A Machine Learning Model for Predicting Progressive Crack Extension
based on Direct Current Potential Drop Fatigue Data
Abstract
Time history data collected from a Direct Current Potential Drop (DCPD)
fatigue experiment at a range of temperatures was used to train a
Bidirectional Long-Short Term Memory Neural Network (BiLSTM) model. The
model was trained on high sampling rate experimental data from crack
initiation up through the Paris regime. The BiLSTM model was able to
predict the progressive crack extension at intermediate temperatures and
stress intensities. The model was able to reproduce crack jumps and
overall crack progression. The BiLSTM model demonstrated the potential
to be used as a tool for future investigation into fundamental
mechanisms such as high-temperature oxidation and new damage models.