering, Vol. 90 https://doi.org/10.1016/j.applthermaleng.2015.07.001	journal	November 2015
Diagnostic Bayesian networks for diagnosing air handling units faults – part I: Faults in dampers, fans, filters and sensors Zhao, Yang; Wen, Jin; Xiao, Fu Applied Thermal Engineering, Vol. 111 https://doi.org/10.1016/j.applthermaleng.2015.09.121	journal	January 2017
Fault detection and diagnosis of chiller using Bayesian network classifier with probabilistic boundary He, Suowei; Wang, Zhiwei; Wang, Zhanwei Applied Thermal Engineering, Vol. 107 https://doi.org/10.1016/j.applthermaleng.2016.06.153	journal	August 2016
Bayesian network based FDD strategy for variable air volume terminals Xiao, Fu; Zhao, Yang; Wen, Jin Automation in Construction, Vol. 41 https://doi.org/10.1016/j.autcon.2013.10.019	journal	May 2014
P&ID-based symptom detection for automated energy performance diagnosis in HVAC systems Taal, Arie; Itard, Laure Automation in Construction, Vol. 119 https://doi.org/10.1016/j.autcon.2020.103344	journal	November 2020
Cross-level fault detection and diagnosis of building HVAC systems Wu, Siyu; Sun, Jian-Qiao Building and Environment, Vol. 46, Issue 8 https://doi.org/10.1016/j.buildenv.2011.01.017	journal	August 2011
Building fault detection and diagnostics: Achieved savings, and methods to evaluate algorithm performance Lin, Guanjing; Kramer, Hannah; Granderson, Jessica Building and Environment, Vol. 168 https://doi.org/10.1016/j.buildenv.2019.106505	journal	January 2020
A fault detection and diagnosis strategy of VAV air-conditioning systems for improved energy and control performances Qin, Jianying; Wang, Shengwei Energy and Buildings, Vol. 37, Issue 10 https://doi.org/10.1016/j.enbuild.2004.12.011	journal	October 2005
A rule-based fault detection method for air handling units Schein, Jeffrey; Bushby, Steven T.; Castro, Natascha S. Energy and Buildings, Vol. 38, Issue 12 https://doi.org/10.1016/j.enbuild.2006.04.014	journal	December 2006
Evaluation of faults impacts on energy consumption and indoor air quality on an air handling unit Ginestet, S.; Marchio, D.; Morisot, O. Energy and Buildings, Vol. 40, Issue 1 https://doi.org/10.1016/j.enbuild.2007.01.012	journal	January 2008
A top-down strategy with temporal and spatial partition for fault detection and diagnosis of building HVAC systems Wu, Siyu; Sun, J. Q. Energy and Buildings, Vol. 43, Issue 9 https://doi.org/10.1016/j.enbuild.2011.04.020	journal	September 2011
An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network Zhao, Yang; Xiao, Fu; Wang, Shengwei Energy and Buildings, Vol. 57 https://doi.org/10.1016/j.enbuild.2012.11.007	journal	February 2013
A machine learning bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system Hu, Min; Chen, Huanxin; Shen, Limei Energy and Buildings, Vol. 158 https://doi.org/10.1016/j.enbuild.2017.10.012	journal	January 2018
A reference architecture for the integration of automated energy performance fault diagnosis into HVAC systems Taal, Arie; Itard, Laure; Zeiler, Wim Energy and Buildings, Vol. 179 https://doi.org/10.1016/j.enbuild.2018.08.031	journal	November 2018
P&ID-based automated fault identification for energy performance diagnosis in HVAC systems: 4S3F method, development of DBN models and application to an ATES system Taal, Arie; Itard, Laure Energy and Buildings, Vol. 224 https://doi.org/10.1016/j.enbuild.2020.110289	journal	October 2020
A simulation-based evaluation of fan coil unit fault effects Chen, Yimin; Lin, Guanjing; Chen, Zhelun Energy and Buildings, Vol. 263 https://doi.org/10.1016/j.enbuild.2022.112041	journal	May 2022
Sensor fault detection and validation of VAV terminals in air conditioning systems Wang, Shengwei; Qin, Jianying Energy Conversion and Management, Vol. 46, Issue 15-16 https://doi.org/10.1016/j.enconman.2004.11.011	journal	September 2005
Fault diagnosis for a solar assisted heat pump system under incomplete data and expert knowledge Liu, Zengkai; Liu, Yonghong; Zhang, Dawei Energy, Vol. 87 https://doi.org/10.1016/j.energy.2015.04.090	journal	July 2015
Combining knowledge and historical data for system-level fault diagnosis of HVAC systems Verbert, K.; Babuška, R.; De Schutter, B. Engineering Applications of Artificial Intelligence, Vol. 59 https://doi.org/10.1016/j.engappai.2016.12.021	journal	March 2017
Uncertainties in conditional probability tables of discrete Bayesian Belief Networks: A comprehensive review Rohmer, Jeremy Engineering Applications of Artificial Intelligence, Vol. 88 https://doi.org/10.1016/j.engappai.2019.103384	journal	February 2020
Assessing new product development project risk by Bayesian network with a systematic probability generation methodology Chin, Kwai-Sang; Tang, Da-Wei; Yang, Jian-Bo Expert Systems with Applications, Vol. 36, Issue 6 https://doi.org/10.1016/j.eswa.2009.02.019	journal	August 2009
