Neural network based prediction of mooring forces in floating production storage and offloading systems

The paper explicates the development of a neural network based prediction of mooring forces of a deep-sea oil exploitation production process. The evolution of a neural network simulator for analysis of the dynamic behavior of a system consisting of a turret-FPSO (floating production storage and off loading) and a shuttle ship in tandem configuration is described. The turret-FPSO is a ship type floating unit and its surge and sway motions are avoided by mooring lines connected in the turret. The study of the dynamics of this system is difficult because there are complex forces interaction due to currents, waves and winds. In general, the mathematical model that represents the dynamics of both ships involves a set of nonlinear equations requiring several parameters very difficult to obtain. In order to deal with such complex modeling a neural network has been devised to simulate the system and to incorporate actual data, so as to identify the dynamics of the system and to study stability influence avoiding possible collisions and mooring line stresses.