Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study
This study presents an advanced methodology that integrates experimental validation with machine learning (ML) models to predict and optimize power density in proton exchange membrane fuel cells (PEMFCs). The models considered include Linear Regression (LR), Stepwise Linear Regression (SLR), Tree Re...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Springer Science and Business Media Deutschland GmbH
2026
|
| Subjects: | |
| Online Access: | http://psasir.upm.edu.my/id/eprint/122921/1/122921.pdf http://psasir.upm.edu.my/id/eprint/122921/ https://link.springer.com/article/10.1007/s11581-025-06923-9?error=cookies_not_supported&code=82f4855e-5ca8-457d-9442-8f30a3c7aa9d |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1860590649942736896 |
|---|---|
| author | Katibi, Kamil Kayode Shukla, Arun Kumar Shitu, Ibrahim Garba Alotaibi, Khalid M. Imran, Ahamad Mojoyinola, Mubarak Olumide Sirajudeen, Abdul Azeez Olayiwola |
| author_facet | Katibi, Kamil Kayode Shukla, Arun Kumar Shitu, Ibrahim Garba Alotaibi, Khalid M. Imran, Ahamad Mojoyinola, Mubarak Olumide Sirajudeen, Abdul Azeez Olayiwola |
| author_sort | Katibi, Kamil Kayode |
| building | UPM Library |
| collection | Institutional Repository |
| content_provider | Universiti Putra Malaysia |
| content_source | UPM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | This study presents an advanced methodology that integrates experimental validation with machine learning (ML) models to predict and optimize power density in proton exchange membrane fuel cells (PEMFCs). The models considered include Linear Regression (LR), Stepwise Linear Regression (SLR), Tree Regression (TR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Gaussian Process Regression (GPR), Neural Networks (NN), Ensemble Learning (ENS), ElasticNet (EL), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). A high-precision experimental setup, employing Nafion 112 membranes, ultra-high-purity gases, and thoroughly controlled operational parameters, generated an extensive data set for model training. Model performance was carefully evaluated using key metrics, including Root Mean Square Error (RMSE), Mean Square Error (MSE), Coefficient of Determination (R²), and Mean Absolute Error (MAE). Among the models tested, GPR and NN demonstrated superior predictive accuracy (RMSE = 32.67 mW cm⁻²; R² = 0.96), capturing nonlinear dependencies in PEMFC dynamics. Residual analysis revealed the models’ ability to predict non-linear dependencies across mid-range operational conditions, while also identifying their limitations under extreme settings, such as high pressure or low current density. Unlike most PEMFC prediction studies that consider only current density and pressure, we explicitly model clamping line load across a wide operating envelope (5–15 N·cm− 1; 5–25 bar). This reveals how compression co-governs gas diffusion and proton conductivity, enabling models that generalize across regimes where flooding, dehydration, and contact resistance jointly shape performance. By integrating data-driven and physics-informed approaches, this research yields nonlinear predictors that provide actionable compression set points to sustain high power density, mitigate degradation risks, and offer indispensable guidelines for designing efficient and robust PEMFC systems, thereby advancing the development of green energy technologies. |
| format | Article |
| id | my.upm.eprints-122921 |
| institution | Universiti Putra Malaysia |
| language | en |
| publishDate | 2026 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| record_format | eprints |
| spelling | my.upm.eprints-1229212026-03-10T02:19:50Z http://psasir.upm.edu.my/id/eprint/122921/ Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study Katibi, Kamil Kayode Shukla, Arun Kumar Shitu, Ibrahim Garba Alotaibi, Khalid M. Imran, Ahamad Mojoyinola, Mubarak Olumide Sirajudeen, Abdul Azeez Olayiwola This study presents an advanced methodology that integrates experimental validation with machine learning (ML) models to predict and optimize power density in proton exchange membrane fuel cells (PEMFCs). The models considered include Linear Regression (LR), Stepwise Linear Regression (SLR), Tree Regression (TR), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Gaussian Process Regression (GPR), Neural Networks (NN), Ensemble Learning (ENS), ElasticNet (EL), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). A high-precision experimental setup, employing Nafion 112 membranes, ultra-high-purity gases, and thoroughly controlled operational parameters, generated an extensive data set for model training. Model performance was carefully evaluated using key metrics, including Root Mean Square Error (RMSE), Mean Square Error (MSE), Coefficient of Determination (R²), and Mean Absolute Error (MAE). Among the models tested, GPR and NN demonstrated superior predictive accuracy (RMSE = 32.67 mW cm⁻²; R² = 0.96), capturing nonlinear dependencies in PEMFC dynamics. Residual analysis revealed the models’ ability to predict non-linear dependencies across mid-range operational conditions, while also identifying their limitations under extreme settings, such as high pressure or low current density. Unlike most PEMFC prediction studies that consider only current density and pressure, we explicitly model clamping line load across a wide operating envelope (5–15 N·cm− 1; 5–25 bar). This reveals how compression co-governs gas diffusion and proton conductivity, enabling models that generalize across regimes where flooding, dehydration, and contact resistance jointly shape performance. By integrating data-driven and physics-informed approaches, this research yields nonlinear predictors that provide actionable compression set points to sustain high power density, mitigate degradation risks, and offer indispensable guidelines for designing efficient and robust PEMFC systems, thereby advancing the development of green energy technologies. Springer Science and Business Media Deutschland GmbH 2026-01-15 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/122921/1/122921.pdf Katibi, Kamil Kayode and Shukla, Arun Kumar and Shitu, Ibrahim Garba and Alotaibi, Khalid M. and Imran, Ahamad and Mojoyinola, Mubarak Olumide and Sirajudeen, Abdul Azeez Olayiwola (2026) Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study. Ionics, 32 (2). pp. 1-22. ISSN 0947-7047; eISSN: 1862-0760 https://link.springer.com/article/10.1007/s11581-025-06923-9?error=cookies_not_supported&code=82f4855e-5ca8-457d-9442-8f30a3c7aa9d Chemical Engineering (all) Materials Science (all) 10.1007/s11581-025-06923-9 |
| spellingShingle | Chemical Engineering (all) Materials Science (all) Katibi, Kamil Kayode Shukla, Arun Kumar Shitu, Ibrahim Garba Alotaibi, Khalid M. Imran, Ahamad Mojoyinola, Mubarak Olumide Sirajudeen, Abdul Azeez Olayiwola Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title | Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title_full | Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title_fullStr | Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title_full_unstemmed | Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title_short | Optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| title_sort | optimization and prediction of power density in proton exchange membrane fuel cells for green energy using advanced machine learning models: a comparative study |
| topic | Chemical Engineering (all) Materials Science (all) |
| url | http://psasir.upm.edu.my/id/eprint/122921/1/122921.pdf http://psasir.upm.edu.my/id/eprint/122921/ https://link.springer.com/article/10.1007/s11581-025-06923-9?error=cookies_not_supported&code=82f4855e-5ca8-457d-9442-8f30a3c7aa9d |
| url_provider | http://psasir.upm.edu.my/ |