首页> 外文会议>IEEE Conference on Industrial Electronics and Applications >A new methodology for condition monitoring based on perceptual hashing
【24h】

A new methodology for condition monitoring based on perceptual hashing

机译:基于感知哈希的状态监测新方法

获取原文

摘要

A common problem that machine condition monitoring encounters is the high data throughput and bandwidth consumption, especially for wave signals sampled with high frequency. In order to reduce the data dimension while retrieve much diagnostic information from the monitored data, a new methodology is proposed based on perceptual hashing, which can take the respective advantage of Cloud computing and Edge computing. The feasibility of this methodology is discussed and demonstrated through a naive perceptual hashing example with bearing vibration signals. Considerations in perceptual hashing of monitored data and modeling for performance assessment, diagnosis and prognosis are further discussed. With perceptual hashing, not only the data dimension can be reduced, but also the diagnostic modeling can benefit from the geometric structure of machine condition hash (MCH).
机译:机器状态监视遇到的一个常见问题是高数据吞吐量和带宽消耗,尤其是对于以高频采样的波信号而言。为了在从监视的数据中检索大量诊断信息的同时减小数据量,提出了一种基于感知哈希的新方法,该方法可以利用云计算和边缘计算的各自优势。通过一个带有轴承振动信号的幼稚感知哈希实例,讨论并证明了该方法的可行性。进一步讨论了在监视数据的感知哈希以及用于性能评估,诊断和预后建模方面的注意事项。通过感知哈希,不仅可以减少数据维度,而且诊断建模还可以受益于机器条件哈希(MCH)的几何结构。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号