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 five thousand scans of steady-state data were used to develop polynomial regression models of seven system features. A reference model was also developed using an artificial neural network (ANN), and it is compared to the polynomial models.