Real-time Human Response Prediction Using a Non-intrusive Data-driven Model Reduction Scheme
This work addresses a specific bottleneck in model order reduction for time-dependent parameters in engineering applications like vehicle safety, representing an incremental advance over existing methods.
The paper tackled the problem of approximating parameterized ordinary differential equations with time-dependent parameters, which previous methods neglected, by introducing a two-step model order reduction scheme that combines classic reduction with an LSTM to predict reduced dynamics, achieving high accuracy and real-time capability in a car occupant model scenario.
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. This enables the parameters to be taken into account during 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.