Loading...

General regression neural network application to axial compressor performance map

Ghorbanian, K ; Sharif University of Technology | 2007

205 Viewed
  1. Type of Document: Article
  2. DOI: 10.2514/6.2007-1165
  3. Publisher: 2007
  4. Abstract:
  5. General regression neural network (GRNN) is employed to reconstruct the compressor performance map. Two different models are adopted to examine the accuracy of the GRNN technique. The results indicate that the GRNN predictions for both models are very sensitive to the width of the probability a. Further, since the distribution of data is multimodal with large variance differences modes, two solutions are suggested: a locally optimized value for the probability, and the second one is rotated general regression neural network (RGRNN) providing a more accurate result compared to an overall value for the probability. The results show that as the number of samples is reduced to about 70% of the available samples, the performance map is predicted with an accuracy of approximately 90%. In general, the results highlight the capability of both RGRNN and GRNN in performing design approaches as well as optimization studies of sufficient accuracy with modest amount of data for axial compressors
  6. Keywords:
  7. Axial compressors ; Distribution of data ; Rotated general regression neural network (RGRNN) ; Axial compression ; Compressors ; Mathematical models ; Optimization ; Probability ; Regression analysis ; Neural networks
  8. Source: 45th AIAA Aerospace Sciences Meeting 2007, Reno, NV, 8 January 2007 through 11 January 2007 ; Volume 20 , 2007 , Pages 13962-13971 ; 1563478900 (ISBN); 9781563478901 (ISBN)
  9. URL: https://arc.aiaa.org/doi/abs/10.2514/6.2007-1165