engleski

Evaluation of the ship added resistance in waves using artificial neural network

The International Maritime Organization subjected the emission of harmful gases to increasingly stringent regulations, via the introduction of mandatory technical measures for new ships and operational measures for existing ships, with the aim of increasing the energy efficiency of ships and reducing CO2 emissions. Since the ship added resistance in waves causes a reduction in ship speed and has a negative impact on the fuel consumption and CO2 emission, it is very important to predict the increase in ship resistance due to waves already in the ship design phase. Added resistance, as a time averaged second order wave force, is considered as a non-viscous phenomenon, allowing the application of methods and solvers based on the potential flow theory, but also an extrapolation of the results from model to ship scale without the scale effects. It should be noted that the determination of added resistance in waves requires rather complex hydrodynamic calculations to ensure an acceptable accuracy of the results. Within this research, the possibility of application and advantages of artificial neural networks (ANN) to estimate relationships between the input data and solutions to the nonlinear multivariable regression problems is investigated. A model that allows simple but sufficiently accurate and reliable estimation of the ship added resistance sailing at actual sea states is proposed. The proposed model is based on the results of hydrodynamic calculations of added resistance in waves for various hull forms at different sea states and ANN, which has the ability to learn from examples. Hull forms of modern container ships with different types of bow and stern, section type and block coefficient (prismatic coefficient) are generated in order to create a sufficiently large database for the training process. Hydrodynamic calculations are conducted using the Boundary Integral Equations Method based on the potential flow theory. The obtained numerical results are validated against the available experimental data and verified i.e., the numerical uncertainty is assessed. The input variables of the proposed ANN model are ship characteristics, speed and sea state, and is based on Levenberg-Marquard learning algorithm with Bayesian regularization. The model incorporates three sub-models based on the data classification with respect to the wave zero crossing period, and can have a practical benefit during the design phase of a ship with the block coefficient in the range between 0.510 and 0.780, or the prismatic coefficient in the range between 0.530 and 0.811, which sails at Froude numbers between 0.174 and 0.258.

added resistance in waves ; container ship ; potential flow theory ; artificial neural network ; sea state

nije evidentirano