A Real-Time Remaining Fatigue Life Prediction Approach Based on a Hybrid Deep Learning Network

被引:3
|
作者
Zhu, Yifeng [1 ,2 ]
Zhang, Jianzhao [3 ]
Luo, Jiaxiang [3 ]
Guo, Xinyan [4 ]
Liu, Ziyu [3 ]
Zhang, Ruonan [1 ,2 ]
机构
[1] Taihu Lab Deepsea Technol Sci, Wuxi 214082, Peoples R China
[2] China Ship Sci Res Ctr, Wuxi 214082, Peoples R China
[3] South China Univ Technol, Sch Automation Sci & Engn, Guangzhou 510641, Peoples R China
[4] South China Univ Technol, Sch Civil Engn & Transportat, Guangzhou 510641, Peoples R China
基金
中国国家自然科学基金;
关键词
crack propagation; remaining fatigue life; deep learning; real-time prediction;
D O I
10.3390/pr11113220
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Fatigue failure is a typical failure mode of welded structures. It is of great engineering significance to predict the remaining fatigue life of structures after a certain period of service. In this paper, a two-stage hybrid deep learning approach is proposed only using the response of structures under fatigue loading to predict the remaining fatigue life. In the first stage, a combination of convolutional neural network (CNN), squeeze-and-excitation (SE) block, and long short-term memory (LSTM) network is employed to calculate health indicator values based on the current measured data sequence. In the second stage, a particle filtering-based algorithm is utilized to predict the remaining fatigue life using the previously calculated health indicators. Experimental results on different welded specimens under the same loading conditions demonstrate that the hybrid deep learning approach achieves superior prediction accuracy and generalization ability compared to CNN, LSTM, or CNN-LSTM models in the first stage. Moreover, the average relative deviation between the predicted and actual fatigue life is less than 6% during the final quarter of the crack propagation and fracture stage.
引用
下载
收藏
页数:16
相关论文
共 50 条
  • [31] Real-time remaining useful life prediction based on adaptive kernel window width density
    Zhang, Jiangmin
    Shi, Hui
    Dong, Zengshou
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2022, 33 (10)
  • [32] Deep-Learning Based Prognosis Approach for Remaining Useful Life Prediction of Turbofan Engine
    Muneer, Amgad
    Taib, Shakirah Mohd
    Fati, Suliman Mohamed
    Alhussian, Hitham
    SYMMETRY-BASEL, 2021, 13 (10):
  • [33] Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach
    Chen, Zhenghua
    Wu, Min
    Zhao, Rui
    Guretno, Feri
    Yan, Ruqiang
    Li, Xiaoli
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2021, 68 (03) : 2521 - 2531
  • [34] A Real Time Deep Learning Based Approach for Detecting Network Attacks
    Callegari, Christian
    Giordano, Stefano
    Pagano, Michele
    BIG DATA RESEARCH, 2024, 36
  • [35] A Deep Learning-based Approach for Real-time Facemask Detection
    Boulila, Wadii
    Alzahem, Ayyub
    Almoudi, Aseel
    Afifi, Muhanad
    Alturki, Ibrahim
    Driss, Maha
    20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 2021, : 1478 - 1481
  • [36] A Real-time Fire Segmentation Method Based on A Deep Learning Approach
    Li, Mengna
    Zhang, Youmin
    Mu, Lingxia
    Xin, Jing
    Yu, Ziquan
    Jiao, Shangbin
    Liu, Han
    Xie, Guo
    Yi, Yingmin
    IFAC PAPERSONLINE, 2022, 55 (06): : 145 - 150
  • [37] An Efficient Hybrid Deep Learning Approach for Accurate Remaining EV Range Prediction
    Eissa, Magdy Abdullah
    Chen, Pingen
    2023 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, AIM, 2023, : 430 - 435
  • [38] Aircraft Engines Remaining Useful Life Prediction Based on A Hybrid Model of Autoencoder and Deep Belief Network
    Al-Khazraji, Huthaifa
    Nasser, Ahmed R.
    Hasan, Ahmed M.
    Al Mhdawi, Ammar K.
    Al-Raweshidy, Hamed
    Humaidi, Amjad J.
    IEEE ACCESS, 2022, 10 : 82156 - 82163
  • [39] Remaining Useful Life Prediction for Lithium-Ion Batteries Based on a Hybrid Deep Learning Model
    Chen, Chao
    Wei, Jie
    Li, Zhenhua
    PROCESSES, 2023, 11 (08)
  • [40] Real-Time Hybrid Deep Learning-Based Train Running Safety Prediction Framework of Railway Vehicle
    Lee, Hyunsoo
    Han, Seok-Youn
    Park, Keejun
    Lee, Hoyoung
    Kwon, Taesoo
    MACHINES, 2021, 9 (07)