- Author
-
Kim, M.
|
Yoon, S. H.
|
Payne, W. V.
|
Domanski, P. A.
- Title
- Development of the Reference Model for a Residential Heat Pump System for Cooling Mode Fault Detection and Diagnosis.
- Coporate
- Korea Institute of Energy Research, Daejeon 305-343, Korea
Korea Institute of Machinery and Materials, Daejeon 305-343, Korea
National Institute of Standards and Technology, Gaithersburg, MD
- Journal
-
International Journal of Refrigeration,
- Sponsor
- Korea Institute of Machinery and Materials, Daejeon 305-343, Korea
- Keywords
-
heat pumps
|
residential buildings
|
cooling
|
fault trees
|
neural networks
|
steady state
|
tests
|
temperature
|
air conditioning
- Identifiers
- artificial neural network; heat pump fault detection; polynomial reference model; Fault Detection and Diagnosis (FDD); fault-free steady-state reference model; measurement uncertainties; system features used in fault detection; operating conditions for fault-free tests; MSR of the models fit to a reduced dataset; MSR of the models fit to the full dataset; MSR of the reduced dataset model applied to the full dataset
- Abstract
- Development of a reference model to predict the value of system parameters during fault free operation is a basic step for fault detection and diagnosis (FDD). In order to develop an accurate and effective reference model of a heat pump system, experimental data that cover a wide range of operating conditions are required. In this study, laboratory data were collected under various operating conditions and then filtered through a moving window steady-state detector. Over sixteen thousand scans of steady-state data were used to develop polynomial regression models of seven system features using three independent variables. The reference model was also developed using an artificial neural network (ANN), and its advantages and disadvantages are discussed. The models were evaluated, and the root mean square error for each model was calculated and compared