ANN based optimization of supercritical ORC-Binary geothermal power plant: Simav case study

Arslan O., Yetik Ö.

APPLIED THERMAL ENGINEERING, vol.31, pp.3922-3928, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 31
  • Publication Date: 2011
  • Doi Number: 10.1016/j.applthermaleng.2011.07.041
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.3922-3928
  • Keywords: Levenberg-Marquardt, Pola-Ribiere conjugate gradient, Scaled conjugate gradient, Artificial neural network, ORC-Binary, Super critical cycle, ARTIFICIAL NEURAL-NETWORKS, ORGANIC RANKINE-CYCLE, WORKING FLUIDS, ENERGY, PERFORMANCE, GENERATION, RESOURCES, ELECTRICITY, PREDICTION, PARAMETERS
  • Eskisehir Osmangazi University Affiliated: Yes


Artificial neural network is a new tool, which works rapidly for decision making and modeling of the processes within the expertise. Therefore, ANN can be a solution for the design and optimization of complex power cycles, such as ORC-Binary. In the present 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 to find the best approach. The most suitable algorithms found were LM 16 for s1 type cycle and LM 14 for s2 type cycle. The Organic Rankine Cycle (ORC) uses organic fluids as a working fluids and this process allows the use of low temperature heat sources and offers an advantageous efficiency in small-scale concepts. The most profitable cycle is obtained with a benefit of 124.88 million US$ from s1 type supercritical ORC-Binary plant with an installed capacity of 64.2 MW when the working fluid is R744 and the design parameters of T-1b, T-2a and P-2a are set to 80 degrees C, 130 degrees C and 12 MPa, respectively. (C) 2011 Elsevier Ltd. All rights reserved.