Comparison of random forest, support vector regression, and long short term memory for performance prediction and optimization of a cryogenic organic rankine cycle (ORC)

Yuan Zhang, Xiaocheng Wu, Zhen Tian, Wenzhong Gao, Hao Peng and Ke Yang

Energy, 2023, vol. 280, issue C

Abstract: In this paper, three machine learning algorithms (Random Forest (RF), Support Vector Regression (SVR), and Long Short Term Memory (LSTM)) were used to predict and compare the thermodynamic performance of a 1 kW Organic Rankine Cycle (ORC) system under cryogenic operating conditions (i.e., cold source temperature < −160 °C). The cryogenic ORC system uses liquid nitrogen as the cold source, hot water as the heat source, and propane as the working fluid. Ten key operating parameters were selected as input parameters through Variable Importance Measures, and the output work of the expander, the cold exergy efficiency, and the system exergy destruction were used as output parameters. Moreover, the multi-objective optimization of this experimental system was conducted by applying the Non-dominated Sorting Genetic Algorithm III. The results showed that the RF algorithm was the most suitable algorithm among the three machine learning algorithms. According to the optimal results of the prediction model, the maximum error was 5.0251%, which was relatively small compared to the optimal results under experimental conditions. The related results demonstrate the feasibility of machine learning for cryogenic ORC data prediction, which can guide the design and improvement of ORC systems under low-temperature cold source conditions.

Keywords: Cryogenic organic rankine cycle; Machine learning algorithms; Performance prediction; Multi-objective optimization (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223015402
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:280:y:2023:i:c:s0360544223015402

DOI: 10.1016/j.energy.2023.128146

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().