Fault detection and diagnosis of HVAC systems
This paper presents a model-based fault detection and diagnosis (FDD) system for building heating, ventilating, and air conditioning (HVAC). Model-based fault detection is based on the strategy of determining the difference or the residuals between the normal and the existing patterns. Their approach was to attack the problem on many levels of abstraction: from the signal level, controller programming level, and system component, all the way up to the information and knowledge processing level. The various issues of real implementation of the system and the processing of real-time on-line data in actual systems of campus buildings using the proven technology and off-the-shelf commercial tools are discussed. The research was based on input and output points and software control programs found in typical direct digital control systems used for variable-air-volume air handlers and VAV cooling and hot water reheat terminal units.
- Research Organization:
- Univ. of Cincinnati, OH (US)
- OSTI ID:
- 20002338
- Report Number(s):
- CONF-990102-; ISSN 0001-2505; TRN: IM200002%%338
- Resource Relation:
- Conference: ASHRAE Winter Meeting, Chicago, IL (US), 01/23/1999--01/27/1999; Other Information: PBD: 1999; Related Information: In: ASHRAE transactions 1999: Technical and symposium papers. Volume 105, Part 1, 1387 pages.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems
AN APPROACH TO BRINGING AUTOMATED FAULT DETECTION AND DIAGNOSIS (AFDD) TOOLS FOR HVAC&R INTO THE MAINSTREAM