Data-driven models for crashworthiness optimisation: intrusive and non-intrusive model order reduction techniques

Abstract

To enable multi-query analyses, such as optimisations of large-scale crashworthiness problems, a numerically efficient model is crucial for the development process. Therefore, data-driven Model Order Reduction (MOR) aims at generating low-fidelity models that approximate the solution while strongly reducing the computational cost. MOR methods for crashworthiness became only available in recent years; a detailed and comparative assessment of their potential is still lacking. Hence, this work evaluates the advantages and drawbacks of intrusive and non-intrusive projection based MOR methods in the framework of non-linear structural transient analysis. Both schemes rely on the collection of full-order training simulations and a subsequent subspace construction via Singular Value Decomposition. The intrusive MOR is based on a Galerkin projection and a consecutive hyper-reduction step. In this work, its inter-and extrapolation abilities are compared to the non-intrusive technique, which combines the subspace approach with machine learning methods. Moreover, an optimisation analysis incorporating the MOR methods is proposed and discussed for a crashworthiness example.

Dimensional reduction for parametric projection‐based reduced‐order models in crash

“…Therefore, parametric pROMs are the subject of this publication. The key question is how to properly create a parametric pROM, and more specifically, how to effectively reduce the dimension of the problem as the global POD approach reaches its limits [3]. One approach for parametric MOR is manifold interpolation [15], however, only suitable for linear models.…”

“…Data-fit models are purely data-driven models that learn correlations in the data, usually blind to the underlying physics. Gaussian process regression is a popular technique in this field [2,3]. Hierarchical models are physics-based models that rely on additional simplifications.…”

Dynamic Modeling With Integrated Concept Drift Detection for Predicting Real-Time Energy Consumption of Industrial Machines

“…Furthermore, many researchers use synthetic datasets, in which all concept drift points are known in advance. However, working with real-world industrial datasets is far more challenging as they typically include many missing values or unrecorded features, as well as unknown concept drifts and machine running conditions [13], [19].…”