Process history-based Fault Detection and Diagnosis for VAVAC systems

Author

Beghi, Alessandro ; Cecchinato, Luca ; Corso, Lorenzo ; Rampazzo, Mirco ; Simmini, Francesco

Author_Institution

Dept. of Inf. Eng., Univ. of Padova, Padua, Italy

fYear

2013

fDate

28-30 Aug. 2013

Firstpage

1165

Lastpage

1170

Abstract

Faulty operations of Heating, Ventilation and Air Conditioning (HVAC) systems can lead to discomfort for the occupants, energy wastage, unreliability and shorter equipment life. Cost-effective Fault Detection and Diagnosis (FDD) methods can therefore ensure an increase in the system uptime, reliability, and overall efficiency. In this paper, a simulation environment based on Matlab/Simulink^® is used in order to evaluate the performance of a FDD method using Support Vector Machines (SVMs). In detail, the proposed method is evaluated by performing extensive simulations to allow the investigation of the most common and relevant faults affecting this kind of systems.

Keywords

HVAC; fault diagnosis; mathematics computing; preventive maintenance; reliability; support vector machines; FDD methods; HVAC systems; Matlab; SVM; Simulink; VAVAC systems; cost-effective fault detection and diagnosis methods; energy wastage; equipment life shortability; equipment unreliability; fault diagnosis; faulty operations; heating ventilation and air conditioning; occupant discomfort; process history-based fault detection; simulation environment; support vector machines; system uptime; Atmospheric modeling; Coils; Cooling; Mathematical model; Shock absorbers; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications (CCA), 2013 IEEE International Conference on

Conference_Location

Hyderabad

ISSN

1085-1992

Type

conf

DOI

10.1109/CCA.2013.6662909

Filename

6662909