Operation characteristics and performance prediction of a 3 kW organic Rankine cycle (ORC) with automatic control system based on machine learning methodology

Yong-Qiang Feng, Qiang Zhang, Kang-Jing Xu, Chun-Ming Wang, Zhi-Xia He and Tzu-Chen Hung

Energy, 2023, vol. 263, issue PC

Abstract: Automatic control system enables the laboratory organic Rankine cycle (ORC) to adapt to variable operating conditions of industrial application. In this study, the operation characteristics of a 3 kW ORC with automatic control system applied to a chemical plant, as well as the performance prediction and optimization using machine learning methodology, are addressed. The dynamic behaviors for startup, operating and stop stages are discussed. The BP-ORC neural network model is established based on 3400 sets of experimental data, while the prediction accuracy is analyzed based on the errors of the training and test samples. The effects of six operation parameters on system performance are examined, while the bi-objective optimization for maximum thermal efficiency and maximum net output work is investigated. Results indicate that the component response times for startup stage and stop stage are 90s and 300s, respectively. Increasing the mass flow rate, decreasing the expander outlet temperature and increasing the expander inlet temperature ensure a higher net output work, while increasing the expander inlet temperature, decreasing the expander outlet temperature and increasing pump outlet pressure enable a higher thermal efficiency. The optimum net output work and thermal efficiency from Pareto-optimal solution are 2.87 kW and 8.855%, respectively.

Keywords: Organic Rankine cycle (ORC); Automatic control system; Machine learning methodology; Thermal efficiency; 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 (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222027438
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:263:y:2023:i:pc:s0360544222027438

DOI: 10.1016/j.energy.2022.125857

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 ().