【目的】针对大规模电力-交通耦合网络在遭遇突发韧性故障时，传统方案生成速度慢、难以实时响应动态信息交互，且人工智能算法在应用中易因缺乏安全机制引发电压越限等安全事故的问题，提出一种基于安全深度强化学习（safe deep reinforcement learning， SDRL）的电力-交通耦合网络韧性提升策略。【方法】首先，构建电力-交通两阶段优化架构，第一阶段以最小重构成本优先保障高价值负荷，第二阶段以最小交通调度成本优化电动汽车路径。然后，设计基于改进彩虹算法的分层决策模型。上层输出电网联络开关动作方案，并将重构后的电网状态输入下层。下层结合电网重构状态与实时交通信息，优化电动汽车路径选择，确保适配电网恢复需求。此外，嵌入拉格朗日乘子安全机制，构建含风险惩罚的目标函数，实现动态惩罚电压越限、电流越限等风险行为。【结果】基于上海实际路网与IEEE 123节点配电网的仿真表明，所提策略可显著提升系统在故障场景下的韧性与运行安全性。与混合整数规划、粒子群优化方法相比，所提方法在负荷恢复率、恢复速度、电压稳定性和策略安全性等方面均表现出更优的综合性能。【结论】所提方法证明了分层安全深度强化学习在电力-交通耦合网络韧性提升中的有效性。该方法通过两阶段架构解决了电力-交通网络目标割裂的问题，实现了计算效率、负荷恢复率与运行安全性的平衡协同。

[Objective] To address the problems that when large-scale electrification-transportation coupling network （ETCN） encounters sudden resilience faults， traditional schemes have slow generation speed， are difficult to respond to dynamic information interaction in real time， and artificial intelligence algorithms are prone to cause safety accidents such as voltage over-limit due to the lack of security mechanisms in application， this paper proposes a resilience improvement strategy for ETCN based on safe deep reinforcement learning （SDRL）. [Methods] First， the paper establishes a two-stage electrification-transportation optimization framework： the first stage prioritizes the protection of high-value loads with minimum reconfiguration cost， while the second stage optimizes electric vehicle （EV） routing with minimum traffic dispatch cost. Second， a hierarchical decision-making model based on a modified Rainbow algorithm is designed. The upper layer outputs the action plan of the power grid interconnection switch and inputs the reconstructed power grid state to the lower layer. The lower layer integrates grid reconfiguration state with real-time traffic information to optimize EV routing selection， with the objective to ensure that EV routing optimization can real-time adapt to the power grid’s recovery needs. In addition， the Lagrange multiplier safety mechanism is embedded， and an objective function with risk penalties is constructed to achieve dynamic penalties for risk behaviors such as voltage over-limit and current over-limit. [Results] Finally， the simulation based on the actual road network in Shanghai and the IEEE123-node distribution network shows that the proposed strategy can significantly enhance the resilience and operational safety of the system in fault scenarios. Compared with the mixed integer programming and particle swarm optimization methods， the method proposed in this paper demonstrates superior comprehensive performance in terms of load recovery rate， recovery speed， voltage stability and strategy security. [Conclusions] This paper verifies the effectiveness of hierarchical safe deep reinforcement learning in improving the resilience of ETCN. This method solves the problem of the separation of electrification-transportation targets through a two-stage architecture， achieving a balanced synergy among computing efficiency， load recovery rate and operational safety.