A Novel Modelling Method for Fault Detection and Diagnosis in Large Water Chillers without Water Flow Measurements

DOI

10.2991/aiie-15.2015.139How to use a DOI?

Keywords

fault detection and diagnosis; water chiller; reference model

Abstract

Conventional fault detection and diagnosis in water chillers needs water flow measurements to calculate system load. However, the measurement of water flow meters usually fluctuates greatly, and high accuracy flow meters are very expensive. In this paper, a novel modelling method using a new reference model for fault detection and diagnosis in water chillers was developed, and the real evaporator water flow rate was replaced by a pseudo evaporator water flow rate that was equal to the designed evaporator water flow rate or the average evaporator flow rate under stable operation conditions. The new-developed reference model was validated by the data sets from ASHRAE 1043-RP. The validation results showed that the new developed reference model has good prediction accuracy and clear diagnosis rules, which can be used for fault detection and diagnosis in water chillers in the absence of water flow measurements.

Copyright

© 2015, 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  - C.Y. Zheng
AU  - W. Chen
PY  - 2015/07
DA  - 2015/07
TI  - A Novel Modelling Method for Fault Detection and Diagnosis in Large Water Chillers without Water Flow Measurements
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 518
EP  - 522
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.139
DO  - 10.2991/aiie-15.2015.139
ID  - Zheng2015/07
ER  -