Fatigue Life Prediction Models

Probablistic Physics Guided Neural Networks

This is a neural network model that uses known physics knowledge to guide the training of the model. This specific architecture is called a Probablistic Phyiscs guided Neural Network and was created by Jie Chen and Yongming Liu who introduced and discussed it in their paper.

This model is uses the PPgNN architecture to predict Creep-Fatigue and Thermomechanical Fatigue Life of Ni-base Superalloys. The model will plot data points that have similar parameters to the one inputted into the model including runout cases. Tests that did not runout are displayed as a blue dot, while tests that did runout are displayed as a red triangle. The table of contentes above provides links to different versions of the PPgNN created for fatigue life predictions for superalloys.

Future Models