Neural Network Predictions of the 4-Quadrant Wageningen Propeller Series
DAVID TAYLOR MODEL BASIN WASHINGTON DC HYDROMECHANICS LAB
Pagination or Media Count:
The Maneuvering and Control Division of the Naval Surface Warfare Center NSWC along with Applied Simulation Technologies have been developing and applying neural networks to problems of naval interest. This report describes the development of feedforward neural network FFNN predictions of four-quadrant thrust and torque behavior for the Wageningen B-Screw Series of propellers and for two Wageningen ducted propeller series. The purpose of the work is twofold to create a prediction tool that accurately recovers measured data for those propellers in the series for which measured data is available, and to further provide reasonable four-quadrant thrust and torque predictions for the remaining propellers for which no measured data is available. Substantial results, varying each of the inputs over the full operating range, will be presented which establish that these two goals have been well attained.
- Marine Engineering
- Fluid Mechanics