Data-driven simulation for general purpose multibody dynamics using deep neural networks
This addresses simulation challenges in engineering domains like robotics or mechanics by providing a data-driven alternative, though it appears incremental as it applies existing DNN methods to multibody dynamics.
The paper tackles simulating multibody dynamics by introducing a deep neural network framework to create a meta-model that estimates motion data like displacement and forces without solving analytical equations, achieving accurate and reliable results as evaluated on several systems.
In this paper, a machine learning-based simulation framework of general-purpose multibody dynamics is introduced. The aim of the framework is to generate a well-trained meta-model of multibody dynamics (MBD) systems. To this end, deep neural network (DNN) is employed to the framework so as to construct data-based meta-model representing multibody systems. Constructing well-defined training data set with time variable is essential to get accurate and reliable motion data such as displacement, velocity, acceleration, and forces. As a result of the introduced approach, the meta-model provides motion estimation of system dynamics without solving the analytical equations of motion. The performance of the proposed DNN meta-modeling was evaluated to represent several MBD systems.