山东科学 ›› 2018, Vol. 31 ›› Issue (4): 8-14.doi: 10.3976/j.issn.1002-4026.2018.04.002

• 海洋科技与装备 • 上一篇    下一篇

基于BP神经网络的船舶航向智能PID控制研究

李小峰,于慧彬   

  1. 齐鲁工业大学(山东省科学院),山东省科学院海洋仪器仪表研究所,山东省海洋监测仪器装备技术重点实验室,国家海洋监测设备工程技术研究中心,山东 青岛 266001
  • 收稿日期:2017-12-04 出版日期:2018-08-20 发布日期:2018-08-20
  • 通信作者: 于慧彬。E-mail:binbinyu@163.com。 E-mail:binbinyu@163.com
  • 作者简介:李小峰(1983—),女,硕士,工程师,研究方向为自动化控制系统、嵌入式系统与智能控制。
  • 基金资助:

    山东省科技重大专项(2015ZDZX08001);国家重点研发计划(2016YFE0205700)

Research on intelligent PID control of ship course based on BP neural network

LI Xiao-feng,YU Hui-bin
  

  1. Shandong Provincial Key Laboratory of Marine monitoring instrument equipment technology,National Engineering and Technological Research Center of Marine Monitoring Equipment,Institute of Oceanographic Instrumentation,QiLu University of Technology (Shandong Academy of Sciences),Qingdao 266001,China
  • Received:2017-12-04 Online:2018-08-20 Published:2018-08-20

摘要:

针对船舶航向控制非线性的特性,以船舶航向运动一阶KT模型为研究对象,设计了基于BP神经网络的自整定PID算法航向控制器。将传统PID与BP神经网络结合,对被控对象由BP神经网络进行辨识,给出PID控制参数,由PID控制算法进行控制并优化收敛速度。根据真实渡轮船舶特征参数,利用MATLAB/Simulink仿真软件建立船舶航向运动控制系统模型。仿真结果表明,基于BP神经网络的PID控制系统超调小、鲁棒性好,可长时间稳定工作,几乎无稳态误差,控制算法的实用性以及动态控制系统的优越性得到验证。

关键词: PID控制, MATLAB仿真, BP神经网络, 船舶操纵

Abstract:

According to the nonlinear characteristics of ship course control, and taking the first-order KT model of ship course motion as the research object, the selftuning PID algorithm course controller based on BP neural network was designed. Combining the traditional PID and the BP neural network, the controlled object was identified by the BP neural network, the PID control parameters were given, and the PID control algorithm was used to control and optimize the
convergence speed. Based on a true ferry′s characteristic parameters, the ship′s course motion control system model was established using MATLAB/Simulink simulation software. The simulation results show that the design has small overshoot, good robustness, capable to work steadily for a long time, and almost no steadystate error. The practicability of the control algorithm and the superiority of the PID control system were verified.

Key words: BP neural network, ship manoeuvring, MATLAB simulation, PID control

中图分类号: 

  • TP 273