计算机与现代化 ›› 2012, Vol. 1 ›› Issue (6): 27-30.doi: 10.3969/j.issn.1006-2475.2012.06.008

• 人工智能 • 上一篇    下一篇

基于频率特性的模拟电路故障诊断研究

胡海涛,李志华   

  1. 河海大学能源与电气学院,江苏 南京 211100
  • 收稿日期:2012-02-21 修回日期:1900-01-01 出版日期:2012-06-14 发布日期:2012-06-14

Study on Fault Diagnosis in Analog Circuits Based on Frequency Characteristics

HU Hai-tao, LI Zhi-hua   

  1. College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
  • Received:2012-02-21 Revised:1900-01-01 Online:2012-06-14 Published:2012-06-14

摘要: 由于模拟电路存在容差性、元件参数连续可变性和非线性等因素,且实际中也受到可测试点数量的限制,基于传统模拟电路故障诊断法在实际工程中难以取得理想的效果。而神经网络具有容错性、泛化能力和非线性处理能力等特点,本文针对雷达电路的故障进行快速有效的特征提取,构造神经网络样本,并结合电路的频率特性来解决模拟电路故障诊断中存在的问题。

关键词: 模拟电路, 故障诊断, 特征提取, 神经网络, 频率特性

Abstract: Analog circuit has its tolerance on component parameters, continuous response and nonlinearity, and the limitation of the number of test points, it is difficult to achieve expected results in practical engineering based on classical circuit fault diagnosis. While neural network has the characteristics of fault tolerance, generalization ability and non-linear processing, this paper extracts the fault feature in radar circuit rapidly and validly, constructs the samples of neural network, and solves the problems in fault diagnosis of analog circuits with frequency characteristics of circuits.

Key words: analog circuit, fault diagnosis, feature extraction, neural network, frequency characteristics

中图分类号: