当前位置: X-MOL 学术Comput. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Cascaded fault detection system of error back-propagation network based on node association degree
Computer Communications ( IF 4.5 ) Pub Date : 2021-05-11 , DOI: 10.1016/j.comcom.2021.04.011
Feifei Yin , Bingzhe He

In view of the problems of low fault identification rate and large global error of network fault system designed by the existing methods, an automatic fault detection system based on node association degree is proposed. Firstly, the hardware design of the system is completed by describing and analyzing the initialization module, detector training module, memory antibody module and fault automatic detection module. Secondly, the system software is designed by network anomaly diagnosis and configuration anomaly detection. Finally, the system can detect the cascade fault of the backward propagation network by the design of software and hardware. The experimental results show that the system designed in this paper has high fault identification rate and small global error of fault detection, and can accurately detect the network cascade faults.



中文翻译:

基于节点关联度的误差反向传播网络级联故障检测系统

针对现有方法设计的网络故障系统故障识别率低,全局误差大的问题,提出了一种基于节点关联度的故障自动检测系统。首先,通过描述和分析初始化模块,检测器训练模块,记忆抗体模块和故障自动检测模块来完成系统的硬件设计。其次,通过网络异常诊断和配置异常检测设计系统软件。最后,该系统可以通过软件和硬件的设计来检测反向传播网络的级联故障。实验结果表明,本文设计的系统具有较高的故障识别率和较小的全局故障检测误差,可以准确地检测出网络级联故障。

更新日期:2021-05-18
down
wechat
bug