Real-time Human Response Prediction Using a Non-intrusive Data-driven Model Reduction Scheme

被引:2
作者
Kneifl, J. [1 ]
Hay, J. [1 ,2 ]
Fehr, J. [1 ]
机构
[1] Univ Stuttgart, Inst Engn & Computat Mech, Pfaffenwaldring 9, D-70569 Stuttgart, Germany
[2] ZF Friedrichshafen AG, Safe Mobil Simulat, D-88046 Friedrichshafen, Germany
关键词
Model Reduction; Machine Learning; Occupant Safety; Human Body Modeling; Parameterized Ordinary Differential Equations; Long Short-Term Memory;
D O I
10.1016/j.ifacol.2022.09.109
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recent research in non-intrusive data-driven model order reduction (MOR) enabled accurate and efficient approximation of parameterized ordinary differential equations (ODEs). However, previous studies have focused on constant parameters, whereas time-dependent parameters have been neglected. The purpose of this paper is to introduce a novel two-step MOR scheme to tackle this issue. In a first step, classic MOR approaches are applied to calculate a low-dimensional representation of high-dimensional ODE solutions, i.e., to extract the most important features of simulation data. Based on this representation, a long short-term memory (LSTM) is trained to predict the reduced dynamics iteratively in a second step considering the parameters at the respective time step. The potential of this approach is demonstrated on an occupant model within a car driving scenario. The reduced model's response to time-varying accelerations matches the reference data with high accuracy for a limited amount of time. Furthermore, real-time capability is achieved. Accordingly, it is concluded that the presented method is well suited to approximate parameterized ODEs and can handle time-dependent parameters in contrast to common methods. Copyright (C) 2022 The Authors.
引用
收藏
页码:283 / 288
页数:6
相关论文
共 11 条
[11]   Model order reduction based on Runge-Kutta neural networks [J].
Zhuang, Qinyu ;
Lorenzi, Juan Manuel ;
Bungartz, Hans-Joachim ;
Hartmann, Dirk .
DATA-CENTRIC ENGINEERING, 2021, 2