Performance analysis of refrigeration system using artificial neural network

Abstract

In this research work. three artificial neural networks (ANNS) module named network newlinenetworks, and network with network type feed- forward back propagation is developed tor newlineperformance analysis of single-stage vapor compression refrigeration system Using newlinerefrigerant RI54a, which does not damage ozone layer. Experimental investigation is done to find the effect of suction pressure and other variables like suction temperature to compressor. newlinedelivery pressure, delivery temperature to compressor. to the heat absorbed at evaporator per newlinekg of refrigerant. compressor work per kg of refrigerant, and coefficient of performance at simple vapor compression system. Experimentation is performed under transient as well as steady condition as compressor speed changes due to fluctuation of voltage and rate o1 cooling at condenser also varies due to day to day changes in environmental condition. Due to transient condition the conventional analytical approach involves more complicated analytical equation and theoretical assumptions. whereas experimental studies are more expensive and time consuming, so in this research work an attempt has been made to train artificial neural networks (ANNs) .