极端天气下城市新型电力系统风险评估方法研究

刘畅; 孙秋洁; 张新伟; 李鹏; 周辉; 张思航; 李军辉

doi:10.13637/j.issn.1009-6094.2025.120310.13637/j.issn.1009-6094.2025.1203

Chinese

您当前的位置：

首页 >

文章列表页 >

极端天气下城市新型电力系统风险评估方法研究

安全评价安全工程 | 更新时间：2026-04-17

- 极端天气下城市新型电力系统风险评估方法研究
- 极端天气下城市新型电力系统风险评估方法研究
- 安全与环境学报 2026年26卷第4期页码：1255-1265
- 作者机构：
  
  1. 国网电力工程研究院有限公司
  2. 国网浙江省电力有限公司经济技术研究院
  3. 清华大学安全科学学院
  4. 国网浙江省电力有限公司金华供电公司
- 作者简介：
- 基金信息：
  
  国家电网公司总部科技项目(5100-202319017A-1-1-ZN)
- DOI：10.13637/j.issn.1009-6094.2025.120310.13637/j.issn.1009-6094.2025.1203
  中图分类号： TM73;P429
- 纸质出版：2026
- 稿件说明：
移动端阅览
[1]刘畅,孙秋洁,张新伟,等.极端天气下城市新型电力系统风险评估方法研究[J].安全与环境学报,2026,26(04):1255-1265.
[1]刘畅,孙秋洁,张新伟,等.极端天气下城市新型电力系统风险评估方法研究[J].安全与环境学报,2026,26(04):1255-1265. DOI： 10.13637/j.issn.1009-6094.2025.120310.13637/j.issn.1009-6094.2025.1203.

DOI：10.13637/j.issn.1009-6094.2025.1203.

摘要

随着新能源占比持续提升，叠加台风、强降雨等极端天气影响，城市新型电力系统面临多重安全风险辨识及量化评估难题，传统的风险评估方法在应对多重风险协同作用及耦合加剧的量化分析方面存在局限性，因此，提出了一种知识图谱与PageRank算法结合的极端天气下城市新型电力系统风险评估方法。首先，以极端天气引发的城市新型电力系统故障事故案例为数据源，基于规则与深度学习的知识抽取方式对事故案例进行知识抽取，并借助Neo4j构建包含“灾害类型、事故类型、故障类型、事故部位、事故后果”五类属性的风险知识图谱。随后，结合PageRank算法与介数中心性指标，分析了城市新型电力系统风险知识图谱中的关键风险节点。结果表明：在案例事故类型中，设备本体损坏的PageRank值为1.025 5、介数中心性为669.07

两项指标均处于高位表明该事故影响范围广泛，且在风险演化过程中处于关键路径；故障类型中，断线的介数中心性相对较高(为32.05)

而PageRank值相对较低(为0.294 3)

表明该故障发生概率较低但具备高传播影响力。同时架空线路是新型电力系统中较容易发生故障的部位，应加强该环节的状态监测并根据极端天气强度提升线路的抗灾能力。

Abstract

As the proportion of new energy sources continues to rise

the power system faces significant uncertainties in generation

transmission

load

and storage. Coupled with the impact of extreme weather events such as typhoons and heavy rainfall

new urban power systems encounter multiple challenges in identifying and quantitatively assessing risks. Traditional risk assessment methods are limited in their ability to analyze multiple risks and their interconnections quantitatively. Therefore

this paper proposes a risk assessment method for new urban power systems under extreme weather conditions by combining knowledge graphs with the PageRank algorithm. First

case studies of power system failures due to extreme weather serve as the data source for knowledge extraction

utilizing a combination of rule-based and deep learning approaches. A risk knowledge graph is then constructed using Neo4j

incorporating five types of attributes: ‘disaster type'

‘failure type'

‘accident type'

‘accident location'

and ‘accident consequences'. Next

the PageRank algorithm and degree centrality metrics are employed to analyze key risk nodes within the urban power system's risk knowledge graph. In the case of accident types

the PageRank value for equipment body damage is 1.025 5

and the betweenness centrality is 669.07. Both indicators being high suggests that the impact of this accident is widespread and that it lies on a critical path in the risk evolution process. Among failure types

the betweenness centrality for disconnection is relatively high at 32.05

while the PageRank value is relatively low at 0.294 3

indicating that this fault has a low probability of occurrence but possesses high propagation influence. Additionally

overhead lines emerge as the most critical failure points in the new power system. Therefore

enhancing the monitoring of transmission line status and improving their disaster resistance capabilities are essential.

