Alternative approach in performance analysis of organic rankine cycle (ORC)

Abstract

In this study, artificial neural networks (ANNs) and adaptive neuro-fuzzy (ANFIS) have been used for performance analysis of organic rankine cycle (ORC) using refrigerants R123, R125, R227, R365mfc, SES36. It is well known that the steam generator temperature, condenser temperature, subcooling temperature, and superheating temperature affect the efficiency ratio of ORC. Therefore, efficiency ratio is forecasted depending on variable system parameters values. The results of ANN are compared with ANFIS in which the same data sets are used. Furthermore, new formulations derived from ANN for five refrigerants are presented for the determination of the efficiency ratio. The R2 values obtained from the networks were 0.99917, 0.99670, 0.99870, 0.99928, and 0.99911 for the R123, R125, R227, R365mfc, SES36 respectively which is very satisfactory. © 2018 American Institute of Chemical Engineers Environ Prog, 38: 254–259, 2019.