| Author(s) |
David E Farache, George M Nishibuchi, John G Gulley, Sebastian Elizondo, Alex Post, Kyle Stubbs, Keith Kruger, Arun Mannodi-Kanakkithodi, Michael S. Titus |
| Abstract Scope |
Requirements of stress rupture life and elongation of nickel alloy 718 are often prescribed by specification AMS5596 or AMS5663, which broadly state that the stress rupture life and elongation must exceed 23 h and 4% at 649 ºC (1200 ºF), respectively. Variability in product stress-rupture life can range from less than 2 h to more than 1000 h, which can cause significant delays for testing, shipping, and delivery of product. In this work, we predict the stress-rupture life and elongation of HAYNES® 718 sheet product utilizing machine learning models. The models utilized data from 448 lots of material and inputs including composition, room temperature mechanical property data, processing data such as finish gauge, total reduction, final reduction, rule of mixture average properties including density, electronegativity, and bulk and Young’s modulus, and environmental factors such as daily maximum and minimum temperatures and humidity. Different sets of input features were chosen from the highest absolute Pearson correlation values, Gini coefficient, SHAP, and SISSO analysis, and four separate random forest models were trained using an 80%-20% split between training and testing data. The resulting mean squared errors of best performing models of stress-rupture life and elongations were 102 h and 7.2%, respectively. Input features of highest importance were observed to be room temperature tensile properties, finish gauge, and tramp elements such as Co, P, and Si. These models can be utilized to accelerate acceptance testing of 718 product by identifying product exhibiting anomalously low or high creep rupture life and elongation. |