上海交通大学学报(自然版) ›› 2013, Vol. 47 ›› Issue (06): 884-888.

• 交通运输 • 上一篇    下一篇

基于果蝇优化算法的支持向量机参数优化在船舶操纵预报中的应用

王雪刚a,邹早建a,b   

  1. (上海交通大学  a.船舶海洋与建筑工程学院; b.海洋工程国家重点实验室, 上海 200240)
     
  • 收稿日期:2012-08-13
  • 基金资助:

    国家自然科学基金项目(50979060),教育部高等学校博士学科点专项科研基金项目(20110073110009)

FOA-Based SVM Parameter Optimization and Its Application in Ship Manoeuvring Prediction

WANG Xueganga,ZOU Zaojiana,b
  

  1. (a.School of Naval Architecture, Ocean and Civil Engineering; b.State Key Laboratory of Ocean Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
     
  • Received:2012-08-13

摘要:

应用果蝇优化算法对船舶操纵运动预报的ε-支持向量机(ε-SVM)的参数进行优化,建立船舶操纵运动预报黑箱模型,并用所建立的模型对Z形试验进行预报.通过预报结果与仿真试验结果对比,验证了该优化算法的有效性.研究结果表明,所设计的参数寻优方法具有算法设置简单、调整参数少以及不易陷入局部极小值等优点.
 
 

关键词: 船舶操纵预报, 果蝇优化算法, 支持向量机, 参数优化

Abstract:

The fruit fly optimization algorithm (FOA) was applied to optimize the parameters of ε-support vector machine (εSVM). By using the ε-SVM, a black-box model for predicting the ship manoeuvring motion was established and applied to predict the zig-zag tests. The validity of the proposed algorithm was verified by comparing the predicted results with the simulation data. It is shown that the proposed algorithm is simple, convenient and effective.

Key words:  ship manoeuvring prediction; , fruit fly optimization algorithm(FOA), support vector machine(SVM), parameter optimization

中图分类号: