Researchers have developed NL-MambaXCT, a novel framework utilizing Mamba architecture and self-supervised learning for defect classification in X-ray computed tomography (XCT) images of Nomex honeycomb structures. This approach combines masked image modeling for pre-training on unlabeled data with a Nested Learning formulation, featuring two-timescale parameter dynamics and a deep-momentum optimizer. The model achieved high accuracy and F1 scores, outperforming existing CNN, attention, and single-timescale Mamba baselines, suggesting its potential for efficient and robust industrial inspection in aerospace manufacturing. AI
IMPACT This research offers a more efficient and accurate method for defect detection in critical aerospace components, potentially improving manufacturing quality and safety.
RANK_REASON This is a research paper detailing a novel model architecture and methodology for a specific technical problem. [lever_c_demoted from research: ic=1 ai=1.0]
- X-ray computed tomography
- Mamba
- Nested Learning
- NL-MambaXCT
- Nomex honeycomb
- self-supervised learning
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
