Nandana Menon

REBCO coated conductors are of significant interest for high-field superconducting applications owing to their exceptional critical current retention under high magnetic fields. However, depending on the fabrication route, microstructural inhomogeneities such as porosity, Cu x O precipitates, and a -axis oriented grains can emerge at various length scales, disrupting current transport and limiting the critical current density. This study investigates and characterizes such defects in commercial REBCO conductors of varying specifications. Top-view scanning electron microscope (SEM) images of the REBCO layer were acquired following chemical etching of Cu and Ag layers to expose the microstructure for analysis. Conventional image analysis and segmentation techniques prove insufficient for reliably quantifying these defects, while manual identification remains prohibitively labor-intensive. To overcome these limitations, a machine learning approach is explored to enable rapid, automated, and accurate defect detection. Specifically, an open-source computer vision model, Mask region-based convolutional neural network, is fine-tuned on domain-specific SEM image data. The fine-tuned model achieved a validation mean average precision of 45.23% and enabled quantitative defect analysis across 63 tapes. Partial correlation analysis, controlling for confounding between defect types, revealed independent associations with critical current density that varied in strength and sign across defect types and measurement conditions. These findings motivate further targeted characterization to establish the microstructural origins of these relationships and inform conductor optimization.

An investigation of instance segmentation of cracks in Nb₃Sn 4-stack 40-strand Rutherford cables using machine learning is presented. Three samples were uniaxially and biaxially loaded before metallographic inspections were performed. The Mask R-CNN model was used in the Detectron2 framework with pre-trained weights but fine-tuned to detect and segment cracks. The model detected cracks with bounding box and mask average precisions (AP) of 42.8 and 27.9, respectively, and was used for instance segmentation of all cracks in the three samples. More cracks were found in the sample pre-loaded along the z-axis (i.e., along the cable length). Pre-loading along the x-axis (i.e., on the cables’ edges) reduced the number of cracks and changed the crack orientation distribution, away from being highly aligned with the y-axis (i.e., normal to the cables’ broad faces), i.e., the direction with the highest applied load. Fine-tuning of the Segment Anything Model (SAM) was also studied but performed poorly without human-provided prompts. However, the zero-shot capability of SAM showed high promises to accelerate the image annotation process for applications beyond this study.

Multi-fidelity (MF) modeling is a powerful statistical approach that can intelligently blend data from varied fidelity sources. This approach finds a compelling application in predicting melt pool geometry for laser-directed energy deposition (L-DED). One major challenge in using MF surrogates to merge a hierarchy of melt pool models is the variability in input spaces. To address this challenge, this paper introduces a novel approach for constructing an MF surrogate for predicting melt pool geometry by integrating models of varying complexity, that operate on heterogeneous input spaces. The first thermal model incorporates five input parameters i.e., laser power, scan velocity, powder flow rate, carrier gas flow rate, and nozzle height. In contrast, the second thermal model can only handle laser power and scan velocity. A mapping is established between the heterogeneous input spaces so that the five-dimensional space can be morphed into a pseudo two-dimensional space. Predictions are then blended using a Gaussian process-based co-kriging method. The resulting heterogeneous multi-fidelity Gaussian process (Het-MFGP) surrogate not only improves predictive accuracy but also offers computational efficiency by reducing evaluations required from the high-dimensional, high-fidelity thermal model. The results underscore the benefits of employing Het-MFGP for modeling melt pool behavior in L-DED. The framework successfully demonstrates how to leverage multimodal data and handle scenarios where certain input parameters may be difficult to model or measure.