摘要
提出了一种基于人工免疫的数据模式进化学习模型及其相应的算法,给出了抗体(检测器)群体合理数量的确定方法。将其应用于机床齿轮箱运行状态检测及故障诊断,实验结果表明,所提出的模型和动态克隆进化算法能对检测器群体的分布和总数量实现动态优化,对数据模式进行聚类,获得了较高的异常检测准确率和较强的故障诊断能力。
A evolving learning model of data mode based on artificial immune theory and algorithm is proposed.A method for making certain the quantity of antibody population or detectors in reason is presented.Astringency of the algorithm is analyzed.The model and algorithm is used in detection and diagnosis to work condition of gear case in machine tools.The experiment result indicates that the model and algorithm are able to realize optimization to distribution and quantity of detecting vector population and clustering of data modes.Upper veracity of anomaly detection and strong ability of fault diagnosis is obtained.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第20期40-43,123,共5页
Computer Engineering and Applications
基金
高等学校博士学科点专项基金(编号:20020008004)
关键词
人工免疫
进化学习
异常检测
故障诊断
artificial immune,evolution and learning,anomaly detection,fault diagnosis
