Prediction of Wave and Current Forces on Slender Structures Using Artificial Neural Networks

Hydrodynamic forces generated from waves and currents on slender cylinders are of great concern in designing offshore structures. Numerous analytical and experimental methods such as the Morison equation have been suggested to estimate the wave forces on slender structures. However, such methods have shown some inaccuracy in their estimations. In recent years, artificial neural networks have received a great deal of attention and have been used effectively in many of engineering subjects. In this paper, artificial neural networks have been used to predict waves and current forces on slender cylinders. The data generated from laboratory experiments were used to train and evaluate the prediction performance of the artificial neural networks used in this paper. A number of neural networks were designed, trained and evaluated. Results indicated the success of application of neural networks approach which can efficiently predict the waves and current forces on slender cylinders after conducting appropriate training. Furthermore, the results are quite acceptable in comparison with test results and better than the results obtained from other methods such as the Morison equation.