基于遗传优化径向基神经网络的船舶航向控制  

Ship Course Control Based on Genetic Optimization of Radial Basis Neural Network

作　　者：杜加宝[1] 李敬东 王仁强[1] 孙建明[1] 邓华[1] 

机构地区：[1]江苏海事职业技术学院航海学院,江苏南京211170

出　　处：《广州航海学院学报》2017年第4期20-23,共4页Journal of Guangzhou Maritime University

基　　金：江苏海事职业技术学院课题(XR1501;XR1502);江苏高校品牌专业建设工程资助项目(PPZY2015B177)

摘　　要：设计了一种基于遗传算法优化径向基神经网络的船舶智能自动舵.针对船舶航向控制过程中的非线性和不确定性,将RBF网络直接逼近船舶模型内部不确定项和外界扰动,借助李雅普诺夫理论推演控制系统渐进稳定.利用遗传算法对径向基神经网络进行优化提高逼近性能.对比仿真结果显示,同等条件下,上述控制器较一般自适应控制和模糊PID控制系统稳定时间普遍快40%,平均超调量缩小100%,控制输入舵角进一步平滑稳定,且船舶航向对船舶内外部干扰不敏感.The intelligent autopilot is designed for ship on the basis of Radial Basis Function neural network optimized by genetic algorithm. Considering the nonlinearity and uncertainty of procedure for ship course control design,RBF network is used to approach the ship's inside uncertainties and external disturbances,ship course control law is designed by Lyapunov theory to derivate system stability. Genetic Algorithm is used to optimize the Radial Basis Function neural network so as to improve the performance of network approaching. Simulation results show that,the controller is faster 40% and lower overshoot reduced 100% compared with adaptive control algorithm and fuzzy PID control algorithm under the same conditions. And ship course is not sensitive to internal and external interference.

关 键 词：!自适应控制 RBF神经网络 遗传算法 自动舵 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置]