Enhancing Hierarchical Multiscale Off-Road Mobility Model by Neural Network Surrogate Model

A hierarchical multiscale off-road mobility model is enhanced through the development of an artificial neural network (ANN) surrogate model that captures the complex material behavior of deformable terrain. By exploiting the learning capability of neural networks, the incremental stress and strain relationship of granular terrain is predicted by the ANN representative volume elements (RVE) at various states of the stress and strain. A systematic training procedure for ANN RVEs is developed with a virtual tire test rig model for producing training data from the discrete-element (DE) RVEs without relying on computationally intensive full vehicle simulations on deformable terrain. The ANN surrogate RVEs are then integrated into the hierarchical multiscale computational framework as a lower-scale model with the scalable parallel computing capability, while the macroscale terrain deformation is described by the finite element (FE) approach. It is demonstrated with several numerical examples that off-road vehicle mobility performances predicted by the proposed FE-ANN multiscale terrain model are in good agreement with those of the FE-DE multiscale model while achieving a substantial computational time reduction. The accuracy and robustness of the ANN RVE for fine-grain sand terrain are discussed for scenarios not considered in training datasets. Furthermore, a drawbar pull test simulation is presented with the ANN RVE developed with data in the cornering scenario and validated against the full-scale vehicle test data. The numerical results confirm the predictive ability of the FE-ANN multiscale terrain model for off-road mobility simulations.

[1]  M. Lefik,et al.  Artificial neural network as an incremental non-linear constitutive model for a finite element code , 2003 .

[2]  Trenton Kirchdoerfer,et al.  Data-driven computational mechanics , 2015, 1510.04232.

[3]  P. Jayakumar,et al.  Efficient generation of accurate mobility maps using machine learning algorithms , 2020 .

[4]  Hiroyuki Sugiyama,et al.  Physics-Based Flexible Tire Model Integrated With LuGre Tire Friction for Transient Braking and Cornering Analysis , 2016 .

[5]  Jian Fei Chen,et al.  Assessment of rolling resistance models in discrete element simulations , 2011 .

[6]  Rui Zhao,et al.  Stress-Strain Modeling of Sands Using Artificial Neural Networks , 1995 .

[7]  Ning Guo,et al.  A coupled FEM/DEM approach for hierarchical multiscale modelling of granular media , 2014 .

[8]  James H. Garrett,et al.  Knowledge-Based Modeling of Material Behavior with Neural Networks , 1992 .

[9]  Hammad Mazhar,et al.  Parallel Computing in Multibody System Dynamics: Why, When, and How , 2014 .

[10]  David Gorsich,et al.  The Next Generation NATO Reference mobility model development , 2017 .

[11]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[12]  H. Sugiyama,et al.  Physics-Based Deformable Tire–Soil Interaction Model for Off-Road Mobility Simulation and Experimental Validation , 2018 .

[13]  Karl Iagnemma,et al.  Next-Generation NATO Reference Mobility Model (NG-NRMM) , 2016 .

[14]  Jo Yung Wong,et al.  Theory of ground vehicles , 1978 .

[15]  Hiroyuki Sugiyama,et al.  Continuum Mechanics Based Bilinear Shear Deformable Shell Element Using Absolute Nodal Coordinate Formulation , 2015 .

[16]  Yang Liu,et al.  A nonlocal multiscale discrete‐continuum model for predicting mechanical behavior of granular materials , 2016 .

[17]  Antonio M. Recuero,et al.  A high-fidelity approach for vehicle mobility simulation: Nonlinear finite element tires operating on granular material☆ , 2017 .

[18]  Tamer M. Wasfy,et al.  Prediction of vehicle mobility on large-scale soft-soil terrain maps using physics-based simulation , 2018 .

[19]  Hiroyuki Sugiyama,et al.  Hierarchical Multiscale Modeling of Tire–Soil Interaction for Off-Road Mobility Simulation , 2019, Journal of Computational and Nonlinear Dynamics.

[20]  Musharraf Zaman,et al.  Modeling of soil behavior with a recurrent neural network , 1998 .

[21]  Huei Peng,et al.  Modeling of wheel-soil interaction over rough terrain using the discrete element method , 2013 .

[22]  Genki Yagawa,et al.  Implicit constitutive modelling for viscoplasticity using neural networks , 1998 .

[23]  C. O’Sullivan.  Particulate Discrete Element Modelling: A Geomechanics Perspective , 2011 .

[24]  Jaroslaw Knap,et al.  Accelerated scale-bridging through adaptive surrogate model evaluation , 2018, J. Comput. Sci..

[25]  Hiroyuki Sugiyama,et al.  Parallelized Multiscale Off-Road Vehicle Mobility Simulation Algorithm and Full-Scale Vehicle Validation , 2020 .

[26]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[27]  D. Owen,et al.  Computational methods for plasticity : theory and applications , 2008 .

[28]  François Chollet,et al.  Deep Learning with Python , 2017 .

[29]  Antonio M. Recuero,et al.  An integrated framework for high-performance, high-fidelity simulation of ground vehicle-tyre-terrain interaction , 2019, International Journal of Vehicle Performance.

[30]  Kun Wang,et al.  A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning , 2018, Computer Methods in Applied Mechanics and Engineering.