journal6 ›› 2009, Vol. 30 ›› Issue (3): 62-65.

• 物理与电子 • 上一篇    下一篇

非线性模拟电路故障的BPNN诊断算法设计与实现

  

  1. (1.湖南大学电气与信息工程学院自动化系,湖南  长沙 410082;2.中南大学基础医学院,湖南  长沙 410078)
  • 出版日期:2009-05-25 发布日期:2012-04-23
  • 作者简介:谢宏(1964-),男,湖南大学电气与信息工程学院自动化系副教授,博士,主要从事电路与系统理论及故障诊断、神经网络、智能控制研究;何怡刚(1966-),男,湖南大学电气与信息工程学院自动化系教授,博士生导师,主要从事电路与系统理论及故障诊断、神经网络、有源滤波器等研究.
  • 基金资助:

    教育部高校博士学科点专项基金资助项目(20060532002);湖南省自然科学基金资助项目(06JJ2024)

Algorithm  and Its Realization of Fault Location for Nonlinear Analog Circuits Based on BP Neural Network

  1. (1.College of Electrical and Information Engineering,Hunan University,Changsha,410082,China;2.Basic Medical College,Central South,University,Changsha 410078,China)
  • Online:2009-05-25 Published:2012-04-23

摘要:提出了用Volterra频域核作为故障特征对弱非线性定常动态网络进行故障诊断的方法,利用计算方法求出电路响应在各种常见故障状态下的Volterra级数解的各阶频域核,将其输入给BP神经网络,利用BPNN的分类功能建立故障字典,对实测的故障网络的各阶频域核进行测试样本分类来实现故障诊.通过故障诊断实例给出了各阶频域核的统一递推离散算式,并采用了改进BPNN算法及其程序实现.

关键词: 故障诊断, 非线性电路, 频域核, 神经网络

Abstract: A fault location method for nonlinear circuit by taking the cores of  Volterra series in frequency domain as the fault characters is proposed.Via calculating the frequency cores of Volterra series in frequency domain for the response of usual fault states and feeding them into BPNN as the fault features,the fault dictionary is built.The fault location for nonlinear analog circuit is completed by BPNN classifying the Volterra frequency cores tested from the nonlinear network.The paper presents the unified recursive computing formulae for frequency cores,an improved BPNN algorithm and its program.At last,an example of this method is given.

Key words: fault location, nonlinear circuit, frequency core, neural network

公众号 电子书橱 超星期刊 手机浏览 在线QQ