Abstract：Surface cracks often exist in pressure vessels with long service. The safety assessment based on fracture analysis has a strong practical significance for the stable running of pressure vessels. The conventional method is to evaluate the safety of pressure vessels with surface cracks by using 2D J-integral, but there are two obvious problems in practice. One is the inapplicability of 2D J-integral for surface semi-elliptic cracks, the other is the numerical simulation is time-consuming for elastoplastic vessels. Aiming to solve these two problems, an artificial neural network safety evaluation method based on the three-dimensional J-integral is proposed in this paper. The 3D J-integral is applied to quantify the stress intensity at the crack tip of surface crack in pressure vessel and the trained neural network is to predict the 3D J-integral. By finite element method, 1200 cases of elastoplastic pressure vessels with surface cracks with different geometric sizes, crack sizes and internal pressures are calculated. The 3D J-integral results of semi-elliptical crack tip are analyzed. A correction factor F is constructed to characterize the material properties, the singularity of crack tip and the influence of vessel’s geometry on the 3D J-integral. Based on the generated machine learning data set from FEM calculation, the back propagation neural network (BPNN) model is built, and the GABPNN prediction model is formed by genetic algorithm optimization. The data set is randomly divided into training set(90%) and validation set(10%). The training process shows that genetic algorithm optimization can accelerate the convergence speed of neural network and improve the stability of training. The results show that the prediction accuracy of BPNN and GABPNN model is more than 96%, and relatively accurate results can be obtained on the unknown data. The 3D J-integral of crack tip can be predicted efficiently, which provides a new idea and method for the realization of the computer aided on-site safety assessment of pressure vessels with surface cracks.
2023, Vol. 44 
