In-Process Surface Analysis of a Sub-Scale Aerospace Component
Bibliographic record
Abstract
Comparing manufactured parts to their engineering design definition is the basis for Quality Control. Traditionally, Geometric Dimensioning and Tolerancing (GD&T) standards define how fabrication specifications are generated from the design intent. Due to the additive nature of the composite layup process, the Automated Fiber Placement (AFP) process requires a new paradigm for quality control to realize its full potential. To ensure the traditional GD&T part dimensional verification standards are met for the finished the part, the AFP process requires a ply-by-ply inspection of the as-built laminate to ensure that each layer in the ply stack conforms with the manufacturing allowable specifications. Each ply can be considered as an individual part which must be carefully inspected and mated with the other plies in the stack to form a composite assembly. Evaluating each ply as its own part introduces complexity and significant overhead to the composite layup process.To address this shortcoming, Fives and the Canadian National Research Council have proposed an In-Process Inspection (IPI) system based on Optical Coherence Tomography (OCT) technology that can perform high-resolution surface profilometry simultaneous to layup. Previous presentations about this technology have demonstrated how surface profile measurements and a rigorous sensor spatial calibration procedure are key enablers to accurately capture the layup surface. Furthermore, the methodology to automatically align the as-manufactured measurements to the as-designed engineering model was demonstrated as a key step to compare fabrication data to the CAD design reference.This paper will build on the previously described work and outline the feature detection engine of the IPI platform to locate and measure gaps, laps, tow-end location, and topical defects. A comprehensive feature detection sub-system must employ many layers of detection granularity. In this work, tow, course, ply, and volumetric level features are classified and regionally quantified as defects based on the Digital Ply Book provided by the Fives ACES Offline Programing software. A sub-scale component with features typical of aerospace parts will be used to demonstrate the technology. Preliminary results and several relevant disposition strategies will be described.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".