A Machine Learning Framework to Predict the Tensile Stress of Natural Rubber: Based on Molecular Dynamics Simulation Data

Abstract

Natural rubber (NR), with its excellent mechanical properties, has been attracting considerable scientific and technological attention. Through molecular dynamics (MD) simulations, the effects of key structural factors on tensile stress at the molecular level can be examined. However, this high-precision method is computationally inefficient and time-consuming, which limits its application. The combination of machine learning and MD is one of the most promising directions to speed up simulations and ensure the accuracy of results. In this work, a surrogate machine learning method trained with MD data is developed to predict not only the tensile stress of NR but also other mechanical behaviors. We propose a novel idea based on feature processing by combining our previous experience in performing predictions of small samples. The proposed ML method consists of (i) an extreme gradient boosting (XGB) model to predict the tensile stress of NR, and (ii) a data augmentation algorithm based on nearest-neighbor interpolation (NNI) and the synthetic minority oversampling technique (SMOTE) to maximize the use of limited training data. Among the data enhancement algorithms that we design, the NNI algorithm finally achieves the effect of approaching the original data sample distribution by interpolating at the neighborhood of the original sample, and the SMOTE algorithm is used to solve the problem of sample imbalance by interpolating at the clustering boundaries of minority samples. The augmented samples are used to establish the XGB prediction model. Finally, the robustness of the proposed models and their predictive ability are guaranteed by high performance values, which indicate that the obtained regression models have good internal and external predictive capacities.

Impact of Sacrificial Hydrogen Bonds on the Structure and Properties of Rubber Materials: Insights from All-Atom Molecular Dynamics Simulations

“…Stress–strain ( σ T – ε T ) curves are generated by uniaxial stretching deformation to determine the mechanical properties, and this method is consistent with our previous study. − To maintain a constant volume within the simulation box, we apply stretching along the Z -direction at a steady engineering strain rate, ε̇ T (as defined in eq ), concurrently reducing the lengths in the X and Y directions at the same rate. where L Z ( t ) and L Z (0) denote the length of the box in the Z -direction at time t and the initial moment, respectively. ε T is the applied tensile strain, and the ε̇ T is set to 10 –8 s –1 .…”