Novel regenerator design for caloric cycles using artificial neural network — Genetic algorithm method and additive manufacturing
Bibliographic record
Abstract
Regenerators play an important role in the active caloric regeneration cycle to increase temperature span and system efficiency. However, most of the caloric cycles use limited designs of regenerators due to the limitations of conventional manufacturing. Therefore, this study proposes a novel regenerator design with a high heat transfer coefficient using the high design flexibility of additive manufacturing. The packed rod bed increases the heat transfer coefficient by using elliptical rods in the regenerator interfering with the flow. However, it also causes an increase in the pressure drop. Therefore, the geometric conditions of the regenerator were optimized using the proposed artificial neural network – genetic algorithm method with the help of CFD. Artificial neural network models were used to predict j and f factors of the packed rod bed and showed a mean relative error of less than 2.0 % for j factor, a mean relative error of less than 7.5 % for f factor. The optimized regenerator through the artificial neural network – genetic algorithm method increased the system efficiency by 4.7 % and the cooling capacity by 13.0 % compared to the baseline caloric cycle using a parallel plate matrix. The results of the optimization process were analyzed using artificial neural networks. This analysis shows that the well-trained artificial neural networks does not only help to find optimized geometric conditions but also helps to analyze the effects of geometric conditions on the heat exchanger performance. The new design of the regenerator can be easily applied to other caloric cycles through the artificial neural network – genetic algorithm method.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".