Data Mining on Crash Simulation Data

TL;DR

This paper presents a data mining approach to analyze crash simulation data from BMW, aiming to uncover insights into how geometric variations affect crash performance, thereby aiding automotive design optimization.

Contribution

It introduces a comprehensive method for data analysis of finite element crash simulation data, including data pre-processing and integration into engineering workflows.

Findings

Successful application to BMW data demonstrates effectiveness

Revealed relationships between design variations and crash outcomes

Enhanced understanding of crash simulation data utilization

Abstract

The work presented in this paper is part of the cooperative research project AUTO-OPT carried out by twelve partners from the automotive industries. One major work package concerns the application of data mining methods in the area of automotive design. Suitable methods for data preparation and data analysis are developed. The objective of the work is the re-use of data stored in the crash-simulation department at BMW in order to gain deeper insight into the interrelations between the geometric variations of the car during its design and its performance in crash testing. In this paper a method for data analysis of finite element models and results from crash simulation is proposed and application to recent data from the industrial partner BMW is demonstrated. All necessary steps from data pre-processing to re-integration into the working environment of the engineer are covered.