Machine Learning to Accelerate Alloy Design

A method for predictive analytics, one that incorporates a prediction step, for the purpose of efficiently searching composition space of alloys or composites of interest, and hence accelerating design of high-entropy alloys with desired material characteristics, a method utilizing

• a database importing step, for ingesting the relevant materials data,
• an optional preprocessing step, for unified comparison of materials data across data sets,
• an optional feature selection step, for extracting the features primarily impacting the material properties of interest,
• a prediction step, for predicting the material properties of interest given the materials data ingested, where the prediction step employs a prediction technique, suitable for the data available and the problem at hand, where the prediction step is capable of accommodating physics-based models for improved prediction accuracy, and where the prediction technique employed can involve regression analysis, when limited data is available, but a machine learning predictor, when sufficient data is available, and
• a reporting and evaluation step, for evaluating the materials properties of interest.

An apparatus, referred to as intelligent additive manufacturing, for laser metal powder bed fusion, an apparatus comprising of

• a module for distributing the laser energy over the powder bed and providing a list of control parameters,
• a module for monitoring the response of the powder bed and providing a list of sensed parameters, including temperature,
• a module for generating auxiliary digital training data and listing different physical measurands, and
• a module for linking control parameters to values of monitoring sensors and auxiliary digital data via an artificial intelligent processor for training and operator purposes.
• an apparatus that uses multi-beam to control temperature of melt pool of the powder bed and the energy distribution over the powder bed.