Overview: Computer Vision and Machine Learning for Microstructural Characterization and Analysis
- PDF / 4,847,021 Bytes
- 15 Pages / 593.972 x 792 pts Page_size
- 66 Downloads / 234 Views
Overview: Computer Vision and Machine Learning for Microstructural Characterization and Analysis ELIZABETH A. HOLM, RYAN COHN, NAN GAO, ANDREW R. KITAHARA, THOMAS P. MATSON, BO LEI, and SRUJANA RAO YARASI Microstructural characterization and analysis is the foundation of microstructural science, connecting materials structure to composition, process history, and properties. Microstructural quantification traditionally involves a human deciding what to measure and then devising a method for doing so. However, recent advances in computer vision (CV) and machine learning (ML) offer new approaches for extracting information from microstructural images. This overview surveys CV methods for numerically encoding the visual information contained in a microstructural image using either feature-based representations or convolutional neural network (CNN) layers, which then provides input to supervised or unsupervised ML algorithms that find associations and trends in the high-dimensional image representation. CV/ML systems for microstructural characterization and analysis span the taxonomy of image analysis tasks, including image classification, semantic segmentation, object detection, and instance segmentation. These tools enable new approaches to microstructural analysis, including the development of new, rich visual metrics and the discovery of processing-microstructure-property relationships. https://doi.org/10.1007/s11661-020-06008-4 The Minerals, Metals & Materials Society and ASM International 2020
I.
INTRODUCTION: THE QUANTIFICATION OF MICROSTRUCTURE
IN 1863, the geologist Henry Clifton Sorby examined acid-etched and polished steel under a microscope and observed a complex collection of substructures that we now call microstructure.[1] Over the next two decades, Sorby related these visual entities to the chemistry, history, and behavior of various steel alloys, making the first connections between materials structure, composition, processing, and properties.[2] Sorby’s observations were necessarily qualitative; for example, he wrote, ‘‘There is also often great variation in the size of the crystals [grains] of iron…and one cannot but suspect that such great irregularities might be the cause of the fracture…’’[2] However, by the early 1900s, methods for
ELIZABETH A. HOLM, RYAN COHN, NAN GAO, ANDREW R. KITAHARA, BO LEI, and SRUJANA RAO YARASI are with the Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213. Contact e-mail: [email protected] THOMAS P. MATSON is with the Department of Materials Science and Engineering, Carnegie Mellon University and also with the Department of Materials Science and Engineering, MIT, Cambridge, MA 02139. Manuscript submitted May 3, 2020.
METALLURGICAL AND MATERIALS TRANSACTIONS A
measuring microstructural features had been developed, and in 1916 the first ASTM metallographic standard E 2 to 17T included planimetric grain size measurement.[3] Throughout the 20th century, metallurgists and materials scientists continued to create and refine
Data Loading...
