About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Fatigue in Materials: Fundamentals, Multiscale Characterizations and Computational Modeling
|
Presentation Title |
Investigation of Stress Corrosion Cracking in CMSX-4 Turbine Blade Alloys Using AI and Deep-learning Assisted X-ray Microscopy |
Author(s) |
Ria L. Mitchell, Andy Holwell, Hrishikesh Bale, Mustafa Elsherkisi |
On-Site Speaker (Planned) |
Ria L. Mitchell |
Abstract Scope |
Single crystal nickel superalloys are typically used in power generation and aviation applications. Recently, incidents of failure due to increased temperature has caused Type II hot corrosion leading to cracking in blade roots, ending in catastrophic failure. Understanding the failure mechanism and crack characterization during stress corrosion cracking is vital in solving this issue. Here, we demonstrate a novel high resolution X-ray microscopy (XRM) workflow using deep-learning based reconstruction for artefact detection and data reconstruction, providing advanced denoising, improved quantification of features, upscaling of data/images, and increased throughput. Further, deep learning reconstruction has enabled the integration of XRM with finite element models (FEM) to enable mapping of real-life cracks. Combination of these computational, deep-learning, and microscope-based approaches have created a novel approach to studying stress corrosion cracking. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, Characterization, Other |