基于双向生成对抗网络的滚动轴承智能诊断方法OA
Intelligent diagnosis method of rolling bearing based on BiGAN
滚动轴承是旋转机械中的关键部件,直接影响设备的可靠性.人工智能的发展在轴承故障诊断领域取得了令人瞩目的成就.然而,滚动轴承数据集的不平衡(正常样本远丰富于故障样本)会导致诊断模型精度较低.为了解决这个问题,本文提出了一种基于双向生成对抗网络(BiGAN)的故障诊断方法.首先,通过集合经验模式分解对信号进行去噪,使其自动分配到一个合适的参考尺度,并避免模态混叠.其次,构建含有梯度惩罚项的BiGAN模型,利用单样本离差标准化方法稳定模型训练过程,实现…查看全部>>
Rolling bearing is a critical component in the rotating machinery,which directly affects the reliability of the equipment. The artificial intelligence-enabled bearing fault diagnosis model has achieved impressive successes over the years. However,rolling bearings' imbalanced data sets (normal samples are much larger than failure samples) degrade the diagnostic performance. To address this issue,a bidirectional generative adversarial network(BiGAN) based faul…查看全部>>
张皓;谷立臣;郭子辰
西安建筑科技大学机电工程学院,陕西西安 710055西安建筑科技大学机电工程学院,陕西西安 710055西安建筑科技大学机电工程学院,陕西西安 710055
滚动轴承故障诊断双向生成对抗网络(BiGAN)卷积神经网络(CNN)数据不平衡
rolling bearingfault diagnosisbidirectional generative adversarial network (BiGAN)convolutional neural network (CNN)data imbalance
《测试科学与仪器》 2024 (2)
264-275,12
This work was supported by National Natura Science Foundation of China(No.51675399)Shaanxi Natural Science Foundation General Program(No.2021JM-359)and Yulin Industry-University-Research Cooperation Project(No.2019-172).
评论