Investigation of Stress Corrosion Cracking in CMSX-4 Turbine Blade Alloys Using Deep Learning Assisted X-ray Microscopy and Correlative Imaging Workflow
Bibliographic record
Abstract
Single crystal Ni superalloys are typically used in power generation and aviation applications due to their unique properties. Incidents of failure due increased temperature around root blade regions has caused Type II hot corrosion leading to cracking in blade roots resulting in catastrophic failure [1]. Understanding the failure mechanism and crack characterisation is vital in solving this industrial issue. The complex hierarchical microstructure of single crystal Ni superalloys demands the use of multi-modal, multiscale imaging approach combining non-destructive and destructive methods that enable covering the broad span of length scales ranging from millimetre to nanometer scale in order to get a full understanding of the link between the microstructure and the mechanical behaviour under service conditions. Here we demonstrate a unique workflow of characterization using correlative microscopy combining the information gathered from 3D non-destructive X-ray microscopy aided with deep-learning based algorithms to navigate to specific sites of interest. In the present study, these sites of interests were crack front of deep surface cracks that resulted from stress corrosion cracking and extended nearly 500 um below the surface. We demonstrate combining fs-laser micromachining and focused ion beam milling to precisely isolate a crack tip that was identified from the 3D X-ray tomography data. Furthermore we extend the study to lift out the isolated block from the bulk and utilize it to prepare site-specific TEM lamella and image the remaining block in high resolution 3D FIB tomography producing rich datasets that elucidate the interactions of the cracks with the local microstructure. By extracting the fracture tip, both crystal plasticity and crystal deformity can be studied in detail resulting in orientation tomography of the corroded region of stress. Combining this correlative workflow we are able to demonstrate a unique technique in C-ring analysis and identifying structural defects not visible using typical microscopy techniques. 3D rendering of X-ray microscopy data reconstructed and segmented using deep-learning algorithms. Red features indicate semi-circular surface cracks formed due to stress-corrosion cracking. Green features represent voids seen along the dendritic direction of the single crystal CMSX-4 nickel based super alloy sample. FIB cross-section of the surface crack illustrates the γ/ γ” phases along with secondary transverse cracks. Top surface illustrates the corrosion products
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".