Using Bayesian networks for root cause analysis in statistical process control Alaeddini, Adel; Dogan, Ibrahim Expert Systems with Applications, Vol. 38, Issue 9 https://doi.org/10.1016/j.eswa.2011.02.171	journal	September 2011
A new approach for probability calculation of fuzzy events in Bayesian Networks İçen, Duygu; Ersel, Derya International Journal of Approximate Reasoning, Vol. 108 https://doi.org/10.1016/j.ijar.2019.03.004	journal	May 2019
A practical chiller fault diagnosis method based on discrete Bayesian network Wang, Yalan; Wang, Zhiwei; He, Suowei International Journal of Refrigeration, Vol. 102 https://doi.org/10.1016/j.ijrefrig.2019.03.008	journal	June 2019
Integration of structural health monitoring and fatigue damage prognosis Ling, You; Mahadevan, Sankaran Mechanical Systems and Signal Processing, Vol. 28 https://doi.org/10.1016/j.ymssp.2011.10.001	journal	April 2012
A real-time fault diagnosis methodology of complex systems using object-oriented Bayesian networks Cai, Baoping; Liu, Hanlin; Xie, Min Mechanical Systems and Signal Processing, Vol. 80 https://doi.org/10.1016/j.ymssp.2016.04.019	journal	December 2016
Bayesian Reasoning and Machine Learning Barber, David Cambridge University Press https://doi.org/10.1017/CBO9780511804779	book	January 2012
Building fault detection data to aid diagnostic algorithm creation and performance testing Granderson, Jessica; Lin, Guanjing; Harding, Ari Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-0398-6	journal	February 2020
A Hierarchical Rule-Based Fault Detection and Diagnostic Method for HVAC Systems Schein, Jeffrey; Bushby, Steven T. HVAC&R Research, Vol. 12, Issue 1 https://doi.org/10.1080/10789669.2006.10391170	journal	January 2006
Sensitivity analysis in discrete Bayesian networks Castillo, E.; Gutierrez, J. M.; Hadi, A. S. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, Vol. 27, Issue 4 https://doi.org/10.1109/3468.594909	journal	July 1997
Fault Diagnosis of HVAC Air-Handling Systems Considering Fault Propagation Impacts Among Components Yan, Ying; Luh, Peter B.; Pattipati, Krishna R. IEEE Transactions on Automation Science and Engineering, Vol. 14, Issue 2 https://doi.org/10.1109/TASE.2017.2669892	journal	April 2017
Bayesian Networks in Fault Diagnosis Cai, Baoping; Huang, Lei; Xie, Min IEEE Transactions on Industrial Informatics, Vol. 13, Issue 5 https://doi.org/10.1109/TII.2017.2695583	journal	October 2017
Using Ranked Nodes to Model Qualitative Judgments in Bayesian Networks Fenton, Norman E.; Neil, Martin; Caballero, Jose Galan IEEE Transactions on Knowledge and Data Engineering, Vol. 19, Issue 10 https://doi.org/10.1109/TKDE.2007.1073	journal	October 2007
Improving Construction of Conditional Probability Tables for Ranked Nodes in Bayesian Networks Laitila, Pekka; Virtanen, Kai IEEE Transactions on Knowledge and Data Engineering, Vol. 28, Issue 7 https://doi.org/10.1109/TKDE.2016.2535229	journal	July 2016
Knowledge Engineering for Bayesian Networks: How Common Are Noisy-MAX Distributions in Practice? Zagorecki, Adam; Druzdzel, Marek J. IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 43, Issue 1 https://doi.org/10.1109/TSMCA.2012.2189880	journal	January 2013
Verification and Validation of Hierarchical Fault Diagnosis in Satellites Formation Flight Barua, Amitabh; Khorasani, K. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 42, Issue 6 https://doi.org/10.1109/TSMCC.2012.2187188	journal	November 2012
An Offshore Risk Analysis Method Using Fuzzy Bayesian Network Ren, J.; Jenkinson, I.; Wang, J. Journal of Offshore Mechanics and Arctic Engineering, Vol. 131, Issue 4 https://doi.org/10.1115/1.3124123	journal	September 2009
Detection of Faults and Drifts in the Energy Performance of a Building Using Bayesian Networks Bigaud, David; Charki, Abderafi; Caucheteux, Antoine Journal of Dynamic Systems, Measurement, and Control, Vol. 141, Issue 10 https://doi.org/10.1115/1.4043922	journal	June 2019
Maintenance of Smart Buildings using Fault Trees Cauchi, Nathalie; Hoque, Khaza Anuarul; Stoelinga, Marielle ACM Transactions on Sensor Networks, Vol. 14, Issue 3-4 https://doi.org/10.1145/3232616	journal	November 2018

Similar Records

Voltron Compatible Whole Building Root-Fault Detection and Diagnosis

Technical Report · Fri Nov 30 23:00:00 EST 2018 · OSTI ID:1524639

Using EMIS to Identify Top Opportunities for Commercial Building Efficiency

Technical Report · Tue Apr 11 00:00:00 EDT 2017 · OSTI ID:1350976

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

Journal Article · Tue Apr 05 20:00:00 EDT 2022 · Renewable and Sustainable Energy Reviews · OSTI ID:1865322

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Discrete Bayesian Network
HVAC system
cross-level fault
pattern matching
root cause fault diagnosis

Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Citation Formats

References (45)

Similar Records

Related Subjects