作　　者： ;

机构地区： 茂名学院

出　　处： 《煤矿机械》 2007年第12期193-195,共3页

摘　　要： 针对目前旋转机组故障诊断中存在的样本需求量大及诊断学习缺乏自主连续性等问题,提出了基于人工免疫原理的故障诊断方法。以状态征兆为抗原,各种故障模式下的故障检测器作为抗体,通过反向选择算法判别机组运行是否正常,利用动态规模免疫算法进化学习获得能识别抗原结构的记忆抗体。根据最大故障隶属度诊断故障类型,以旋转机组振动为诊断对象的仿真结果表明,该方法可行,且适合故障样本难以获得的小样本故障诊断。 In order to solve the problems such as large sample demands and discontinuous learning in the fault diagnosis techniques, a new method based on immunology principles is proposed. Taking state symptoms as antigens, and detectors under different fault modes as antibodies, the normal conditions and anomaly are distinguished with negative selections algorithm. Memory antibodies that can identify the structures of antigens are generated with the mechanism of variable immune algorithm. Fault types are determined by the maximum fault membership. The proposed method was applied to the Vibration diagnosis of rotatory machine unit. The simulation result shows that the method is practicable and appropriate with low demands on fault samples.

关 键 词： 免疫原理 旋转机组 故障诊断 反向选择算法 动态规模免疫算法

领　　域： [自动化与计算机技术] [自动化与计算机技术]