AI Science Tracker
EN

Machine-learning-assisted prediction and optimization of tensile strength in particulate-filled polymer composites

Not stated in the abstract reviewed · 15 Nov 2026 · materials

Discovery

Machine-learning-assisted prediction and optimization of tensile strength in particulate-filled polymer composites

Source check: Source checked. Not independent scientific confirmation.

Finding: LASSO, K-nearest neighbors, support-vector regression and genetic-algorithm-optimized SVR were compared for tensile-strength prediction in metal-powder/resin composites. Evaluation used nested five-fold cross-validation on 45 experimental conditions, so performance is bounded to this dataset.

Technology: LASSO, KNN, SVR and GA-SVR regressors

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
LASSO, KNN, SVR and GA-SVR regressors
Test and result
A 45-condition metal-powder/resin composite dataset was used to predict tensile strength; nested five-fold cross-validation compared the models.
Limitation / still unknown
Small dataset; cross-validation is internal and does not establish performance on independently produced composites.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-026-78358-9

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse materials discoveries.