基于动态自学习阈值和趋势滤波的机械故障智能预警方法

Translated title of the contribution: A mechanical fault early warning methodology based on dynamic self-learing threshold the trend filtering techniques

Ming Zhang, Kun Feng, Zhinong Jiang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

针对当前机械在线监测系统报警难以实现机械故障早期预警问题, 提出一种智能预警方法. 基于在线监测系统大量监测数据统计分析, 采用动态的自学习阈值算法计算预警阈值, 并应用 l1 趋势滤波技术消除随机误差获取滤波后的趋势. 应用动态自学习阈值替代监测系统中的常规报警阈值, 比较自学习预警阈值与滤波后的趋势, 实现了机械故障早期预警. 工程实例表明, 该方法能够对机械故障实现早期预警, 对预防机械事故的发生有重要的作用.
Translated title of the contributionA mechanical fault early warning methodology based on dynamic self-learing threshold the trend filtering techniques
Original languageChinese
Pages (from-to)8-14
JournalJOURNAL OF VIBRATION AND SHOCK
Volume33
Issue number24
DOIs
Publication statusPublished - 24 Dec 2014

Fingerprint

Dive into the research topics of 'A mechanical fault early warning methodology based on dynamic self-learing threshold the trend filtering techniques'. Together they form a unique fingerprint.

Cite this