1.南京南自华盾数字技术有限公司,江苏省南京市 320100
2.南京航空航天大学MBA教育中心,江苏省南京市 320100
吴翰林(1996—),男,通信作者,硕士,工程师,主要研究方向:电力信息化及系统规划设计。E-mail:nuaawhl@nuaa.edu.cn
周海春(1984—),男,工程师,主要研究方向:电力信息化及系统规划设计。E-mail:nuaawhl@nuaa.edu.cn
王腾(1989—),男,工程师,主要研究方向:电力信息化及系统规划设计。E-mail:nuaawhl@nuaa.edu.cn
收稿:2026-01-08,
修回:2026-04-22,
网络首发:2026-06-24,
纸质出版:2026-09-25
移动端阅览
吴翰林,周海春,王腾等.面向海上风电的知识图谱与小样本学习融合式智能运维设计[J].电力系统自动化,2026,50(18):176-190.
WU Hanlin,ZHOU Haichun,WANG Teng,et al.Design of Intelligent Operation and Maintenance Integrating Knowledge Graph and Few-shot Learning for Offshore Wind Power[J].Automation of Electric Power Systems,2026,50(18):176-190.
吴翰林,周海春,王腾等.面向海上风电的知识图谱与小样本学习融合式智能运维设计[J].电力系统自动化,2026,50(18):176-190. DOI: 10.7500/AEPS20260108003.
WU Hanlin,ZHOU Haichun,WANG Teng,et al.Design of Intelligent Operation and Maintenance Integrating Knowledge Graph and Few-shot Learning for Offshore Wind Power[J].Automation of Electric Power Systems,2026,50(18):176-190. DOI: 10.7500/AEPS20260108003.
为解决海上风电运维场景中多模态数据融合不足、样本数据稀疏等问题,提出一种知识图谱与小样本学习深度融合的技术方案,重点解决海上风电领域知识组织、小样本实体识别及知识补全难题。首先,构建“环境-设备-故障-运维”4维海上风电知识图谱,实现异构数据的系统化组织;其次,设计元学习与对比自监督学习融合框架,拆解出故障诊断、操作指导、信息查询、环境关联及综合信息5类查询意图子任务,结合对比损失函数优化特征表征,提升小样本场景下的实体识别能力;再次,引入边标记图神经网络,显式建模实体间语义关系、相似度及置信度等边特征,通过迭代更新节点与边特征实现知识图谱缺失实体的加权投票补全;最后,建立基于知识图谱的闭环迭代机制,保障知识匹配精度与模型泛化性能。实验结果表明,在小样本数据条件下,所提技术方案相比于传统方法的实体识别准确率、关联补全性能和查询重写准确率均有较大提升,为海上风电领域知识工程构建提供了技术支撑。
To address the challenges of insufficient multi-modal data fusion and sparse sample data in offshore wind power operation and maintenance scenarios
this paper proposes a technical scheme that deeply integrates knowledge graph and few-shot learning
focusing on resolving the key problems of knowledge organization
few-shot entity recognition
and knowledge completion in the offshore wind power field. Firstly
a four-dimensional offshore wind power knowledge graph encompassing environment
equipment
fault
and operation and maintenance is constructed to achieve systematic organization of heterogeneous data. Secondly
a integrated framework combining meta-learning and contrastive self-supervised learning is designed
which decomposes query intentions into five sub-tasks: fault diagnosis
operational guidance
information retrieval
environmental correlation
and comprehensive information. A contrastive loss function is employed to optimize feature representations
thereby enhancing entity recognition capability in few-shot scenarios. Thirdly
an edge-labeled graph neural network is introduced to explicitly model edge features such as semantic relations
similarity
and confidence between entities. Through iterative updating of node and edge features
weighted voting-based completion of missing entities in the knowledge graph is achieved. Finally
a closed-loop iterative mechanism based on the knowledge graph is established to ensure knowledge matching accuracy and model generalization performance. Experimental results demonstrate that
under few-shot data conditions
the proposed technical scheme achieves significant improvements in entity recognition accuracy
association completion performance
and query rewriting accuracy over traditional methods
providing technical support for knowledge engineering in the offshore wind power field.
熊仁树 . 新政策背景下的海上风电运维管理创新研究 [J]. 风能 , 2026 ( 1 ): 80 - 83 .
