免疫算法在联锁数据异常诊断中的应用  

Immune algorithm applied to abnormal diagnosis of interlocking data

作　　者：单国超 SHAN Guochao(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China)

机构地区：[1]西南交通大学信息科学与技术学院,成都611756

出　　处：《铁路计算机应用》2019年第1期26-29,42,共5页Railway Computer Application

摘　　要：由于免疫系统在自己与非己的识别方面有其独到之处,提出利用免疫算法对联锁数据进行异常诊断。研究中采用汉明距离匹配规则的阴性选择算法,输入正常二进制数据生成非我空间的检测器即异常样本集合,并对采集到的联锁数据进行监控。通过Matlab仿真实验建立计算机联锁数据的异常诊断过程,同时实时地监控联锁数据,与异常数据集合进行比较,实现免疫功能。实验结果表明,免疫算法可实现基本的联锁数据异常诊断,是异常数据诊断的一种有效方法。Because the immune system has its own characteristics in identifying itself and non self,in this paper,an immune algorithm was applied to diagnose abnormal data of interlocking data.In the study,the Hamming distance matching rule based negative selection algorithm was used to input the normal binary data,generate the non-self space detector which was the abnormal sample set,and monitor the collected interlocking data.Through the simulation experiment with matlab,an abnormal diagnosis process of the computer interlocking data was established,and at the same time,the interlocking data was monitored in real time,and compared with the abnormal data set to implement the immune function.Experimental results show that the immune algorithm can implement the basic interlocking data dia.

关 键 词：联锁数据 异常诊断 免疫算法 阴性选择 

分 类 号：U284.3[交通运输工程—交通信息工程及控制] TP39[交通运输工程—道路与铁道工程]