This paper presents a machine learning (ML) method to study crack propagation issues in fracture mechanics and correlates the results with experimental and numerical data. The main goal is to accurately predict crack propagation in engineering fracture structures without the need for re-modeling or re-computation. The approach employs an artificial neural network (ANN) to predict the crack propagation in a fuselage panel under constant amplitude mode, an ADB610 steel specimen with a stress ratio of 0.3, and an L-shaped concrete specimen under load ratio. Based on the optimal parameters learned by the model from the dataset, a trained ANN is used to predict crack propagation quickly without any other analytical tools. The effectiveness and accuracy of the method are verified by comparing the results obtained from the ANN model with the results from the numerical method or experimental data. The predicted results show well-agreed with experimental data and numerical data.