loading page

Multiaxial fatigue life prediction for various metallic materials based on the hybrid CNN-LSTM neural network
  • +3
  • Jianxiong Gao,
  • Fei Heng,
  • Rongxia Xu,
  • Haojin Yang,
  • Qin Cheng,
  • Yuanyuan Liu
Jianxiong Gao
Xinjiang University

Corresponding Author:[email protected]

Author Profile
Fei Heng
Xinjiang University
Author Profile
Rongxia Xu
Xinjiang University
Author Profile
Haojin Yang
Xinjiang University
Author Profile
Qin Cheng
Xinjiang University
Author Profile
Yuanyuan Liu
Xinjiang University
Author Profile


A new algorithm optimization-based hybrid neural network model is proposed in the present study for the multiaxial fatigue life prediction of various metallic materials. Firstly, a convolutional neural network (CNN) is applied to extract the in-depth features from the loading sequence comprised of the critical fatigue loading conditions. Meanwhile, the multiaxial historical loading information with time-series features is retained. Then, a long short-term memory (LSTM) network is adopted to capture the time-series features and in-depth features of the CNN output. Finally, a full connection layer is used to achieve dimensional transformation, which makes the fatigue life predictable. Herein, the hyperparameters of the LSTM network are automatically determined using the slime mould algorithm (SMA). The test results demonstrate that the proposed model has pleasant prediction performance and extrapolation capability, and it is suitable for the life prediction of various metallic materials under uniaxial, proportional multiaxial, non-proportional multiaxial loading conditions.
05 Nov 2022Submitted to Fatigue & Fracture of Engineering Materials & Structures
05 Nov 2022Submission Checks Completed
05 Nov 2022Assigned to Editor
08 Nov 2022Reviewer(s) Assigned
07 Dec 2022Review(s) Completed, Editorial Evaluation Pending
11 Jan 2023Editorial Decision: Revise Minor
01 Feb 20231st Revision Received
01 Feb 2023Submission Checks Completed
01 Feb 2023Assigned to Editor
01 Feb 2023Reviewer(s) Assigned
09 Feb 2023Review(s) Completed, Editorial Evaluation Pending
13 Feb 2023Editorial Decision: Accept