Abstract
<title>Abstract</title> <p>Particulate-filled polymer composites (PFPCs) are characterized by high specific strength, good formability, and considerable design flexibility, making them key materials for rapid tooling in aerospace equipment manufacturing. In this study, metal powder/resin composites were investigated, and an experimental dataset of tensile strength was established. Three machine-learning regression algorithms, namely linear least absolute shrinkage and selection operator (LASSO) regression, k-nearest neighbors (KNN), and support vector regression (SVR), were employed to develop tensile-strength prediction models. A genetic algorithm (GA) was subsequently used to optimize the parameters of the SVR model, thereby establishing a GA-SVR-based tensile-strength optimization model for the composites.The results indicated that the tensile strength initially increased and then decreased with increasing particle volume fraction. A similar trend was observed with increasing particle size, whereas ball-milling time had only a limited effect on tensile strength. After optimization, the maximum tensile strength of the composite reached 63.72 MPa, corresponding to a particle volume fraction of 34.9%, a particle size of 32.3 µm, and a ball-milling time of 3.6 h. The proposed prediction method offers high efficiency and accuracy. Its application in teaching can also help students develop the ability to employ machine-learning algorithms to advance the preparation of advanced materials.</p>