摘要
往复压缩机气阀是整个机体中故障率最高的部件,针对其故障模式复杂、难以辨识的特点,选取与气阀运行状态密切相关的6个振动参数作为特征参数,采用模糊聚类方法对气阀故障和运行状态进行评判。用现场实际采集的20个样本进行模糊聚类分析,求出故障特征,并与频谱分析和现场实际情况进行比较,聚类结果与实际情况相吻合,证明此方法应用于运行状态评判和挖掘故障特征是有效的。
According to the character of frequent fault occurrence, difficult diagnosis of large reciprocating compressor valves, fuzzy clustering method was used. The principle and procedure of fuzzy C-means algorithm were discussed. Several parameters were selected as feature parameters, and then fuzzy C-means algorithm was applied to analyze valve running conditions. Applied example is also given. The result of fault diagnosis has been proved to be reliable and accurate.
出处
《机械强度》
EI
CAS
CSCD
北大核心
2007年第3期521-524,共4页
Journal of Mechanical Strength
基金
教育部新世纪优秀人才支持计划(NCET-05-0110)~~
关键词
往复式压缩机
故障诊断
模糊聚类
故障特征
Reciprocating compressor
Fault diagnosis
Fuzzy clustering algorithm
Fault feature
