Data analytics for simulation repositories in industry
Simulations are used intensively in the developing process of new industrial products and have achieved a high degree of detail. In that workflow often thousand finite element model variants, representing different product configurations, are simulated within a few days or even overnight. Currently the decision process for finding the optimal product parameters involves the comparative evaluation of large finite element simulation bundles by post-processing each one of those results using 3D visualisation software. This time consuming process creates a severe bottleneck in the product design and evaluation workflow. To handle these data we investigate an analysis approach based on nonlinear dimensionality reduction to find a low dimensional parameterisation of the dataset. In such a reduced representation, similar model variants are organised in clusters and the influence of the input variables can be analysed along such a parameterisation. We demonstrate the application of this approach to a realistic and relevant industrial example for robustness analysis of the bumper location in a frontal crash simulation. The approach has the potential to considerably speed up the virtual product development process by allowing an intuitive and interactive simultaneous evaluation of many product designs.
Full Text: PDF