Abstract
The aim of the present work is to develop a strategy enabling fast CFD-based computation of compressor maps for aero engines. The introduced process consists of two phases. In the first phase the compressor limits due to surge and choke are identified and approximated by utilizing methods of support vector machine (SVM). These limit lines are refined within an iterative, distance-based approach. Subsequently, in the second phase the three-dimensional shape of the compressor map is approximated by a response surface method (RSM). The process is validated with an application to an industrial 4.5-stage research compressor, where very good agreement between evaluated and approximated values is obtained.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bestle D (1994) Analyse und Optimierung von Mehrkörpersystemen. Springer, Berlin
Bouhamidi A, Le Méhauté A (2004) Radial basis functions under tension. J Approximation Theory 127:135–154. https://doi.org/10.1016/j.jat.2004.03.005
Fei J, Zhao N, Shi Y, Feng Y, Wang Z (2016) Compressor performance prediction using a novel feed-forward neural network based on Gaussian kernel function. Adv Mech Eng 8. https://doi.org/10.1177/1687814016628396
Ghorbanian K, Gholamrezaei M (2009) An artificial neural network approach to compressor performance prediction. Appl Energy 86:1210–1221. https://doi.org/10.1016/j.apenergy.2008.06.006
Janke C, Bestle D, Becker B (2015) Compressor map computation based on 3D CFD analysis. CEAS Aeronaut J 6:515–527
Keskin A (2007) Process integration and automated multi-objective optimization supporting aerodynamic compressor design, Dissertation, BTU Cottbus. Shaker, Aachen
Lapworth B (2004) HYDRA-CFD: A framework for collaborative CFD development. In: International conference on scientific and engineering computation. IC-SEC, Singapore
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825–2830
Schoelkopf B (2001) Learning with kernels. The MIT Press, Cambridge
Sodemann A, Li Y, Lee J, Lancaster R (2006) Data-driven surge map modeling for centrifugal air compressors. In: ASME international mechanical engineering congress and exposition. ASME, Chicago
Vapnik V (1999) The nature of statistical learning theory. Springer, New York
Vapnik V, Cortes C, Saitta L (1995) Support-vector networks. In: Machine learning. Kluwer Academic Publishers, Boston
Acknowledgements
This work has been carried out in collaboration with Rolls-Royce Deutschland as part of the research project VITIV (Virtual Turbomachinery, Proj.-No. 80164702) funded by the State of Brandenburg, the European Regional Development Fund, and Rolls-Royce Deutschland. Rolls-Royce Deutschland’s permission to publish this work is greatly acknowledged.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
In order to solve the optimization problem (20), matrices
are introduced. The Langrange function (21) then simplifies to
and the Karush-Kuhn-Tucker conditions, Bestle (1994), read as
Substituting
from (57) and inserting it into (56) simplifies the Lagrange function to
or Eq. (23), where the term \(b\pmb {\lambda }^{T}\mathbf {y}\) vanishes due to Eq. (58). The dual problem summarizes maximization of the Lagrange function w.r.t. \(\pmb {\lambda }\), the condition \(\pmb {\lambda } \le \mathbf {0}\) from (60) and constraint (58). Substituting the optimal solution (22) in (61) results in the optimal normal vector (24). The optimal offset may be found from any of the active conditions, where \(\lambda _{i}<0\) in (60) results in
due to \(y_{i}=\pm 1\). The mean value of all \(N_{a}\) active constraints is then
Alternatively only \(N_{a}=2\) active training points \(\mathbf {x}^{+},\ \mathbf {x}^{-}\) on opposite sides of the separation line with \(y^{+}=+1\) and \(y^{-}=-1\) may be used canceling the first sum in (64) and yielding Eq. (25), Vapnik (1999).
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Ivanov, D., Bestle, D., Janke, C. (2019). A Response Surface Based Strategy for Accelerated Compressor Map Computation. In: Andrés-Pérez, E., González, L., Periaux, J., Gauger, N., Quagliarella, D., Giannakoglou, K. (eds) Evolutionary and Deterministic Methods for Design Optimization and Control With Applications to Industrial and Societal Problems. Computational Methods in Applied Sciences, vol 49. Springer, Cham. https://doi.org/10.1007/978-3-319-89890-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-89890-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-89889-6
Online ISBN: 978-3-319-89890-2
eBook Packages: EngineeringEngineering (R0)