全封闭往复式压缩机制造缺陷诊断方法研究  

A diagnosis method for manufacturing defects of hermetic reciprocating compressor

作　　者：金华强[1,2] 孙哲 顾江萍 黄跃进[2] 张晓娇 王新雷 郑爱武 沈希 Jin Huaqiang;Sun Zhe;Gu Jiangping;Huang Yuejin;Zhang Xiaojiao;Wang Xinlei;Zheng Aiwu;Shen Xi(College of Education,Zhejiang University of Technology,Hangzhou 310023;College of Mechanical Engineering,Zhejiang University of Technology,Hangzhou 310023;Department of Agricultural and Biological Engineering,University of Illinois at Urbana-Champaign,Urbana IL 61801;JiaXiPera Compressor Co.Ltd,Jiaxing 314011)

机构地区：[1]浙江工业大学教科学院,杭州310023 [2]浙江工业大学机械工程学院,杭州310023 [3]伊利诺伊大学香槟校区农业与生物工程学院,厄巴纳IL61801 [4]加西贝拉压缩机有限公司,嘉兴314011

出　　处：《高技术通讯》2021年第7期754-765,共12页Chinese High Technology Letters

基　　金：浙江省重点研发(2020C04010);浙江省基础公益研究计划(LGG19E050020);浙江省教育厅科研(Y201636617)资助项目。

摘　　要：全封闭往复式压缩机作为制冷系统的核心部件,其品质决定了整机系统的能效水平、静音效果和产品寿命。在生产线制造过程中,针对全封闭结构特点难以识别缺陷产品的短板问题,本文提出了一种基于壳体振动信号的压缩机制造缺陷诊断方法。首先通过集合经验模态分解(EEMD)对振动信号进行频谱分解,再利用多尺度样本熵(MSE)来表征不同尺度下各模态分量的复杂度并以此作为特征向量,最后利用支持向量机(SVM)完成制造缺陷的分类。实验结果表明,本文所提诊断方法能准确实现典型制造缺陷的识别与分类,为全封闭往复式压缩机制造缺陷的在线检测提供了相关理论与检测依据。As the core component of the refrigeration system,the quality of hermetic reciprocating compressor determines the energy efficiency level,silent effect,and product life of the whole system.In the manufacturing process of the production line,in order to solve the shortcomings that it is difficult to identify the defective product due to the characteristics of the hermetic structure,this paper proposes a diagnosis method for manufacturing defects based on the vibration signal of the compressor shell.First,the ensemble empirical mode decomposition(EEMD)is used to spectrally decompose the vibration signal.Furthermore,the multiscale sample entropy(MSE)is utilized to characterize the complexity of each intrinsic mode function(IMF)at different scales,and the values are used as the feature vector.Finally,the support vector machine(SVM)is used to complete the classification of manufacturing defects.Experimental results show that the detection the proposed method can accurately identify and classify typical manufacturing defects,and provide relevant theoretical and testing base for the online detection of hermetic refrigeration compressors.

关 键 词：全封闭压缩机 制造缺陷 集合经验模态分解(EEMD) 多尺度样本熵(MSE) 支持向量机(SVM) 

分 类 号：TB652[一般工业技术—制冷工程]