Virtual Sensor Based on a Deep Learning Approach for Estimating Efficiency in Chillers

Abstract

Intensive use of heating, ventilation and air conditioning (HVAC) systems in buildings entails an analysis and monitoring of their e ciency. Cooling systems are key facilities in large buildings, and par- ticularly critical in hospitals, where chilled water production is needed as an auxiliary resource for a large number of devices. A chiller plant is often composed of several HVAC units running at the same time, be- ing impossible to assess the individual cooling production and e ciency, since a sensor is seldom installed due to the high cost. We propose a virtual sensor that provides an estimation of the cooling production, based on a deep learning architecture that features a 2D CNN (Convolu- tional Neural Network) to capture relevant features on two-way matrix arrangements of chiller data involving thermodynamic variables and the refrigeration circuits of the chiller unit. Our approach has been tested on an air-cooled chiller in the chiller plant at a hospital, and compared to other state-of-the-art methods using 10-fold cross-validation. Our re- sults report the lowest errors among the tested methods and include a comparison of the true and estimated cooling production and e ciency for a period of several days