Machine learning assisted prediction of creep data of India specific reduced activation ferritic martensitic steel

The present study demonstrates the application of machine learning approach for predicting the creep deformation, rupture strain and rupture life of India specific reduced activation ferritic martensitic (INRAFM) steel. In this direction, various regression models were employed and found that the tree-based ensemble method (Extra trees regression (ETR)) offers better prediction of creep behaviour with the root mean square error (RMSE), average cross-validation score and coefficient of determination (R2) values of 0.00203, 0.979 and 0.996 respectively as compared to other models and which was used for further analysis of creep data. Initially, the creep data of INRAFM steel obtained from creep experiments for different stresses (σ) (200, 220, 240 and 260 MPa) at a test temperature (T) of 823 K was used to train the model for predicting strain values (ε) as output, namely ε = f (σ, T, t) approach, where t is time in hours (h). Subsequently, to assess the predictive capabilities of the model, the predicted data for the test condition of 250 MPa and 823 K was compared with experimental data. A good match was found between the predicted and experimental results with a correlation coefficient (Rcc) of 0.994. Later, the model was applied for predicting the creep curves at intermediate stress levels for the same temperature. Additionally, an effort has been made to predict the rupture time of the steel by providing strain as input variable, namely t = f (σ, T, ε) approach. The predicted rupture time values corresponding to different rupture strains are close to the experimental data. A comparison between both the predictive approaches (based on ε = f (σ, T, t) and t = f (σ, T, ε)) was carried out and presented. The results obtained in the present work reveal the potential of ETR approach for prediction of creep data.