LCF AND TMF OF SINGLE-CRYSTAL AND DIRECTIONALLY-SOLIDIFIED NI-BASE SUPERALLOYS PREDICTED USING A PROBABILISTIC PHYSICS-GUIDED NEURAL NETWORK
Predicting the life under thermomechanical fatigue (TMF) is challenging because there are several parameters defining the mechanical and thermal cycles including dwell periods within the cycle that can impact life. The relationships between these TMF history parameters and fatigue life are not always clear. A probabilistic physics-guided neural network was developed and trained to learn these relationships and predict the cycles to failure for a wide range of possible creep-fatigue and TMF histories using life data extracted from the literature.
Georgia Institute of Technology, Atlanta, Georgia, United States of America
Mon 15:40 - 16:00
Materials Data in Assessment of Components Operating in Extreme Environments