关键词

Keywords

references

盛伟，关城，张苏，等.基于情景相似的电网企业台风灾害应急决策[J].中国安全科学学报，2023,33(11):174-180.SHENG W,GUAN C,ZHANG S,et al.Research on typhoon disaster emergency decision-making of power grid enterprises based on similar scenarios[J].China Safety Science Journal,2023,33(11):174-180.

蔡新雷，董锴，孟子杰，等.考虑源荷可调节资源参与的电网风险评估指标体系及方法[J].广东电力，2024,37(1):27-38.CAI X L,DONG K,MENG Z J,et al.Index system and method of power grid risk assessment with participation of adjustable source and load resource[J].Guangdong Electric Power,2024,37(1):27-38.

刘文霞，刘佳怡，万海洋，等.面向多类型极端天气的新型电力系统规划方案全场景风险评估[J].电力系统自动化，2025,49(4):65-78.LIU W X,LIU J Y,WAN H Y,et al.Full-scenario risk assessment of new power system planning scheme for multiple types of extreme weather[J].Automation of Electric Power Systems,2025,49(4):65-78.

王东，王佳琪，陈红，等.基于贝叶斯网络的我国电网安全风险关联分析[J].安全与环境学报，2021,21(5):1947-1956.WANG D,WANG J Q,CHEN H,et al.Correlation analysis of the safety risks in China's power grid based on the Bayesian network[J].Journal of Safety and Environment,2021,21(5):1947-1956.

邱刚，高超，陈杰，等.架空输电线路雷击跳闸风险评估方法研究[J].机械设计与制造，2025(2):99-102,108.QIU G,GAO C,CHEN J,et al.Research on the risk assessment method of lightning tripping for overhead transmission lines[J].Machinery Design & Manufacture,2025(2):99-102,108.

王明达，李云飞，张榜，等.危险货物道路运输安全管理知识图谱的构建[J].安全与环境学报，2022,22(6):3197-3207.WANG M D,LI Y F,ZHANG B,et al.Study on construction of safety management knowledge graph for road transport of dangerous goods[J].Journal of Safety and Environment,2022,22(6):3197-3207.

GLAVAŠ G,ŠNAJDER J.Construction and evaluation of event graphs[J].Natural Language Engineering,2015,21(4):607-652.

HUO X S,YIN Y A,JIAO L D,et al.A data-driven and knowledge graph-based analysis of the risk hazard coupling mechanism in subway construction accidents[J].Reliability Engineering & System Safety,2024,250:110254.

王晶晶，罗兰君，安天成，等.知识图谱在应急管理领域应用研究综述[J].中国安全生产科学技术，2025,21(4):189-194.WANG J J,LUO L J,AN T C,et al.Review on application of knowledge graph in field of emergency management[J].Journal of Safety Science and Technology,2025,21(4):189-194.

尚明远，罗锋，魏艳霞，等.基于深度学习和知识图谱的变电站设备故障智能诊断[J].电气自动化，2024,46(6):100-102,105.SHANG M Y,LUO F,WEI Y X,et al.Intelligent diagnosis of substation equipment faults based on deep learning and knowledge graph[J].Electrical Automation,2024,46(6):100-102,105.

饶桐，龚泽威一，于虹，等.知识图谱在输变电设备运维中的应用[J].电网与清洁能源，2024,40(6):91-96,106.RAO T,GONG Z W Y,YU H,et al.Application of knowledge graph in operation and maintenance of power transmission equipment[J].Power System and Clean Energy,2024,40(6):91-96,106.

田波，张越，蒙飞，等.电网故障处置信息自适应理解框架及关键技术[J].中国电力，2024,57(7):188-195.TIAN B,ZHANG Y,MENG F,et al.Adaptive understanding framework and key technology of power grid fault disposal information[J].Electric Power,2024,57(7):188-195.

王晶，王琼，周永博，等.面向电力物联网调度任务的分布式知识图谱[J].无线电通信技术，2023,49(3):432-437.WANG J,WANG Q,ZHOU Y B,et al.Union of distributed knowledge maps for power internet of things[J].Radio Communications Technology,2023,49(3):432-437.

蒲昊苒，阴艳超，徐成现.维修知识图谱与深度学习网络在发动机故障智能推理中的应用[J].机械科学与技术，2025,44(2):225-235.PU H R,YIN Y C,XU C X.Study on maintenance knowledge graph and deep learning network in intelligent reasoning of engine fault[J].Mechanical Science and Technology for Aerospace Engineering,2025,44(2):225-235.

