Application of black-box models to HVAC systems for fault detection

Conference · Fri Nov 01 00:00:00 EST 1996

OSTI ID:392491

Peitsman, H C ^[1]; Bakker, V E ^[2]

---

1. TNO Building and Construction Research, Delft (Netherlands). Dept. of Indoor Environment, Building Physics and Systems
2. Univ. of Twente, Enschede (Netherlands). Dept. of Computer Science

This paper describes the application of black-box models for fault detection and diagnosis (FDD) in heating, ventilating, and air-conditioning (HVAC) systems. In this study, multiple-input/single-output (MISO) ARX models and artificial neural network (ANN) models are used. The ARX models are examined for different processes and subprocesses and compared with each other. Two types of models are established--system models and component models. In the case of system models, the HVAC system as a whole is regarded as a black box instead of as a collection of component models. With the component model type, the components of the HVAC system are regarded as separate black boxes.

• OSTI ID: 392491
• Report Number(s): CONF-960254-; TRN: IM9647%%345
• Resource Relation: Conference: Winter meeting of American Society of Heating, Refrigeration and Air Conditioning Engineers, Atlanta, GA (United States), 17-21 Feb 1996; Other Information: PBD: 1996; Related Information: Is Part Of ASHRAE transactions 1996: Technical and symposium papers. Volume 102, Part 1; PB: 1278 p.
• Country of Publication: United States
• Language: English

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
SPACE HVAC SYSTEMS
DIAGNOSTIC TECHNIQUES
MATHEMATICAL MODELS
NEURAL NETWORKS
COMPARATIVE EVALUATIONS
FAILURES
DATA ANALYSIS
BUILDINGS