On the neural network calculation of the Lamé coefficients through eigenvalues of the elasticity operator (original) (raw)
Related papers
Numerical implementation of a neural network based material model in finite element analysis
International Journal for Numerical Methods in Engineering, 2004
Neural network (NN) based constitutive models can capture non-linear material behaviour. These models are versatile and have the capacity to continuously learn as additional material response data becomes available. NN constitutive models are increasingly used within the finite element (FE) method for the solution of boundary value problems. NN constitutive models, unlike commonly used plasticity models, do not require special integration procedures for implementation in FE analysis. NN constitutive model formulation does not use a material stiffness matrix concept in contrast to the elasto-plastic matrix central to conventional plasticity based models. This paper addresses numerical implementation issues related to the use of NN constitutive models in FE analysis. A consistent material stiffness matrix is derived for the NN constitutive model that leads to efficient convergence of the FE Newton iterations. The proposed stiffness matrix is general and valid regardless of the material behaviour represented by the NN constitutive model. Two examples demonstrate the performance of the proposed NN constitutive model implementation.
Polymers
The presented work deals with the creation of a new radial basis function artificial neural network-based model of dynamic thermo-mechanical response and damping behavior of thermoplastic elastomers in the whole temperature interval of their entire lifetime and a wide frequency range of dynamic mechanical loading. The created model is based on experimental results of dynamic mechanical analysis of the widely used thermoplastic polyurethane, which is one of the typical representatives of thermoplastic elastomers. Verification and testing of the well-trained radial basis function neural network for temperature and frequency dependence of dynamic storage modulus, loss modulus, as well as loss tangent prediction showed excellent correspondence between experimental and modeled data, including all relaxation events observed in the polymeric material under study throughout the monitored temperature and frequency interval. The radial basis function artificial neural network has been confirm...
Artificial Neural Networks - Recent Advances, New Perspectives and Applications [Working Title]
This chapter explores the use of an artificial neural network (ANN) to obtain the elastic constants of the components of a metal laminated composite material (MLCM). The dataset for the training and validation of the ANN was obtained by applying an analytical model developed for the study of stresses in MLCM. The information used in the dataset corresponds to MLCM configurations and data generated with variants registered in the structural presentation of the inputs and outputs. The best configuration found for the generation of the ANN models yielded an average relative error of less than 4% in relation to the results of the constants evaluated and published in a previous article. As shown in this research, it is important to have a clear definition of the problem as well as an effective selection and preparation of the characteristics of the training data during the constitutive modeling of composite materials and the correct application of the ANN.
Neural networks for computing in the elastoplastic analysis of structures
Meccanica, 1995
A neural network model is proposed and studied for the treatment of elastoplastic analysis problems. These problems are formulated as Q.P.P.s with inequality subsidiary conditions. In order to treat these conditions the Hopfield model is appropriately generalized and a neural model is proposed covering the case of inequalities. Finally, the parameter identification problem is formulated as a supervised leaming problem. Numerical applications close the presentation of the theory and the advantages of the neural network approach are illustrated.
Artificial Neural Networks in numerical modelling of composites
Computer Methods in Applied Mechanics and Engineering, 2009
In this paper, we show some different concepts for the use of Artificial Neural Networks in modelling of composites and hierarchical structures. Starting from a relatively small set of suitable numerical experiments performed on a unit cell, a proper set of corresponding input-output data is created to train the network to identify the effective properties. Furthermore, ANN based procedures can be exploited in a multiscale analysis as a tool for the stress-strain recovery at lower levels of the hierarchical structure and/or to estimate the state of yielding of the materials. This kind of application is of great computational importance, since with material non-linearity they allow for a significantly improved computational efficiency. Finally, ANNs may be used to define the homogenised properties for a class of parameterised unit cells or when material characteristics depend upon a parameter (e.g. temperature, damage, etc.). The problem of the best ANN (or sufficiently good ANN) for each type of applications is discussed by means of the examples presented throughout the paper.
