Wave-Based Neural Network with Attention Mechanism for Damage Localization in Materials
Bibliographic record
Abstract
Cracks are omnipresent in materials and lead to billions of dollars in losses annually due to catastrophic and spectacular failures. Nondestructive wave-based methods are used to identify cracks, but these methods are cumbersome and require experts, leading to limited investigation. This research propose MicroCracksAttNet50E model that leverages numerical data to detect and localize damage in materials and structures, with a particular focus on microcracks that are imperceptible to the naked eye or conventional imaging methods but have the potential to develop into larger, hazardous fissures. The paper also includes a comparative analysis between the current study and the previous work, specifically evaluating the model that performed best in the prior paper (1D-DenseNet-Resize&Conv). Despite having approximately eight times fewer layers and over 200,000 fewer trainable parameters than DENSE variants, MicroCracksAttNet50E achieves similar or even better performance, with an accuracy of 0.860 and a precision of 0.881, compared to the best-performing DENSE model with an accuracy of 0.836 and a precision of 0.875. This improvement primarily highlights the effectiveness of the attention mechanism in MicroCracksAttNet50E, which focuses on critical areas to detect smaller cracks more accurately.
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 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".