ABSTRACT In this work, the long-term creep life of P91 steels with the limited experiment data was predicted using the domain knowledge and back propagation artificial neural networks (BP-ANN). Based on the traditional creep life models of Larson-Miller (L-M) parameter and θ projection, the domain knowledge was incorporated to expand the creep dataset. Then, the fuzzy C-means (FCM) clustering algorithm was introduced for training data collection. Consequently, the creep life prediction was conducted with the corresponding dataset and BP-ANN. The obtained results demonstrated that in contrast to the conventional prediction models of creep life, the prediction accuracy for long-term creep life of P91 steels can be improved significantly by the present model. For instance, the predicted creep lives 200,000 h exhibit the average errors of 6.0%. In addition, the present study offers a convenient tool to solve the issue of limited experiment data, particularly the long-term creep of P91 steels.
Read full abstract