2019 Pittsburgh AISTech

Sessions Speakers Exhibitors Products Press Releases Show Specials Floor Plan Buzz

Machine Learning Approaches for the Analysis of Non-Metallic Inclusion Data Sets (Room 315)

07 May 19
11:30 AM - 12:00 PM

Tracks: Computer Applications

One of the most prominent techniques used for of inclusion analysis is automated scanning electron microscopy (SEM) coupled with energy-dispersive x-ray spectroscopy (EDS). The output data generated from the analysis is extensive, and many studies have focused on examining the chemistries and size distributions of inclusions. This work applies machine learning approaches to classify inclusions and to characterize relationships between the variables that describe an inclusion population. Machine learning enables investigation of trends in the data and relationships between other variables that can often be difficult to perceive. Techniques to optimize data analysis and collection will also be examined.