报告详情
  1. 活动首页
  2. 报告清单
  3. 报告详情
Electric Motor Bearing Fault Noise Detection with Mel-Transformer Model and Multi-Timescale Feature Extraction
编号：109 访问权限：仅限参会人 更新：2023-11-20 13:45:43 浏览：499次 口头报告

报告开始：2023年12月09日 15:00（Asia/Shanghai）

报告时间：15min

所在会场：[S7] Power system protection and control [S7] Power system protection and control

演示文件

提示：该报告下的文件权限为仅限参会人，您尚未登录，暂时无法查看。

摘要
Bearings are often found in various industrial systems such as electric motors, and their failure often results in industrial losses and personal danger. This paper proposes a transformer-based method to classify the bearing noise signal efficiently and accurately. Firstly, the vibration noise sample signals are used to be extract the fault feature information by multi-timescale Mel-spectrograms. Secondly, this paper proposes Mel-transformer architecture which is the first to apply the vision Transformer-based algorithm model to fault detection task. This method has a powerful ability to automatically extract audio feature information from the Mel-spectrogram feature map and can distinguish various fault types effectively. Compared with convolutional neural network (CNN) based model, the proposed method is more suitable for processing large-scale bearing data in the industry and requires lower computing resources. It also overcomes the problem that the model cannot be processed in parallel on the vibration sequence due to the limitation of the RNN structure. The effectiveness and feasibility of the proposed method are verified by CWRU dataset.
关键词
electric motor,bearing,Artificial Intelligence,feature extraction
报告人
Chao Gong
Professor Northwestern Polytechnical University

稿件作者
Xiaotian Zhang UoY
Yunshu Liu The Chinese University of Hong Kong
Chao Gong Northwestern Polytechnical University
Yu Nie University of york
Jose Rodriguez Universidad Andres Bello
发表评论
验证码 看不清楚，更换一张
全部评论
重要日期

  • 会议日期

    12月08日

    2023

    至

    12月10日

    2023

  • 11月01日 2023

    初稿截稿日期

  • 12月10日 2023

    注册截止日期

主办单位
IEEE IAS
承办单位
Southwest Jiaotong University (SWJTU)
联系方式
登录查看完整联系方式
历届会议
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询