Answers are grounded in this paper and cite their sources.
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 R2 (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 R2 of 0.72 and RMSE of 5.2 mm3. 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.
No takes yet. Share an insight, caveat, or question.
Zahmatkesh et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: