Predictive Modelling of PEMFC Degradation Against Hydrogen Crossover Using Machine Learning Models in Matlab
Bibliographic record
Abstract
The complexity and nonlinearity of the connection between the hydrogen crossover and OCV decay led to extremely challenging establishment of their relationship and the possible prediction of their values using both experimental and conventional computational modeling approaches.Thus, machine learning becomes invaluable in providing low cost and efficient surrogate models that can capture and comprehend the effects of influential factors affecting the trends in the hydrogen crossover and OCV which makes the system highly complicated.To address the challenges in the characterization of PEMFC performance degradation as affected by the temporal hydrogen crossover, this work developed five ML-based models to carry out the OCV predictions using Matlab.The results of model performance evaluation, statistical analysis, and model fit performance suggest that Gaussian Process Regression-based model gave the best prediction accuracy among the other models using algorithms such as the Tri-Layered Neural Network, Ensemble, Decision Tree, and Kernel, with R and R 2 values of 1.0000 and 1.0000, respectively.During the deployment of GPR-based model, these values were observed to decrease to 0.9893 and 0.9787, respectively; still, an indicative of a well-performing model.Inversely, the model has showed more generalizability towards new experimental data and has minimized overfitting which makes it an excellent model for deployment.This finding is also aligned with the minimal RMSE, MSE, and MAE values of 0.0053, 0.00002765, and 0.0030, respectively.Given this, this work demonstrated the usability of machine learning to address the complexity of PEMFC degradation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".