Journal of Harmonized Research in Engineering

ANN MODEL FOR PERFORMANCE ANALYSIS OF VCR SYSTEM WITH SUCTION PRESSURE, SUCTION TEMPERATURE, COMPRESSION RATIO AS INPUT PARAMETRE AND COP AS OUTPUT PARAMETER

Abstract

Author(s): Rakesh Kumar Agrawal, G.K. Agrawal, A.S. Zadgaonkar

 Artificial neural network (ANN) network4 has been developed for performance analysis of simple vapour compression system for various values of suction pressure, suction temperature, compression ratio as input parameter and coefficient of performance as output parameter. 54 set of experimental data is used to train ANN, network4 and 06 set of experimental data is used to test ANN, network4. Value of experimental COP and that predicted by ANN network4 for the data used to test the network resemble close to each other with R2=0.999217, RMSE =0.163, COV=2.84%. In developed ANN model network4 , network type feed forward back propagation, Adaptation learning function LEARNGDM , Training function TRAINLM, performance function MES, , No of neurons 08, No of layers 01, and Transfer function LOGSIG, with other training parameter has been used to successfully train ANN network4. We accomplish ANN with developed network4 can be successfully applied for evaluating COP of simple vapour compression refrigeration (VCR) system for given value of suction pressure, suction temperature, and compression ratio as input parameter,& hence ANN may be very useful tool for performance analysis of refrigeration system. Keywords: ANN, VCR system, COP, Compression ratio, Suction pressure, Suction temperature