A method is presented for prediction of pressure pulses induced by propeller that requires a minimum number of inputs compared to similar theoretical models. The method is based on database of model-scale measurements carried out at MARINTEK since 1980. This database is analyzed with the help of artificial neural networks both for single screw and twin screw vessels for non-cavitating as well as cavitating case. An user-friendly Windows software is developed integrating the method. A short description of artificial neural network is presented. Model scale verification of the method shows good agreement between measured and predicted values.

This content is only available via PDF.
You do not currently have access to this content.