Machine Learning in 3D Printing
Bibliographic record
Abstract
In just a brief span of time, 3D printing process has made significant strides across various applications. A fundamental advantage of 3D printing lies in its ability to effortlessly produce intricate geometries. In this context, a central issue within 3D printing pertains to precision and achieving minimal tolerances using this technique. Given the mechanism of the 3D printing process, the resulting components can exhibit deviations from the original CAD model, leading to an increased incidence of defects, and reduced production output compared to other methods. Porosity, fractures, and surface unevenness are prevailing challenges inherent to 3D printing that are generally inevitable due to the manufacturing process. Among the available alternatives, compensating for these issues in the automotive industry seems to offer the most advantageous balance, considering aspects like cost and feasibility of implementation. Consequently, identifying discrepancies during the manufacturing process (real-time defect diagnosis and monitoring) and subsequently implementing corrective measures can be executed nearly simultaneously. In the realm of 3D printing, a modern approach involving artificial intelligence (AI), particularly machine learning (ML), has recently emerged to address the challenge of real-time monitoring. Moreover, this approach can extend to optimizing processing parameters, estimating costs, and addressing other pertinent considerations. ML holds the potential to train models for predicting outcomes based on unseen data, especially when abundant data and features are available. This chapter delves into the techniques and recent advancements concerning the integration of AI/ML in 3D printing, as well as the recent progress in monitoring the printing process.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".