Loading...

Liquid-liquid coaxial swirl injector performance prediction using general regression neural network

Ghorbanian, K ; Sharif University of Technology | 2009

742 Viewed
  1. Type of Document: Article
  2. DOI: 10.1002/ppsc.200701104
  3. Publisher: 2009
  4. Abstract:
  5. A general regression neural network technique was applied to design optimization of a liquid-liquid coaxial swirl injector. Phase Doppler Anemometry measurements were used to train the neural network. A general regression neural network was employed to predict droplet velocity and Sauter mean diameter at any axial or radial position for the operating range of a liquid-liquid coaxial swirl injector. The results predicted by neural network agreed satisfactorily with the experimental data. A general performance map of the liquid-liquid coaxial swirl (LLCS) injector was generated by converting the predicted result to actual fuel/oxidizer ratios. © 2008 WILEY-VCH Verlag GmbH & Co. KGaA
  6. Keywords:
  7. Coaxial injector ; Liquid-liquid injector ; Neural network ; Swirl atomizer ; Fuel injection ; Jet pumps ; Liquids ; Regression analysis ; Droplet velocities ; Experimental datum ; Fuel/oxidizer ratios ; General regression neural networks ; Operating ranges ; Performance maps ; Performance predictions ; Phase doppler anemometry measurements ; Radial positions ; Sauter mean diameters ; Swirl injectors ; Neural networks
  8. Source: Particle and Particle Systems Characterization ; Volume 25, Issue 5-6 , 2009 , Pages 454-464 ; 09340866 (ISSN)
  9. URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/ppsc.200701104