报告详情
Fault Identification through harmonic dynamics of Bearing-Rotating systems
编号：4
访问权限：仅限参会人
更新：2025-11-10 10:13:40 浏览：32次
口头报告
报告开始：暂无开始时间（Asia/Shanghai）
报告时间：暂无持续时间
所在会场：[暂无会议] [暂无会议段]
暂无文件
摘要
Rotating machinery plays a crucial role in industrial production and is one of the most widely used types of equipment, including generators, motors, steam turbines, pumps, etc. The operational status of rotating machinery directly affects factory production efficiency, safety, and costs. Most failures in rotating machinery are caused by faults in key components, among which bearings are the most frequently faulty parts. Therefore, research on bearing fault diagnosis technology has significant theoretical and practical value.
This paper takes bearings as the research object and designs a bearing fault diagnosis algorithm by extracting the harmonic dynamic characteristics of bearing vibration signals and combining them with a Convolutional Neural Network (CNN) model. The algorithm analyzes the spectral distribution of faulty bearing vibration signals based on Fourier Transform, utilizes signal fitting algorithms to extract the harmonic dynamic characteristics of the vibration signals, then inputs the feature data into the CNN for learning and testing. Finally, it is validated on the CWRU dataset, achieving a diagnosis success rate as high as 90.62% on a multi-condition ten-classification problem.
The research aims to achieve better bearing diagnosis results, intending to provide new ideas and methods for the development of bearing fault diagnosis technology and offer more reliable assurance for the stable operation of rotating machinery in industrial production.
This paper takes bearings as the research object and designs a bearing fault diagnosis algorithm by extracting the harmonic dynamic characteristics of bearing vibration signals and combining them with a Convolutional Neural Network (CNN) model. The algorithm analyzes the spectral distribution of faulty bearing vibration signals based on Fourier Transform, utilizes signal fitting algorithms to extract the harmonic dynamic characteristics of the vibration signals, then inputs the feature data into the CNN for learning and testing. Finally, it is validated on the CWRU dataset, achieving a diagnosis success rate as high as 90.62% on a multi-condition ten-classification problem.
The research aims to achieve better bearing diagnosis results, intending to provide new ideas and methods for the development of bearing fault diagnosis technology and offer more reliable assurance for the stable operation of rotating machinery in industrial production.
关键词
bearing fault diagnosis;,Neural network,harmonic content
报告人
Chengfei Li
Dr. Zhejiang Academy of Special Equipment Science稿件作者
全部评论
重要日期
-
会议日期
11月21日
2025
至11月23日
2025
-
10月20日 2025
初稿截稿日期
-
11月23日 2025
注册截止日期
主办单位
IEEE Instrumentation and Measurement Society
South China University of Technology
South China University of Technology
承办单位
South China University of Technology
联系方式
- Icsmd
- ic******@163.com
历届会议
-
2023年11月02日 中国 China
International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2023年11月02日 中国 Xi'an
2023 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2022年11月30日 中国 Harbin
International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence -
2021年10月21日 中国 Nanjing
2021 International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence -
2020年10月15日 中国 Xi'an
International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence
发表评论