Department of Materials Science and Engineering, University of Wisconsin-Madison, Madison, WI, 53706, USA.
Nuclear Engineering and Radiological Sciences, University of Michigan - Ann Arbor, Ann Arbor, MI, 48109, USA.
Sci Rep. 2023 Mar 30;13(1):5178. doi: 10.1038/s41598-023-32454-2.
Accurately quantifying swelling of alloys that have undergone irradiation is essential for understanding alloy performance in a nuclear reactor and critical for the safe and reliable operation of reactor facilities. However, typical practice is for radiation-induced defects in electron microscopy images of alloys to be manually quantified by domain-expert researchers. Here, we employ an end-to-end deep learning approach using the Mask Regional Convolutional Neural Network (Mask R-CNN) model to detect and quantify nanoscale cavities in irradiated alloys. We have assembled a database of labeled cavity images which includes 400 images, > 34 k discrete cavities, and numerous alloy compositions and irradiation conditions. We have evaluated both statistical (precision, recall, and F1 scores) and materials property-centric (cavity size, density, and swelling) metrics of model performance, and performed targeted analysis of materials swelling assessments. We find our model gives assessments of material swelling with an average (standard deviation) swelling mean absolute error based on random leave-out cross-validation of 0.30 (0.03) percent swelling. This result demonstrates our approach can accurately provide swelling metrics on a per-image and per-condition basis, which can provide helpful insight into material design (e.g., alloy refinement) and impact of service conditions (e.g., temperature, irradiation dose) on swelling. Finally, we find there are cases of test images with poor statistical metrics, but small errors in swelling, pointing to the need for moving beyond traditional classification-based metrics to evaluate object detection models in the context of materials domain applications.
准确量化辐照合金的肿胀对于理解反应堆中合金的性能至关重要，对于反应堆设施的安全可靠运行也至关重要。然而，典型的做法是由领域专家研究人员手动对合金的电子显微镜图像中的辐射诱导缺陷进行量化。在这里，我们采用端到端的深度学习方法，使用掩模区域卷积神经网络 (Mask R-CNN) 模型来检测和量化辐照合金中的纳米级空腔。我们已经组装了一个带有标记空腔图像的数据库，其中包括 400 张图像、超过 34k 个离散空腔以及许多合金成分和辐照条件。我们评估了模型性能的统计（精度、召回率和 F1 分数）和材料特性中心（空腔尺寸、密度和肿胀）指标，并对材料肿胀评估进行了针对性分析。我们发现，我们的模型对材料肿胀的评估具有平均（标准差）肿胀均方误差，基于随机留一交叉验证的平均（标准差）肿胀均方误差为 0.30（0.03）%。该结果表明，我们的方法可以准确地提供每幅图像和每种条件下的肿胀指标，这可以为材料设计（例如，合金细化）和服务条件（例如，温度、辐照剂量）对肿胀的影响提供有帮助的见解。最后，我们发现有些测试图像的统计指标较差，但肿胀误差较小，这表明需要超越传统的分类指标，在材料领域应用的背景下评估目标检测模型。
