Multiaxial fatigue life prediction for various metallic materials based on the hybrid CNN‐LSTM neural network

Abstract

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 composed 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 mold 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, nonproportional multiaxial loading conditions.

Random Forest-Based Fatigue Reliability-Based Design Optimization for Aeroengine Structures

“…Currently, extensive efforts have been carried out to boost the resist fatigue performance of aeroengine structures [7][8][9][10], including fatigue reliability modeling under random loads [11][12][13][14][15], probabilistic fatigue life evaluation considering material variability [16][17][18][19], constitutive responsebased fatigue failure accounting for model uncertainties [20][21][22][23][24], stochastic randomness-based fatigue failure evaluation [25][26][27], and so forth. During the above investigations, the disperse characteristics of fatigue life were sufficiently studied, laying the groundwork for fatigue reliability degree assessment.…”

Fatigue life prediction of composite bolted joints based on finite element model and machine learning

“…Lu et al 26 proposed a method based on improved CNN–BP to predict multibeam sonar grid data and proved that the method has feasibility, reliability, and high accuracy. Heng et al 27 proposed a multiaxial fatigue life prediction model of various metal materials model based on a CNN–LSTM hybrid neural network. In addition, the CNN hybrid neural network can also be used for lithium battery remaining life and load prediction 28–31 .…”

Topological optimization and fatigue life prediction of a single pad externally adjustable fluid film bearing

“…It is possible to prevent bearing catastrophic disasters by forecasting the bearing's failure or remaining useful life. The research of fatigue life prediction is significantly impacted by advancements in computer performance and technical innovations such as artificial intelligence and machine learning techniques 33 – 35 . Therefore, it is essential to find the fatigue life through numerical study.…”