辽宁石油化工大学学报

辽宁石油化工大学学报 ›› 2015, Vol. 35 ›› Issue (2): 58-61.DOI: 10.3696/j.issn.1672-6952.2015.02.013

• 计算机与自动化 • 上一篇    下一篇

一种基于量子神经网络的模拟电路故障诊断方法

张朝龙1, 2,何怡刚1,袁莉芬1,陈立平1   

  1. ( 1. 合肥工业大学电气与自动化工程学院, 安徽合肥2 3 0 0 0 9; 2. 安庆师范学院物理与电气工程学院, 安徽安庆2 4 6 0 1 1)
  • 出版日期:2015-04-25 发布日期:2015-05-06
  • 作者简介:张朝龙( 1 9 8 2 - ) , 男, 博士研究生, 讲师, 从事模拟和混合信号电路的故障诊断和预测研究; E - m a i l : z h a n g c l @a q t c .e d u. c n。
  • 基金资助:
    国家杰出青年科学基金项目( 5 0 9 2 5 7 2 7) ; 国防科技计划项目( C 1 1 2 0 1 1 0 0 0 4、 9 1 4 0 A 2 7 0 2 0 2 1 1 D Z 5 1 0 2) ; 国家自然科学基金项目 ( 6 1 1 0 2 0 3 5, 6 1 4 0 1 1 3 9, 6 1 4 0 3 1 1 5) ; 教育部科学技术研究重大项目( 3 1 3 0 1 8) ; 安徽省科技计划重点项目( 1 3 0 1 0 2 2 0 3 6) 。

An Analog Circuit Fault Diagnostics Approach Based on QNN

Zhang Chaolong1,2, He Yigang1, Yuan Lifen1, Chen Liping1   

  1. (1.School of Electrical Engineering and Automation, Hefei University of Technology,Hefei Anhui 230009,China; 2.School of Physics and Electronic Engineering, Anqing Normal University, Anqing Anhui 246011,China)
  • Published:2015-04-25 Online:2015-05-06

摘要:  针对模拟电路中部分故障类别发生重叠的特点, 提出了一种基于量子神经网络算法的模拟电路故障诊断方法。在被测电路输出端采集时域响应信号, 计算其峭度和熵, 作为特征量, 并应用量子神经网络算法对模拟电路的各个不同的故障类别进行辨别。实验结果表明, 构建的神经网络具有简单的网络结构, 且故障诊断正确率较
高, 达到9 9. 6 2%。

关键词: 模拟电路, 故障诊断, 峭度, 熵, 量子神经网络

Abstract: To solve the overlap of part of fault classes in the analog circuit fault diagnostics, a novel analog circuit fault diagnostics approach based on quantum neural networks algorithm was presented. Kurtosis and entropy were calculated as features after the time domain response signals of the circuit under test were measured, and then the different fault classes were identified by quantum neural networks algorithm. The simulation demonstrated that constructed neural network had simple network structure and the fault diagnosis accuracy was higher, which reached 99.62%.

Key words: Analog circuit, Fault diagnostics, Kurtosis, Entropy, Quantum neural networks

引用本文

张朝龙,何怡刚,袁莉芬,陈立平. 一种基于量子神经网络的模拟电路故障诊断方法[J]. 辽宁石油化工大学学报, 2015, 35(2): 58-61.

Zhang Chaolong, He Yigang, Yuan Lifen, Chen Liping. An Analog Circuit Fault Diagnostics Approach Based on QNN[J]. Journal of Liaoning Petrochemical University, 2015, 35(2): 58-61.

使用本文

0
    /   /   推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal.lnpu.edu.cn/CN/10.3696/j.issn.1672-6952.2015.02.013

               http://journal.lnpu.edu.cn/CN/Y2015/V35/I2/58