摘要
针对复合材料拉挤多腔板的结构复杂问题,采用传统的无损检测方式很难对复合材料拉挤多腔板的型腔结构进行缺陷检测。因此,拟设计一种激振敲击检测方案,通过控制激振器的方式敲击多腔板型材来获得振动信号,避免了传统的力锤敲击检测获得的振动信号存在严重失真的影响。最后使用小波包进行特征提取和支持向量机(SVM)相结合的方法对敲击检测的多腔板进行故障诊断。实验结果表明:使用小波包分析和支持向量机相结合的方法对复合材料拉挤多腔板的分类识别取得了较好的结果。
In view of the complex structure of composite pultruded multi-cavity plate,it is difficult to detect the defects of the cavity structure of composite pultruded multi-cavity plate by traditional nondestructive testing.Therefore,it is proposed to design a vibration excitation knocking detection scheme to obtain the vibration signal by knocking the multi-cavity plate profile by controlling the vibration exciter,so as to avoid the serious distortion of the vibration signal obtained by the traditional force hammer knocking detection.Finally,wavelet packet feature extraction and support vector machine(SVM)are used to diagnose the fault of multi-cavity plate.The experimental results show that the fault diagnosis of composite pultruded multi-cavity plates can be carried out by the combination of wavelet packet analysis and support vector machine.
作者
赵如杰
张凯
张师榕
Zhao Rujie;Zhang Kai;Zhang Shirong(Institute of Equipment Reliability,Shenyang University of Chemical Technology,Shenyang,Liaoning 110142,China;School of Mechanical Engineering,Anhui Polytechnic University,Wuhu,Anhui 241000,China)
出处
《黑龙江工业学院学报（综合版）》
2021年第10期60-65,共6页
Journal of Heilongjiang University of Technology(Comprehensive Edition)
基金
国家自然科学基金(NSFC-辽宁联合基金)“大型重载滚动轴承的可靠性和寿命预测的理论与方法研究”(项目编号:U1708254)。
关键词
小波包
敲击检测
SVM
特征提取
wavelet packet
knock detection
SVM
feature extraction
作者简介
赵如杰,硕士,沈阳化工大学装备可靠性研究所。研究方向:故障诊断;通讯作者:张凯,博士,副教授,沈阳化工大学装备可靠性研究所。研究方向:信号处理;张师榕,硕士,安徽工程大学机械工程学院。研究方向:故障诊断。
