Predicting Abrasion Resistance in Thermoplastic Polyurethanes Using Machine Learning
Bibliographic record
Abstract
ABSTRACT Abrasion resistance is a critical property of thermoplastic polyurethane (TPU), especially for applications in automotive, footwear, and medical devices where durability under mechanical stress is essential. Conventional testing methods for abrasion, such as ISO 4649, are time‐consuming and require specialized equipment. This study introduces a machine learning (ML)‐based predictive framework to estimate TPU abrasion volume loss using mechanical and structural property data extracted from the CAMPUS database. Key features including viscoelastic moduli, tensile and tear strength, Shore hardness, and density were selected through Pearson correlation analysis. Six supervised regression models were developed and evaluated: Linear, Polynomial, Decision Tree, Random Forest, Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR). SVR achieved the highest R 2 (0.79) on testing data, but its poor training performance indicated underfitting and sensitivity to data sparsity. In contrast, GBR demonstrated more consistent and generalizable predictions, achieving an R 2 of 0.72 and RMSE of 5.2 mm 3 . The results underscore the potential of ML algorithms to model structure–property relationships in elastomers. This approach offers a cost‐ and time‐efficient alternative for early‐stage screening of TPU grades and accelerates the design of abrasion‐resistant polymer formulations.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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 | 0.001 |
| 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 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".