|
|
Grupo de Dinâmica e Hidrodinâmica de Navios > 2.3 Manobrabilidade e Controlo de Navios > Publicações
Moreira, L., Mesbahi, E. e Guedes Soares, C. (2000), “The Application of the Static ANNs in Modelling and Simulation of Marine Propulsion System”, Proceedings of the Marine Science and Technology for Environmental Sustainability Conference (ENSUS), 4-6 September, Newcastle, pp. 230-241
This paper presents a simulation model, which is able to describe the dynamic behaviour of a marine propulsion plant at varying operational and transient conditions. The propulsion plant comprises of many elements (hull, propeller, reduction gear, and engine) whose functional relationships between inputs and outputs are described by look-up tables, mathematical operators and differential equations. The model is able to describe the behaviour of the propulsion system, providing the time histories of all output variables such as propeller speed and displacement, propulsive coefficient kT and kQ, propeller thrust and ship resistance, propeller torque, overall system efficiency and ship's speed.
Application of artificial neural networks (ANNs) in some cases can be used to identify and consequently model complex marine system characteristics. Simulation results obtained by using ANN based models can be more accurate in comparison to the convetional modelling techniques. ANNs are found to be able to provide a generic and practical method for learning real-valued, discrete-valued and vector-valued functions from examples. A combination of conventional and physical modelling techniques in parallel with ANN models are used to model a marine propulsion plant as a case study. Performance of static ANNs is finally compared with traditional procedures in prediction of propulsive coefficients kT and kQ.
Peça uma cópia desta publicação
Para informação sobre todas as publicações do CENTEC pode descarregar: Lista Completa de Publicações do CENTEC
|