Automated Crash Avoidance systems have been on the market for the past decade and are growing rapidly in use. Activation of an automatic crash avoidance system such as pre-crash avoidance by braking or steering or a combination of both can influence the position of the occupant in a crash. Therefore, an active finite element human body model (HBM) with active muscles was developed and validated to enable prediction of human kinematics and injury risk in pre-crash avoidance manoeuvres followed by a crash. Such active finite element analyses are very complex and time consuming to run due to the long duration of the pre-crash event. Running a 3 second crash avoidance and crash analysis with the active human body model can take as long as three days on a computational server. The long run time makes the models not suitable for large parametric studies. Therefore, there is a need for a time and cost-efficient method to carry out such pre-crash and crash analysis.
Objective and Aim
The aim of the study is to develop a method for time-efficient analysis of combined occupant
pre-crash kinematics and crash injury risks by training a model using machine learning.
• Identify alternative methods used for modelling of computationally expensive finite
• Identify important model inputs for active human body models
• Train the machine learning model for varying pre-crash maneuvers and parameters
using the LUNAR software
• Demonstrate the applicability of the method for combined pre-crash and crash
• Compare the ML and FE predicted kinematics and injury risks
Students will learn and develop skills in modelling in ANSA and performing explicit FE
simulations in the software LS-DYNA with focus on biomechanical modelling.
• 1-2 Master students with Engineering background
• Machine Learning and Finite Element Method background is meritorious
If you find this opportunity interesting and in line with your profile. Do not wait with your application! We will start the recruitment process immediately and the position could be filled before the final application date, 2022-01-31.
If you have any questions, you are welcome to contact the supervisors/examiners:
Ekant Mishra (firstname.lastname@example.org) and
Karl-Johan Larsson (email@example.com),
Autoliv Research, Vårgårda