Machine Learning-Accelerated Virtual Testing
Machine Learning-Accelerated Virtual Testing for Automotive Head Impacts
Brain injury is a significant threat to road safety today and this challenge is expected to become more complex with the advent of automated vehicles that introduce new user aspects (eg, seat positions). Virtual testing based on finite element (FE) models is driving the transformation of vehicle assessment and safety research to enhance the protection of road users. However, the FE simulation is notoriously time-expensive, resource-intensive, and exclusively accessible to FE-skilled specialists, hindering the scalability and applicability of virtual testing for automotive assessment and fast-paced traffic safety research. This project wants a data-driven, machine learning (ML) model of the human head with rapid and reliable brain strain prediction across diverse automotive impacts to accelerate the virtual testing workflows. New knowledge of brain biomechanics relevant to current and future road users will be generated. This project will contribute to a paradigm shift in traffic safety investigations from the current FE-based, time-consuming evaluations to ML-accelerated virtual testing with drastically improved throughput, reinforcing Sweden's leading role in road safety worldwide. The partner responsible for the application is the Royal Institute of Technology and the industrial partner is Autoliv (Dr. Shiyang Meng). Volvo Cars and Euro NCAP will be served as reference groups.
Contact: Azilis Even
Funded by:
