Mass Optimization Of 3D-Printed Composites Using Topology Optimization And Artificial Neural Network
Bibliographic record
Abstract
Additive manufacturing is a crucial new trend that is steadily taking over traditional methods.Despite its many advantages, the anisotropic nature of the produced parts of most additive manufacturing methods is a significant disadvantage.Of the methods that suffers from this anisotropy drawback is the fused filament fabrication (also known as fused deposition modeling).As a result of this anisotropy in the mechanical properties, a need arises to define the optimum direction of printing to be used for a certain loading condition.Topology optimization is a great numerical design tool for weight and material savings.It's basically used to determine where to put material to optimize a certain objective function under specific constraints.The design variables in a topology optimization are typically chosen as the densities of the finite elements.Adding the printing direction as an additional design variable complicates the problem further.This eventually gives rise to a huge selection of local minima and further increases in the computational costs.In this work, we attempt to utilize artificial neural networks to tackle this problem.Selected results of mass minimization problems run in ANSYS are used as input data for the neural network model, which is used to predict the fiber angle that has the minimum mass under specific stress constraints.Results so far are promising with small errors considering the computational savings achieved.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.001 |
| 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".