A design-integrated visual intelligence framework for multi-scale defect quality assurance in micro-component engineering
Bibliographic record
Abstract
This study presents a design-integrated visual intelligence framework for micro-component quality assurance, enabling interpretable defect detection and real-time feedback in CAD-centric engineering workflows. The proposed Multi-Scale Multi-Feature Hybrid Model (MSMFHM) combines morphological and textural representations through bidirectional cross-attention with entropy-guided weighting. The architecture consists of a Resize-Focus preprocessor, Multi-Scale Mix Module, Multi-Feature Fusion Module, and dual-head decoder, aligning visual features with boundary-represented (B-Rep) CAD entities for tolerance verification and design traceability. Experiments on the TEC-Defect dataset demonstrate a Top-1 accuracy of 96.8% and a Macro-F1 score of 95.1%. Zero-shot validation on the DAGM2007 dataset confirms cross-domain generalization. The framework achieves 168 FPS at 3.8 GFLOPs on embedded hardware, ensuring deployment efficiency. Grad-CAM visualizations highlight interpretable feature attention and precise defect localization. The MSMFHM framework establishes an intelligent, CAD-integrated defect analysis pipeline, promoting proactive quality assurance and cyber-physical co-design across manufacturing processes.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".