Performance Prediction of a Range of Diverse Solid Oxide Fuel Cells using Deep Learning and Principal Component Analysis
Bibliographic record
Abstract
Solid oxide fuel cell (SOFC) is a common fuel cell type that has high efficiency. SOFC is a complex non-linear system, subject to aging and manufacturing variation, which makes performance prediction difficult. To estimate the SOFC performance data-driven methods allow a trade-of between computation cost and accuracy. Eight different SOFC tubular cells with different properties are fabricated and experimentally tested in 18 different operating conditions. A deep neural network (DNN) is used to predict the output voltage of the cells. The input features of this network are the cell physical properties determined by scanning electron microscope (SEM) analysis and the operating parameters. As a first step, all measurable features are provided to principal component analysis (PCA) for feature selection resulting in a 50% reduction in features, resulting in a corresponding 50% reduction in the training time of the DNN. This trained DNN is able to capture the non-linear voltage drop of concentration polarization in the current density-voltage (J-V) curves. The prediction performance of the network is evaluated using three performance metrics of coefficient of determination (R 2 ), root mean square error (RMSE), and mean absolute percentage error (MAPE) with satisfactory accuracy for both the training and test datasets. For all predictions, R 2 is 0.99, MAPE is less than 1%, and RMSE is 0.0001 on the test dataset. During the training process, both the validation loss and training loss approach zero indicating that the trained model is not over-fitted. The DNN model can be useful for design and operation optimization purposes.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".