Leveraging machine learning for predicting human body model response in restraint design simulations
Hamed Joodaki, Bronisław Gepner, Jason Kerrigan
Abstract
The objective of this study was to leverage and compare multiple machine learning techniques for predicting the human body model response in restraint design simulations. Parametric simulations with 16 independent variables were performed. Ordinary least-squares (OLS), least absolute shrinkage and selection operator (LASSO), neural network (NN), support vector regression (SVR), regression forest (RF), and an ensemble method were used to develop response surface models of the simulations. The hyperparameters of the machine learning techniques were optimized through grid search and cross-validation to avoid under-fitting and over-fitting. The ensemble method outperformed other techniques, followed by LASSO, SVR, NN, RF, and OLS. Findings indicated that optimizing the metamodel hyper-parameters are essential to predict the optimum set of restraint design parameters.