基于RBF神经网络PID的UUV轨迹跟踪控制  

Research on UUV Trajectory Tracking Control Based on RBF Neural Network PID

作　　者：王景楠 薛晨阳[1] 齐向东 刘丹 WANG Jinnan;XUE Chenyang;QI Xiangdong;LIU Dan(Key Laboratory of Instrumentation Science and Dynamic Measuremen(t North University of China),Ministry of Education,Taiyuan 030051,China)

机构地区：[1]中北大学仪器科学与动态测试教育部重点实验室,山西太原030051

出　　处：《中北大学学报（自然科学版）》2024年第6期843-851,共9页Journal of North University of China(Natural Science Edition)

基　　金：山西省科技创新人才专项资助(202304051001030)。

摘　　要：无人水下航行器(Unmanned UnderwaterVehicle,UUV)在执行水下任务过程中需要沿预设路径稳定航行以保证专用设备正常工作,其在环境复杂的深海中易受到多种来源的干扰。针对在复杂水域环境中UUV的路径追踪问题,本文将路径跟踪问题解耦为水平面航向控制和垂直面深度控制,提出一种RBF神经网络优化的PID控制算法。首先建立了UUV水下运动学模型,在传统PID控制器的基础上引入RBF神经网络结构,给出RBF参数迭代公式对扰动进行补偿并实时优化PID参数。在Simlink中搭建了RBF神经网络PID仿真模型,对无人水下航行器的轨迹跟踪控制进行了仿真,水平面和垂直面上的误差对比仿真结果表明,与传统PID控制算法相比,RBF神经网络PID控制器的超调量减小了15百分点,振荡幅值降低了10%,克服未知扰动的能力更强。通过湖试试验验证了航迹跟踪控制器效果,实验表明,UUV可在复杂水域实现较好的姿态控制效果及路径追踪能力,能够满足水下任务需求,但在实际应用中应考虑UUV执行机构的时滞问题,以提高控制器的适应性。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 susceptible 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 problem 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 controller,and the iterative formula of RBF parameters was given to compensate for the disturbance and optimize 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 percentage points,the oscillation amplitude is reduced by 10%,and the ability to overcome unknown disturbances 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 complex 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.

关 键 词：无人水下航行器 轨迹跟踪 径向基函数神经网络 PID整定 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程] TP183[自动化与计算机技术—控制科学与工程]