随着远距离大容量高压直流输电规模的不断增加，直流受端系统的暂态电压稳定性问题日趋严峻。量测技术与人工智能的迅速发展为解决直流受端系统的暂态电压评估问题提供了新思路。为此提出了一种基于智能增强的多二元表法来评估直流系统暂态电压。首先，通过提取直流系统暂态时序特征并利用ReliefF法进行特征降维。然后利用反向传播（back propagation，BP）神经网络对暂态电压稳定裕度指标进行回归拟合，采用改进粒子群优化（particle swarm optimization，PSO）算法求解多二元表积分权值。最后，搭建了电压崩溃模型并进行仿真验证。结果表明，所提智能增强的多二元表暂态电压评估方法对直流受端系统具有较好的准确性和适应性，具有在线应用的潜力。

With the increasing scale of long-distance and large-capacity HVDC transmission, the problem of transient voltage stability of DC receiving-end system is becoming more and more serious. The rapid development of measurement technology and artificial intelligence provides a new idea for solving the transient voltage assessment problem of DC receiving-end system. Therefore, this paper proposes a multi-binary table method based on intelligent enhancement to evaluate the transient voltage of DC system. Firstly, the feature dimension is reduced by extracting the transient time series features of the DC system and using the ReliefF method. Then, the back propagation （BP） neural network is used to perform regression fitting on the transient voltage stability margin index, and the improved particle swarm optimization （PSO） algorithm is used to solve the multi-binary table integral weights. Finally, a voltage collapse model is built and verified by simulation. The results show that the proposed intelligent enhanced multi-binary table transient voltage assessment method has good accuracy and adaptability to the DC receiving-end system, and has the potential for online application.