一个基于焦点注意力的大型卷积内核网络,用于检测涂层燃料颗粒的异常
Zhaochuan Hu1, Jiang Yu1, Hang Zhang1,2
1State Key Laboratory of Advanced Design and Manufacture for Vehicle Body, Hunan University, Changsha 410082, China.
Sensors (Basel, Switzerland)
|September 19, 2025
概括
本研究引入了一种先进的检测框架,用于识别高温气冷反应堆中的异常燃料颗粒. 新方法通过更好地处理边缘异常和微妙特征,显著提高了准确性,提高了反应堆的安全性.
科学领域:
- 核工程 核工程是指核工程.
- 材料科学 材料科学 材料科学
- 计算机视觉 计算机视觉
背景情况:
- 精确测量燃料颗粒的涂层厚度对于高温气冷反应堆 (HTGR) 的安全至关重要.
- 现有的检测技术在准确性,效率和自动化方面扎,特别是在鉴定由于边缘效应和弱形态特征的异常颗粒方面.
研究的目的:
- 开发一种创新的检测框架,用于准确识别异常燃料颗粒.
- 克服当前处理不完整粒子和微妙异常的方法的局限性.
主要方法:
- 提出了一个基于焦点关注的大型卷积内核网络检测框架.
- 使用视觉变压器骨干与适应性受体场的大型选择性内核模块.
- 实现了多级特征融合模块,用于跨层交互,以及焦点注意模块,用于增强突出表示.
主要成果:
- 提出的方法显著降低了错误检测率到1.96%.
- 通过增强异常检测,错误检测率降至1.9%.
- 证明了对边缘异常和弱形态特征的改进处理.
结论:
- 基于焦点关注的大型卷积内核网络框架有效地增强了对异常燃料颗粒的检测.
- 这种方法可以提高关键反应堆组件的测量精度和自动化.
- 该方法为确保高强度电压电路安全运行提供了一个有前途的解决方案.
相关概念视频
01:10Detection of Black Holes
2.5K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.5K
01:05Difference from Background: Limit of Detection
8.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.0K