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

This study proposes a fatigue life prediction method for composite bolted joints, which combines algorithm optimization-based hybrid neural networks with finite element modeling. First, based on the Hashin failure criterion of physical mechanism, a finite element model for fatigue life prediction of composite bolted joints is established, and the simulation calculations have been conducted using various initial conditions. Then, by integrating the simulation and experiment data, we have established a fatigue life database that serves machine learning training and prediction. Finally, the data undergo a comprehensive process of deep feature extraction through the utilization of a convolutional neural network (CNN). The resulting deep features are utilized as inputs for training the backpropagation neural network (BPNN) to predict fatigue life. The results indicate this synergistic combination of CNN and BPNN results in a substantial improvement in prediction accuracy and has remarkable superiority in predicting the fatigue life of composite bolted joints. An FE model is established to predict the fatigue life of composite bolt joints. A fatigue life prediction model is proposed based on the hybrid neural network. The advantages of convolution neural network and BP neural network are combined. The superiority of the CNN-BP hybrid neural network has been verified.