Surrogate Modeling of Suspensions with High Stiffness Element for Real-Time Analysis Using Machine Learning

The aim of this study is to generate a surrogate model of a suspension system with high stiffness elements for real-time analysis using machine learning. A Long Short-Term Memory networks was used as a machine learning method to generate surrogate models for three-degree-of-freedom quarter car model with a bush element. To evaluate the performance of the machine learning models, the simulation results and computation time were compared with the 3DOF model. As a result, it was confirmed that the response of the body acceleration was predicted with good accuracy by predicting the bush deformation and calculating the body acceleration based on the prediction results, instead of predicting the body acceleration directly. It was also confirmed that the machine learning model can accurately predict the body acceleration in less calculation time than the original model.