Loading...

Prediction of velocity distribution in the mixing region of swirl sprays using neural network implementation

Soltani, M. R ; Sharif University of Technology | 2003

19 Viewed
  1. Type of Document: Article
  2. Publisher: 2003
  3. Abstract:
  4. Phase Doppler Anemometer (PDA) was used to measure velocity distribution in the mixed spray field of two identical pressure-swirl atomizers placed beside each other. A memory-based network that provides estimates of continuous variables was developed to simulate the results. This general regression neural network (GRNN) is a one-pass learning algorithm with a highly parallel structure and can be used for any multidimensional regression problem, where an assumption of linearity is not justified. The approach is not limited to any particular form and requires no pre-knowledge of the appropriate form that any usual correlation technique requires. The predicted results are in excellent agreement with those obtained by PDA system. © 2003 by M. R. Soltani. Published by the American Institute of Aeronautics and Astronautics, Inc
  5. Keywords:
  7. Source: 33rd AIAA Fluid Dynamics Conference and Exhibit 2003, Orlando, FL, 23 June 2003 through 26 June 2003 ; 2003 ; 9781624100956 (ISBN)
  8. URL: https://arc.aiaa.org/doi/10.2514/6.2003-4270