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 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). Five data sets of materials are involved for case studies. The predictive performance of the proposed model is compared with those obtained using support vector machine (SVM), LSTM network, and a critical plane model. The results demonstrate the better predictive performance of the proposed model, and it is suitable for the life prediction of various metallic materials under uniaxial, proportional multiaxial, non-proportional multiaxial loading conditions. Besides, the proposed model outperforms the SVM and LSTM network in terms of extrapolation capability.