Due to the huge amount of the customers'data the rise of various financial products and the short?term impact of the epidemic, banks are facing with increasing pressure resulting in the business volume declined sharply. The traditional classification tree model can not make more accurate prediction of long?term deposits and carry out accurate marketing to customers according to customer information. Therefore, this paper proposes a three?layer neural network model. Through the experiment, the customer data of grape Island banking institutions are predicted, and compared with the prediction results of a traditional decision tree, random forest model, AdaBoost model and XGBoost model. The experiment shows that compared with the other four models, the neural network model has a better effect of prediction, the model evaluation AUC reaches 0.977 7 and the accuracy reaches 99.06%.

Crack was one of the most dangerous pressure piping flaws. Beyond that, it was the main cause of pressure pipeline accidents. Based on related concepts of fracture mechanics, the 3-D models of pressure pipeline subjected to internal pressure and its surface oblique cracks under different Angles were established according to the ANSYS finite element software. In addition to that, the stress intensity factor of crack tip was calculated and analyzed by the finite element and the change rules between the stress intensity factor and crack Angles were concluded. According to that, the crack tip stress field strength was analyzed quantitatively. At the same time, it also provided some data supports for the study of inclined crack on the surface of pressure pipeline.