Knowledge-Augmented Large Language Model-Based Intelligent Auxiliary Decision-Making for Transmission-Line Fault Handling

ZHOU Liangcai; LIU Linlin; SUN Zhihao; SHI Di; CHEN Xin

doi:null

您当前的位置：

首页 >

文章列表页 >

Knowledge-Augmented Large Language Model-Based Intelligent Auxiliary Decision-Making for Transmission-Line Fault Handling

更新时间：2026-09-04

- Knowledge-Augmented Large Language Model-Based Intelligent Auxiliary Decision-Making for Transmission-Line Fault Handling
- JOURNAL OF XI’AN JIAOTONG UNIVERSITY (2026)
- 作者机构：
  
  1.国家电网有限公司华东分部，200120，上海
  2.智博能源科技（江苏）有限公司，211300，南京
  3.西安交通大学电气工程学院，710049，西安
- 作者简介：
- 基金信息：
- DOI：
  CLC： TM771
- Received：11 July 2026，
  
  Revised：2026-08-24，
  
  Accepted：04 September 2026，
- 稿件说明：
移动端阅览
ZHOU Liangcai, LIU Linlin, SUN Zhihao, et al. Knowledge-Augmented Large Language Model-Based Intelligent Auxiliary Decision-Making for Transmission-Line Fault Handling[J]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY,2026.
DOI：

ZHOU Liangcai, LIU Linlin, SUN Zhihao, et al. Knowledge-Augmented Large Language Model-Based Intelligent Auxiliary Decision-Making for Transmission-Line Fault Handling[J]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY,2026. DOI：

摘要

针对输电线路故障处置中规程匹配效率低、历史案例关联不足，以及通用大语言模型缺乏电气机理约束、易生成不可靠建议的问题，提出一种知识增强大语言模型智能辅助决策方法。该方法在检索增强生成框架下，构建融合序分量特征、告警事件轨迹、故障处置规程和典型案例的跨模态知识库，设计物理一致性约束的混合检索评分函数，将语义相似度、电气特征相似度、元数据匹配度和故障机理一致性纳入统一相关性度量，并引入置信度感知生成机制，在证据不足或证据冲突时触发保守提示或人工复核。基于多场景输电线路故障问答样本和IEEE 39 节点系统进行验证，结果表明：Top-1和Top-3 检索命中率、故障诊断准确率、处置完整性和依据可追溯率分别达到88.6%、95.7%、94.3%、91.4% 和 94.3%，幻觉率降至2.9%；相较仅语义RAG方法，故障诊断准确率提高11.4%，幻觉率降低8.5%。该方法通过显式融合故障物理机理、规程知识和大语言模型推理能力，提高了输电线路故障处置建议的准确性、可追溯性和安全可靠性。

Abstract

To address inefficient rule matching

insufficient historical-case association

and unreliable suggestions from general large language models in transmission-line fault handling

this paper proposes a knowledge-enhanced LLM-based intelligent decision-support method. Within a retrieval-augmented generation framework

the method constructs a cross-modal knowledge base integrating sequence-component features

alarm-event trajectories

fault-handling procedures

and typical cases. A physics-consistency-constrained hybrid retrieval score is developed to jointly measure semantic similarity

electrical-feature similarity

metadata matching

and fault-mechanism consistency. A confidence-aware generation mechanism is also introduced to trigger conservative prompts or manual review when evidence is insufficient or conflicting. Validation using multi-scenario transmission-line fault question-answering samples and the IEEE 39-bus system shows that the Top-1 and Top-3 retrieval hit rates

fault-diagnosis accuracy

decision completeness

and evidence traceability reach 88.6%

95.7%

94.3%

91.4%

and 94.3%

respectively

while the hallucination rate is reduced to 2.9%. Compared with semantic-only RAG

the method improves fault-diagnosis accuracy by 11.4% and reduces the hallucination rate by 8.5%. The results demonstrate that explicitly integrating fault mechanisms

procedural knowledge

and LLM reasoning improves the accuracy

traceability

and safety reliability of transmission-line fault-handling suggestions.

关键词

Keywords

references

XIE X , ZHANG J , SUN Y , et al . A measurement-based dynamic harmonic model for single-phase diode bridge rectifier-type devices [J ] . IEEE Transactions on Instrumentation and Measurement , 2024 , 73 : 1 - 13 .

