Accelerated design of architectured ceramics with tunable thermal resistance via a hybrid machine learning and finite element approach
Bibliographic record
Abstract
Topologically interlocked architectures can transform brittle ceramics into tougher materials, while making the material design procedure a cumbersome task since modeling the whole architectural design space is not efficient and, to a degree, is not viable. We propose an approach to design architectured ceramics using machine learning (ML), trained by finite element analysis data and together with a self-learning algorithm, to discover high-performance architectured ceramics in thermomechanical environments. First, topologically interlocked panels are parametrically generated. Then, a limited number of designed architectured ceramics subjected to a thermal load is studied. Finally, the multilinear perceptron is employed to train the ML model in order to predict the thermomechanical performance of architectured panels with varied interlocking angles and number of blocks. The developed feed-forward artificial neural network framework can boost the architectured ceramic design efficiency and open up new avenues for controllability of the functionality for various high-temperature applications. This study demonstrates that the architectured ceramic panels with the ML-assisted engineered patterns show improvement up to 30% in frictional energy dissipation and 7% in the sliding distance of the tiles and 80% reduction in the strain energy, leading to a higher safety factor and the structural failure delay compared to the plain ceramics.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".