Application of EEMD multi-scale entropy and LSSVM in analog circuit fault diagnosis

ZHUANG Cheng-cheng; YI Hui; ZHANG Jie

Chinese

您当前的位置：

首页 >

文章列表页 >

Application of EEMD multi-scale entropy and LSSVM in analog circuit fault diagnosis

更新时间：2026-09-04

- Application of EEMD multi-scale entropy and LSSVM in analog circuit fault diagnosis
- Vol. 36, Issue 10, Pages: 78-82(2019)
- 作者机构：
  
  南京工业大学机构电气工程与控制科学学院,江苏,南京,211816
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2019
- 稿件说明：
移动端阅览
庄城城, 易辉, 张杰. EEMD多尺度熵和LSSVM在模拟电路故障诊断中的应用[J]. 微电子学与计算机, 2019, 36(10): 78-82.

ZHUANG Cheng-cheng, YI Hui, ZHANG Jie. Application of EEMD multi-scale entropy and LSSVM in analog circuit fault diagnosis[J]. 2019, 36(10): 78-82.
庄城城, 易辉, 张杰. EEMD多尺度熵和LSSVM在模拟电路故障诊断中的应用[J]. 微电子学与计算机, 2019, 36(10): 78-82. DOI：

ZHUANG Cheng-cheng, YI Hui, ZHANG Jie. Application of EEMD multi-scale entropy and LSSVM in analog circuit fault diagnosis[J]. 2019, 36(10): 78-82. DOI：

摘要

针对模拟电路故障信号的非线性、非平稳性的特点

提出一种基于集合经验模态分解结合多尺度熵和最小二乘支持向量机的模拟电路故障诊断方法.该方法中

首先利用集合经验模态分解算法对输出响应信号进行分解

得到固有模态分量.然后求出各分量的多尺度熵并构造故障特征向量.最后将故障特征向量输入LSSVM分类器中进行检测.实验结果表明

该方法可以有效地提取模拟电路故障特征信息

能够实现模拟电路故障的精确诊断.

Abstract

Aiming at the nonlinearity and nonstationarity of analog circuit fault signals

a fault diagnosis method based on ensemble empirical mode decomposition (EEMD) combined with multi-scale entropy and least square support vector machine (LSSVM) is proposed. In this method

the set empirical mode decomposition algorithm is used to decompose the output response signal to get the intrinsic mode components

then the multi-scale entropy of each component is obtained and the fault eigenvectors are constructed. Finally

the fault eigenvectors are input into LSSVM classifier for detection.The experimental results show that this method can effectively extract fault feature information of analog circuits

and achieve accurate fault diagnosis of analog circuits.

关键词

Keywords

references

SONG P, HE Y Z, CUI W J. Statistical property featureextraction based on FRFT for fault diagnosis of analogcircuits [J].Analog Integrated Circuits and SignalProcessing, 2016, 87(3) : 427-436. DOI: 427

程文韬, 邓芳明, 郝勇, 等.基于小波和ELM的电路故障诊断方法研究[J].仪表技术与传感器, 2016(7):89-92. DOI: 89

何威, 何怡刚, 罗旗舞, 等.基于连续小波奇异熵的模拟电路故障诊断新方法[J].电子测量与仪器学报, 2017, 31(12):1967-1973. DOI: 1967

COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropyanalysis of biological signals[J]. Physical review. E, Statistical, nonlinear, and soft matter physic, 2005, 71(2) : 1-18. DOI: 1

贾亚飞, 朱永利, 王刘旺, 等.基于VMD和多尺度熵的变压器内绝缘局部放电信号特征提取及分类[J].电工技术学报, 2016, 31(19):208-215. DOI: 208

单剑锋, 汪良伟, 宋晓涛.基于HHT和SVDD的模拟电路故障诊断研究[J].计算机技术与发展, 2015, 25(7):179-183. DOI: 179

刘波, 易辉, 薄翠梅, 等.MCKD与改进的LSSVM在滚动轴承故障诊断中的应用[J].电子技术应用, 2018, 44(7):81-85. DOI: 81

杨望灿, 张培林, 王怀光, 等.基于EEMD的多尺度模糊熵的齿轮故障诊断[J].振动与冲击, 2015, 34(14):163-167. DOI: 163

WU Z H, HUANG N E.Ensemble empirical modedecomposition:A noise assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41. DOI: 1

胡天骐, 单剑锋, 宋晓涛.基于改进PSO-LSSVM的模拟电路诊断方法[J].计算机技术与发展, 2015, 25(6):193-196. DOI: 193

王震, 李志华, 邵新添.基于改进的EMD方法的模拟电路故障诊断研究[J].信息技术, 2017, (12):37-40. DOI: 37

刘琳.一种模拟电路故障诊断方法研究[J].现代电子技术, 2017, 40(6):183-186. DOI: 183

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of LS-SVM Based on PSO to Fault Prediction of Communication Equipment

A feature-oriented context understanding and slice analysis network for tuberculosis detection

Steganography model guided by attention mechanism and improved dense convolution

Design of ultra-low power real-time clock circuits

A review of large model development: technological evolution from BERT to Deepseek

Related Author

LI Wen-yuan

YAN Hai-hua

YAO Hong-jie

Related Institution

1 Xi'an Communication Institute

2 Troopy 75706

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