Neural network model for estimation of hull bending moment and shear force of ships in waves

A time-domain technique based on Artificial Neural Networks (ANN's) for estimating wave-induced ship hull bending moment and shear force from ship motions, which are calculated by a theoretical method under regular waves, is presented. The objective of the use of this methodology is to obtain an expedite hull monitoring tool to be used on board the ships. The ANNs are used to model the time-domain relationship between the wave-induced vertical bending moment and shear force and the ship motions: sway acceleration, pitch angle, roll angle, vertical acceleration, heading angle and yaw rate. A mathematical model using a strip theory provides the ship motions data in the frequency domain allowing the validation of the method through simulations.