Research On Intelligent Predictive Control For Unmanned Surface Vehicle Trajectory Tracking

Unmanned Surface Vehicle(USV),as an intelligent surface unmanned movement platform,is playing an increasingly important role in the field of lake monitoring and hydrological investigation because of its small size and portability.In this thesis,the selfdeveloped small torpedo USV is taken as the research object.In order to solve the problem of GPS signal lock-out in the on-board navigation system during the USV trajectory tracking,the integrated navigation method of USV trajectory tracking under the lock-out environment is studied.Aiming at the difficulty of accuracy maintenance and trajectory tracking control in USV navigation,the intelligent predictive control for trajectory tracking of USV is studied.The main contents are as follows:Firstly,the research status of USV and trajectory tracking technology at home and abroad is described,and the body structure and control system of small torpedo USV are designed,the on-board equipment selection is completed,and the trajectory tracking control scheme of small torpedo USV is designed.Then,in view of the situation that GPS signals are out of lock due to the occlusion of trees and bridges during USV trajectory tracking,the Adaptive Kalman Filter(AKF)model of USV integrated navigation was established,and an assisted integrated navigation method based on BP neural network was proposed.When GPS signal is locked,the improved artificial fish swarm algorithm is used to optimize the initial weights and thresholds of BP neural network and conduct online training.When GPS signals are out of lock,the trained BP neural network is used to predict GPS signals,and the adaptive Kalman filter algorithm is used to calculate the optimal state estimate.Simulation experiments show that the proposed method can effectively improve the accuracy of integrated navigation system data fusion.Secondly,in order to solve the difficulty of accuracy maintenance and trajectory tracking control in USV navigation due to the interference of external environment,a mathematical model of USV was established and a trajectory tracking method based on intelligent predictive control was proposed.In the rolling optimization process of predictive control,the improved particle swarm optimization algorithm is used to optimize the performance index function,which improves the calculation accuracy of the controller.Simulation results show that the proposed USV trajectory tracking control method has high tracking accuracy.Finally,the torpedo-shaped small USV control system is developed and the relevant experiment and analysis are carried out.The development work includes the hardware and software design of the control system.The hardware design part includes the schematic design of the circuit and the drawing of the circuit board.The software design part includes the design of the water surface monitoring software and the writing of the driver program of the lower computer system.After the functional debugging of each module,the assembly of the USV prototype is completed and the experiment is carried out.The experimental links include the land joint adjustment,pool experiment and trajectory tracking lake test.The experimental results show that the torpedo small USV control system runs stably and has good tracking performance.