基于神经网络-PID控制的水面无人艇控制系统设计

Design of Unmanned Surface Vehicle Control System Based on Neural Network-PID Control

为了提高在存在外界干扰和障碍物的环境下水面无人艇(unmannedsurfacevehicle,USV)控制系统的准确性和鲁棒性,提出了神经网络-PID控制算法。首先,使用人工势场法规划路径,得到一条从起点到终点的可行路径;然后,利用神经网络的自学习能力修正控制参数,实现控制参数的实时在线调节,精确调控USV沿着规划好的路径行进。在不同环境下进行仿真测试,仿真结果表明,与常规PID控制算法和模糊PID控制算法相比,所提算法降低了超调量和稳态误差,提高了控制系统的实时响应速度与USV的定位和航行精度。所提算法的抗干扰能力和控制精度优于与常规PID控制算法和模糊PID控制算法。

In order to improve the accuracy and robustness of the control system of unmanned surface vehicle(USV)in the environment with external interference and obstacles,a neural network-PID control algorithm is proposed.Firstly,the artificial potential field method is used to plan the path,and a feasible path from the starting point to the end point is obtained.Then,the self-learning ability of the neural network is used to modify the control parameters,so that the real-time online adjustment of the control parameters is realized,and the USV is precisely controlled along the planned path.Simulation tests are carried out in different environments.The simulation results show that compared with the conventional PID control algorithm and fuzzy PID control algorithm,the proposed algorithm reduces the overshoot and steady-state error,and improves the real-time response speed of the control system and the positioning and navigation accuracy of USV.The anti-interference ability and control precision of the proposed algorithm are superior to the conventional PID control algorithm and fuzzy PID control algorithm.