Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

被引:21
|
作者
Pu, Ziqiang [1 ,2 ]
Cabrera, Diego [3 ]
Sanchez, Rene-Vinicio [3 ]
Cerrada, Mariela [3 ]
Li, Chuan [1 ]
de Oliveira, Jose Valente [4 ,5 ]
机构
[1] Chongqing Technol & Business Univ, Natl Res Base Intelligent Mfg Serv, Chongqing 400067, Peoples R China
[2] Univ Algarve, P-8005139 Faro, Portugal
[3] Univ Politecn Salesiana, GIDTEC Res Grp, Cuenca 010105, Ecuador
[4] Univ Algarve, P-1049001 Lisbon, Portugal
[5] Univ Lisbon, Inst Super Tecn, Ctr Intelligent Syst, IDMEC, P-1049001 Lisbon, Portugal
来源
APPLIED SCIENCES-BASEL | 2020年 / 10卷 / 21期
基金
中国国家自然科学基金;
关键词
feature extraction; generative adversarial network; random forest; unbalance data; fault diagnosis; BAYESIAN HIERARCHICAL-MODELS; DEEP BOLTZMANN MACHINE; NEURAL-NETWORK;
D O I
10.3390/app10217712
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.
引用
收藏
页码:1 / 21
页数:21
相关论文
共 50 条
  • [1] Fault diagnosis of wind turbines with generative adversarial network-based oversampling method
    Yang, Shuai
    Zhou, Yifei
    Chen, Xu
    Deng, Chunyan
    Li, Chuan
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (04)
  • [2] Application of Generative Adversarial Networks for Intelligent Fault Diagnosis
    Cao, Sican
    Wen, Long
    Li, Xinyu
    Gao, Liang
    2018 IEEE 14TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2018, : 711 - 715
  • [3] Learning inverse kinematics and dynamics of a robotic manipulator using generative adversarial networks
    Ren, Hailin
    Ben-Tzvi, Pinhas
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2020, 124
  • [4] Generative Oversampling Method for Imbalanced Data on Bearing Fault Detection and Diagnosis
    Suh, Sungho
    Lee, Haebom
    Jo, Jun
    Lukowicz, Paul
    Lee, Yong Oh
    APPLIED SCIENCES-BASEL, 2019, 9 (04):
  • [5] An evaluation method of conditional deep convolutional generative adversarial networks for mechanical fault diagnosis
    Luo, Jia
    Huang, Jinying
    Ma, Jiancheng
    Li, Hongmei
    JOURNAL OF VIBRATION AND CONTROL, 2022, 28 (11-12) : 1379 - 1389
  • [6] Data augment method for machine fault diagnosis using conditional generative adversarial networks
    Wang, Jinrui
    Han, Baokun
    Bao, Huaiqian
    Wang, Mingyan
    Chu, Zhenyun
    Shen, Yuwei
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING, 2020, 234 (12) : 2719 - 2727
  • [7] An evaluation method of conditional deep convolutional generative adversarial networks for mechanical fault diagnosis
    Luo, Jia
    Huang, Jinying
    Ma, Jiancheng
    Li, Hongmei
    JVC/Journal of Vibration and Control, 2022, 28 (11-12): : 1379 - 1389
  • [8] A Novel Method for Imbalanced Fault Diagnosis of Rotating Machinery Based on Generative Adversarial Networks
    Li, Zhenxiang
    Zheng, Taisheng
    Wang, Yang
    Cao, Zhi
    Guo, Zhiqi
    Fu, Hongyong
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
  • [9] Cross domain fault diagnosis based on generative adversarial networks
    Alabsi, Mohammed
    Pearlstein, Larry
    Franco-Garcia, Michael
    JOURNAL OF VIBRATION AND CONTROL, 2024, 30 (13-14) : 3184 - 3194
  • [10] Generative adversarial networks for data augmentation in machine fault diagnosis
    Shao, Siyu
    Wang, Pu
    Yan, Ruqiang
    COMPUTERS IN INDUSTRY, 2019, 106 : 85 - 93