Modeling Of A Direct Expansion Solar Assisted Heat Pump Using Artificial Neural Networks

摘要

This study presents the applicability of artificial neural networks (ANNs) to model a direct expansion solar assisted heat pump (DXSAHP). The experiments were conducted to determine the effects of solar intensity under the meteorological conditions of Calicut, India. The parameters such as coefficient of performance, compressor pressure ratio, air temperature at condenser outlet, and solar energy input ratio predicted from the experimental observations were used as training data. An ANN model for the system was developed based on back propagation learning algorithm. The results showed that the network yields a correlation coefficient in the range of 0.9973-0.9996, with minimum root mean square values between 0.0108 and 0.3884 and coefficient of variance in the range of 0.2828-0.9495. The results confirmed that ANN modeling of DXSAHP is acceptable.