Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis

被引:21
|
作者
Lee, Kihoon [1 ]
Han, Soonyoung [1 ]
Pham, Van Huan [1 ]
Cho, Seungyon [1 ]
Choi, Hae-Jin [1 ,2 ]
Lee, Jiwoong [3 ]
Noh, Inwoong [3 ]
Lee, Sang Won [3 ]
机构
[1] Chung Ang Univ, Sch Mech Engn, 84 Heukseok Ro, Seoul 06974, South Korea
[2] Chung Ang Univ, Dept Comp Sci & Engn, 84 Heukseok Ro, Seoul 06974, South Korea
[3] Sungkyunkwan Univ, Sch Mech Engn, 2066 Seobu Ro, Suwon 16419, South Korea
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 05期
关键词
deep learning; fault diagnosis; industrial robot; prognostics and health management (PHM); spot welding; transfer learning; INDUCTION-MOTORS; GEARBOX;
D O I
10.3390/app11052370
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Fault diagnosis is a top-priority task for the health management of manufacturing processes. Deep learning-based methods are widely used to secure high fault diagnosis accuracy. Actually, it is difficult and expensive to collect large-scale data in industrial fields. Several prerequisite problems can be solved using transfer learning for fault diagnosis. Data from the source domain that are different but related to the target domain are used to increase the diagnosis performance of the target domain. However, a negative transfer occurs that degrades diagnosis performance due to the transfer when the discrepancy between and within domains is large. A multi-objective instance weighting-based transfer learning network is proposed to solve this problem and successfully applied to fault diagnosis. The proposed method uses a newly devised multi-objective instance weight to deal with practical situations where domain discrepancy is large. It adjusts the influence of the domain data on model training through two theoretically different indicators. Knowledge transfer is performed differentially by sorting instances similar to the target domain in terms of distribution with useful information for the target task. This domain optimization process maximizes the performance of transfer learning. A case study using an industrial robot and spot-welding testbed is conducted to verify the effectiveness of the proposed technique. The performance and applicability of transfer learning in the proposed method are observed in detail through the same case study as the actual industrial field for comparison. The diagnostic accuracy and robustness are high, even when few data are used. Thus, the proposed technique is a promising tool that can be used for successful fault diagnosis.
引用
收藏
页码:1 / 21
页数:21
相关论文
共 50 条
  • [31] Multi-objective Identification of UAV Based on Deep Residual Network
    Wang JiaQi
    Dai JiYang
    Zhai JinYou
    Ying Jin
    3RD INTERNATIONAL CONFERENCE ON AUTOMATION, CONTROL AND ROBOTICS ENGINEERING (CACRE 2018), 2018, 428
  • [32] Intelligent Fault Diagnosis of Induction Motors Based on Multi-Objective Feature Selection Using NSGA-II
    Arjmand-M, Amir-Hossein
    Sargolzaei, Nader
    2016 6TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE), 2016, : 183 - 188
  • [33] Multi-objective Complexity Reduction for Set-based Fault Diagnosis
    Savchenko, Anton
    Andonov, Petar
    Rumschinski, Philipp
    Findeisen, Rolf
    2017 6TH INTERNATIONAL SYMPOSIUM ON ADVANCED CONTROL OF INDUSTRIAL PROCESSES (ADCONIP), 2017, : 589 - 594
  • [34] An Intelligent Scheduling Strategy in Fog Computing System Based on Multi-Objective Deep Reinforcement Learning Algorithm
    Ibrahim, Media Ali
    Askar, Shavan
    IEEE ACCESS, 2023, 11 : 133607 - 133622
  • [35] Intelligent and sustainable waste classification model based on multi-objective beluga whale optimization and deep learning
    Sayed G.I.
    Abd Elfattah M.
    Darwish A.
    Hassanien A.E.
    Environmental Science and Pollution Research, 2024, 31 (21) : 31492 - 31510
  • [36] Learning Multi-Objective Network Optimizations
    Lee, Hoon
    Lee, Sang Hyun
    Quek, Tony Q. S.
    2022 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2022, : 91 - 96
  • [37] Multi-objective path planning based on deep reinforcement learning
    Xu, Jian
    Huang, Fei
    Cui, Yunfei
    Du, Xue
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 3273 - 3279
  • [38] Deep Residual Network Combined with Transfer Learning Based Fault Diagnosis for Rolling Bearing
    Zhou, Jianmin
    Yang, Xiaotong
    Li, Jiahui
    APPLIED SCIENCES-BASEL, 2022, 12 (15):
  • [39] Planetary gearbox fault diagnosis method based on deep belief network transfer learning
    Chen R.
    Yang X.
    Hu X.
    Li J.
    Chen C.
    Tang L.
    Zhendong yu Chongji/Journal of Vibration and Shock, 2021, 40 (01): : 127 - 133and150
  • [40] Deep Transfer Learning based Multisource Adaptation Fault Diagnosis Network for Industrial Processes
    Chai, Zheng
    Zhao, Chunhui
    IFAC PAPERSONLINE, 2021, 54 (03): : 49 - 54