Abstract
U-10Zr-based nuclear fuel is pursued as a primary candidate for
next-generation sodium-cooled fast reactors. However, more advanced
characterization and analysis are needed to form a fundamental understating of
the fuel performance, and make U-10Zr fuel qualify for commercial use. The
movement of lanthanides across the fuel section from the hot fuel center to the
cool cladding surface is one of the key factors to affect fuel performance. In
the advanced annular U-10Zr fuel, the lanthanides present as fission gas
bubbles. Due to a lack of annotated data, existing literature utilized a
multiple-threshold method to separate the bubbles and calculate bubble
statistics on an annular fuel. However, the multiple-threshold method cannot
achieve robust performance on images with different qualities and contrasts,
and cannot distinguish different bubbles. This paper proposes a hybrid
framework for efficient bubble segmentation. We develop a bubble annotation
tool and generate the first fission gas bubble dataset with more than 3000
bubbles from 24 images. A multi-task deep learning network integrating U-Net
and ResNet is designed to accomplish instance-level bubble segmentation.
Combining the segmentation results and image processing step achieves the best
recall ratio of more than 90% with very limited annotated data. Our model shows
outstanding improvement by comparing the previously proposed thresholding
method. The proposed method has promising to generate a more accurate
quantitative analysis of fission gas bubbles on U-10Zr annular fuels. The
results will contribute to identifying the bubbles with lanthanides and finally
build the relationship between the thermal gradation and lanthanides movements
of U-10Zr annular fuels. Mover, the deep learning model is applicable to other
similar material micro-structure segmentation tasks.