Prediction Model of Mechanical Properties of Elastic Composites Based on Machine Learning Algorithm

The objective of this study is to establish a predictive model for the mechanical performance of elastic composite materials, leveraging ML (Machine Learning) algorithms to enhance prediction accuracy and efficiency. Through the compilation and structuring of extensive experimental data, ML techniques are employed to train and refine predictive models. Experimental outcomes reveal that the Gradient Boosted Decision Tree (GBDT) model excels in metrics, including MSE, coefficient of determination, and MAE. Specifically, the GBDT model boasts an MSE of merely 4.11, an MAE of 1.12, an R-squared of 0.92, and an impressive prediction accuracy of 98%. These results suggest that the model demonstrates high predictive precision and stability, particularly when tackling nonlinear relationships and intricate datasets. This investigation offers substantial support for the design and optimization of elastic composite materials, paving the way for future studies. Future plans include expanding the dataset and exploring cutting-edge ML technologies to further bolster the model’s predictive capabilities and broaden its applicability.