Analysis of Car Crash Simulation Data with Nonlinear Machine Learning Methods

Bohn, Bastian; Garcke, Jochen; Iza-Teran, Rodrigo; Paprotny, Alexander; Peherstorfer, Benjamin; Schepsmeier, Ulf; Thole, Clemens A.

doi:10.1016/j.procs.2013.05.226

Cited by 53 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the complete algorithm is not accessible to the authors, it will not be considered in this article. The Simdata-NL project [11,12], on the other hand, used similar techniques to detect bifurcations and to group similarly behaving nodes. None of them were directly developed to separate a model for subsequent model reduction but they can be accommodated to our needs.…”

Section: Overview Of Crash Analysismentioning

confidence: 99%

“…In [11,12], a method was developed to cluster (finite element) nodes with different moving patterns and intensity across several simulations with small variations in the thickness of the sheet metal. In the end, the clusters were used to analyze the presence of bifurcations.…”

Section: Preprocessingmentioning

confidence: 99%

“…In [11], model reduction was applied to each cluster. Since no new simulations were done with a reduced system, this approach can be seen as data compression.…”

Section: Quality Of Clusters and Nonlinear Behaviormentioning

confidence: 99%

See 2 more Smart Citations

Identification of nonlinear behavior with clustering techniques in car crash simulations for better model reduction

Grunert

Fehr

2016

Adv. Model. and Simul. in Eng. Sci.

View full text Add to dashboard Cite

Background: Car crash simulations need a lot of computation time. Model reduction can be applied in order to gain time-savings. Due to the highly nonlinear nature of a crash, an automatic separation in parts behaving linearly and nonlinearly is valuable for the subsequent model reduction. Methods: We analyze existing preprocessing and clustering methods like k-means and spectral clustering for their suitability in identifying nonlinear behavior. Based on these results, we improve existing and develop new algorithms which are especially suited for crash simulations. They are objectively rated with measures and compared with engineering experience. In future work, this analysis can be used to choose appropriate model reduction techniques for specific parts of a car. A crossmember of a 2001 Ford Taurus finite element model serves as an industrial-sized example. Results: Since a non-intrusive black box approach is assumed, only heuristic approaches are possible. We show that our methods are superior in terms of simplicity, quality and speed. They also free the user from arbitrarily setting parameters in clustering algorithms. Conclusion: Though we improved existing methods by an order of magnitude, preparing them for the use with a full car model, they still remain heuristic approaches that need to supervised by experienced engineers.

show abstract

Section: Overview Of Crash Analysismentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Identification of nonlinear behavior with clustering techniques in car crash simulations for better model reduction

Grunert

Fehr

2016

Adv. Model. and Simul. in Eng. Sci.

View full text Add to dashboard Cite

show abstract

“…The algorithm is the following: first some constraints in the entire set of constraints are selected by a dedicated process, The number of constraints in this problem is now 2 times the length of g . After solving this linear problem, the violations for every constraints may be evaluated using (8). It corresponds to the gap between the high-fidelity data D BC ,* and the approximations made by the current reduced order model M =< * • O .…”

Section: Formulation Of the Linear Programsmentioning

confidence: 99%

“…These methods allow the use of partial or incomplete data (sample mesh in the DEIM and truncated integration domain in the APHR) to build a reduced order model. It is proposed in [7,8] to identify the parts having a non-linear behaviour and the parts having a linear behaviour using a clustering technique and to solve the non-linear problem with the DEIM and the linear part with Krylov subspaces [9]. As well as the APHR [10], this recent method has been applied to crash simulation but it seems limited to particular parts or small models with a low number of parameters.…”

Section: Introductionmentioning

confidence: 99%

A parametric and non-intrusive reduced order model of car crash simulation

Guennec

Brunet

Daim

et al. 2018

Computer Methods in Applied Mechanics and Engineering

View full text Add to dashboard Cite

Model reduction and clustering techniques for crash simulations

Fehr

Grunert

2015

Proc Appl Math and Mech

View full text Add to dashboard Cite

Model reduction in car crash simulations is a fairly new research field. In this paper, a possible workflow is presented: Since nonlinear behavior can occur, parts with linear and nonlinear behavior need to be separated with clustering methods such as k-means or spectral clustering. For the latter, a nonlinear reduction technique such as POD-DEIM needs to be applied. A longitudinal chassis beam of a 2001 Ford Taurus is used to examine the different clustering methods.

show abstract

Analysis of Car Crash Simulation Data with Nonlinear Machine Learning Methods

Cited by 53 publications

References 18 publications

Identification of nonlinear behavior with clustering techniques in car crash simulations for better model reduction

Identification of nonlinear behavior with clustering techniques in car crash simulations for better model reduction

A parametric and non-intrusive reduced order model of car crash simulation

Model reduction and clustering techniques for crash simulations

Contact Info

Product

Resources

About