Hybrid, finite element-artificial neural network model for composite materials
An application of Artificial Neural Networks for a definition of the effective constitutive law for a composite is described in the paper. First, a classical homogenisation procedure is directly interpreted with a use of this numerical tool. Next, a self-learning Finite Element code (FE with ANN inside) is used in the case when the effective constitutive law is deduced from a numerical experiment (substituting here a purely phenomenological approach). The new contribution to the classical selflearning procedure consists of its adaptation to a case of a non-monotonic loading (non one-to-one load-deformation curve). This new ability of the method is principally due to the incremental form of the constitutive equation and the respective scheme of the neural network structure. Also an organisation of a constitutive data-base containing learning patterns is suitably modified. It is shown by examples that the training process is very quick. The error of this method is smaller, comparing to other schemes of data acquisition.
Neural network for constitutive modelling in finite element analysis
2003
Finite element method has, in recent years, been widely used as a powerful tool in analysis of engineering problems. In this numerical analysis, the behavior of the actual material is approximated with that of an idealized material that deforms in accordance with some constitutive relationships. Therefore, the choice of an appropriate constitutive model, which adequately describes the behavior of the material, plays a significant role in the accuracy and reliability of the numerical predictions. Several constitutive models have been developed for various materials. Most of these models involve determination of material parameters, many of which have no physical meaning [1, 2]. In this paper a neural network-based finite element analysis will be presented for modeling engineering problems. The methodology involves incorporation of neural network in a finite element program as a substitute to conventional constitutive material model. Capabilities of the presented methodology will be illustrated by application to practical engineering problems. The results of the analyses will be compared to those obtained from conventional constitutive models.
Solving Inverse Problems in Viscoelasticity by Using Neural Network
Mechanical spectrum is a characteristic of polymers that describes their time-dependent mechanical properties. Mechanical spectrum represents molecular structural rearrangements on macro scale. Mechanical spectrum determines contribution of individual groups of molecules into the response of the whole material on external excitation and cannot be directly determined experimentally. Mathematical approach of mechanical spectrum determination requires solution of inverse problems that appear to be ill-posed in the case of non-standard excitations. This paper proposes artificial neural network as a tool for solving inverse problems that appear in case of ramp loading excitation that is usually provided by tensile-testing experiments. Two ways of modeling of physical systems using neural networks will be addressed in this work: conventional way that has mathematical background and is based on classical neural network theory, and non-conventional way of creation of the so-called “pre-stru...
Journal of Engineering Mechanics, 2022
We explore an application of the Physics Informed Neural Networks (PINNs) in conjunction with Airy stress functions and Fourier series to find optimal solutions to a few reference biharmonic problems of elasticity and elastic plate theory. Biharmonic relations are fourth-order partial differential equations (PDEs) that are challenging to solve using classical numerical methods, and have not been addressed using PINNs. Our work highlights a novel application of classical analytical methods to guide the construction of efficient neural networks with the minimal number of parameters that are very accurate and fast to evaluate. In particular, we find that enriching feature space using Airy stress functions can significantly improve the accuracy of PINN solutions for biharmonic PDEs.
Machine Learning Control Design for Elastic Composite Materials
2021
A novel numerical method, based on a machine learning approach, is used to solve an inverse problem involving the Dirichlet eigenfrequencies for the elasticity operator in a bounded domain filled with a composite material. The inhomogeneity of the material under study is characterized by a vector which is designed to control the constituent mixture of homogeneous elastic materials that compose it. Using the finite element method, we create a training set for a forward artificial neural network, solving the forward problem. A forward nonlinear map of the Dirichlet eigenfrequencies as a function of the vector design parameter is then obtained. This forward relationship is inverted and used to obtain a training set for an inverse radial basis neural network, solving the aforementioned inverse problem. A numerical example showing the applicability of this methodology is presented. Keywords: Machine learning • Composite materials • Inverse problems • Eigenfrequencies of the elasticity operator • Finite element method European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 777778: MATHROCKS PROJECT.