高级检索
    李千目 刘凤玉. 战略互联网风险检测与故障分析方法[J]. 计算机研究与发展, 2008, 45(10): 1718-1723.
    引用本文: 李千目 刘凤玉. 战略互联网风险检测与故障分析方法[J]. 计算机研究与发展, 2008, 45(10): 1718-1723.
    Li Qianmu and Liu Fengyu. A Risk Detection and Fault Analysis Method for the Strategic Internet[J]. Journal of Computer Research and Development, 2008, 45(10): 1718-1723.
    Citation: Li Qianmu and Liu Fengyu. A Risk Detection and Fault Analysis Method for the Strategic Internet[J]. Journal of Computer Research and Development, 2008, 45(10): 1718-1723.

    战略互联网风险检测与故障分析方法

    A Risk Detection and Fault Analysis Method for the Strategic Internet

    • 摘要: 随着新一代战略互联网规模的不断扩大,网络应用不断增加,传统的网络故障诊断系统功能单一、操作复杂、效率低下,已不能满足军网管理的发展需要.基于粗糙集的神经网络理论,提出网络性能检测与故障分析的RSNN算法,实现不一致情况下的故障规则获取和学习样本的净化处理.该算法具有简化样本、适应性强、容错性高等特点,能有效处理网络故障诊断中噪声和不相容的信息.由于诊断问题的实质是一种映射,该算法用一种前馈型网络来逼近这种映射关系,实现对故障的有效分类.实验表明,利用该方法实现的系统与同类的其他方法相比,大幅提高了诊断准确率和诊断速度.

       

      Abstract: With the development of computer science and communication network, the scale of the strategic Internet is growing larger with the emergence of more network applications. Owing to the simple function, complex operation and lower efficiency, the old network troubleshooting system already cant satisfy for the demands of carrier development. Put forward in this paper is RSNN algorithm, a design fault diagnosis method, which tightly combines neural network and rough sets. Reduced information table can be obtained, which implies that the number of evaluation criteria is reduced with no information loss through rough set approach. And then, this reduced information is used to develop classification rules and train neural network to infer appropriate parameters. The rules developed by RS-neural network analysis show the best prediction accuracy, if a case does match any of the rules. Its capable of overcoming several shortcomings in existing diagnosis systems, such as a dilemma between stability and redundancy. Since the essence of fault diagnosis is a kind of mapping, an artificial neural network model is adopted to deal with the mapping relation, categorizing the network faults. The experiment system implemented with this method shows a good diagnostic ability.

       

    /

    返回文章
    返回