Anti-rolling fin control for ship stabilization

Abstract

Active fin control is the most effective anti-rolling approach for ship stabilization system, however the accurate model of whole nonlinear dynamic ship system under random wave or wind impact is difficult to obtain. In this paper, a guarded heuristic genetic algorithm fin controller (GHGAFC) including a heuristic genetic algorithm fin controller (HGAFC) and a guarded fin controller (GFC) is developed for ship stabilization system. In the HGAFC design, the gradient descent training is embedded into conventional genetic algorithm (GA) to construct a main controller to search the optimum fin control angle under the occurrence of uncertainties. In order to ensure the system states around a defined bound region, a guarded fin controller (GFC) is added to adjust the control angle. In the stabilization system, the gyroscope and accelerometer are used to detect the swaying conditions and the gathered data are sent to embedded microcontroller to calculate the command. To verify the effectiveness of the proposed fin controller, some simulations are carried out under the assumption that the sea surface is modeled as a one-dimension linear free surface. The performance is also compared with other announced GA-fuzzy, GA-PID and conventional supervisory GA control schemes under the same conditions.