Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach
Prior to the long-term utilization of solid oxide fuel cell (SOFC), one of the most remarkable electrochemical energy conversion devices, a variety of difficult experimental validation procedures is required, so it would be time-consuming and steep to predict the applicability of these devices in th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/21/7760 |
| _version_ | 1797467419096121344 |
|---|---|
| author | Mohammad Hossein Golbabaei Mohammadreza Saeidi Varnoosfaderani Arsalan Zare Hirad Salari Farshid Hemmati Hamid Abdoli Bejan Hamawandi |
| author_facet | Mohammad Hossein Golbabaei Mohammadreza Saeidi Varnoosfaderani Arsalan Zare Hirad Salari Farshid Hemmati Hamid Abdoli Bejan Hamawandi |
| author_sort | Mohammad Hossein Golbabaei |
| collection | DOAJ |
| description | Prior to the long-term utilization of solid oxide fuel cell (SOFC), one of the most remarkable electrochemical energy conversion devices, a variety of difficult experimental validation procedures is required, so it would be time-consuming and steep to predict the applicability of these devices in the future. For numerous years, extensive efforts have been made to develop mathematical models to predict the effects of various characteristics of solid oxide fuel cells (SOFCs) components on their performance (e.g., voltage). Taking advantage of the machine learning (ML) method, however, some issues caused by assumptions and calculation costs in mathematical modeling could be alleviated. This paper presents a machine learning approach to predict the anode-supported SOFCs performance as one of the most promising types of SOFCs based on architectural and operational variables. Accordingly, a dataset was collected from a study about the effects of cell parameters on the output voltage of a Ni-YSZ anode-supported cell. Convolutional machine learning models and multilayer perceptron neural networks were implemented to predict the current-voltage dependency. The resulting neural network model could properly predict, with more than 0.998 R<sup>2</sup> score, a mean squared error of 9.6 × 10<sup>−5</sup>, and mean absolute error of 6 × 10<sup>−3</sup> (V). Conventional models such as the Gaussian process as one of the most powerful models exhibits a prediction accuracy of 0.996 R<sup>2</sup> score, 10<sup>−4</sup> mean squared, and 6 × 10<sup>−3</sup> (V) absolute error. The results showed that the built neural network could predict the effect of cell parameters on current-voltage dependency more accurately than previous mathematical and artificial neural network models. It is noteworthy that this procedure used in this study is general and can be easily applied to other materials datasets. |
| first_indexed | 2024-03-09T18:53:22Z |
| format | Article |
| id | doaj.art-ec0294fca2524039bbfd869c13ddf83a |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-09T18:53:22Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-ec0294fca2524039bbfd869c13ddf83a2023-11-24T05:40:24ZengMDPI AGMaterials1996-19442022-11-011521776010.3390/ma15217760Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning ApproachMohammad Hossein Golbabaei0Mohammadreza Saeidi Varnoosfaderani1Arsalan Zare2Hirad Salari3Farshid Hemmati4Hamid Abdoli5Bejan Hamawandi6School of Metallurgy and Materials, College of Engineering, University of Tehran, Tehran 1417935840, IranSchool of Metallurgy and Materials Engineering, Iran University of Science and Technology, Tehran 1684613114, IranSchool of Metallurgy and Materials, College of Engineering, University of Tehran, Tehran 1417935840, IranSchool of Metallurgy and Materials, College of Engineering, University of Tehran, Tehran 1417935840, IranSchool of Metallurgy and Materials, College of Engineering, University of Tehran, Tehran 1417935840, IranRenewable Energy Research Department, Niroo Research Institute (NRI), Tehran 1468613113, IranDepartment of Applied Physics, KTH Royal Institute of Technology, SE-106 91 Stockholm, SwedenPrior to the long-term utilization of solid oxide fuel cell (SOFC), one of the most remarkable electrochemical energy conversion devices, a variety of difficult experimental validation procedures is required, so it would be time-consuming and steep to predict the applicability of these devices in the future. For numerous years, extensive efforts have been made to develop mathematical models to predict the effects of various characteristics of solid oxide fuel cells (SOFCs) components on their performance (e.g., voltage). Taking advantage of the machine learning (ML) method, however, some issues caused by assumptions and calculation costs in mathematical modeling could be alleviated. This paper presents a machine learning approach to predict the anode-supported SOFCs performance as one of the most promising types of SOFCs based on architectural and operational variables. Accordingly, a dataset was collected from a study about the effects of cell parameters on the output voltage of a Ni-YSZ anode-supported cell. Convolutional machine learning models and multilayer perceptron neural networks were implemented to predict the current-voltage dependency. The resulting neural network model could properly predict, with more than 0.998 R<sup>2</sup> score, a mean squared error of 9.6 × 10<sup>−5</sup>, and mean absolute error of 6 × 10<sup>−3</sup> (V). Conventional models such as the Gaussian process as one of the most powerful models exhibits a prediction accuracy of 0.996 R<sup>2</sup> score, 10<sup>−4</sup> mean squared, and 6 × 10<sup>−3</sup> (V) absolute error. The results showed that the built neural network could predict the effect of cell parameters on current-voltage dependency more accurately than previous mathematical and artificial neural network models. It is noteworthy that this procedure used in this study is general and can be easily applied to other materials datasets.https://www.mdpi.com/1996-1944/15/21/7760solid oxide fuel cell (SOFC)machine learningneural networkgaussian processSOFC performance |
| spellingShingle | Mohammad Hossein Golbabaei Mohammadreza Saeidi Varnoosfaderani Arsalan Zare Hirad Salari Farshid Hemmati Hamid Abdoli Bejan Hamawandi Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach Materials solid oxide fuel cell (SOFC) machine learning neural network gaussian process SOFC performance |
| title | Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach |
| title_full | Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach |
| title_fullStr | Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach |
| title_full_unstemmed | Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach |
| title_short | Performance Analysis of Anode-Supported Solid Oxide Fuel Cells: A Machine Learning Approach |
| title_sort | performance analysis of anode supported solid oxide fuel cells a machine learning approach |
| topic | solid oxide fuel cell (SOFC) machine learning neural network gaussian process SOFC performance |
| url | https://www.mdpi.com/1996-1944/15/21/7760 |
| work_keys_str_mv | AT mohammadhosseingolbabaei performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT mohammadrezasaeidivarnoosfaderani performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT arsalanzare performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT hiradsalari performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT farshidhemmati performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT hamidabdoli performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach AT bejanhamawandi performanceanalysisofanodesupportedsolidoxidefuelcellsamachinelearningapproach |