46 Search Results

Focused ion beam scanning electron microscopy (FIB-SEM) tomography has increasingly been utilized for acquiring three-dimensional (3D) microstructure features at the sub-micron scale in irradiated nuclear materials. This technique involves sequential ion beam slicing followed by electron beam imaging and compositional mapping using energy dispersive spectroscopy (EDS). Despite its growing use, several challenges persist. These include the time-intensive nature of data collection of EDS data, difficulties in distinguishing between various microstructures, and issues with image alignment. These challenges currently limit the broader application of FIB-SEM tomography in the field. To overcome these limitations, we propose using convolutional neural networks (CNNs) tomore » automate microstructure identification in SEM images. Our study introduces a new framework for identifying microstructures in irradiated U-10Zr (wt. %) metallic fuel with limited annotated data. The framework includes the creation of a reliable annotated dataset with paired SEM and ground truth data from EDS maps, the applications of CNNs for microstructure identification, and the validation of model performance. Specifically, we employed the Segment Anything Model (SAM) to align SEM images with corresponding EDS maps and focused ion beam (FIB) tomography SEM data. We evaluate several models, including Patch-based U-Net, Attention U-Net, and Residual U-Net, finding that patch-based U-Net exhibits superior segmentation performance and consistency. This approach reduces reliance on EDS detectors and aids in accelerating nuclear material analysis process, highlighting the potential of advanced deep learning techniques to improve microstructural understanding in nuclear material. This is the first framework to integrate SAM and Patch-based CNN models for semantic segmentation of irradiated nuclear materials, with potential applicability to other tomography datasets.« less

During irradiation, phenomena such as kernel swelling and buffer densification may impact the performance of tristructural isotropic (TRISO) particle fuel. Post-irradiation microscopy is often used to identify these irradiation-induced morphologic changes. However, each fuel compact generally contains thousands of TRISO particles. Manually performing the work to get statistical information on these phenomena is cumbersome and subjective. Here, to reduce the subjectivity inherent in that process and to accelerate data analysis, we used convolutional neural networks (CNNs) to automatically segment cross-sectional images of microscopic TRISO layers. CNNs are a class of machine-learning algorithms specifically designed for processing structured grid data. Theymore » have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we generated a large irradiated TRISO layer dataset with more than 2,000 microscopic images of cross-sectional TRISO particles and the corresponding annotated images. Based on these annotated images, we used different CNNs to automatically segment different TRISO layers. These CNNs include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net performs best in terms of Intersection over Union (IoU). Using CNN models, we can expedite the analysis of TRISO particle cross sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.« less

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorizationmore » based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F₁ score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.« less

To fully evaluate the feasibility of extending the dry storage of aluminum-clad spent nuclear fuel (ASNF) in helium-backfilled cannisters, the amount of radiation-induced molecular hydrogen (H₂) generated and the impact of absorbed radiation dose on the ASNF corrosion layer composition must be accurately assessed. Here, in this study, we report a slowing in the rate of radiolytic H₂ generation for pre-corroded AA1100 and AA6061 aluminum alloy coupons irradiated to up to 53 MGy of absorbed cobalt-60 gamma dose. By exploring a variety of thermal pretreatment conditions for AA6061 coupons, we find that the “steady-state” yield of H₂ depends more onmore » the aluminum alloy used than on the treatments applied prior to dry storage. Scanning electron microscopy and positron annihilation lifetime spectroscopy techniques also provided evidence for gamma radiation-induced defects in the corrosion layers of the investigated aluminum alloy coupons for high absorbed doses (~50 MGy), the consequences of which on cladding integrity and H₂ generation should be explored in future works.« less

Uranium dioxide (UO₂), widely used as driver fuel in light water reactors, experiences microstructure and property change by nuclear fission reactions. This paper bridges the characterization of fresh UO₂ fuel at different length scales, serving as a baseline for future post irradiation examination of irradiated UO₂ fuel. To characterize the microstructural change of nuclear fuel, modern approaches cover a wide range of length scales through different characterization techniques, such as mm scale for Synchrotron-based X-ray computed tomography (SXCT) and microscale for focused ion beam (FIB) and scanning electron microscopy (SEM). It is challenging to bridge the data and knowledge ofmore » the same sample in different length scales. This paper proposed a deep learning framework leveraging transfer learning to detect microstructural defects, trained from a sparse FIB, SEM, and SXCT images. The proposed model achieved superior performance in defect segmentation on multiscale microscopic data compared to four of the latest deep learning models.« less

