Solid Oxide Fuel Cell Voltage Prediction by a Data-Driven Approach

Hristo Ivanov Beloev, Stanislav Radikovich Saitov, Antonina Andreevna Filimonova, Natalia Dmitrievna Chichirova, Egor Sergeevich Mayorov, Oleg Evgenievich Babikov and Iliya Krastev Iliev ()
Additional contact information
Hristo Ivanov Beloev: Department Agricultural Machinery, “Angel Kanchev” University of Ruse, 7017 Ruse, Bulgaria
Stanislav Radikovich Saitov: Department Nuclear and Thermal Power Plants, Kazan State Power Engineering University, 420066 Kazan, Russia
Antonina Andreevna Filimonova: Department Nuclear and Thermal Power Plants, Kazan State Power Engineering University, 420066 Kazan, Russia
Natalia Dmitrievna Chichirova: Department Nuclear and Thermal Power Plants, Kazan State Power Engineering University, 420066 Kazan, Russia
Egor Sergeevich Mayorov: Department Nuclear and Thermal Power Plants, Kazan State Power Engineering University, 420066 Kazan, Russia
Oleg Evgenievich Babikov: Department Nuclear and Thermal Power Plants, Kazan State Power Engineering University, 420066 Kazan, Russia
Iliya Krastev Iliev: Department of Heat, Hydraulics and Environmental Engineering, “Angel Kanchev” University of Ruse, 7017 Ruse, Bulgaria

Energies, 2025, vol. 18, issue 9, 1-24

Abstract: A solid oxide fuel cell (SOFC) is an electrochemical energy conversion device that provides higher thermoelectric efficiency than traditional cogeneration systems. Current research in this field highlights a variety of mathematical models. These models are based on complex physicochemical and electrochemical reactions, enabling accurate simulation and optimal control of fuel cells. However, these models require substantial computational resources, leading to high processing times. White box and gray box models are unable to achieve real-time optimization of control parameters. A potential solution involves using data-driven machine learning (ML) black-box models. This study examines three ML models: artificial neural network (ANN), random forest (RF), and extreme gradient boosting (XGB). The training dataset consisted of experimental results from SOFC laboratory experiments, comprising 32,843 records with 47 control parameters. The study evaluated the effectiveness of input matrix dimensionality reduction using the following feature importance evaluation methods: mean decrease in impurity (MDI), permutation importance (PI), principal component analysis (PCA), and Shapley additive explanations (SHAP). The application of ML models revealed a complex nonlinear relationship between the SOFC output voltage and the control parameters of the system. The default XGB model achieved the optimal balance between accuracy (MSE = 0.9940) and training speed (τ = 0.173 s/it), with performance capabilities that enable real-time enhancement of SOFC thermoelectric characteristics during system operation.

Keywords: solid oxide fuel cell (SOFC); machine learning; voltage prediction; feature-importance analysis (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/9/2174/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/9/2174/ (text/html)

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:gam:jeners:v:18:y:2025:i:9:p:2174-:d:1641348

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().