Local microstructure-properties model for HPVDC Aural™-2 using image analysis and machine learning
Bibliographic record
Abstract
High-integrity die castings require controlled strength and ductility for structural applications. These properties are the product of the local microstructure of the material after die filling and solidification. In this paper, a workflow of metallographic imaging, image analysis, and machine learning is investigated to estimate the mechanical properties at specific locations in a casting based on the local microstructure. Approximately 180 tensile specimens were first extracted from high pressure vacuum die cast Aural™-2/F plates at 1.8, 3.0 and 4.7 mm thickness and tested. Cross-sectional optical micrographs were then taken close to fracture locations at different magnifications to observe the microstructure. Image analysis routines were developed and applied to systematically quantify the key microstructural characteristics that are expected to affect strength and ductility. Challenges related to sampling of multi-scale and heterogeneous material, imaging resolution, high-volume analysis automation, and statistical descriptions were addressed to seek out compromises between characterization effort and accuracy. Finally, the predictive capability of different families of machine learning algorithms was tested with the dataset of the extracted microstructural characteristics for yield strength, elongation at break, and area reduction at fracture. Feature importance was also evaluated to determine key microstructural characteristics used in correlations. This work therefore assesses the potential for local, destructive estimation of expected in-service mechanical behaviour, for instance in regions where tensile coupons cannot be extracted. Validated relationships between microstructure and properties could also eventually complement simulation-based microstructure predictions from process parameters in an integrated computational materials engineering framework for designing new, lightweight die-cast structural components.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".