Scholarlink

Motor bearing is a core component of motor. Most of the motor fault diagnosis and remaining useful life prediction methods are based on neural networks, but there is a main problem that couldn’t be solved. While using neural networks, a large amount of labeled data is needed during network training, and the lack of labeled data and difficulty in obtaining the labeled data seriously restrict the feature extraction. In this paper, we use GAN to solve this problem. The effectiveness is verified in the experiment.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Different Working Conditions’ Bearings Vibration Signal Based on GAN with Few Labeled Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jiaxuan Han,
  • Mingjun Zhu,
  • Wei Sun,
  • Dawei Li,
  • Ronghai Qu

摘要

Motor bearing is a core component of motor. Most of the motor fault diagnosis and remaining useful life prediction methods are based on neural networks, but there is a main problem that couldn’t be solved. While using neural networks, a large amount of labeled data is needed during network training, and the lack of labeled data and difficulty in obtaining the labeled data seriously restrict the feature extraction. In this paper, we use GAN to solve this problem. The effectiveness is verified in the experiment.