首页 | 本学科首页   官方微博 | 高级检索  
     

基于PCA和PNN的模拟电路故障诊断
引用本文:孙健,王成华,闫之烨,洪峰. 基于PCA和PNN的模拟电路故障诊断[J]. 微电子学, 2014, 0(1): 123-126
作者姓名:孙健  王成华  闫之烨  洪峰
作者单位:南京信息职业技术学院, 南京 210046;南京航空航天大学 电子信息工程学院, 南京 210016;南京航空航天大学 电子信息工程学院, 南京 210016;南京信息职业技术学院, 南京 210046;南京航空航天大学 电子信息工程学院, 南京 210016
基金项目:国家自然科学基金资助项目(50907033)。
摘    要:为了解决模拟电路故障识别困难的问题,提出一种基于主成分分析和概率神经网络的模拟电路故障诊断方法。该方法对采集到的模拟电路故障信息进行特征提取,将提取的故障特征归一化处理后输入概率神经网络,进行训练和故障模式的分类识别。实验结果表明,该方法是有效的,具有较高的故障诊断率。

关 键 词:模拟电路   故障诊断   主成分分析   概率神经网络

Fault Diagnosis of Analog Circuit Based on PCA and PNN
SUN Jian,WANG Chenghu,YAN Zhiye and HONG Feng. Fault Diagnosis of Analog Circuit Based on PCA and PNN[J]. Microelectronics, 2014, 0(1): 123-126
Authors:SUN Jian  WANG Chenghu  YAN Zhiye  HONG Feng
Affiliation:Nanjing College of Information Technology, Nanjing 210046, P.R.China;College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P.R.China;College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P.R.China;Nanjing College of Information Technology, Nanjing 210046, P.R.China;College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P.R.China
Abstract:In order to solve the problem with identification of fault in analog circuit, a fault diagnosis method for analog circuits was proposed based on principal component analysis (PCA) and probabilistic neural network (PNN). In this technique, PCA was applied to extract features of the collected information about fault in analog circuit, and the extracted fault features were normalized and input into PNN for training and identification of classified fault modes. Experimental results showed that this method was effective and had higher fault diagnosis rate.
Keywords:Analog circuit   Fault diagnosis   Principal component analysis   Probabilistic neural network
本文献已被 CNKI 等数据库收录!
点击此处可从《微电子学》浏览原始摘要信息
点击此处可从《微电子学》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号