Approach for machine learning based design of experiments for occupant simulation

The complexity of crash scenarios in the context of vehicle safety is steadily increasing. This is especially the case on the way to mixed traffic challenges with non-automated and automated driving vehicles. The number of simulations required to design a robust restraint system is thus also increasing. The vast range of possible scenarios here is causing a huge parameter space. Simultaneously biofidelic simulation models are resulting in very high computational costs and therefore the number of simulations should be limited to a feasible operational range. In this study, a machine-learning based design of experiments algorithm is developed, which specifically addresses the issues when designing a safety system with a limited number of simulation samples taking diversity of the occupant and accident scenario into account. In contrast to an optimization task, where the aim is to meet a target function, our job has been to find the critical load case combinations to make sure that these are addressed and not missed. A combination of a space-filling approach and a metamodel has been established to find the critical scenarios in order to improve the system for those cases. It focuses specifically on the areas that are difficult to predict by the metamodel. The developed method was applied to iteratively generate a simulation matrix of a total of 208 simulations with a generic interior model and a detailed FE human body model. Kinematic and strain-based injury metrics were used as simulation output. These were used to train the metamodels after each iteration and derive the simulation matrix for the next iteration. In this paper we present a method that allows the training of a robust metamodel for the prediction of injury criteria, considering both varying load cases and varying restraint system parameters for individual anthropometries and seating postures. Based on that, restraint systems or metamodels can be optimized to achieve the best overall performance for a huge variety of possible scenarios with a specific focus on critical scenarios.

[1]  M. Östling,et al.  Generic Crash Pulses Representing Future Accident Scenarios of Highly Automated Vehicles , 2022, SAE International Journal of Transportation Safety.

[2]  Jonas Kneifl,et al.  Real-time Human Response Prediction Using a Non-intrusive Data-driven Model Reduction Scheme , 2021, IFAC-PapersOnLine.

[3]  Hamed Joodaki,et al.  Is optimized restraint system for an occupant with obesity different than that for a normal BMI occupant? , 2021, Traffic injury prevention.

[4]  N. Lubbe,et al.  Rib Cortical Bone Fracture Risk as a Function of Age and Rib Strain: Updated Injury Prediction Using Finite Element Human Body Models , 2021, Frontiers in Bioengineering and Biotechnology.

[5]  Bronislaw Gepner,et al.  Leveraging machine learning for predicting human body model response in restraint design simulations , 2020, Computer methods in biomechanics and biomedical engineering.

[6]  V. Roshan Joseph,et al.  Designing computer experiments with multiple types of factors: The MaxPro approach , 2020, Journal of Quality Technology.

[7]  Li Shengbo,et al.  A framework for rapid on-board deterministic estimation of occupant injury risk in motor vehicle crashes with quantitative uncertainty evaluation , 2020, Science China Technological Sciences.

[8]  Matthew B. Panzer,et al.  Occupant Safety in Vehicles Equipped With Automated Driving Systems, Part 3: Biofidelity Evaluation of GHBMC M50-OS Against Laboratory Sled Tests , 2020 .

[9]  Jeffrey Richard Crandall,et al.  Methodology for vehicle safety development and assessment accounting for occupant response variability to human and non-human factors , 2020, Computer methods in biomechanics and biomedical engineering.

[10]  J. Watt,et al.  Machine Learning Refined , 2020 .

[11]  Corina Klug,et al.  Postprocessing of Human Body Model Results – Introduction of the Open Source Tool DYNASAUR , 2018 .

[12]  Nianfei Gan,et al.  Hybrid meta-model-based design space exploration method for expensive problems , 2018, Structural and Multidisciplinary Optimization.

[13]  Harry Singh,et al.  Vehicle Interior and Restraints Modeling Development of Full Vehicle FiniteElement Model Including Vehicle Interior and Occupant Restraints Systemsfor Occupant Safety Analysis Using THOR Dummies , 2018 .

[14]  Liang Xia,et al.  A system methodology for optimization design of the structural crashworthiness of a vehicle subjected to a high-speed frontal crash , 2017 .

[15]  Jianguang Fang,et al.  On design optimization for structural crashworthiness and its state of the art , 2017 .

[16]  Jeremy Watt,et al.  Machine Learning Refined: Foundations, Algorithms, and Applications , 2016 .

[17]  Costin D. Untaroiu,et al.  Performance-Based Classification of Occupant Posture to Reduce the Risk of Injury in a Collision , 2013, IEEE Transactions on Intelligent Transportation Systems.

[18]  Thomas J. Santner,et al.  Noncollapsing Space-Filling Designs for Bounded Nonrectangular Regions , 2012, Technometrics.

[19]  Luc Pronzato,et al.  Design of computer experiments: space filling and beyond , 2011, Statistics and Computing.

[20]  Costin D. Untaroiu,et al.  Identification of occupant posture using a Bayesian classification methodology to reduce the risk of injury in a collision , 2011 .

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  Sudhanshu K. Mishra,et al.  Some New Test Functions for Global Optimization and Performance of Repulsive Particle Swarm Method , 2006 .

[23]  L. Breiman Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[24]  Tim Oates,et al.  Efficient progressive sampling , 1999, KDD '99.

[25]  Lotta Jakobsson,et al.  Integrated safety: establishing links for a comprehensive virtual tool chain , 2019 .

[26]  Tanja Hueber,et al.  Gaussian Processes For Machine Learning , 2016 .

[27]  Krystoffer Mroz,et al.  Predicting rib fracture risk with whole-body finite element models: development and preliminary evaluation of a probabilistic analytical framework. , 2012, Annals of advances in automotive medicine. Association for the Advancement of Automotive Medicine. Annual Scientific Conference.

[28]  Dirk Gorissen,et al.  Space-filling sequential design strategies for adaptive surrogate modelling , 2009, SOCO 2009.