摘要： 电网异构故障处置面临三元组重叠识别困难、多模态特征融合低效等挑战。针对于异构化故障信息，不同数据类型的表达差异和关联性挖掘困难增加了解决问题的复杂性。为此，提出基于对抗训练与自适应关系权重的联合优化框架(Heterogeneous knowledge graph - Adaptive weight graphical convolutional networks, HKG-AWGCN)。首先，构建电网领域本体符号，定义5类实体和8种关系，建立实体-关系的标准化映射规则。在知识抽取阶段，设计多阶段对抗训练机制。通过(BERT-BiLSTM)ATT-CRF模型提取基础三元组后，在CRF层注入FGM对抗扰动优化实体边界识别，并采用关系感知注意力模块解决重叠关系路径冲突。在知识优化阶段，提出自适应权重异构图卷积网络，通过电气参数约束的关系权重计算聚合故障传播多模态子图特征，并设计联合损失函数同步优化节点嵌入与拓扑结构。实验部分分别从时序建模性能、图结构数据处理性能、多模态特征融合性能进行对比试验，通过与BiLSTM-CRF、GraphTransformer等8类基线模型对比发现，HKG-AWGCN在准确率、召回率、F1值等核心指标上分别达到96.07%、95.58%和95.15%，为电网故障处置提供了可解释的决策支持。

Abstract: Handling heterogeneous faults in power grids faces challenges such as difficult identification of overlapping triples and inefficient multi-modal feature fusion. For heterogeneous fault information, the representation differences of different data types and the difficulty in mining correlations increase the complexity of problem-solving. Therefore, this work proposes a joint optimization framework based on adversarial training and adaptive relation weights (Heterogeneous knowledge graph-Adaptive weight graphical convolutional networks, HKG-AWGCN). First, ontological symbols in the power grid domain are constructed. Five types of entities and eight types of relations are defined, and standardized mapping rules for entity-relation are established. In the knowledge extraction stage, a multi-stage adversarial training mechanism is designed. After extracting basic triples through the (BERT-BiLSTM)ATT-CRF model, FGM adversarial perturbations are injected into the CRF layer to optimize entity boundary recognition, and a relation-aware attention module is adopted to solve the conflict of overlapping relation paths. In the knowledge optimization stage, an adaptive-weight heterogeneous graph convolutional network is proposed. Multi-modal sub-graph features of fault propagation are aggregated through relation weight calculation constrained by electrical parameters, and a joint loss function is designed to optimize node embedding and topological structure synchronously. This work conducts comparative experiments on sequential modeling performance, graph-structured data processing performance, and multi-modal feature fusion performance. By comparing with 8 types of baseline models such as BiLSTM-CRF and GraphTransformer, it is found that HKG-AWGCN reaches 96.07% in accuracy, 95.58% in recall, and 95.15% in F1-score, providing interpretable decision-making support for power grid fault handling.