[1]肖迎群,何怡刚,张广辉.小波范数熵特征提取的模拟电路故障诊断方法[J].机械与电子,2015,(06):3-9.
　XIAO Yingqun,HE Yigang,ZHANG Guanghui.A Fault Diagnosis Approach of Electric Circuit Based on Wavelet Norm Entropy asFeature Extractor[J].Machinery & Electronics,2015,(06):3-9.
点击复制

小波范数熵特征提取的模拟电路故障诊断方法
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2015年06期
页码:
3-9
栏目:
设计与研究
出版日期:
2015-06-26

文章信息/Info

Title:
A Fault Diagnosis Approach of Electric Circuit Based on Wavelet Norm Entropy as Feature Extractor
文章编号:
1001-2257(2015)06-0003-07
作者:
肖迎群1; 何怡刚1; 2; 张广辉1
(1.贵州理工学院电气工程学院,贵州 贵阳 550003; 2.合肥工业大学电气与自动化工程学院,安徽 合肥 230009)
Author(s):
XIAO Yingqun1; HE Yigang1; 2; ZHANG Guanghui1
(1. School of Electrical Engineering,Guizhou Institute of Technology,Guiyang 550003,China; 2. School of Electrical Engineering and Automation,Hefei University of Technology,Hefei 230009,China)
关键词:
小波理论;  范数熵;  遗传算法;  神经网络;  故障诊断
Keywords:
wavelet theory;  norm entropy;  genetic algorithm;  neural network;  fault diagnosis
分类号:
TN707; TP183
文献标志码:
A
摘要:
提出一种遗传优化神经网络与小波范数熵相结合的新型模拟电路故障诊断方法,降低神经网络的结构冗余度和减少过拟合现象。小波范数熵方法提取了故障数据的本质特征,遗传算法优化了神经网络的体系结构,诊断系统实施了模拟数据的故障分类。仿真结果表明,同小波变换预处理的故障诊断系统相比较,这种诊断系统具有更好的网络收敛性能、更高的诊断精确度和更强的推广能力,能对模拟电路故障元件进行有效识别和分类。
Abstract:
A fault diagnosis method combing wavelet norm entropy theory and genetic neural networks is introduced in order to reduce structural redundancy of neural networks and its over-fitting of nonlinear approximation. Wavelet norm entropy theory is used to extract the intrinsic features of fault data, and a genetic algorithm is utilized to reduce the architecture of the neural network and a fault diagnosis system of analog circuit is constructed to execute fault classification. Simulation results show that in comparison to wavelet transformation pretreatment the proposed system has better convergence performance, higher diagnosis accuracy and better generalization ability. Ultimately, the system can effectively recognize and classify the faulty components of electric circuits.

参考文献/References:

[1] 杨士元.模拟系统的故障诊断与可靠性设计[M].北京:清华大学出版社,1993.
[2] Bandler J W,Salama A E. Fault diagnostic of analog circuits[J].Proceedings of the IEEE,1985,73(8): 1279-1325.
[3] Spina R,Upadhyaya S. Linear circuit fault diagnosis using neuromorphic analyzers [J]. IEEE Transactions on Circuits and Systems II,1997,44( 3): 188-196.
[4] Aminian M,Aminian F. Neural-network based analog- circuit fault diagnosis using wavelet transform as preprocessor[J]. IEEE Transactions on Circuits and Systems II,2000,47(2): 151-156.
[5] Aminian F,Aminian M,Collins H W.Analog fault diagnosis of actual circuits using neural networks[J]. IEEE Transactions on Instrumentation and Measurement,2002,51(3): 544-550.
[6] He Y,Tan Y,Sun Y. Wavelet neural network approach for fault diagnosis of analog circuits[J].Circuits,Devices and Systems,IEE Proceedings,2004,151(4): 379-384.
[7] 肖迎群,何怡刚. 基于脊波网络的模拟电路故障诊断[J].电工技术学报,2010,25(6): 155-162.
[8] Xiao Yingqun,He Yigang. A linear ridgelet network approach for fault diagnosis of analog circuit[J]. Science China:Information Sciences,2010,53(11): 2251-2264.
[9] Yuan Lifen,He Yigang,Huang Jiaoying,et al. A new neural-network-based fault diagnosis approach for analog circuits by using Kurtosis and entropy as a preprocessor [J]. IEEE Transactions on Instrumentation and Measurement,2010,59(3): 586-595.
[10] 金瑜,陈光楀,刘红.基于小波神经网络的模拟电路故障诊断[J].仪器仪表学报,2007,28(9):1600-1604.
[11] 谢宏,何怡刚,吴杰.基于小波-神经网络模拟电路故障诊断方法的研究[J].仪器仪表学报,2004,25(5):672-675.
[12] Yao Xin.Evolving artificial neural networks[J]. Proceedings of the IEEE,1999,87(9): 887-898.
[13] Goldberg D E,Deb K.A comparison of selection schemes used in genetic algorithms[J].Foundations of Genetic Algorithms,1991(11): 69-93.
[14] Arifovic J,Gencay R. Using genetic algorithms to select architecture of a feedforward artificial neural network[J]. Physica A,2001,289(3): 574-594.
[15] Sarimveis H,Alexandridis A,Mazarakis S,et al. A new algorithm for developing dynamic radial basis function neural network models based on genetic algorithms[J]. Computers and Chemical Engineering,2004,28(1/2): 209-217.
[16] 杨福生.小波变换的工程分析与应用[M].北京:科学出版社,2000.
[17] Uya M,Yildirim S,Gencoglu M T. An effective wavelet-based feature extraction method of power quality disturbance signals[J]. Electric Power Systems Research,2008,78(10): 1747-1755.
[18] Arivazhagan S,Ganesan L. Texture classification using wavelet transform[J].Pattern Recognition Letters,2003,24(9/10): 1513-1521.
[19] Madan M Gupta,Liang Jin,Noriyasu Homma. Static and dynamic neural network[M]. IEEE Press,2003.
[20] Michalewicz Z.Genetic algorithms+data structures=evolution programs [M]. Springer,1996.
[21] Sivanandam S N,Deepa S N.Introduction to genetic algorithms [M]. Springer,2008.

备注/Memo

备注/Memo:
收稿日期:2015-04-27
基金项目:贵州省科学基金重点项目(黔科合LH字[2014]7356号); 贵州理工学院高层次人才科研启动经费项目(XJGC20131203)
作者简介:肖迎群(1975-),男,湖南邵阳人,博士后,副教授,主要研究方向为高维数据分析,模拟系统故障诊断。
更新日期/Last Update: 2015-06-26