Highly accurate Machine Learning models for Automotive Crash applications using CAE centric AI/ML Platform

In the automotive industry, there have been many efforts of late in using Machine Learning tools to aid virtual simulation and decrease product development time and cost. As the simulation world grapples with how best to incorporate ML techniques, two main challenges are evident. There is the risk of not knowing if the trained model is sound enough to drive the design. In addition, the complexity of porting simulation data back and forth to a ML software can make the process cumbersome. We would like to put forth a highly accurate and comprehensive one-stop ML workflow that has been implemented within a commercially available CAE driven platform called DEP MeshWorks. MeshWorks is used for rapid concept CAE and CAD model generation and parametrization. The AI platform within Meshworks leverages the inherent best-in-class parameterization capability to help rapidly generate data for training purposes. It is relatively quick to set up a fully parameterized CAE model and vary design features without a need for remeshing. MeshWorks has also introduced a seamless way of having CAE training data talk with Physics Informed Neural Network (PINN) Machine Learning models by transposing simulation output into a form usable by the ML models. In a first of its kind, a unique data structure named mwplot has been introduced to store all type of training data - scalars, vectors, nodal-field and nodal-time-history. This data structure will serve as the go-between of sorts between simulation output and the inbuilt ML tool. The output from the ML tool in mwplot form can be used to predict, optimise and even synthesize (GENAI) for the design objective within the MeshWorks platform. The ML tool inbuilt within MeshWorks is a PINN (Physics informed Neural Network) variant. It augments the empirical training by checking against governing physics so that any anomaly in the data can be accounted for while preserving the prediction capabilities. All these attributes make for a potent and efficient one-stop ML workflow that has been successfully used by various OEMS, the details of which will be shared.