Performance of machine learning algorithms to evaluate the physico-mechanical properties of nanoparticle panels
Bibliographic record
Abstract
Nanoparticles significantly enhance the properties of wood-based materials, especially particleboards and wood panels. This review analyzes secondary data on nanoparticle integration in board production, aiming to evaluate the relationships among physical (water absorption (WA) and thickness swelling (TS)) and mechanical (modulus of rupture (MOR), modulus of elasticity (MOE); and internal bond (IB) strength) properties and to predict performance using machine learning (ML) algorithms. These algorithms include Pearson correlation, hierarchical clustering, and decision tree (DT) models. Results indicate that nanoparticles such as graphene oxide (GO), reduced graphene oxide (rGO), hydrolysis lignin, and calcium carbonate improve mechanical properties, with MOR values of 27.38–52.65 MPa and MOE of 2591.6–4680 MPa, meeting EN312 load-bearing standards. Zinc oxide nanoparticles yield superior dimensional stability by achieving a low TS of 9.33%. However, according to the American National Standard for Particleboard (ANSI/A208.1-1999), most nanoparticle boards produced met general-purpose standards except for WA and TS, which exceeded the maximum limits of 8% and 3%, respectively. Only crosslinked chitosan and zinc oxide nanoparticle panels meet the minimum requirements for TS (17%) and the maximum MOR (11.00 MPa) and MOE (1,800.00 MPa) for general purposes in dry conditions (furniture and interior fitments) according to the Brazilian standard (ABNT NBR). The Pearson correlation analysis reveals a strong relationship between board properties (R = 0.94 for WA–TS; R = 0.93 for MOR–MOE), confirming that nanoparticle treatments enhance performance while maintaining inherent material behavior. Hierarchical clustering grouped nanoparticles by performance: zinc oxide and chitosan+UF+epoxy formed a cluster with the lowest WA and TS, indicating optimal dimensional stability, while GO, rGO, and chitosan-based composites clustered with moderate values. For mechanical properties, APTES-modified nanocellulose, aluminum oxide, and zinc oxide formed a high-performance cluster (high MOR, MOE, IB). DT algorithms demonstrated high predictive accuracy (R 2 = 0 . 92 for WA-TS, 0.96 for MOR-MOE, and 0.80 for IB-MOE), identifying critical thresholds: WA below 29.73% corresponded to minimal TS (9.94%), MOR above 38.18 MPa led to MOE above 3598.86 MPa, and IB above 0.88 MPa corresponds to MOE greater than 2,747.99 MPa. This data-driven framework enables targeted nanoparticle selection to fabricate engineered wood products and can be included in industry quality control standards to advance sustainable material development through ML-guided optimization.
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 | 0.005 | 0.013 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".