Emulate Engineering Expertise with Machine Learning for Automotive Crashworthiness Optimization, by BMW

Crash engineers orchestrate the chain of events that needs to fall into place during the crash event. This includes judgments on which crush behavior is favourable combined with the timing of discrete events such as bolts breaking or parts coming into contact at the right time. Handling these by scalar key performance indicators (KPI’s), of, for instance, energy absorption, peak force level before failure, crush behavior, and weight results in either too complex and over-constrained optimization problems to be solved by the surrogate approach or simply in a way to long response time for the fast-paced engineering processes.

Learn from Moritz Frenzel how the merging of high-class simulation and optimization techniques with state-of-the-art machine learning algorithms puts prediction quality and speed on the next level.