Exploring processing, microstructure, and properties
“The project has validated the use of the deep learning method for
real–world steels applications and provided us with insights that
can help us to improve steel properties and focus valuable
experimental resources more efficiently.”
Lode Duprez, chief scientific officer at OCAS
Alchemite™ was applied at OCAS (a joint venture between ArcelorMittal and the Flemish regional government) to understand steel performance. Benefits of the project were assessed as:
- Alchemite™ deep learning allows extraction of hidden information from microstructural images.
- Alchemite™ provides models with good predictive power, going from processing and /or microstructure to properties.
- The model becomes less of a ‘black box’ when supported by analytics features, such as importance charts and sensitivity plots, and through providing reliable uncertainty estimates on predictions.
- The ability to deal with sparse and noisy data is essential for extracting useful information out of real-world datasets.
Summary
Leading steel research centre OCAS has used Alchemite™ deep learning to model the behaviour of steels. Key objectives for the project included: determining whether the method was effective for real-world, sparse data; finding out whether image data from microstructural analysis could add value to the machine learning models; and gaining insight into Processing – Structure – Property (‘PSP’) relationships. Alchemite™ was able to build models with high accuracy, improving its predictive power by extracting hidden information from microstructural images. Outputs from the project could be applied to focus valuable experimental resources more efficiently and to find new processing parameter combinations that meet specific target property requirements for steels.
