The optimisation of electromagnetic devices using a combined finite element/neural network approach with on‐line training

DOI10.1108/03321649910274801MaRDI QIDQ4700664zbMATH OpenOpenAlexFDO

Authors Jean Seguin, F. Dandurand, David A. Lowther, J. K. Sykulski

Publication date 25 October 2000

Published in COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1108/03321649910274801

zbMATH Keywords

optimizationdesignneural networkselectromagneticssensitivity evaluationfinite elementary

Mathematics Subject Classification ID

Electromagnetic theory (general) (78A25) Finite element, Galerkin and related methods applied to problems in optics and electromagnetic theory (78M10) Optimization problems in optics and electromagnetic theory (78M50)

Recommendations

• Approximation de calculs éléments finis par réseaux neuronaux: quelques applications en optimisation
• A constructive algorithm of neural approximation models for optimization problems
• A novel approach based on recurrent neural networks applied to nonlinear systems optimization
• Neural approach for solving several types of optimization problems
• Design and analysis of an efficient neural network model for solving nonlinear optimization problems

Cited in

(6)

• Identification of hidden ferrous 3D objects using finite elements
• Reducing computational effort in field optimisation problems
• Parameters optimization and nonlinearity analysis of grating eddy current displacement sensor using neural network and genetic algorithm
• FIR-type and IIR-type neural networks, and their application to shape optimization of a magnetic pole
• Improved fast evolutionary program for optimum design of power transformer
• A constructive algorithm of neural approximation models for optimization problems

This page was built for publication: The optimisation of electromagnetic devices using a combined finite element/neural network approach with on‐line training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4700664)