FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310286275> ?p ?o ?g. }

• W4310286275 endingPage "115766" @default.
• W4310286275 startingPage "115766" @default.
• W4310286275 abstract "We present a new Integrated Finite Element Neural Network framework (I-FENN), with the objective to accelerate the numerical solution of nonlinear computational mechanics problems. We leverage the swift predictive capability of neural networks (NNs) and we embed them inside the finite element stiffness function, to compute element-level state variables and their derivatives within a nonlinear, iterative numerical solution. This process is conducted jointly with conventional finite element methods that involve shape functions: the NN receives input data that resembles the material point deformation and its output is used to construct element-level field variables such as the element Jacobian matrix and residual vector. Here we introduce I-FENN to the continuum damage analysis of quasi-brittle materials, and we establish a new non-local gradient-based damage framework which operates at the cost of a local damage approach. First, we develop a physics informed neural network (PINN) to resemble the non-local gradient model and then we train the neural network offline. The network learns to predict the non-local equivalent strain at each material point, as well as its derivative with respect to the local strain. Then, the PINN is integrated in the element stiffness definition and conducts the local to non-local strain transformation, whereas the two PINN outputs are used to construct the element Jacobian matrix and residual vector. This process is carried out within the nonlinear solver, until numerical convergence is achieved. The resulting method bears the computational cost of the conventional local damage approach, but ensures mesh-independent results and a diffused non-local strain and damage profile. As a result, the proposed method tackles the vital drawbacks of both the local and non-local gradient method, respectively being the mesh-dependence and additional computational cost. We showcase through a series of numerical examples the computational efficiency and generalization capability of I-FENN in the context of non-local continuum damage, and we discuss the future outlook. The PINN training code and associated training data files have been made publicly available online, to enable reproducibility of our results." @default.
• W4310286275 created "2022-11-30" @default.
• W4310286275 creator A5061087099 @default.
• W4310286275 creator A5061440922 @default.
• W4310286275 date "2023-02-01" @default.
• W4310286275 modified "2023-10-16" @default.
• W4310286275 title "Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics" @default.
• W4310286275 cites W1498436455 @default.
• W4310286275 cites W1523953618 @default.
• W4310286275 cites W1677182931 @default.
• W4310286275 cites W1968326286 @default.
• W4310286275 cites W1969052431 @default.
• W4310286275 cites W1971812145 @default.
• W4310286275 cites W1977458616 @default.
• W4310286275 cites W2024540604 @default.
• W4310286275 cites W2030721701 @default.
• W4310286275 cites W2033675870 @default.
• W4310286275 cites W2052196552 @default.
• W4310286275 cites W2071364738 @default.
• W4310286275 cites W2074300745 @default.
• W4310286275 cites W2096089512 @default.
• W4310286275 cites W2099648545 @default.
• W4310286275 cites W2100865094 @default.
• W4310286275 cites W2105484555 @default.
• W4310286275 cites W2116379499 @default.
• W4310286275 cites W2130550753 @default.
• W4310286275 cites W2145995141 @default.
• W4310286275 cites W2261676784 @default.
• W4310286275 cites W2298469575 @default.
• W4310286275 cites W2408353796 @default.
• W4310286275 cites W2570295260 @default.
• W4310286275 cites W2734889697 @default.
• W4310286275 cites W2745164289 @default.
• W4310286275 cites W2760972773 @default.
• W4310286275 cites W2768208814 @default.
• W4310286275 cites W2785071288 @default.
• W4310286275 cites W2888515987 @default.
• W4310286275 cites W2897929694 @default.
• W4310286275 cites W2899283552 @default.
• W4310286275 cites W2919115771 @default.
• W4310286275 cites W2921773029 @default.
• W4310286275 cites W2959296226 @default.
• W4310286275 cites W2966489697 @default.
• W4310286275 cites W2967252474 @default.
• W4310286275 cites W2996028791 @default.
• W4310286275 cites W2998847955 @default.
• W4310286275 cites W2999081549 @default.
• W4310286275 cites W2999772350 @default.
• W4310286275 cites W3004450693 @default.
• W4310286275 cites W3011806874 @default.
• W4310286275 cites W3033580147 @default.
• W4310286275 cites W3049609037 @default.
• W4310286275 cites W3084017095 @default.
• W4310286275 cites W3092743582 @default.
• W4310286275 cites W3093832692 @default.
• W4310286275 cites W3101260193 @default.
• W4310286275 cites W3111914315 @default.
• W4310286275 cites W3119817371 @default.
• W4310286275 cites W3120780149 @default.
• W4310286275 cites W3127492339 @default.
• W4310286275 cites W3134417697 @default.
• W4310286275 cites W3137392741 @default.
• W4310286275 cites W3183360516 @default.
• W4310286275 cites W3184867249 @default.
• W4310286275 cites W3199291008 @default.
• W4310286275 cites W3201666041 @default.
• W4310286275 cites W3213846592 @default.
• W4310286275 cites W4200180012 @default.
• W4310286275 cites W4221152086 @default.
• W4310286275 cites W4225422786 @default.
• W4310286275 cites W4225707765 @default.
• W4310286275 cites W4226068867 @default.
• W4310286275 cites W4226480439 @default.
• W4310286275 cites W4283067940 @default.
• W4310286275 doi "https://doi.org/10.1016/j.cma.2022.115766" @default.
• W4310286275 hasPublicationYear "2023" @default.
• W4310286275 type Work @default.
• W4310286275 citedByCount "4" @default.
• W4310286275 countsByYear W43102862752023 @default.
• W4310286275 crossrefType "journal-article" @default.
• W4310286275 hasAuthorship W4310286275A5061087099 @default.
• W4310286275 hasAuthorship W4310286275A5061440922 @default.
• W4310286275 hasBestOaLocation W43102862752 @default.
• W4310286275 hasConcept C121332964 @default.
• W4310286275 hasConcept C127413603 @default.
• W4310286275 hasConcept C135628077 @default.
• W4310286275 hasConcept C14198674 @default.
• W4310286275 hasConcept C154945302 @default.
• W4310286275 hasConcept C158622935 @default.
• W4310286275 hasConcept C200331156 @default.
• W4310286275 hasConcept C28826006 @default.
• W4310286275 hasConcept C33923547 @default.
• W4310286275 hasConcept C41008148 @default.
• W4310286275 hasConcept C50644808 @default.
• W4310286275 hasConcept C6213913 @default.
• W4310286275 hasConcept C62520636 @default.
• W4310286275 hasConcept C66938386 @default.
• W4310286275 hasConceptScore W4310286275C121332964 @default.

• next