摘要
针对支持向量机在旋转机械的故障诊断中存在的模型超参数选择的不确定性,利用超参数相关理论和先验知识界定模型超参数选择区间,结合全局搜索和局部搜索实现参数优化组合,运用泛化模式搜索的模型超参数选择方法,并将改进的支持向量机模型引入旋转机械的故障诊断。结果表明,改进的模型具有较高的搜索效率和参数优化选择性能,提高了故障诊断的精度。
A method for solving the uncertainty of support vector hyper-parameter (SVP) selection in rotating machinery fault diagnosis,named generalized pattern search (GPS),was presented in this paper. Firstly,the range of parameters was determined by SVP with some prior information. Secondly,optimum parameters were obtained through a global search and a local search. Finally,an improved support vector machines(SVM) model was introduced into the rotating machinery field for fault diagnosis. The experimental results show that the search efficiency,the optimizing parameter performance and the fault diagnosis accuracy were significantly improved by the method. This method has a better application prospect in the rotating machinery fault diagnosis field.
出处
《振动.测试与诊断》
EI
CSCD
北大核心
2009年第3期270-273,共4页
Journal of Vibration,Measurement & Diagnosis
基金
国家自然科学基金资助项目(编号:50505016)
国家"八六三"计划资助项目(编号:2007AA04Z424)
关键词
旋转机械
故障诊断
改进支持向量机模型
泛化模式搜索
超参数选择
rotating machine fault diagnosis improved support vector machines(SVM) model generalized pattern search hyper-parameter selection