Designing hydrogen-bonded self-healing polymers that exhibit high mechanical strength and efficient self-healing capability remains a major challenge. We employed molecular dynamics simulations to generate raw data for investigating the effects of four key features (hydrogen bond strength, hydrogen bond density, healing temperature, and healing time) on self-healing efficiency. Then, machine learning methods were used to construct predictive modeling and analyze feature importance using different algorithms. The Random Forest model exhibits a superior performance with the highest explanatory power and prediction accuracy. Finally, an inverse design approach was employed to identify optimal feature combinations that satisfy the requirements of the target healing efficiency. This integrated approach enables the rational design of polymers with customized healing and mechanical properties, providing theoretical guidance for the development of advanced self-healing polymers.
Li et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: