Conference article

The sustainable working media selection is one of the most important stages in renewable energy technologies. The compromise among such properties as contribution to greenhouse effect; flammability; toxicity; thermodynamic behaviour; performance specifications; and the others defines a sustainable decision. The aim of present work is to apply a fuzzy set methodology providing sustainability among thermodynamic; economic; and environmental requirements. The organic Rankine cycle (ORC) for the class of working fluids based on the hydrofluoroethers (HFE) is considered to demonstrate a proposed approach. To select new working fluids; which have no information on thermodynamic behavior; artificial neural networks (ANN) approach is offered to forecast the ORC energy efficiency. The ANN correlations for coefficient of performance (COP) and pressure ratio (output) as functions of critical temperature; critical pressure and normal boiling temperature (input) are built via REFPROP database. The validation set has been used to estimate the ORC energy efficiency without of thermodynamic property calculations. The accuracy of ANN prediction for the cycle performances does not exceed 4% relative to the training set values. The Bellman – Zadeh model as the intersection of membership functions (fuzzy criteria mappings) is applied to sustainable selection of working media.

Working Fluids; Organic Rankine Cycle; Coefficient of Performance; Artificial Neural Networks