Abstract
Predicting cracks in a structure requires engineers to understand the material properties of the structure and to design appropriate equations for the crack model. Furthermore, solving the system of equations of the model is often computationally expensive. Therefore, we combine a mathematical model with a forecasting method for finding results faster when utilizing numerical methods to solve equations with a dense mesh density. In which, the Isotropic Brittle Fracture Model (BFM) is combined with Long Short Term Memory-Time Series Forecasting Model (LTSFM). In particular, the crack propagation based on the change of phase-field variable is approximated using the Finite Element Method (FEM) where the staggered Scheme and Master-Slave Method for establishing Dirichlet boundary conditions in the crack model are applied. The data, after created by the crack model, are used to train and predict by LTSFM for the propagation of cracks in the structure via the change of the value of phase-field variables. As a result, the combination of the analytical mathematical model and forecasting model reduces the computational time while ensuring correct trends of crack propagation based on the value of phase-field variables.

This publication has 14 references indexed in Scilit: