|Table of Contents|

Volterra Series Kernels Estimation Algorithm Based on GA Optimized BP Neural Network Identification

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2012年06期
Page:
0-
Research Field:
Publishing date:

Info

Title:
Volterra Series Kernels Estimation Algorithm Based on GA Optimized BP Neural Network Identification
Author(s):
MEN Zhi guo1PENG Xiuyan 1WANG Xingmei 2HU Zhonghui 1SUN Shuangshuang 3
1.College of Automation;2.College of Computer Science and Technology;3.College of Science,Harbin Engineering University,Harbin 150001,China
Keywords:
genetic algorithmback propagation neural networkchaos characteristic identificationship motionmultistep prediction
PACS:
TP29
DOI:
-
Abstract:
In order to obtain more effective prediction results of ship motion,a method is proposed using the genetic algorithm(GA)optimized singleoutput threelayer back propagation(BP)neural network to identify Volterra series kernels.The GA,the BP neural network and the features of the Volterra series model are further analyzed based on the chaos characteristic identification of ship motion attitude time series.The best initial weights and thresholds are obtained by using the GA optimized BP neural network.The final optimal weights and thresholds of model parameters are obtained by the BP neural network algorithm.The multistep prediction of the time series of a ship roll motion is done by making Taylor series decomposition to obtain Volterra series kernels of each order.The simulation experiments show that the proposed algorithm has high precision and long prediction time and effectiveness and adaptability.

References:

[1]Chatterjee A.Parameter estimation of Duffing oscillator using Volterra series and multitone excitation[J].International Journal of Mechanical Sciences,2010,52(1):1716-1722. 
[2]Du Baozhu,Lam J.Stability analysis of static recurrent neural networks using delaypartitioning and projection[J].Neural Networks,2009,22(1):343-347. 
[3]Wu Wei,Wang Jian,Cheng Mingsong,et al.Convergence analysis of online gradient method for BP neural networks[J].Neural Networks,2011,24(1):91-98.
[4]陈得宝,赵春霞.基于改进GA的WRBF神经网络设计与应用[J].南京理工大学学报,2007,31(3):370-374. Chen Debao,Zhao Chunxia.Design and application of WRBF neural network based on improved GA[J].Journal of Nanjing University of Science and Technology,2007,31(3):370-374.
[5]李辉,蔡敏,陈斌.基于自适应遗传算法优化BP神经网络[J].信息化研究,2010,36(9):36-39. Li Hui,Cai Min,Chen Bin.Optimized BP neural network based on selfadapted genetic algorithm[J].Informatization Research,2010,36(9):36-39. 
[6]PengXiuyan,Men Zhiguo,Wang Xingmei,et al.The ship motion prediction approach based on BP neural network to identify volterra series kernels[A].Proceedings of the 2011 IEEE International Conference on Information Science and Engineering[C].Yangzhou,China:IEEE,2011:2197-2200.
[7]孙冬梅,李永新.基于Volterra级数及神经网络的非线性系统建模[J].仪器仪表学报,2003,24(4):5-7. Sun Dongmei,Li Yongxin.Nonlinear system modeling method based on Volterra series and neurel network[J].Chinese Journal of Scientific Instrument,2003,24(4):5-7.
[8]唐婉莹,杨宇川,段秀云.BP神经网络对含铝炸药爆热预测的研究[J].南京理工大学学报,2003,27(2):184-187. Tang Wanying,Yang Yuchuan,Duan Xiuyun.Prediction of explosion heat of aluminiferous explosive by BP neural network[J].Journal of Nanjing University of Science and Technology,2003,27(2):184-187. 
[9]WongW K,Yuen C W M,Fan D D,et al.Stitching defect detection and classification using wavelet transform and BP neural network[J].Expert Systems with Applications,2009,36(1):3845-3856. 
[10]Yu Shiwei,Guo Xiufu,Zhu Kejun,et al.A neurofuzzy GABP method of seismic reservoir fuzzy rules extraction[J].Expert Systems with Applications,2010,37(3):2037-2042. 
[11]Xie Qiu,Liu Zixian.Efficiency evaluation for collaborative design based on GABP algorithm[A].Proceedings of the 2008 12th International Conference on Computer Supported Cooperative Work in Design[C].Xi’an,China:IEEE,2008:234-240.

Memo

Memo:
-
Last Update: 2012-12-29