.png){kind=icon}
返回
Rolling element bearings diagnostics using the Symbolic Aggregate approXimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ymssp.2015.01.033.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Rolling element bearings are a very critical component in various engineering assets. Therefore it is of paramount importance the detection of possible faults, especially at an early stage, that may lead to unexpected interruptions of the production or worse, to severe accidents. This research work introduces a novel, in the field of bearing fault detection, method for the extraction of diagnostic representations of vibration recordings using the Symbolic Aggregate approXimation (SAX) framework and the related intelligent icons representation. SAX essentially transforms the original real valued time-series into a discrete one, which is then represented by a simple histogram form summarizing the occurrence of the chosen symbols/words. Vibration signals from healthy bearings and bearings with three different fault locations and with three different severity levels, as well as loading conditions, are analyzed. Considering the diagnostic problem as a classification one, the analyzed vibration signals and the resulting feature vectors feed simple classifiers achieving remarkably high classification accuracies. Moreover a sliding window scheme combined with a simple majority voting filter further increases the reliability and robustness of the diagnostic method. The results encourage the potential use of the proposed methodology for the diagnosis of bearing faults. (C) 2015 Elsevier Ltd. All rights reserved.
Keyword:
Symbolic Aggregate approXimation
Bearing fault diagnosis
Condition monitoring
Classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
1.3W
被引数:
6.6W
机构
引用论文
.png){kind=icon}
查看更多内容