Fault Detection Methods in Air-Conditioning System Based on Parametric Statistics Characteristics

DOI

10.2991/icmse-17.2017.79How to use a DOI?

Keywords

Air-conditioning systems; hybrid system model; fault detection; ROC analysis

Abstract

Fault detection for air-conditioning system was the key to guarantee performance and energy-saving. However, it was hard to resolve the parameter drift, multiple modes, incipient failures and existing failures via the conventional fault detection for air-conditioning system. This paper aimed at air-conditioning system with identical units and established hybrid mathematical models. The characteristic parameters of similar units was obtained by the Interactive Multi-mode(IMM) filter further processing parameter statistical properties of similar units, according to statistical properties of the parameters detect fault in the system. The results demonstrated that the fault detection method can be used to effectively detect incipient failures and preexisting failures in the air-conditioning system under the conditions of parameter drifting.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuan Liu
AU  - Pengcheng Zhao
AU  - Wei Li
AU  - Xiaozuo Lu
AU  - Yimin Wang
PY  - 2017/04
DA  - 2017/04
TI  - Fault Detection Methods in Air-Conditioning System Based on Parametric Statistics Characteristics
BT  - Proceedings of the 2017 7th International Conference on Manufacturing Science and Engineering (ICMSE 2017)
PB  - Atlantis Press
SP  - 412
EP  - 419
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-17.2017.79
DO  - 10.2991/icmse-17.2017.79
ID  - Liu2017/04
ER  -