A fast algorithm for inversion of MLP networks in design problems
- 1 September 2005
- journal article
- Published by Emerald in COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering
- Vol. 24 (3), 906-920
- https://doi.org/10.1108/03321640510598229
Abstract
Purpose – To present a neural network-based approach to the design of electromagnetic devices. Design/methodology/approach – A neural model is created which reproduces the relationship between the design parameters of the device and the performance parameters, typically field values. Findings – The neural model is a single hidden layer MLP network, trained by using a set of cases calculated, for example, by means of a finite element analysis. The design problem can be solved by fixing the performance values at the output of the network and by calculating the corresponding input values. The relationship between the input and the output of the neural network is represented by three equations systems. By means of these three systems, we can forward the domain of the input, and we can back propagate the desired output throughout the network layers. In such a way, both the domain of the design parameters and the domain of the desired performances values can be projected in the same space. Whatever point inside the intersection between the two projected domains corresponds to a solution of the design problem. Originality/value – Presents a procedure which is able to find a point belonging to such an intersection.Keywords
This publication has 13 references indexed in Scilit:
- Magnetic design optimization and objective function approximationIEEE Transactions on Magnetics, 2003
- A neural inverse problem approach for optimal designIEEE Transactions on Magnetics, 2003
- Design optimization of electromagnetic devices using artificial neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Use of intelligent-particle swarm optimization in electromagneticsIEEE Transactions on Magnetics, 2002
- ANN inverse mapping technique applied to electromagnetic designIEEE Transactions on Magnetics, 2001
- Noninvertibility in neural networksComputers & Chemical Engineering, 2000
- A comparison of optimization techniques for Loney's solenoids design: an alternative Tabu Search algorithmIEEE Transactions on Magnetics, 2000
- Comparison of optimization by response surface methodology with neurofuzzy methodsIEEE Transactions on Magnetics, 2000
- Optimal design of injection mold for plastic bonded magnetIEEE Transactions on Magnetics, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989