Supervised Deep Learning and Classification of Single-Event Transients
Supervised Deep Learning and Classification of Single-Event Transients
复制标题
DOI：
10.1109/tns.2023.3268987
复制
发表时间：
2023-08
影响因子：
1.8
通讯作者：
T. Peyton;J. L. Carpenter;S. Camp;M. Fadul;B. Dean;D. Reising;T. D. Loveless
中科院分区：
文献类型：
--
作者：
T. Peyton;J. L. Carpenter;S. Camp;M. Fadul;B. Dean;D. Reising;T. D. Loveless
本文介绍了一种方法来检测和分类单粒子瞬态（SET），以确定电离辐射影响的起源电路节点。SET是通过双光子吸收（TPA）激光激发在一个定制的CMOS锁相环（PLL）上测量的，卷积神经网络（CNN）被用来对瞬态响应的空间依赖性进行分类。一个聚类技术被描述为识别相关的电路节点的组，并达到90%以上的识别准确率。
This article describes a method to detect and classify single-event transients (SETs) to determine the originating circuit node impacted by ionizing radiation. SETs were measured via two-photon absorption (TPA) laser excitation on a custom CMOS phase-locked loop (PLL), and convolutional neural networks (CNNs) were used to classify the spatial dependencies of the transient responses. A clustering technique is described to identify the groups of related circuit nodes and achieves over 90% identification accuracy.