Neural network guided adjoint computations in dual weighted residual error estimation
نویسندگان
چکیده
Abstract In this work, we are concerned with neural network guided goal-oriented a posteriori error estimation and adaptivity using the dual weighted residual method. The primal problem is solved classical Galerkin finite elements. adjoint in strong form feedforward two or three hidden layers. main objective of our approach to explore alternatives for solving greater potential numerical cost reduction. proposed algorithm based on general theorem including both linear nonlinear stationary partial differential equations goal functionals. Our developments substantiated some experiments that include comparisons computed adjoints element solutions adjoints. programming software, open-source library deal.II successfully coupled LibTorch, PyTorch C++ application interface. Article Highlights Adjoint approximation dual-weighted estimation. Side-by-side accuracy computational computations. Numerical problems yielding excellent effectivity indices.
منابع مشابه
Error Modeling in Distribution Network State Estimation Using RBF-Based Artificial Neural Network
State estimation is essential to access observable network models for online monitoring and analyzing of power systems. Due to the integration of distributed energy resources and new technologies, state estimation in distribution systems would be necessary. However, accurate input data are essential for an accurate estimation along with knowledge on the possible correlation between the real and...
متن کاملDual Weighted Residual Error Control for Frictional Contact Problems
In this paper goal-oriented error control based on dual weighted residual error estimations (DWR) is applied to frictional contact problems. A mixed formulation of the contact problem is used to derive a discretization. It relies on the introduction of Lagrange multipliers to capture the frictional contact conditions. The discretization error is estimated in terms of functionals (the quantities...
متن کاملOn Dual-Weighted Residual Error Estimates for p-Dependent Discretizations
This report analyzes the behavior of three variants of the dual-weighted residual (DWR) error estimates applied to the p-dependent discretization that results from the BR2 discretization of a second-order PDE. Three error estimates are assessed using two metrics: local effectivities and global effectivity. A priori error analysis is carried out to study the convergence behavior of the local and...
متن کاملA posteriori error estimation and anisotropy detection with the dual weighted residual method
In this work we develop a new framework for a posteriori error estimation and detection of anisotropies based on the dual weighted residual method by Becker and Rannacher. The common approach for anisotropic mesh adaptation is to analyze the Hessian of the solution. Eigenvalues and eigenvectors indicate dominant directions and optimal stretching of elements. However this approach is firmly link...
متن کاملEstimation of Residual Error Parameters for Vector Network Analyzers
− Recently, a novel approach for the estimation of the residual error parameters of a calibrated vector network analyzer has been proposed. The method is based on a reflection measurement employing a high precision airline terminated by a short. From this measurement the complex valued residual error parameters are calculated utilizing a sophisticated data analysis scheme. In this work the unce...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: SN applied sciences
سال: 2022
ISSN: ['2523-3971', '2523-3963']
DOI: https://doi.org/10.1007/s42452-022-04938-9