This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacymore » and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.« less

The metallic U-Zr nuclear fuel alloy has garnered renewed interest as a promising candidate for next-generation sodium-cooled fast reactors. Recent studies and technology assessments have identified several areas requiring improvements, enhanced knowledge, and reliable data to strengthen the U-Zr fuel design basis for qualification and commercial applications. One of the most challenging phenomena impacting this fuel system’s performance is fuel-cladding chemical interaction (FCCI). This work aimed to harvest FCCI data by examining selected HT9/U-10Zr (wt. %) fuel samples of prototypic full-length fuel pins through an integrated approach. This approach integrated scanning electron microscopy (SEM) microstructure characterization with localized mechanical propertiesmore » examination to deepen understanding of FCCI phenomenon in HT9/U-10Zr fuel system. Particularly, this study focused on MFF fuel pins irradiated at Fast Flux Test Facility (FFTF), which aimed to qualify metallic fuel as a driver fuel for FFTF and to assess its viability for larger-scale fast reactors. Electron microscopy provided high confidence in detecting and distinguishing the different FCCI layers, while small-scale mechanical testing (SSMT) probed the mechanical properties of these layers. SEM examination of a MFF-2 pin 192167, with a time averaged inner cladding temperature (TICT) slightly over 500°C, revealed minimal cladding-side FCCI (cladding wastage). In contrast, significantly thicker cladding wastage comprising two distinct sublayers was observed in samples from the thermally hot MFF-3 pin 193045 and MFF-5 pin 195011 where the TICT ranged from 610-635°C. SSMT indicated complete embrittlement in the sublayer adjacent to the fuel and a tendency toward embrittlement in the other sublayer. Additionally, a new machine learning method was developed, validated, and used to quantify cladding wastage thickness. The machine learning method reliably predicted the wastage thickness across various fuel pins and sample cross-sections. Furthermore, the available cladding wastage data from HT9/U-10Zr fuel system demonstrated a strong temperature dependency. However, the dataset remains small, and ongoing research activities are essential to further understand the FCCI phenomenon and develop a reliable FCCI model for enhanced fuel performance simulation under various conditions.« less

Silicon carbide (SiC) fiber-reinforced SiC matrix composites (SiCf-SiCm) are promising materials for accident-tolerant fuel (ATF) cladding in light water reactors. This paper, using four-dimensional scanning transmission electron microscopy (4D-STEM), studied the microstructure of SiCf-SiCm at nanoscale and provided grain statistics at the CVI/fiber region. Here, the results reveal that CVI region mainly contain irregular sub-micron grains (115 nm to 1800 nm) with a preferred orientation, while the fiber region has nano equiaxed grains (21 nm to 78 nm) with random orientations. Centered dark field imaging over the fiber regions verified the grain size measurement by 4D-STEM. Through 4D-STEM virtual darkmore » field imaging and orientation mapping, intragranular propagation was identified as the fracture mechanism for a microcrack observed within the CVI region. The amorphous pyrolytic carbon layer was also shown to effectively arrest the microcrack.« less

Advancing the understanding of material behavior and phenomena related to the size effect in small-scale components is important for settings where limited quantities of material samples can be tested. Through research and collaborative efforts, the scientific community and industry stakeholders have established guidelines for sub-sized specimen testing, encompassing best practices for specimen preparation, testing equipment, test procedures, and data analysis methods. However, prior investigations of the specimen size effect in the literature typically involved a relatively small number of test records. To address this limitation, our team created a large dataset of tensile test records for nuclear structural materials collectedmore » from peer-reviewed articles, consisting of 1,070 records with 54 features. In this study, we introduced a machine learning-based approach for predicting tensile properties of sub-sized specimens for stainless steel 316 alloys, and we developed methods for incorporating uncertainty quantification into predicted properties. Furthermore, we leveraged the curated database to investigate the specimen size effect and conducted an empirical validation of the reported critical values for the dimensions and geometry of sub-sized specimens. Additionally, we validated existing analytical models for correlation of the total elongation between sub-sized and standard-sized specimens in tensile testing. Our findings demonstrate the potential of machine learning techniques to enhance understanding of specimen size-related material behavior and highlight the need for coordinated efforts in developing large, open-source databases of mechanical testing data to support further research.« less