Data-driven simulation for general-purpose multibody dynamics using Deep Neural Networks

  • PDF / 6,386,143 Bytes
  • 36 Pages / 439.37 x 666.142 pts Page_size
  • 78 Downloads / 150 Views

DOWNLOAD

REPORT


Data-driven simulation for general-purpose multibody dynamics using Deep Neural Networks Hee-Sun Choi1 · Junmo An2 · Seongji Han1 · Jin-Gyun Kim1 · Jae-Yoon Jung2 · Juhwan Choi3 · Grzegorz Orzechowski4 · Aki Mikkola4 · Jin Hwan Choi1

Received: 25 August 2019 / Accepted: 24 November 2020 © The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2020

Abstract In this paper, we introduce a machine learning-based simulation framework of general-purpose multibody dynamics (MBD). The aim of the framework is to construct a well-trained meta-model of MBD systems, based on a deep neural network (DNN). Since the main advantage of the meta-model is the enhancement of computational efficiency in returning solutions, the modeling would be beneficial for solving highly complex MBD problems in a short time. Furthermore, for dynamics problems, not only the accuracy but

B J.H. Choi

[email protected] H.-S. Choi [email protected] J. An [email protected] S. Han [email protected] J.-G. Kim [email protected] J.-Y. Jung [email protected] J. Choi [email protected] G. Orzechowski [email protected] A. Mikkola [email protected]

1

Department of Mechanical Engineering (Integrated Engineering), Kyung Hee University, 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do 17104, Republic of Korea

2

Department of Industrial and Management Systems Engineering, Kyung Hee University, 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do 17104, Republic of Korea

3

R&D Center, FunctionBay, Inc., 5F, Pangyo Seven Venture Valley 1 danji 2 dong, 15, Pangyo-ro 228 beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of Korea

H.-S. Choi et al.

also the smoothness in time of motion solutions, such as displacement, velocity, and acceleration, are essential aspects to consider. We analyze and discuss the influence of training data structures on both aspects of solutions. As a result of the introduced approach, the meta-model provides motion estimation of system dynamics without solving an analytical equation of motion or a numerical solver. Numerical tests demonstrate the performance of the proposed meta-modeling for representing several MBD systems. Keywords Multibody dynamics · Meta-model · Deep neural network · Feed forward network · Data-driven simulation

1 Introduction Using Machine Learning (ML) with big data is an important subject matter in science and engineering. This is because ML is effective to handle and interpret big data sets for the purpose of finding certain patterns from the data. In particular, Deep Neural Networks (DNNs), which are based on an Artificial Neural Network (ANN) with multiple hidden layers between input and output layers, allows users to handle complex shapes with nonlinear functions with multi-dimensional input data. DNNs have been successfully used in a large number of practical applications. A well trained neural network can provide precise solutions in real-time based on solution-patter recognition trained from data sets. This makes them idea