Crash Simulation

Crash simulation research aims to accurately predict vehicle behavior and component performance during collisions, primarily to improve safety and optimize designs. Current efforts focus on developing efficient surrogate models, often employing machine learning techniques like Gaussian Process Regression and Graph Convolutional Neural Networks, to reduce the computational cost of high-fidelity finite element analysis. These models are applied to various aspects, including battery enclosure design and load-path analysis, leveraging data from virtual crash tests to predict key metrics like energy absorption and intrusion. The resulting advancements improve design processes, leading to safer vehicles and more efficient engineering workflows.