Alternative Approach in Performance Analysis of Organic Rankine Cycle (ORC) Bayram Kılıc¸ and Emre Arabacı Mehmet Akif Ersoy University, Bucak Emin G€ ulmez Technical Sciences Vocational School, Burdur, Turkey; bayramkilic@mehmetakif.edu.tr (for correspondence) Published online 00 Month 2018 in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ep.12901 In this study, artificial neural networks (ANNs) and adap- tive 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, subcool- ing temperature, and superheating temperature affect the effi- ciency 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 R 2 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. V C 2018 American Institute of Chemical Engineers Environ Prog, 00: 000–000, 2018 Keywords: organic rankine cycle, artificial neural network, neuro-fuzzy, gas turbine, energy efficiency INTRODUCTION The Organic Rankine Cycle (ORC) is named for its use of an organic, high molecular mass fluid with a liquid–vapor phase change, or boiling point, occurring at a lower temperature than the water-steam phase change. The fluid allows Rankine cycle heat recovery from lower temperature sources such as biomass combustion, industrial waste heat, geothermal heat, solar ponds and so forth. The low-temperature heat is converted into useful work, that can itself be converted into electricity [1]. The ORC operates on the same principle, only it uses as a working fluid an organic compound specially chosen to boil at a lower temperature, enabling it to extract power from lower temperature heat sources. Yuandan et al. [2] have been investigated the performance of ORC using hot air as heat resource. In work, the zeotropic mix- ture fluids studied are R227ea/R245fa, Butane/R245fa, and RC318/R245fa. They have been calculated and compared the first law efficiency, the second law efficiency, exergy loss distri- butions and net power output of zeotropic mixture fluids with corresponding pure fluids. Nishith and Santanu [3] have been determined that, thermo-economic comparisons of organic Ran- kine and steam Rankine cycles powered by linefocusing con- centrating solar collectors. They have been offered a simple selection methodology based on thermoeconomic analysis, and a comparison diagram for working fluids of power generating cycles. Thoranis et al. [4] have been offered a dimensionless term, the “Figure of Merit” (FOM), to investigate the thermal per- formance of a low temperature, ORC using six zeotropic mix- tures (R245fa/R152a, R245fa/R227ea, R245fa/R236ea, R245ca/ R152a, R245ca/R227ea, and R245ca/R236ea) as working fluids. They have been developed an empirical correlation to estimate the cycle efficiency from the FOM for all working fluids at con- densing temperatures of 25–408C and evaporating temperatures of 80–1308C. Shengming et al. [5] have been suggested a practi- cal method for designing ORC power generation system. They have been built two experimental systems. They have been used to offer data which were essential to establish the relation- ships needed to build the semi-empirical model in the first experimental system and were employed to validate the model in the second experimental system. In their work, the objective function has been derived with a single variable: evaporation temperature by combining the experimental data from the first experimental system and theoretical formulas. Chen et al. [6] have been investigated the performance analysis of ORC for 35 working fluids. In their work, discusses the types of working flu- ids, influence of latent heat, density and specific heat, and the effectiveness of superheating. They have been determined that the properties of the working fluids play vital role in the cycle performance. Hui-tao et al. [7] have investigated exergy analysis of ORC units operating by low-temperature exhaust gas waste heat and charged with dry and isentropic fluid. In addition, they have examined effects of thermodynamic parameters on ther- mal efficiency and exergy efficiency. They are demonstrated that performance of ORC units is primary affected by the ther- modynamic property of working fluid, the pinch point tempera- ture of the evaporator and the waste heat temperature. Li et al. [8] have invesigated thermo-economic analysis and comparison of a CO 2 transcritical power cycle and an ORC using R600a, R123, R245fa, and R601 as the working fluids operating by the low temperature geothermal source with the temperature rang- ing from 908C to 1208C. The results show that the regenerator can increase the thermodynamic performance of the CO 2 tran- scritical power cycle and an ORC. The maximum power output of the regenerative CO 2 transcritical power cycle is higher than that of the basic CO 2 transcritical power cycle. Shengjun et al. [9] have invesigated the parameter optimization and performance of the fluids in subcritical ORC and transcritical power cycle in low-temperature (80–1008C) binary geothermal power system. Matlab is used as optimization method. Five variables using in Matlab. These variables are exergy efficiency, thermal efficiency, recovery efficiency, heat exchanger area per unit power output, and the levelized energy cost. The results of their work show that the choice of working fluid varies the objective function and the value of the optimized operation parameters are not all V C 2018 American Institute of Chemical Engineers Environmental Progress & Sustainable Energy (Vol.00, No.00) DOI 10.1002/ep Month 2018 1 Published online 18 April 2018 in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ep.12901 satisfactory. © 2018 American Institute of Chemical Engineers Envi- ron Prog, 38: 254–259, 2019 254 January/February 2019 Environmental Progress & Sustainable Energy (Vol.38, No.1) DOI 10.1002/ep