用户名 密 码 登 录 忘记密码 免费注册

网站会员中心 | 设为首页 | 加入收藏

 您好，欢迎光临中国轴承行业网         退出登陆

会员中心 | 设为首页 | 加入收藏

协会

统计

国外文献 > 1.轴承 > 6. 信号处理与特征分析 > 特征与分类

关键词搜索：

标 题： A classification method via sparse representation for rolling bearing fault recognition
基于稀疏表示的滚动轴承故障识别分类方法
作 者： Huaqing Wang
Yanliang Ke
Ganggang Luo
Qin Yang
Gang Tang
关键词： Rolling bearing  [滚动轴承]
Fault recognition  [ 故障识别]
Classification  [ 分类]
Sparse representation  [ 稀疏表示]
出版年： 2015
会议名： 28th International Congress and Exhibition on Condition Monitoring and Diagnostic Engineering Management (COMADEM 2015), 10th Regional Congress on Non-Destructive and Structural Testing (X CORENDE)
第28届国际状态监测与诊断工程管理大会暨展览会（COMADEM 2015），第十届区域无损检测与结构测试大会（X CORENDE）
届 次： 28th
摘 要： As a critical equipment of machinery equipment a rolling bearing often suffers from probably failures, which needs to be detected in time to guarantee a running safety of the whole system. The objective of bearing fault diagnosis is to effectively extract fault characteristic frequencies. However, in practice, due to the limit of Shannon sampling principle, large amount of vibration signals and a priori knowledge about the failures are often required. To solve these problems, inspired by a newly developed compressive sensing theory, the present paper proposes a fault diagnosis strategy for rolling bearings through sparse representation. Here a vibration signal spectrum is sparsely represented in a learning over-complete dictionary, and the original signal characteristics are preserved by random mapping while dimensionality reducing, finally the category classification of faulty signals are determined through sparsity promoting and optimization strategy. Simulation and experimental results validate the effectiveness of the proposed method for diagnosis of rolling bearings' faults.

作为机械设备的关键部件，滚动轴承常常会出现故障，需及时检测以确保整个系统的运行安全。轴承故障诊断的目标是有效提取故障特征频率。然而在实际应用中，由于香农采样原理的限制，往往需要大量的振动信号以及关于故障的先验知识。为解决这些问题，本文受新型压缩感知理论的启发，提出了一种基于稀疏表示的滚动轴承故障诊断策略。该方法将振动信号频谱在一种学习型超完备字典中进行稀疏表示，在降低维数的同时通过随机映射保留原始信号特征，最终利用稀疏性促进与优化策略确定故障信号的分类。仿真和实验结果验证了该方法在滚动轴承故障诊断中的有效性。
中文内容为网络AI翻译，专业术语未必准确，仅供参考。

VIP网员

联系我们 | 登录注册 | 会员管理 | 网员服务 | 服务信息 | 广告服务 | 高薪聘请 | 法律声明 | 关于我们

京公网安备 11010202009788    京ICP备2021015424号