Model-based optimization of process parameters in high energy impact additive manufacturing processes
Bibliographic record
Abstract
Cold gas spraying is an emerging technology in additive manufacturing, known for its versatility and broad range of applications. This process enables the deposition of various materials, such as metals, ceramics and polymers, onto substrates by accelerating particles to high velocities within a Laval nozzle. To achieve optimal manufacturing quality at low cost, continuous and precise adjustment of process parameters is essential. However, due to the complex behavior of the gas dynamics, assessing quality during manufacturing is challenging. To address this issue, two data-driven modeling approaches are described and compared that connect process parameters to particle descriptors within the spray jet: a fast and easy-to-implement radial basis function network (RBFN) method and a low-parametric copula-based method in order to probabilistically model the high-dimensional dependencies among particle descriptors. These two modeling approaches are illustrated through an example of data-based optimization of process parameters for a cold gas spray in free jet, but are directly applicable to non-free jet data, if available. Additionally, both methods have low computational cost, making them suitable for applications even in autonomous process control. • Two data-driven modeling approaches for characterizing cold gas spraying. • Modeling of dependencies between particle descriptors using particle tracking velocimetry. • Fast and easy-to-implement radial basis function network approach. • Low-parametric copula-based approach using R-Vine copulas. • Model-based optimization of process parameters in free jet setting.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".