Open AccessAn artificial intelligent approach for the optimization of organic rankine cycle power generation systems
Author(s) -
Jian-Ding Tan,
Chin Wai Lim,
S. P. Koh,
S. K. Tiong,
Ying-Ying Koay
Publication year - 2019
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v14.i1.pp340-345
Subject(s) - organic rankine cycle , convergence (economics) , maximum power point tracking , power (physics) , process (computing) , span (engineering) , computer science , term (time) , electricity generation , engineering , control theory (sociology) , mathematical optimization , mathematics , artificial intelligence , economics , inverter , physics , civil engineering , control (management) , quantum mechanics , economic growth , operating system
The study on Organic Rankine Cycle (ORC) power generation system has gained significant popularity among researchers over the past decade, mainly due to the financial and environmental benefits that the system provides. A good maximum power point tracking (MPPT) mechanism can push the efficiency of an ORC to a higher rate. In this research, a Self-Adjusted Peak Search algorithm (SAPS) is proposed as the MPPT scheme of an ORC system. The SAPS has the ability to perform a relatively detailed search when the convergence reaches the near-optima peak without jeopardizing the speed of the overall convergence process. The SAPS is tested in a simulation to track for a moving maximum power pint (MPP) of an ORC system. Experiment results show that the SAPS outperformed several other well-established optimization algorithm in tracking the moving MPP, especially in term of the solution accuracies. It can thus be concluded that the proposed SAPS performs well as a mean of an MPPT scheme in an ORC system