[1]LI Yang,ZHONG Shi-sheng,ZHANG Yan.Research and simulation of a continuous wavelet process neural network[J].CAAI Transactions on Intelligent Systems,2007,2(6):77-81.
Copy

Research and simulation of a continuous wavelet process neural network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 2 Number of periods: 2007 6 Page number: 77-81 Column: 学术论文—机器学习 Public date: 2007-12-25
Title:
Research and simulation of a continuous wavelet process neural network
Author(s):
LI Yang;  ZHONG Shi-sheng;  ZHANG Yan
Department of Mechanical and Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China
Keywords:
process neuron;  continuous wavelet process neural networks;  learning algorithm;  monitoring of aeroengine lubricating oil system
CLC:
TP183
DOI:
-
Abstract:
A continuous wavelet process neural networks (CWPNN) model is proposed based on wavelet analysis and process neural network theory in which the hidden layer is composed of process neurons and the hidden layer activation function is a wavele ts function. This network not only has excellent learning capability but also hi gh accuracy since it combines the timefrequency local property of wavelet anal y sis with the ability of process neural networks to deal with continuous input si gnals. The corresponding learning algorithm is given. The network was compared w ith a traditional BP neural network while monitoring the state of an aeroengine lubricating oil syste m. The results demonstrated the faster convergence rate and higher accuracy of t he network. Prediction capability was superior to a BP neural network, providing a more effective method for state monitoring of aeroengine lubricating oil syst ems.
References:
［1］何新贵, 梁久祯. 过程神经网络的若干理论问题［J］. 中国工程科学, 2000 ，2(12): 40-44.
?HE Xingui, LIANG Jiuzhen. Some theoretical issueson procedure neural networks ［ J］. Engineering Science, 2000,2(12):40-44.
［2］许少华, 何新贵.基于函数正交基展开的过程神经网络学习算法［J］.计算机学报, 2004, 27(5):645-650.
XU Shaohua, HE Xingui. Learning algorithms of process neural networ ks based on o rthogonal function basis expansion ［J］. Chinese Journal of Computers, 2004, 27 (5):645-650.
［3］何新贵,梁久祯,许少华.过程神经网络的训练及其应用［J］. 中国工程科学, 2001, 3(4):31-35.
HE Xingui, LIANG Jiuzhen, XU Shaohua. Learning and applications of procedure neu ral networks［J］. Engineering Science, 2001, 3(4):31-35.
［4］ZHANG Q H，BENVENISTE A. Wavelet networks［J］. IEEE Transactions on Neural Networks, 1992, 3(6): 889-898.
［5］柳重堪. 正交函数及其应用［M］.北京:国防工业出版社,1982.
［6］王 广, 李 军. 基于神经网络的航空发动机滑油监测分析［J］. 润滑与密封, 2003(5):123-125.
WANG Guang, LI Jun. Aeroengine lube monitoring analysis based on neutral network s［J］.Lubrication Engineering，2003, 5:123-125.
［7］赵学智, 邹春华, 陈统坚,等. 小波神经网络的参数初始化研究［J］. 华南理工大学学报, 2003, 31(2):77-79.
 ZHAO Xuezhi, ZOU Chunhua, CHEN Tongjian,et al. A research on the initialization of parameters of wavelet neural networks［J］.Journal of South China University of Technology,2003, 31(2):77-79.
Similar References:

Memo

-

Last Update: 2009-05-09

Copyright © CAAI Transactions on Intelligent Systems