Genetic algorithm optimisation of a supply ship propulsion and navigation systems

Two different control configurations have been designed for the navigation and propulsion systems of CyberShip I, a scale model of an oil platform supply ship. The first configuration consists of two classical linear PID controllers (one for the navigation system and the other for the propulsion). In the second configuration, a nonlinear sliding mode controller provides the navigation control and a PI control regulates the propulsion. Both control methodologies have parameters that need to be tuned to improve their performance. These parameters have been optimised using genetic algorithms. The performance of these two control methods has been compared and their robustness has been evaluated through the simulation of environmental disturbances. This investigation has been carried out through computer-generated simulations based on a non-linear hydrodynamic model of CyberShip I.