鉴别器
计算机科学
过度拟合
后悔
人工智能
稳健性(进化)
特征(语言学)
方位(导航)
对抗制
生成语法
断层(地质)
深度学习
机器学习
数据挖掘
模式识别(心理学)
人工神经网络
电信
探测器
基因
地质学
哲学
生物化学
地震学
化学
语言学
作者
Shaowei Liu,Hongkai Jiang,Zhenghong Wu,Xingqiu Li
出处
期刊:Measurement
[Elsevier]
日期:2020-08-20
卷期号:168: 108371-108371
被引量:120
标识
DOI:10.1016/j.measurement.2020.108371
摘要
The data imbalance limits the stability and accuracy in fault diagnosis of rolling bearings. In general, traditional methods need the necessary features and a large number of labeled data in advance, which requires lots of time and manpower. In this paper, a novel data augmentation method named variational autoencoding generative adversarial networks with deep regret analysis is proposed to improve the fault diagnosis ability. Firstly, an encoder is merged into the generative adversarial networks to learn deep features of real data for the improvement of data generation quality. Secondly, the discriminator is integrated with the deep regret analysis method to avoid mode collapse by imposing the gradient penalty on it. Thirdly, the feature matching module is adopted in the generator to enhance the deep feature and eliminate overfitting. The proposed method is verified to diagnose two rolling bearing datasets. The results denote that the proposed method has better effectiveness and robustness than typical data synthesis based fault diagnosis methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI