Ultrasonic thickness monitoring of material extrusion parts: machine learning analysis, and erosion testing
Bibliographic record
Abstract
Material extrusion is a cost-effective additive manufacturing method, yet parts can serve in corrosive or abrasive environments where hidden flaws can be critical. Ultrasonic non-destructive testing (NDT) offers in-situ quality evaluation, but layer-wise anisotropy and varied process parameters in additive manufacturing can complicate interpretation. We assess the capability of A-scan ultrasound to measure material extrusion part thickness across different infill patterns and infill densities, nominal part thicknesses, nozzle diameter, presence/absence of top or bottom skins and orientation of the measurements. A Random Forest model links process parameters to ultrasound and caliper data, enabling data-driven thickness prediction. Concentric infill produced time-of-flight readings that agreed best with caliper measurements and were insensitive to transducer orientation. Overall, A-scan reliably quantified thickness within the 2.5–10 mm range of the chosen contact probe. The machine-learning model achieved high R 2 and small errors for thickness and time-of-flight, demonstrating its potential for automated process monitoring. Finally, real-time ultrasound tracking of specimens subjected to simulated slurry erosion captured progressive wall loss, underscoring the feasibility of continuous integrity surveillance in service. These results establish practical guidelines for ultrasonic NDT of material extrusion parts.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.001 | 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".