Advertisement

Optimization of Centrifugal Impeller Using Evolutionary Strategies and Artificial Neural Networks

  • René Meier
  • Franz Joos
Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

In order to optimize turbo machine components it is necessary to describe the behaviour of multimodal objective functions (OF). Instead very time-consuming evaluations using a three-dimensional Navier–Stokes solver have to be performed to get the characteristics of these OF. In this study an Artificial Neural Network (ANN) is considered to use it as a performance predictor with the view to replace the evaluation of the objective function to speed up the optimization process.

Keywords

Artificial neural networks Centrifugal impeller Evolutionary strategies Resilient backpropagation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aungier, R. H. (2000). Centrifugal compressors. New York: ASME Press.Google Scholar
  2. Joos, F., & Bartold, A. (2008). Optimization of a centrifugal impeller using evolutionary algorithms. ASME Paper GT2008–50805.Google Scholar
  3. Lüdke, K. H. (2004). Process centrifugal compressors. Berlin: Springer.Google Scholar
  4. Rechenberg, I. (1994) Evolutionsstrategie ’94. Stuttgart: Frommann-Holzboog.Google Scholar
  5. Rojas, R. (1993). Theorie der Neuronalen Netze. Berlin: Springer.Google Scholar
  6. Schwefel, H.-P. (1995). Evolution and optimum seeking. New York: Wiley.Google Scholar
  7. Weicker, K. (2002). Evolutionäre Algorithmen. Stuttgart: Teubner.Google Scholar
  8. Zell, A. (1997). Simulation Neuronaler Netze. München: Oldenbourg.Google Scholar
  9. Zell, A., Mamier, G., Vogt, M., Mache, N., Hübner, R., Döring, S., et al. (n.d.). SNNS user manual, version 4.2 (pp. 145–150). University of Stuttgart, University of Tübingen.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  1. 1.Laboratory of Turbo MachineryHelmut-Schmidt-University/University of the Federal Armed Forces HamburgHamburgGermany

Personalised recommendations