流体机械

2020, v.48;No.580(10) 48-53

[打印本页] [关闭]
本期目录(Current Issue) | 过刊浏览(Past Issue) | 高级检索(Advanced Search)

基于二叉树支持向量机的往复压缩机气阀故障诊断方法
Fault Diagnosis of Reciprocating Compressor Gas Valve Based on Binary Tree Support Vector Machine

肖军;舒悦;谢传东;刘晓明;刘志龙;
Xiao Jun;Shu Yue;Xie Chuandong;Liu Xiaoming;Liu Zhilong;State Key Laboratory of Compressor Technology,Hefei General Machinery Research Institute Co.,Ltd.;Hefei General Environment Control Technology Co.,Ltd.;

摘要(Abstract):

针对往复压缩机气阀故障,提出一种结合模糊C均值聚类和支持向量机的二叉树多分类诊断方法。首先利用小波包分析提取气阀振动信号不同频段的能量作为故障特征量,然后应用该诊断方法对气阀故障模式进行识别。结果表明,构建的多分类方法对压缩机气阀故障的诊断效果很好,相比传统的多分类器诊断正确率更高。
For the valve faults of reciprocating compressors,a binary tree multi-classification diagnosis method based on fuzzy C-means clustering and support vector machine was proposed.Firstly,the energy values of different frequency bands of valve vibration signal were extracted using the wavelet packet analysis as the fault feature quantities,and then the fault mode of the valve was identified by this diagnosis method.The results show that the proposed multi-classification method is effective in the diagnosis of compressor valve faults,and has higher accuracy than the traditional multi-classifier.

关键词(KeyWords): 支持向量机;二叉树;往复压缩机;气阀;故障诊断
support vector machine;binary tree;reciprocating compressor;gas valve;fault diagnosis

Abstract:

Keywords:

基金项目(Foundation): 安徽省科技重大专项项目(18030901026);; 安徽省自然科学基金青年项目(1908085QE234);; 安徽省重点研究和开发计划项目(201904a07020052);; 合肥通用机械研究院有限公司博士科技基金项目(2019010384);合肥通用机械研究院青年科技基金项目(2018010761)

作者(Authors): 肖军;舒悦;谢传东;刘晓明;刘志龙;
Xiao Jun;Shu Yue;Xie Chuandong;Liu Xiaoming;Liu Zhilong;State Key Laboratory of Compressor Technology,Hefei General Machinery Research Institute Co.,Ltd.;Hefei General Environment Control Technology Co.,Ltd.;

参考文献(References):

扩展功能
本文信息
服务与反馈
本文关键词相关文章
本文作者相关文章
中国知网
分享