BROWSE
Detail
Conference Paper
Ongoing Energy Fault Detection Using a Data-Driven Chiller Performance Prediction Model
Cited - time in 
Share 
Share
- Authors
- Hyunjin Yoon, Jong-Hyun Jang
- Issue Date
- 2012-12
- Citation
- International Conference on Computing and Convergence Technology (ICCCT) 2012, pp.866-869
- Language
- English
- Type
- Conference Paper
- Abstract
- Ongoing energy fault detection is a process of continuously comparing the actual performance of the building system calculated from the current monitoring data with the pre-determined target performance predicted by a mathematical model. In this paper, a noble ongoing energy fault detection method using multiple locally weighted linear regression models is proposed to provide more accurate prediction and reduce false alarms. In order to demonstrate the efficiency of the proposed method, its performance is empirically evaluated over the monitoring data acquired from a real-world centrifugal chiller and compared with the one of previous method in terms of both prediction and detection accuracy.
- KSP Keywords
- Accurate prediction, Building systems, Chiller performance, Current monitoring, Data-Driven, Detection accuracy, Fault detection method, Linear regression model, Locally weighted linear regression, Mathematical model, Monitoring data