QIU W , SUN K , LI K J , et al . Cyber-attack detection: modeling and roof-PV generation system defending [J ] . IEEE Transactions on Industry Applications , 2023 , 59 ( 1 ): 160 - 168 .

SUN C , HUANG S , POMPILI D . LLM-based multi-agent decision-making: challenges and future directions [J ] . IEEE Robotics and Automation Letters , 2025 , 10 ( 6 ): 5681 - 5688 .

FANG L , XIANG W , PAN S , et al . Spatiotemporal pretrained large language model for forecasting with missing values [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 8 ): 13838 - 13850 .

赵俊华 , 文福拴 , 黄建伟 , 等 . 基于大语言模型的电力系统通用人工智能展望: 理论与应用 [J ] . 电力系统自动化 , 2024 , 48 ( 6 ): 13 - 28 .

ZHAO Junhua , WEN Fushuan , HUANG Jianwei , et al . Prospect of large language model-based artificial general intelligence for power systems: theory and application [J ] . Automation of Electric Power Systems , 2024 , 48 ( 6 ): 13 - 28 .

李刚 , 方鸿 , 刘云鹏 , 等 . 新型电力系统中的大模型驱动技术: 现状、机遇与挑战 [J ] . 高电压技术 , 2024 , 50 ( 7 ): 2864 - 2878 .

LI Gang , FANG Hong , LIU Yunpeng , et al . Large model-driven technologies in new power systems: status, opportunities and challenges [J ] . High Voltage Engineering , 2024 , 50 ( 7 ): 2864 - 2878 .

严新荣 , 高翔 , 林达 , 等 . 大模型在电力行业的应用与挑战 [J ] . 发电技术 , 2025 , 46 ( 4 ): 637 - 649 .

YAN Xinrong , GAO Xiang , LIN Da , et al . Applications and challenges of large models in the electric power industry [J ] . Power Generation Technology , 2025 , 46 ( 4 ): 637 - 649 .

CHENG Y , ZHAO H , ZHOU X , et al . GAIA: a large language model for advanced power dispatch [EB/OL ] . ( 2024-08-07 )[ 2026-06-29 ] . arXiv: 2408.03847 .

LIU J , RAHMAN A . Fault diagnosis in power grids with large language model [EB/OL ] . ( 2024-07-11 )[ 2026-06-30 ] . arXiv: 2407.08836 .

HUANG X , QI L , PAN J . A new protection scheme for MMC-based MVdc distribution systems with complete converter fault current handling capability [J ] . IEEE Transactions on Industry Applications , 2019 , 55 ( 5 ): 4515 - 4523 .

KOSYANCHUK V , SELVESYUK N , ZYBIN E , et al . Application of a deterministic optical network model for the implementation of an expert system knowledge base for information transmission failure management [J ] . Engineering Proceedings , 2023 , 33 ( 1 ): 51 .

边莉 , 边晨源 . 电网故障诊断的智能方法综述 [J ] . 电力系统保护与控制 , 2014 , 42 ( 3 ): 146 - 153 .

BIAN Li , BIAN Chenyuan . Review of intelligent methods for power grid fault diagnosis [J ] . Power System Protection and Control , 2014 , 42 ( 3 ): 146 - 153 .

王守鹏 , 赵冬梅 . 电网故障诊断的研究综述与前景展望 [J ] . 电力系统自动化 , 2017 , 41 ( 8 ): 1 - 12 .

WANG Shoupeng , ZHAO Dongmei . Review and prospect of power grid fault diagnosis [J ] . Automation of Electric Power Systems , 2017 , 41 ( 8 ): 1 - 12 .

LI W , DEKA D , CHERTKOV M , et al . Real-time faulted line localization and PMU placement in power systems through convolutional neural networks [J ] . IEEE Transactions on Power Systems , 2019 , 34 ( 6 ): 4640 - 4651 .

蒲天骄 , 谈元鹏 , 彭国政 , 等 . 电力领域知识图谱的构建与应用 [J ] . 电网技术 , 2021 , 45 ( 6 ): 2080 - 2091 .

PU Tianjiao , TAN Yuanpeng , PENG Guozheng , et al . Construction and application of knowledge graph in the electric power field [J ] . Power System Technology , 2021 , 45 ( 6 ): 2080 - 2091 .

郭榕 , 杨群 , 刘绍翰 , 等 . 电网故障处置知识图谱构建研究与应用 [J ] . 电网技术 , 2021 , 45 ( 6 ): 2092 - 2100 .

