Dynamic Bayesian Network for Fault Diagnosis

Ojas Pradhan, Jin Wen, Yimin Chen, Teresa Wu, Zheng O'Neill

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

A comparative study between using a dynamic Bayesian network (DBN) against using a static Bayesian network (BN) for building heating ventilating, and air conditioning fault diagnosis (HVAC) is presented. Contrarily to a static BN, DBN method incorporates temporal dependencies between fault nodes between timesteps using temporal conditional probabilities. This allows fault beliefs to accumulate over time and hence improves the diagnosis accuracy. The two methods are evaluated using real building data obtained from a campus building. Overall, the DBN showed improved fault belief when diagnosing and isolating faults across various components and sub-systems. Sensitivity tests on the temporal conditional probabilities for DBN showed that the model is robust.

Original languageEnglish (US)
Title of host publicationASHRAE Virtual Annual Conference, ASHRAE 2021
PublisherASHRAE
Pages6-9
Number of pages4
ISBN (Electronic)9781955516006
StatePublished - 2021
Externally publishedYes
Event2021 ASHRAE Virtual Annual Conference, ASHRAE 2021 - Virtual, Online
Duration: Jun 28 2021Jun 30 2021

Publication series

NameASHRAE Transactions
Volume127

Conference

Conference2021 ASHRAE Virtual Annual Conference, ASHRAE 2021
CityVirtual, Online
Period6/28/216/30/21

ASJC Scopus subject areas

  • Building and Construction
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'Dynamic Bayesian Network for Fault Diagnosis'. Together they form a unique fingerprint.

Cite this