scholarly journals Nonlinear multiscale simulation of elastic beam lattices with anisotropic homogenized constitutive models based on artificial neural networks

2021 ◽  
Author(s):  
Til Gärtner ◽  
Mauricio Fernández ◽  
Oliver Weeger
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Lattice Structure ◽  
Constitutive Models ◽  
Multiscale Simulation ◽  
Multiscale Approach ◽  
Perturbation Approach ◽  
Material Symmetry ◽  
Highly Nonlinear ◽  
Artificial Neural

AbstractA sequential nonlinear multiscale method for the simulation of elastic metamaterials subject to large deformations and instabilities is proposed. For the finite strain homogenization of cubic beam lattice unit cells, a stochastic perturbation approach is applied to induce buckling. Then, three variants of anisotropic effective constitutive models built upon artificial neural networks are trained on the homogenization data and investigated: one is hyperelastic and fulfills the material symmetry conditions by construction, while the other two are hyperelastic and elastic, respectively, and approximate the material symmetry through data augmentation based on strain energy densities and stresses. Finally, macroscopic nonlinear finite element simulations are conducted and compared to fully resolved simulations of a lattice structure. The good agreement between both approaches in tension and compression scenarios shows that the sequential multiscale approach based on anisotropic constitutive models can accurately reproduce the highly nonlinear behavior of buckling-driven 3D metamaterials at lesser computational effort.

Modeling Vehicles’ Offset Impacts Using Recurrent Artificial Neural Networks

2000 ◽  
Author(s):  
Tarek A. Omar ◽  
Azim Eskandarian ◽  
Nabih E. Bedewi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Nonlinear Dynamic ◽  
Numerical Examples ◽  
Fe Simulations ◽  
First Case ◽  
Highly Nonlinear ◽  
Vehicle Structure ◽  
Artificial Neural ◽  
The Impact

Abstract In the last few years, the demand for general-purpose Finite Element (FE) vehicle models with fine mesh and small elements has increased the size of these models dramatically. The FE simulation of these models requires extensive CPU time, which makes the simulation cost an important issue to consider. The main objective of this research is to develop an accurate and computationally inexpensive method to predict a vehicle’s crash performance in the event of a collision. This becomes very important as the demand for performing several impact scenarios for each vehicle becomes excessive. This demand is driven by the desire to investigate different impact scenarios and to study the effect of the impact velocity, the offset-barrier ratio, and the impact angle on the dynamic behavior of the vehicle structure in crash events. In the last decade, Artificial Neural Networks (ANN) emerged as a reliable tool for solving nonlinear problems in variety of applications. The most important feature in ANNs is its ability to infer the nonlinear characteristics of any complex system, even if the mathematical model of the system does not exist. This is an extremely important feature when dealing with highly nonlinear dynamic problems such as vehicles collision. In a previous research conducted by the authors, advanced ANNs were developed and trained to model vehicles frontal impacts. This paper extends the concept and technique in order to use ANNs in modeling vehicles offset-barrier impacts. Special ANNs were developed, trained and tested through numerical examples for two different offset impact cases. The first case was 50% offset-barrier impact at five different impact velocities, while the second case was 35 mph frontal impact at five different offset-barrier ratios. Validated FE vehicle model was used to perform FE simulations for many different offset-barrier impacts. The crash profiles obtained from the FE simulations were used to train and test the developed ANNs. The results of these numerical examples indicated the ability of the ANNs to accurately capture the nonlinear dynamic characteristics of the vehicle structure for offset impacts. The trained networks could then be used to predict the crash profiles of any offset impact scenario within the training range.

scholarly journals Prediction of Soil Deformation in Tunnelling Using Artificial Neural Networks

2016 ◽  
Vol 2016 ◽  
pp. 1-16 ◽  
Author(s):  
Jinxing Lai ◽  
Junling Qiu ◽  
Zhihua Feng ◽  
Jianxun Chen ◽  
Haobo Fan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Rock Mass ◽  
Constitutive Models ◽  
Future Research ◽  
Dynamic Prediction ◽  
Regression Methods ◽  
Ann Models ◽  
Rock Mass Deformation ◽  
Artificial Neural

In the past few decades, as a new tool for analysis of the tough geotechnical problems, artificial neural networks (ANNs) have been successfully applied to address a number of engineering problems, including deformation due to tunnelling in various types of rock mass. Unlike the classical regression methods in which a certain form for the approximation function must be presumed, ANNs do not require the complex constitutive models. Additionally, it is traced that the ANN prediction system is one of the most effective ways to predict the rock mass deformation. Furthermore, it could be envisaged that ANNs would be more feasible for the dynamic prediction of displacements in tunnelling in the future, especially if ANN models are combined with other research methods. In this paper, we summarized the state-of-the-art and future research challenges of ANNs on the tunnel deformation prediction. And the application cases as well as the improvement of ANN models were also presented. The presented ANN models can serve as a benchmark for effective prediction of the tunnel deformation with characters of nonlinearity, high parallelism, fault tolerance, learning, and generalization capability.

scholarly journals Anisotropic hyperelastic constitutive models for finite deformations combining material theory and data-driven approaches with application to cubic lattice metamaterials

2020 ◽  
Author(s):  
Mauricio Fernández ◽  
Mostafa Jamshidian ◽  
Thomas Böhlke ◽  
Kristian Kersting ◽  
Oliver Weeger
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Finite Deformations ◽  
Material Behavior ◽  
Data Driven ◽  
Material Symmetry ◽  
Calibration Data ◽  
Simulation Data ◽  
Cubic Lattice ◽  
Artificial Neural

AbstractThis work investigates the capabilities of anisotropic theory-based, purely data-driven and hybrid approaches to model the homogenized constitutive behavior of cubic lattice metamaterials exhibiting large deformations and buckling phenomena. The effective material behavior is assumed as hyperelastic, anisotropic and finite deformations are considered. A highly flexible analytical approach proposed by Itskov (Int J Numer Methods Eng 50(8): 1777–1799, 2001) is taken into account, which ensures material objectivity and fulfillment of the material symmetry group conditions. Then, two non-intrusive data-driven approaches are proposed, which are built upon artificial neural networks and formulated such that they also fulfill the objectivity and material symmetry conditions. Finally, a hybrid approach combing the approach of Itskov (Int J Numer Methods Eng 50(8): 1777–1799, 2001) with artificial neural networks is formulated. Here, all four models are calibrated with simulation data of the homogenization of two cubic lattice metamaterials at finite deformations. The data-driven models are able to reproduce the calibration data very well and reproduce the manifestation of lattice instabilities. Furthermore, they achieve superior accuracy over the analytical model also in additional test scenarios. The introduced hyperelastic models are formulated as general as possible, such that they can not only be used for lattice structures, but for any anisotropic hyperelastic material. Further, access to the complete simulation data is provided through the public repository https://github.com/CPShub/sim-data.

Determination of S-N curves with the application of artificial neural networks

1999 ◽  
Vol 22 (8) ◽  
pp. 723-728 ◽  
Author(s):  
Artymiak ◽  
Bukowski ◽  
Feliks ◽  
Narberhaus ◽  
Zenner
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Artificial Neural

FUTURE OF ARTIFICIAL NEURAL NETWORKS IN SPACE EXPLORATION AND SPACE ENGINEERING

2018 ◽  
pp. 6-11
Author(s):  
Kobiljon Kh. Zoidov ◽  
◽  
Svetlana V. Ponomareva ◽  
Daniel I. Serebryansky ◽  
◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Space Exploration ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document