Physics-informed machine learning for composition-process-property alloy design: shape memory alloy demonstration
This work addresses alloy design challenges for materials scientists by enabling machine learning to handle physical complexities that have long stymied physics-based models, though it is incremental as it builds on existing feature engineering approaches.
The authors tackled the problem of predicting composition-process-property relationships for shape memory alloys (SMAs) in a high-dimensional design space, achieving validated blind predictions for thermal hysteresis and transformation temperatures using physics-informed feature engineering.
Machine learning (ML) is shown to predict new alloys and their performances in a high dimensional, multiple-target-property design space that considers chemistry, multi-step processing routes, and characterization methodology variations. A physics-informed featured engineering approach is shown to enable otherwise poorly performing ML models to perform well with the same data. Specifically, previously engineered elemental features based on alloy chemistries are combined with newly engineered heat treatment process features. The new features result from first transforming the heat treatment parameter data as it was previously recorded using nonlinear mathematical relationships known to describe the thermodynamics and kinetics of phase transformations in alloys. The ability of the ML model to be used for predictive design is validated using blind predictions. Composition - process - property relationships for thermal hysteresis of shape memory alloys (SMAs) with complex microstructures created via multiple melting-homogenization-solutionization-precipitation processing stage variations are captured, in addition to the mean transformation temperatures of the SMAs. The quantitative models of hysteresis exhibited by such highly processed alloys demonstrate the ability for ML models to design for physical complexities that have challenged physics-based modeling approaches for decades.