High-Throughput Approaches to Establish Quantitative Process–Structure–Property Correlations in Ni-Base Superalloy

Senanayake, Nishan M.; Mukhopadhyay, Suparno; Carter, Jennifer L. W.

doi:10.1007/978-3-030-51834-9_66

Cited by 2 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The γ″ (Ni 3 Nb-D0 22 crystal structure), and γ′ (Ni 3 Al,-L1 2 crystal structure) precipitate phases mainly contribute overall favorable high-temperature properties [1]. The measurement of these individual microstructural features is important for implementation of process-structure-property models and calibration of precipitation simulation models that inform the optimization of processing routes [3][4][5][6]. Due to the nanoscale size, morphology, and chemical similarities of phases, the quantitative characterization of these precipitates is challenging and leads many studies to not include quantified values of the γ″ and γ′ strengthening precipitates [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Senanayake

Carter

2020

Integr Mater Manuf Innov

Self Cite

View full text Add to dashboard Cite

Extracting accurate volume fraction and size measurements of γ″ and γ′ precipitates in iron-based superalloys from micrographs is challenging and conventionally involves manual image processing due to their smaller size, and similar crystal structures and chemistries. The co-precipitation of composite particles further complicates automated segmentation. In this work, different types of traditional machine learning approaches and a convolutional neural network (CNN) were compared to a non-machine learning approach, for the segmentation of the composite particles of γ″ and γ′ precipitates. The objective was to optimize metrics of segmentation accuracy and the required computational resources. The data set contains 47 experimentally generated scanning electron micrographs of IN718 alloy samples, computationally increased to 188 images (900 × 900 px). All algorithms are containerized using singularity, publicly available, and can be modified without dependencies. The CNN and the random forest models achieve 95% and 94% accuracy, respectively, on the test images with better computational efficiency than the non-machine learning algorithm. The CNN tested accurately over a range of imaging conditions.

show abstract