Power generation from medium temperature geothermal resources: ANN-based optimization of Kalina cycle system-34

Recent technical developments have made it possible to generate electricity from geothermal resources of low and medium enthalpy. One of these technologies is the Kalina Cycle System. In this study, electricity generation from Simav geothermal field was investigated using the Kalina cycle system-34 (KCS-34). However, the design of these technologies requires more proficiency and longer times within complex calculations. An artificial neural network (ANN) is a new tool used to make a decision for the optimum working conditions of the processes within the expertise. In this study, the back-propagation learning algorithm with three different variants, namely Levenberg–Marguardt (LM), Pola–Ribiere Conjugate Gradient (CGP), and Scaled Conjugate Gradient (SCG), were used in the network so that the best approach could be found. The most suitable algorithm found was LM with 7 neurons in a single hidden layer. The obtained weights were used in optimization process by coupling the life-cycle-cost concepts.

► ANN (artificial neural network) model was developed to optimize KCS-34 for Simav. The most suitable algorithm found was LM 7 in single-hidden layer. ► A benefit ranging between US$ 56.5 and 152 million can be obtained from the plant. ► Optimum solution is get for T1b = 80 °C-X = 90% when the geothermal wells include vapor fraction of 10%. ► Optimum solution is get for T1b = 90 °C-X = 81% when the geothermal wells include vapor fraction of 30%. ► Plant is profitable for (present worth factor) PWF > 6.7. Most profitable conditions are obtained for X ranging between 80 and 90%.