提出了一种基于OCSVM—CPSO自适应故障诊断模型,它用OCSVM作为基本检测模块,而用CPSO作为最优参数的搜索模块.当在线运行的检测准确率低于某确定的阈值时,启动CPSO搜索新的参数。而准确率达标时,用新参数继续后续检测过程。实验表明:此方法能够有效地实现高准确率在线检测任务。
A new model for self-adaptive fault-diagnoses based-on OCSVM-CPSO has been put forward,which takes OCSVM as basic detecting module and CPSO as searching module for optimizing parameter,and start up CPSO to search new parameters when the accuracy detected has been under a assured threshold,but maintains detecting process by new parameters when he accuracy detected has been above the assured threshold.The simulation-experiments have shown,it can be effectively used for online detecting tasks with higher accuracy.