Thermodynamic performance prediction and optimization of a 1 kW ocean thermal energy cogeneration system based on artificial neural network

Yuan Zhang, Yifan Li, Zhen Tian, Chao Yang, Hao Peng, Ankang Kan and Wenzhong Gao

Energy, 2025, vol. 314, issue C

Abstract: In this paper, a prediction model based on the artificial neural network (ANN) method was constructed, and the thermodynamic performance prediction and optimization were conducted for a system for ocean thermal energy conversion that integrates an air conditioning cycle (OTEC-AC). By employing the variable importance measure (VIM) method, ten key parameters were selected as input parameters, and three output parameters, including system power generation (Wele), cold energy efficiency (ηco), and energy efficiency (ηen) were defined. The accuracies of prediction models constructed by the back propagation neural network (BPNN) and BPNN optimized by the particle swarm optimization algorithm (BPNN-PSO) were compared. Analysis of the thermodynamic characteristics and multi-objective optimization of the system were performed, and performance differences between the experimental data-based and the BPNN-PSO model-based system were compared. Results showed that optimizing the initial weights and thresholds of the model using the PSO algorithm could enhance the model's generalization capability. Multi-objective optimal results based on prediction data were very close to those based on experimental data, with a maximum relative error of 4.4498 %. This study validates the feasibility of using the ANN model for data prediction in OTEC cogeneration systems, which could provide guidelines for the optimal design of related systems.

Keywords: OTEC; Air conditioning; Artificial neural network; Particle swarm optimization algorithm; Multi-objective optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224040428
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:314:y:2025:i:c:s0360544224040428

DOI: 10.1016/j.energy.2024.134264

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 ().