基于克隆优化的船舶号灯神经网络识别模型

朱金善*1; 孙立成2; 胡江强1; 何庆华1

doi:10.16411/j.cnki.issn1006-7736.2015.02.007

大连海事大学学报 >

2015 , Vol. 41 >Issue 2: 41 - 45

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2015.02.007

交通运输工程

基于克隆优化的船舶号灯神经网络识别模型

朱金善^*1 ,
孙立成² ,
胡江强¹ ,
何庆华¹

展开

(1．大连海事大学航海学院，辽宁大连 116026; 2.中国船级社，北京 100007)

朱金善*（1971-），男，博士生，教授，船长，E-mail: zjinshan888@126.com.

收稿日期: 2014-11-05

修回日期: 2014-12-08

网络出版日期: 2015-06-07

基金资助

辽宁省自然科学基金资助项目（2014025008）；中央高校基本科研业务费专项资金资助项目（3132014028）.

收起

Neural network recognition model of ship lights based on clonal optimization

ZHU Jin-shan^*1 ,
SUN Li-cheng² ,
HU Jiang-qiang¹ ,
HE Qing-hua¹

Expand

(1. Navigation College, Dalian Maritime University, Dalian 116026, China; 2.China Classification Society, Beijing 100007, China)

Received date: 2014-11-05

Revised date: 2014-12-08

Online published: 2015-06-07

Fold

摘要

针对复杂光环境下船舶号灯识别模型的高维、强非线性及影响因素复杂等特性，提出一种基于克隆选择优化算法的BP神经网络识别模型.通过对影响因素的筛选确定BP神经网络的输入，将号灯识别码作为网络的输出确定BP神经网络模型.采用免疫克隆选择优化算法，确定网络层数和各层节点数目，结合灵敏度分析法选择非线性寻优的方向和尺度，以减少BP神经网络的迭代次数，提高搜索效率. 通过对海上夜航时拍摄的一些实景照片进行学习和识别的仿真，验证了所建立的船舶号灯识别模型的有效性.

关键词： 船舶号灯; 识别模型; 克隆优化; 神经网络

本文引用格式

朱金善^*1 , 孙立成² , 胡江强¹ , 何庆华¹ . 基于克隆优化的船舶号灯神经网络识别模型[J]. 大连海事大学学报, 2015 , 41(2) : 41 -45 . DOI: 10.16411/j.cnki.issn1006-7736.2015.02.007

Abstract

Aiming at the features of ship lights recognition model under complex light environment such as strong nonlinearity, high dimension and complex environmental disturbances, a ship lights recognition model based on BP neural network was proposed. The relevant factors were selected as network inputs, and the identification code was set as network output to make up BP neural network model. Immune clonal selection optimization algorithm was adopted to decide the network layers and the number of units in each layer, by combining with sensitivity analysis method to search the direction and scale of nonlinear optimization to reduce the number of iterations the BP neural network and improve the search efficiency.Based on the spot photoes of ship lights, simulations of ship lights recognition were conducted by using the improved neural recognition model. Simulation results demonstrate the efficiency of the proposed ship lights recognition model.

Key words： ship lights; recognition model; clonal optimization; BP neural network

参考文献

[1]Gallaway T, Olsen R N, Mitchell D M. The economics of global light pollution [J]. Ecological Economics, 2010,69: 658-665.
[2]Brons J, Bullough J D, Rea M. Outdoor site-lighting performance: A comprehensive and quantitative framework for assessing light pollution [J]. Lighting Res. Technol., 2008, 40: 201–224.
[3]朱金善，孙立成，尹建川等.基于BP神经网络的船舶号灯识别模型与仿真[J]. 应用基础与工程科学学报, 2012, 20(3):455-463.
ZHU Jinshan, SUN Licheng, YIN Jianchuan et al. Simulation of ship lights recognition Model based ON Back Propagation neural network[J].Journal of Basic Science and Engineering, 2012, 20(3):455-463.
[4]胡江强，郭晨，尹建川等. 分级变异的动态克隆选择算法[J].控制与决策,2007,22(6):608-609.
HU Jiang-qiang, GUO Chen，YIN Jian-chuan et al. Dynamic Clonal Selection Algorithm with Classified Mutation[J]. Contol and decision, 2007,22(6):608-609.
[5]刘洋,郭晨. 船舶航向保持RBF神经网络自适应非线性控制[J],大连海事大学学报, 2013,39(4):1-4.
LIU Yang, GUO Chen. RBF neural network based adaptive nonlinear control for ship course keeping [J]. Journal of Dalian Maritime University, 2013,39(4):1-4.
[6]Yin, J. C., Zou, Z. J., Xu, F. Sequential learning radial basis function network for real-time tidal level predictions[J]，Ocean Engineering, 2013,57,49-55.
[7]Cao B Q and Liu J X. Currency Recognition Modeling Research Based on BP Neural Network Improved by Gene Algorithm [C]. 2010 Second International Conference on Computer Modeling and Simulation, IEEE computer society, 2010.
[8]曾志波,丁恩宝,唐登海. 基于BP人工神经网络和遗传算法的船舶螺旋桨优化设计[J].船舶力学, 2010, 14(1-2): 20-27.
Zeng Zhibo, Ding Enbao and Tang Denghai. Ship propeller design optimization based on BP neural network and genetic algorithm [J]. Journal of Ship Mechanics, 2010, 14(1-2): 20-27.
[9]Marquardt D． An algorithm for least squares estimation of nonlinear parameters[J]． Journal of the Society for Industry and Applied Mathematics，1963，11(2) : 431-441．
[10]张鸿燕，耿征.Levenberg-Marquardt算法的一种新解释[J]．计算机工程与应用，2009,45(19):5-8.
ZHANG Hong-yan, GENG Zheng. Novel interpretation for Levenberg-Marquardt algorithm, Computer Engineering and Applications,2009,45（19）：5-8.
[11]Leandro N. de Castro and Fernando J. Von Zuben. Learning and Optimization Using the Clonal Selection Principle. IEEE Transactions on Evolutionary Computation, 2002,6(3):239-251.
[12]杜海峰，焦李成，刘若辰. 免疫优势克隆算法[J]. 电子与信息学报，2004 ,6(12):1998-1924.
Du Hai-feng, Jiao Li-cheng, Liu Ruo-chen. Immunodominance Clone Algorithms. Journal of Electronics & Information Technology. 2004 ,6(12):1998-1924.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献