液压系统故障诊断的高阶统计量-模糊神经网络法  

Fault Diagnosis of Hydraulic System Based on High-order CumulantFuzzy Neural Network

作　　者：石红雁[1] 许纯新[1] 瞿爱琴[1] 

机构地区：[1]吉林大学机械科学与工程学院

出　　处：《农业机械学报》2003年第5期119-122,共4页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目 (项目编号 :5 0 0 75 0 3 3 )

摘　　要：利用高阶统计量模糊神经网络方法对液压系统故障进行诊断 ,解决低信噪比故障特征信号下的故障诊断问题。介绍了高阶统计量和模糊神经网络的基本原理 ,阐述了利用高阶统计量模糊神经网络诊断液压系统故障的方法 ,给出了以阀控液压缸系统为研究对象的诊断实例。试验结果表明 ,利用该方法对液压系统进行故障诊断可以有效地提高故障特征信号的信噪比 。A method to diagnose the fault of the hydraulic system based on the high order cumulant fuzzy neural network method is presented. The basic concepts of high order cumulant and the fuzzy neural network were introduced first. Then the method to diagnose the faults by the high order cumulant fuzzy neural network method was studied. At last an application of diagnosis based on a valve controlled hydraulic cylinder was presented. The result shows that the signal noise ratio of the fault signals can be effectively improved by the high order cumulant fuzzy neural network method. By this method the accuracy and the efficiency to diagnose the faults in hydraulic system are improved.

关 键 词：液压系统 故障诊断 高阶统计量 模糊神经网络法 阀控液压缸系统 信噪比 诊断效率 

分 类 号：TH137.5[机械工程—机械制造及自动化]