Adaptive Fuzzy Design Of Ship's Autopilot Based On DSC-MLP

To employ adaptive,robust and simple autopliot of ship course control has been a hot topic in today's ship motion control.In this paper,employing three kinds of adaptive fuzzy design of ship autopliot algorithms.In the first algorithm,there are two parameters in each subsystem;In the second algorithm,there is one parameter in each subsystem;In the third algorithm,there is only one parameter in the whole system.In this paper,employing T-S fuzzy system to approximate the uncertain functions,but sometimes it causes "dimension curse",at this point,we introduce MLP(minimal learning parameter) to solve the problem.In the design procedure,Backstepping techniques causes "explosion of complexity",introduce DSC(dynamic surface control) to solve this problem. In corporate MLP and DSC,so we can sovle the both problems simultaneously with less parameters and reduce computational load.The proposed algorithms is conventient to be implemented in applications,and can avoid the possible controller sinularity problem.In addtion,the boundedness stability of the closed-loop system is guaranteed and the tracking error can be made arbitrary small. The matlab simulation results validate the effectiveness and the performance of proposed adaptive fuzzy design of ship'autopilot. To further illustrate the control performance of the controller, to change ship course control system model parameters, comparing the simulation results.