摘要

In the view point of recent technological developments, it is available to generate electricity from geothermal resources with low and medium enthalpy One of these technologies is binary cycle system, a kind of Organic Rankine Cycle (ORC), in which geothermal flow energy is used as an energy source. However, the design of these technologies requires more proficiency and longer times within complex calculations. Artificial Neural Network (ANN) is a new tool to make a decision and modeling of the processes within the expertise. In this way, ANN can be a solution for the design of complex power cycles such as ORC-Binary, since ANN is an information technology inspired by human brain's information processing technology. 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 was found as LM with 12 neurons in single hidden layer for b2 type cycle. For b3 type cycle, the most suitable algorithm was found as LM with 8 neurons in the first hidden layer and 10 neurons in the second hidden layer.

  • 出版日期2012-1