The glass transition temperature (T_g) of styrene-butadiene rubber (SBR) is a key parameter determining its low-temperature flexibility and processing performance. Accurate prediction of T_g is crucial for material design and application optimisation. Addressing the limitations of traditional experimental measurements and theoretical models in terms of efficiency, cost, and accuracy, this study proposes a machine learning prediction framework that integrates multi-model ensemble and Bayesian optimization by constructing a multi-component feature dataset and algorithm optimization strategy. Based on the constructed high-quality dataset containing 96 SBR samples, nine machine learning models were employed to predict the T_g of SBR and compare their prediction performance. Ultimately, a GPR-XGBoost mixed model was constructed through model ensemble, achieving high-precision prediction with R² values greater than 0.9 on both the training and test sets. Further feature attribution and local effect analysis were conducted using feature analysis methods such as SHAP and ALE, revealing the nonlinear influence patterns of various components on T_g, providing a theoretical basis for SBR formulation design and T_g regulation. The machine learning prediction framework established in this study combines high-precision prediction with interpretability, significantly enhancing the prediction performance of the T_g of SBR. It offers an efficient tool for SBR molecular design and holds great potential for promotion and application.

Driven by the demands of environmental protection and sustainable development, bio-based polyurethanes exhibit promising application prospects as green damping materials. However, research on their application in vibration and noise reduction remains insufficient, and their damping performance still requires further enhancement. In this work, a bio-based polyurethane elastomer was synthesized using bio-based poly (trimethylene ether) glycol (PO3G) as the soft segment. Composites of the hindered phenol AO-80 and the bio-based polyurethane elastomer were prepared via physical blending. A systematic characterization of hydrogen bonding interactions, mechanical properties, and damping behavior was conducted using Fourier transform infrared spectroscopy, differential scanning calorimetry, tensile testing, and dynamic mechanical analysis. The experimental results indicate that with the increasing AO-80 content results in stronger hydrogen bonding within the composites strengthens.Consequently, the tensile strength improved from 6.3 MPa to 10.2 MPa, the elongation at break increased from 209% to 321%, the glass transition temperature rose from -43.2 ℃ to -23.8 ℃, and the maximum loss factor (tanδ_max) enhanced from 0.71 to 1.06. This work provides a novel approach for developing high-performance bio-based polyurethane damping materials.

Self-healing materials can detect damage and repair it through intrinsic mechanisms, addressing critical issues such as performance degradation and shortened service life of polymer materials during operation. They represent a pivotal research direction in the field of polymer science. Self-healing technologies are broadly classified into two categories: extrinsic and intrinsic. Extrinsic self-healing relies on a synergistic carrier-healing agent-catalyst system. Although the healing process is straightforward, it suffers from inherent limitations including high raw material costs, complex fabrication processes, and limited healing cycles at the same damage site. In contrast, intrinsic self-healing constructs dynamic bond networks via rational molecular design, enabling repeated cyclic healing and overcoming the drawbacks of extrinsic approaches. Compared with rubbers and epoxy resins, polyurethane (PU) elastomers exhibit superior compatibility with dynamic bond networks due to their exceptional molecular designability, making them the preferred substrates for integrating self-healing functionality. Meanwhile, they combine high elasticity, excellent mechanical strength, and good weather resistance, and have found extensive applications in mechanical equipment, aerospace engineering, and other industrial sectors. Nevertheless, they remain susceptible to performance failure induced by external mechanical damage. This study uses a systematic analytical framework covering dynamic bond network design, performance regulation, and scenario adaptation. The self-healing mechanisms, synergistic effects, performance-optimization strategies, and application-scenario requirements of dynamic bond-based self-healing systems are also described. The applications of intrinsic self-healing PU elastomers in fields such as wearable electronics and adhesives are reviewed, and key challenges including the trade-off between conflicting properties and poor environmental adaptability are highlighted. This work aims to provide a valuable reference for the development of function-oriented self-healing PU elastomers.