A Proton Irradiation Damage Compact Model of HfO x /TiO x Heterojunction Memristive Synapses for Hardening Design of Convolutional Neural Network Hardware

IEEE Transactions on Electron Devices 2026

View at publisher
Authors: Shengju Yin, Hongjia Song, Chuan Ma, Jiaqi Yan, chenfeng Lin, Jinbin Wang, Xiangli Zhong
DOI: 10.1109/ted.2026.3663336
Cited by: 0
References: 32

Abstract

Memristive neural network hardware shows great potential for Space applications thanks to its high efficiency, low power, high integration, and radiation tolerance. Yet no memristor model captures the influence of irradiation effects on its conductance update behavior, impeding the radiation-hardening design of memristive neural network hardware. This article presents a proton irradiation damage compact model of memristive synapses. Simulations of$I$–$V$curves and conductance-update linearity agree with experiment within an rms error

Fields of Study & Subjects

Advanced Memory and Neural Computing Radiation Effects in Electronics Ferroelectric and Negative Capacitance Devices

Publication details

Journal / source
IEEE Transactions on Electron Devices
Volume
73
Issue
4
Pages
2352–2359
Publication date
5 March 2026
Language
EN