基于自适应增强算法的卷积神经网络单粒子翻转容错方法OA

Single-Event Upsets(SEUs)in the space radiation environment pose a serious threat to the reliability of satellite-borne intelligent systems.Traditional fault-tolerance methods such as Triple Modu-lar Redundancy(TMR)and periodic scrubbing face challenges including excessive resource overhead and high power consumption.This paper presents a lightweight fault-tolerance method based on Adaptive Boosting-based Fault-Tolerance Method(AB-FTM)to address SEU vulnerabilities in convolutional neu-ral networks.The proposed approach constructs a heterogeneous ensemble architecture comprising three weak models(ResNet20,ResNet32,ResNet44)and integrated with a dynamic weight adjustment mecha-nism.By integrating a dynamic weight adjustment mechanism,the method not only significantly re-duces the parameter scale(achieving an 18.2%reduction compared to ResNet110)but also enhances classification accuracy,robustness,and fault tolerance.Experimental validation on datasets including CI-FAR-10,MNIST,EuroSAT,and Galaxy10 DECals demonstrates that when 0.032 ‰ of parameters are affected by single-event upsets,the proposed method improves classification accuracy by 53.25%,63.49%,57.67%,and 47.43%respectively compared to the TMR-based ResNet110,significantly outperforming traditional triple modular redundancy solutions.This approach provides a novel solution for future space science satellites employing satellite-borne intelligent systems,balancing reliability,lightweight design,and computational efficiency.