Machine Learning Study of the Effect of Process Parameters on Tensile Strength of FFF PLA and PLA-CF
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Material extrusion is a popular additive manufacturing technology due to its low cost, wide market availability, ability to construct complex parts, safety, and cleanliness. However, optimizing the process parameters to obtain the best possible mechanical properties has not been extensively studied. This paper aims to develop ensemble learning-based models to predict the ultimate tensile strength, Young’s modulus, and the strain at break of PLA and PLA-CF 3D-printed parts, using printing temperature, printing speed, and layer thickness as process parameters. Additionally, the study investigates the impact of process parameters and material selection on the mechanical properties of the printed parts and uses genetic algorithms for multi-objective optimization according to user specifications. The results indicate that process parameters and material selection significantly influence the mechanical properties of the printed parts. The ensemble learning predictive models yielded an R2 value of 91.75% for ultimate tensile strength, 94.08% for Young’s modulus, and 88.54% for strain at break. The genetic algorithm successfully identified optimal parameter values for the desired mechanical properties. For optimal ultimate tensile strength, PLA-CF was used at 222.28 °C, 0.261 mm layer, 40.30 mm/s speed, yielding 41.129 MPa. For Young’s modulus: 4423.63 MPa, PLA-CF, 200.01 °C, 0.388 mm layer, 40.38 mm/s. For strain at break: 2.249%, PLA, 200.34 °C, 0.390 mm layer, 45.30 mm/s. Moreover, this work is the first to model the process–structure property relationships for an additive manufacturing process and to use a multi-objective optimization approach for multiple mechanical properties, utilizing ensemble learning-based algorithms and genetic algorithms.
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.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it