The importance of reducing the noise impact of ships is being recognised worldwide. Consequently, the inclusion of this principle among the objectives and constraints of new designs is becoming a standard. For this reason, considerable attention is given to the propeller being often the dominant source of underwater radiated noise, especially when cavitation occurs, as it happens in most cases when a ship sails at design speed. The designers of quieter propulsion systems require the availability of predictive tools able to verify the compliance with noise requirements and to compare the effectiveness of different design solutions. In this context, tools able to provide a reliable estimate of propeller noise spectra based just on the information available during propeller design represent a fundamental tool to speed up the design process avoiding model scale tests. This work focuses on developing a tool able to predict the cavitating marine propeller generated noise spectra at design stage exploiting the most recent advances in Deep Learning, able to take advantage of both structured and unstructured data, and in hybrid modelling, able to exploit both data and physical knowledge about the problem. For this purpose authors will make use of a dataset collected by means of dedicated model scale measurements in a cavitation tunnel combined with the detailed flow characterisation obtainable by calculations carried out with a Boundary Element Method. The performance of the proposed approaches are analysed considering different scenarios and different definitions of the input and output variable used during the modelisation.

Reducing the noise impact of ships on the marine environment is one of the objectives of new propellers designs, since they represent the dominant source of underwater radiated noise, especially when cavitation occurs. Consequently, ship designers require new predictive tools able to verify the compliance with noise requirements and to compare the effectiveness of different design solutions. In this context, tools able to provide a reliable estimate of propeller noise spectra based just on the information available at design stage represent a fundamental tool to speed up the design process avoiding model scale tests. This work focus on developing such a tool, adopting methods coming from the world of Machine Learning and Deep Neural Networks, in order to create a model able to predict the cavitating marine propeller noise spectra. For this purpose authors will make use of a dataset collected by means of dedicated model scale measurements in a cavitation tunnel combined with the detailed flow characterization obtainable by calculations carried out with a Boundary Element Method. The performance of the proposed approaches are analyzed considering different definitions of the input and output variables used during the modelization.

Twin screw ships may experience considerably asymmetric propeller functioning during manoeuvres. This phenomenon may result in large power fluctuations during tight manoeuvres, with increases of shaft torque up to and over 100% of the steady values in straight course and considerable unbalances; this, in its turn, may be potentially dangerous, especially in case of particularly complex propulsion plant configurations, such as those with coupled shaftlines. A joint research project supported by the Italian Navy has been set up in order to deeply investigate the phenomenon, by means of large scale model testing and related numerical simulations. In the present work, the extensive experimental campaign results on a free running model of a twin-screw ship are presented, allowing to obtain a deeper insight of the problem. In particular, tests have been carried out simulating different simplified control schemes, starting from the most common constant rate of revolution tests and including different control strategies (constant torque and power). Usual standard manoeuvres (turning circle, zigzag and spiral) have been carried out, providing results for asymmetric shaft functioning and ship manoeuvrability behaviour. Results from the present analysis allow to obtain the complete model for the time domain simulation of asymmetric shaft functioning.

Marine propulsion plants can experience large power fluctuations during tight maneuvers, with increases of shaft torque up to and over 100% of the steady values in straight course and considerable asymmetry between internal and external shafts during turning circle. This phenomenon (studied in Viviani et al 2007a and 2007b can be of particular interest for twin screw ships propulsion systems with coupled shaftlines, in which asymmetrical loads can represent a challenge for the whole propulsion system (e.g. unique reduction gear, shaftlines, automation). A joint research has been set up in order to deeply investigate the phenomenon, by means of large scale model testing and related numerical simulations. In the present work, preliminary simulation results with different simplified automation systems and with an automation system more similar to the real one are reported, allowing to get a better insight into this complex problem.