GUO Rong , YANG Qun , LIU Shaohan , et al . Research and application of knowledge graph construction for power grid fault handling [J ] . Power System Technology , 2021 , 45 ( 6 ): 2092 - 2100 .

乔骥 , 王新迎 , 闵睿 , 等 . 面向电网调度故障处理的知识图谱框架与关键技术初探 [J ] . 中国电机工程学报 , 2020 , 40 ( 18 ): 5837 - 5848 .

QIAO Ji , WANG Xinying , MIN Rui , et al . Preliminary study on knowledge graph framework and key technologies for power grid dispatching fault handling [J ] . Proceedings of the CSEE , 2020 , 40 ( 18 ): 5837 - 5848 .

叶欣智 , 尚磊 , 董旭柱 , 等 . 面向配电网故障处置的知识图谱研究与应用 [J ] . 电网技术 , 2022 , 46 ( 8 ): 3739 - 3749 .

YE Xinzhi , SHANG Lei , DONG Xuzhu , et al . Research and application of knowledge graph for distribution network fault handling [J ] . Power System Technology , 2022 , 46 ( 8 ): 3739 - 3749 .

谢庆 , 蔡扬 , 谢军 , 等 . 基于ALBERT的电力变压器运维知识图谱构建方法与应用研究 [J ] . 电工技术学报 , 2023 , 38 ( 1 ): 95 - 107 .

XIE Qing , CAI Yang , XIE Jun , et al . Construction method and application of operation and maintenance knowledge graph for power transformers based on ALBERT [J ] . Transactions of China Electrotechnical Society , 2023 , 38 ( 1 ): 95 - 107 .

CHEN Q , LI Q , WU J , et al . Application of knowledge graph in power system fault diagnosis and disposal: a critical review and perspectives [J ] . Frontiers in Energy Research , 2022 , 10 : 988280 .

BOURNE K , ES S . Unlocking data with generative AI and RAG: enhance generative AI systems by integrating internal data with large language models using RAG [M ] . Birmingham : Packt Publishing , 2024 .

LEWIS P , PEREZ E , PIKTUS A , et al . Retrieval-augmented generation for knowledge-intensive NLP tasks [C ] // Advances in Neural Information Processing Systems . Red Hook : Curran Associates Inc. , 2020 : 9459 - 9474 .

GAO Y , XIONG Y , GAO X , et al . Retrieval-augmented generation for large language models: A survey [EB/OL ] . ( 2023-12-18 )[ 2026-06-30 ] . arXiv: 2312.10997 .

BARNETT S , KURNIAWAN S , THUDUMU S , et al . Seven failure points when engineering a retrieval augmented generation system [C ] // Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI . New York : ACM , 2024 . DOI: 10.1145/3644815.3644945 http://dx.doi.org/10.1145/3644815.3644945 .

CASCIANI A , BERNARDI L M , CIMITILE M , et al . Enhancing next activity prediction in process mining with retrieval-augmented generation [J ] . Information Systems , 2026 , 137 : 102642 .

N M A , H S , J F , et al . Fault analysis and circuit breakers selection for electrical lines protection: case of electrical line from Lutchurukuru to Kindu (D. R. Congo) [J ] . International Journal of Computer Science, Engineering and Applications , 2025 , 15 ( 5 ): 21 - 34 .

JONAS S , MEYER A . Fault detection in new wind turbines with limited data by generative transfer learning [J ] . Energy and AI , 2025 , 22 : 100626 .

ROYCHOWDHURY R , WU X , ILLINDALA S M . Delay-structured noise robust dynamic mode decomposition for power system modal estimation with faulty PMU data [J ] . Sustainable Energy, Grids and Networks , 2025 , 44 : 102029 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Binocular Vision-Based Synchronous Measurement Method for Rotational Errors

Study on Electrothermal Characteristics of Dendrite-Induced Internal Short Circuit in Lithium-Ion Batteries

Performance of a Compression Heat Pump for Waste Heat Recovery from Gas-Fired Boiler Flue Gas

Construction and Parameter Identification of a Viscoelastic Constitutive Model for Power Transformer Insulation Spacers

Phase-Field Analysis Method for the Reliability of High-g Micro-Electro-Mechanical System Accelerometers

Related Author

No data

Related Institution

No data

⁰