针对机器学习技术的固有不确定输出特性给航空器适航安全性定量评估造成的挑战，在SAE ARP4761标准框架下，基于条件高斯PAC-Bayes泛化理论提出一种面向卷积神经网络（CNN）分类功能的系统安全性评估方法。首先，基于PAC-Bayes理论，通过条件高斯分布改进训练方法，优化泛化界，获取CNN模型不确定性量化表示。其次，提出一种基于泛化界置信度的软件不确定性与硬件可靠性融合方法，获取CNN部件的综合失效基础数据，支持整机/系统的定量安全性评估。最后，以基于CNN的全球导航卫星系统干扰信号识别模块装机为案例，表明该方法对适航安全性评估的有效支撑作用，为CNN技术的装机应用提供了必要的适航符合性保证。同时也实验验证基于条件高斯的方法比标准PAC-Bayes及Vapnik-Chervonenkis维都具有更紧的计算边界。

To address the airworthiness safety challenges caused by inherent uncertainty outputs of machine learning technology in airborne systems， a system safety assessment method based on the generalization theory is proposed for CNN classification under the framework of SAE ARP4761standards. First， based on the PAC-Bayes theory， the training method is improved through conditional gaussian process to optimize the generalization bound and obtain a quantified representation of the uncertainty of the CNN model. Second， an integration method for software uncertainty and hardware reliability based on generalization bound confidence is proposed to obtain comprehensive failure basic data of CNN components， supporting quantitative safety assessment of the aircraft/system. Finally， taking the airborne GNSS interference signal recognition module based on CNN as a case， the proposed method is shown to be effective in safety assessment， and is also experimentally verified that the generalization boundary based on conditional gaussian process has a tighter computational boundary than that of ordinary PAC-Bayes and Vapnik-Chervonenkis dimensions.