Hostname: page-component-cb9f654ff-r5d9c Total loading time: 0 Render date: 2025-08-07T03:47:40.139Z Has data issue: false hasContentIssue false
  • English
  • Français

Using neural networks to speed up optimization algorithms*

Published online by Cambridge University Press:  15 November 2000

M. Bazan  and
S. Russenschuck
M. Bazan
Affiliation:
The Institute of Computer Science, University of Wrocław, Przesmyckiego 21, 51-151 Wrocław, Poland
S. Russenschuck*
Affiliation:
CERN, 1211 Geneva 23, Switzerland
*
stephan.russenschuck@cern.ch
Get access

Abstract

The paper presents theapplication of Radial-basis-function (RBF) neural networks tospeed up deterministic search algorithms used for the design andoptimization of superconducting LHC magnets.The optimization of the iron yoke of the main dipoles requires anumber of numerical field computations per trial solution as the field quality depends on the excitation of the magnets. This results in computation times of about 30 minutes for each objective functionevaluation (on a DEC-Alpha 600/333) and only the most robust (deterministic)optimization algorithms can be applied. Using a RBF function approximator, the achieved speed-up of thesearch algorithm is in the order of 25% for problems with two parametersand about 18% for problems with three and five design variables.

Keywords

Information

Type
Research Article
Information
The European Physical Journal - Applied Physics , Volume 12 , Issue 2 , November 2000 , pp. 109 - 115
Copyright
© EDP Sciences, 2000

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Footnotes

*

This paper has been presented atNUMELEC 2000.

References

S. Russenschuck, ROXIE: Routine for the Optimization of Magnet X-section, Inverse Field Calculation and Coil END Design (CERN Yellow Report 99-01, 1999).
H.G. Jacob, Rechnergestützte Optimierung statischer und dynamischer Systeme (Springer-Verlag, Berlin, 1982).
Kurz, S., Russenschuck, S., Electr. Eng. 82, 1 (1999). CrossRef
Coccorese, E., Martone, R., Marabito, F.C., IEEE Trans. Magn. 30, 2929 (1994). CrossRef
Ratnajeevan, S., Hoole, H., IEEE Trans. Magn. 29, 1931 (1993).
Alotto, P., Caiti, A., Molinari, G., Repertto, M., IEEE Trans. Magn. 30, 2929 (1994). CrossRef
Th. Ebner, Ch. Magele, B.R. Brandstätter, K.R. Richter, IEEE Trans. Magn. 34, 2928 (1998). CrossRef
Ishikawa, T., Matsunami, M., IEEE Trans. Magn. 33, 1868 (1997). CrossRef
Hartman, E.J., Keeler, J.D., Kowalski, J.M., Neural Comput. 2, 210 (1990). CrossRef
A. Kiełbasinski, H. Schwetlick, Numerische lineare Algebra (VEB Deutscher, Berlin, 1988).
C.M. Bishop, Neural networks for pattern recognition (Oxford University Press, New York, 1995).
Rumelhart, D.E., Hinton, G.E., Williams, R.J., Nature 323, 533 (1986). CrossRef
J. Gnanadesikan, Methods for Statistical Data Analysis of Multivariate Observations (Wiley, New York, 1997).