Minimal function calls approach with on-line learning and dynamic weighting for computationally intensive design optimization

Design/optimization processes requiring intensive finite-element computation can be made significantly more efficient, while preserving good accuracy, by combining the Response Surface Methodology with on-line learning and dynamic weighting. The paper presents such a new development and uses the mul...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on magnetics 2001-09, Vol.37 (5), p.3423-3426
Main Authors: Sykulski, J.K., Al-Khoury, A.H., Goddard, K.F.
Format: Article
Language:English
Subjects:
Applied classical electromagnetism
Brushless motors
Computation
Curve fitting
Design optimization
Dynamics
Electromagnetism
electron and ion optics
Equations
Exact sciences and technology
Finite element methods
Fundamental areas of phenomenology (including applications)
Iron
Learning
Magnetism
Magnetostatics
magnetic shielding, magnetic induction, boundary-value problems
Mathematical analysis
Motors
On-line systems
Optimization methods
Physics
Response surface methodology
Surface fitting
Vectors
Weighting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Design/optimization processes requiring intensive finite-element computation can be made significantly more efficient, while preserving good accuracy, by combining the Response Surface Methodology with on-line learning and dynamic weighting. The paper presents such a new development and uses the multi-parameter design of a brushless pm motor to illustrate the approach.
ISSN:0018-9464
1941-0069
DOI:10.1109/20.952628