Optimization Design of Protective Helmet Structure Guided by Machine Learning

Abstract

With increasing digitization worldwide, machine learning has become a crucial tool in industrial design. This study proposes a novel machine learning-guided optimization approach for enhancing the structural design of protective helmets. The optimal model was developed using machine learning algorithms, including random forest (RF), support vector machine (SVM), eXtreme gradient boosting (XGB), and multilayer perceptron (MLP). The hyperparameters of these models were determined by ten-fold cross-validation and grid search. The experimental results showed that the RF model had the best predictive performance, providing a reliable framework for guiding structural optimization. The results of the SHapley Additive exPlanations (SHAP) method on the contribution of input features show that three structures—the transverse curvature at the foremost point of the forehead, the helmet forehead bottom edge elevation angle, and the maximum curvature along the longitudinal centerline of the forehead—have the highest contribution in both optimization goals. This research achievement provides an objective approach for the structural optimization of protective helmets, further promoting the development of machine learning in industrial design.