Research on UUV Trajectory Tracking Control Based on RBF Neural Network PID
In the process of performing underwater tasks,unmanned underwater vehicle(UUV)need to sail stably along the preset path to ensure the normal operation of special equipment,but they are suscep-tible to interference from multiple sources in the deep sea with complex environment.In order to solve the path tracing problem of UUV in complex water environment,this paper decoupled the path tracing prob-lem into horizontal plane heading control and vertical plane depth control,and proposed a PID control algorithm optimized by RBF neural network.Firstly,the underwater kinematics model of UUV was established,the RBF neural network structure was introduced on the basis of the traditional PID control-ler,and the iterative formula of RBF parameters was given to compensate for the disturbance and opti-mize the PID parameters in real time.In order to simulate the trajectory tracking and controlling of UUV,the simulation model of RBF neural network PID was built in Simlink.By comparing the errors in the horizontal plane and the vertical plane,the simulation results show that compared with the traditional PID control algorithm,the overshoot of the RBF neural network PID controller is reduced by 15 percent-age points,the oscillation amplitude is reduced by 10%,and the ability to overcome unknown distur-bances is stronger.Finally,the lake test is designed to verify the effect of the tracking controller,and the experiments show that the UUV can achieve better attitude control effect and path tracking ability in com-plex waters,and meet the requirements of underwater tasks.However,the time lag of the UUV actuator should be considered in practical application to improve the adaptability of the controller.
UUVtrajectory trackingradial basis function neural networkPID tuning
万方数据
维普
