Improved generative adversarial network for vibration-based fault diagnosis with imbalanced data
Improved generative adversarial network for vibration-based fault diagnosis with imbalanced data
复制标题
改进的生成对抗网络，用于基于不平衡数据的基于振动的故障诊断
DOI：
10.1016/j.measurement.2020.108522
复制
发表时间：
2021-02
期刊：
影响因子：
5.6
通讯作者：
Yuan Qi
中科院分区：
文献类型：
--
作者：
Zhao Bingxi;Yuan Qi
有效的故障诊断是维护机械系统安全运行的关键。近年来，数据驱动方法在智能故障诊断中显示出巨大的潜力。然而，在实际情况下收集的数据可能是不平衡的，这给诊断带来了困难。本文提出了一种改进的生成对抗网络（GAN），以提高不平衡数据的故障诊断性能。与传统的GAN相比，改进的GAN引入了一个辅助分类器来加速训练过程，并引入了一种基于Auto-Encoder的方法来对生成的样本进行相似性估计。同时，设计了在线样本过滤器，确保选择的样本同时满足准确性和多样性的要求。在Case Western Reserve University和XJTU-SY的基准数据集上进行了实验，并与其他智能方法的结果进行了比较，证明了该方法在不平衡故障诊断中的优势。
Effective fault diagnosis is essential for maintaining the safe running of machine systems. Recently, the data-driven methods have shown great potential in intelligent fault diagnosis. However, the data collected in actual situations may be imbalanced which brings difficulties for the diagnosis. In this paper, an improved Generative Adversarial Network (GAN) is proposed to enhance the fault diagnosis performance with imbalanced data. Compared with the traditional GANs, the improved GAN introduces an auxiliary classifier to boost the training process and an Auto-Encoder based method for similarity estimation of generated samples. Meanwhile, an online sample filter is designed to ensure the selected samples meet the requirements of both accuracy and variety simultaneously. Experiments are implemented on the benchmark data from the Case Western Reserve University and the XJTU-SY datasets, and the results are compared with those by other intelligent methods, which proves the advantage of our proposed method in imbalanced fault diagnosis.
登录
查看更多内容
DOI：
10.1016/j.knosys.2015.12.010
发表时间：
2016-03
期刊：
Knowl. Based Syst.
影响因子：
--
作者：
Pinar Tapkan;Lale Özbakır;S. Kulluk;A. Baykasoğlu
通讯作者：
Pinar Tapkan;Lale Özbakır;S. Kulluk;A. Baykasoğlu
影响因子：
12.3
作者：
H. Keskes;A. Braham
通讯作者：
H. Keskes;A. Braham
DOI：
10.1109/icccnt56998.2023.10306417
发表时间：
2022-02
期刊：
2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)
影响因子：
--
作者：
Gilad Cohen;Raja Giryes
通讯作者：
Gilad Cohen;Raja Giryes
影响因子：
5.2
作者：
Tian, Ye;Ma, Jian;Wang, Zili
通讯作者：
Wang, Zili
用于估计滚动轴承剩余使用寿命的混合预测方法
影响因子：
5.9
作者：
Wang, Biao;Lei, Yaguo;Li, Ningbo
通讯作者：
Li, Ningbo