论文部分内容阅读
为了解决网络故障诊断中的模式识别问题,文中从生物免疫系统与网络故障诊断的相似性出发,提出一种基于免疫克隆扩增原理的网络故障诊断方法。该方法模拟生物免疫系统中的克隆、变异、抑制、记忆等特性,通过免疫训练网络故障样本提取网络故障模式,再用最近邻分类原则对故障样本分类。实验结果表明该方法能有效识别网络故障,并且对于未知模式的故障具有一定的泛化性。
In order to solve the problem of pattern recognition in network fault diagnosis, this paper proposes a method of network fault diagnosis based on the principle of immune clone amplification from the similarity of biological immune system and network fault diagnosis. The method simulates the characteristics of cloning, mutation, inhibition and memory in the biological immune system, extracts network failure modes through immune training network fault samples, and then classifies the fault samples according to the nearest neighbor classification principle. Experimental results show that this method can effectively identify network faults and has some generalization to the unknown mode faults.