余建明，单连飞，皮俊波，等.基于知识图谱的故障处置预案解析方法[J].电气自动化，2023,45(2):75-78.YU J M,SHAN L F,PI J B,et al.Analysis method of fault handling plan based on knowledge graph[J].Power System & Automation,2023,45(2):75-78.

XIAO N,PENG B,LI X,et al.Research on the construction and implementation of power grid fault handling knowledge graphs[J].Energy Reports,2023,9:182-189.

JI Z X,WANG X H,ZHANG J,et al.Construction and application of knowledge graph for grid dispatch fault handling based on pre-trained model[J].Global Energy Interconnection,2023,6(4):493-504.

ZHENG S M,LIU Z S,YU Y T,et al.A quality evaluation method for the unstructured defect record of relay protection devices based on ontology and knowledge graph[J].Energy Reports,2023,9(7):771-781.

LUAN T T,LI H R,WANG K,et al.Knowledge graph-based Bayesian network risk assessment model for hydrogen accidents[J].International Journal of Hydrogen Energy,2024,81:927-941.

CHEN J H,ZHUANG C L,SHI J,et al.Risk factors extraction and analysis of Chinese ship collision accidents based on knowledge graph[J].Ocean Engineering,2025,322:120536.

陶希东.建设韧性城市：应对极端气候的重要策略[J].人民论坛，2023(15):62-65.TAO X D.Building resilient cities:a key strategy for coping with climate extremes [J].People's Forum,2023(15):62-65.

林伟芳，易俊，郭强，等.阿根廷“6·16”大停电事故分析及对中国电网的启示[J].中国电机工程学报，2020,40(9):2835-2842.LIN W F,YI J,GUO Q,et al.Analysis on blackout in Argentine power grid on June 16,2019 and its enlightenment to power grid in China[J].Proceedings of the CSEE,2020,40(9):2835-2842.

王国春，董昱，许涛，等.巴西“8·15”大停电事故分析及启示[J].中国电机工程学报，2023,43(24):9461-9470.WANG G C,DONG Y,XU T,et al.Analysis and lessons of Brazil blackout event on August 15[J].Proceedings of the CSEE,2023,43(24):9461-9470.

曾辉，孙峰，李铁，等.澳大利亚“9·28”大停电事故分析及对中国启示[J].电力系统自动化，2017,41(13):1-6.ZENG H,SUN F,LI T,et al.Analysis of “9.28” blackout in south Australia and its enlightenment to China[J].Automation of Electric Power Systems,2017,41(13):1-6.

刘浩，徐晴晴，张来斌，等.极端天气条件下风电机组事故演化知识图谱的构建及分析[J].中国安全生产科学技术，2024,20(10):5-11.LIU H,XU Q Q,ZHANG L B,et al.Construction and analysis of knowledge graph for wind turbine accident evolution under extreme weather conditions[J].Journal of Safety Science and Technology,2024,20(10):5-11.

周义棋，刘畅，龙增，等.电网应急预案知识图谱构建方法与应用[J].中国安全生产科学技术，2023,19(1):5-13.ZHOU Y Q,LIU C,LONG Z,et al.Construction method and application of knowledge graph in emergency plans for power grid[J].Journal of Safety Science and Technology,2023,19(1):5-13.

戴志辉，张富泽，张近月，等.基于MacBERT-BiLSTM-CRF模型的继电保护装置缺陷知识图谱构建方法[J].电力系统保护与控制，2024,52(20):131-143.DAI Z H,ZHANG F Z,ZHANG J Y,et al.Construction method of a defect knowledge map of a relay protection device based on a Mac BERT-BiLSTM-CRF model[J].Power System Protection and Control,2024,52(20):131-143.

陈述，王典学，杨应柳，等.水电工程施工安全隐患语义匹配模型[J].中国安全科学学报，2024,34(12):40-47.CHEN S,WANG D X,YANG Y L,et al.Semantic matching model of potential safety hazards in hydroelectric project construction[J].China Safety Science Journal,2024,34(12):40-47.

浏览量

544

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

航空器维修安全风险因素关联性分析

交叉口右转车-行人交互轨迹预测与风险评估

安全政策知识图谱的构建与推理技术

文本挖掘-模糊层次分析在风险评估中的耦合应用研究

加氢站泄漏动态分析及降低泄漏风险措施