Machine-Learning-Accelerated Simulations for the Design of Airbag Constrained by Obstacles at Rest

Authors: José E. Valenzuela del Río, Elena Arvanitis, and Lucia Mirabella—Siemens Technology, United States; Richard Lancashire, Karan Chatrath, and Peter Ritmeijer—Siemens Industry Software, Netherlands

Abstract

Predicting airbag deployment geometries is an important task for airbag and vehicle designers to meet safety standards based on biomechanical injury risk functions. This prediction is also an extraordinarily complex problem given the number of disciplines and their interactions. State-of-the-art airbag deployment geometry simulations (including time history) entail large, computationally expensive numerical methods such as finite element analysis (FEA) and computational fluid dynamics (CFD), among others. This complexity results in exceptionally large simulation times, making thorough exploration of the design space prohibitive. This paper proposes new parametric simulation models which drastically accelerate airbag deployment geometry predictions while maintaining the accuracy of the airbag deployment geometry at reasonable levels; these models, called herein machine learning (ML)-accelerated models, blend physical system modes with data-driven techniques to accomplish fast predictions within a design space defined by airbag and impactor parameters. These ML-accelerated models are evaluated with virtual test cases of increasing complexity: from airbag deployments against a locked deformable obstacle to airbag deployments against free rigid obstacles; the dimension of the tested design spaces is up to six variables. ML training times are documented for completeness; thus, airbag design explorers or optimization engineers can assess the full budget for ML-accelerated approaches including training. In these test cases, the ML-accelerated simulation models run three orders of magnitude faster than the high-fidelity multi-physics methods, while accuracies are kept within reasonable levels within the design space.

Type: Full Paper

Keywords: Reduced order model, machine learning, neural networks, airbag deployment

© Stapp Association, 2023

Access Additional Papers from This Volume

View additional Full Papers from the Stapp Car Crash Journal, Volume 67.

• Comparison of Adult Female and Male PMHS Pelvis and Lumbar Response to Underbody Blast
  Authors: Hollie Pietsch—US Army DEVCOM Ground Vehicle Systems Center, Wayne State University; Danielle Cristino, Matthew Mason, Andrew Kemper, and Warren…
• Driving Behavior during Left-Turn Maneuvers at Intersections on Left-Hand Traffic Roads
  Author: Yasuhiro Matsui and Masashi Narita—National Traffic Safety and Environment Laboratory, Japan; Shoko Oikawa—Tokyo Metropolitan University, Japan  Abstract Understanding left-turn…
• Evaluation of DAMAGE Algorithm in Frontal Crashes
  Authors: Priya Prasad—Prasad Engineering, Inc.; Saeed D. Barbat and Anil Kalra—Ford Motor Company; Dainius Dalmotas—D.J. Dalmotas Consulting, Inc. Abstract With…
• Examination of Crash Injury Risk as a Function of Occupant Demographics
  Authors: Dainius Dalmotas, Aline Chouinard, Jean-Louis Comeau, Alan German, Glenn Robbins—D.J. Dalmotas Consulting, Inc.; Priya Prasad—Prasad Engineering, Inc. Abstract The…
• Frontal-Crash Occupant Protection in the Rear Seat: Submarining and Abdomen/Pelvis Response in Midsized Male Surrogates
  Authors: Allison J. Guettler, Samuel T. Bianco, Devon L. Albert, David M. Boyle, Andrew R. Kemper, and Warren N. Hardy—Virginia…
• Investigation of THOR-AV 5F Biofidelity in Sled Test Conditions with A Semi-Rigid Seat
  Authors: Z. Jerry Wang—Humanetics Innovative Solutions, Inc.; John Humm and Hans W. Hauschild—Medical College of Wisconsin Abstract THOR-AV 5F, a…
• Machine-Learning-Accelerated Simulations for the Design of Airbag Constrained by Obstacles at Rest
  Authors: José E. Valenzuela del Río, Elena Arvanitis, and Lucia Mirabella—Siemens Technology, United States; Richard Lancashire, Karan Chatrath, and Peter…

Looking for Something Else?