Xiong Renshu . Research on innovation of offshore wind power operation and maintenance management under the new policy background [J]. Wind Energy , 2026 ( 1 ): 80 - 83 .
房方 , 梁栋炀 , 刘亚娟 , 等 . 海上风电智能控制与运维关键技术 [J]. 发电技术 , 2022 , 43 ( 2 ): 175 - 185 .
Fang Fang , Liang Dongyang , Liu Yajuan , et al . Key technologies for intelligent control and operation and maintenance of offshore wind power [J]. Power Generation Technology , 2022 , 43 ( 2 ): 175 - 185 .
杨廷志 , 姜巍 , 罗友竣 . 基于多源数据融合的海上风电智慧运维技术研究 [J]. 水电与新能源 , 2024 , 38 ( 6 ): 28 - 31 .
Yang Tingzhi , Jiang Wei , Luo Youjun . Intelligent operation and maintenance technology for offshore wind power projects based on multi-source data fusion [J]. Hydropower and New Energy , 2024 , 38 ( 6 ): 28 - 31 .
李鹏 , 余涛 , 李立浧 , 等 . 电力人工智能的演变与展望——从专业智能走向通用智能 [J]. 电力系统自动化 , 2024 , 48 ( 16 ): 1 - 17 .
Li Peng , Yu Tao , Li Licheng , et al . Retrospect and prospect of artificial intelligence for electric power system — from domain intelligence to general intelligence [J]. Automation of Electric Power Systems , 2024 , 48 ( 16 ): 1 - 17 .
徐荣 , 郭冲 , 王均平 , 等 . 海上风电供电主设备状态评估与决策系统 [J]. 电工技术 , 2024 ( 24 ): 250 - 253 .
Xu Rong , Guo Chong , Wang Junping , et al . Condition assessment and decision system for main power supply equipment of offshore wind power [J]. Electric Engineering , 2024 ( 24 ): 250 - 253 .
肖凯敏 . 基于区块链的海上风电运维决策系统研究 [D]. 广州 : 广东工业大学 , 2023 .
Xiao Kaimin . Research on offshore wind power operation and maintenance decision system based on blockchain [D]. Guangzhou : Guangdong University of Technology , 2023 .
陈金路 , 张翔宇 , 郑向远 , 等 . 海上风电智能运维关键技术与发展建议 [J]. 海洋开发与管理 , 2023 , 40 ( 6 ): 117 - 128 .
Chen Jinlu , Zhang Xiangyu , Zheng Xiangyuan , et al . Key technologies and development suggestions for intelligent operation and maintenance of offshore wind power [J]. Ocean Development and Management , 2023 , 40 ( 6 ): 117 - 128 .
廖志伟 , 黄泽昇 , 闵文龙 , 等 . 考虑多级时间窗的海上风电机群柔性维护策略 [J/OL]. 电力系统自动化 , 2026-01-28 . https://link.cnki.net/urlid/32.1180.TP.20260127.1720.002 https://link.cnki.net/urlid/32.1180.TP.20260127.1720.002 .
Liao Zhiwei , Huang Zesheng , Min Wenlong , et al . Flexible maintenance strategy for offshore wind turbine clusters considering multi-level time windows [J/OL]. Automation of Electric Power Systems , 2026-01-28 . https://link.cnki.net/urlid/32.1180.TP.20260127.1720.002 https://link.cnki.net/urlid/32.1180.TP.20260127.1720.002 .
樊启祥 , 刘鑫 , 闫姝 , 等 . 全生命周期海上风电智能闭环控制技术创新实践 [J]. 新型电力系统 , 2025 , 3 ( 2 ): 200 - 213 .
Fan Qixiang , Liu Xin , Yan Shu , et al . Innovation and practice of the whole life cycle of offshore wind power based on the intelligent closed-loop control technology [J]. New Type Power Systems , 2025 , 3 ( 2 ): 200 - 213 .
陈亮 , 阳熹 , 杨源 . 智慧海上风电场的定义、架构体系和建设路径 [J]. 南方能源建设 , 2020 , 7 ( 3 ): 62 - 69 .
Chen Liang , Yang Xi , Yang Yuan . Definition, architecture and constructive route of intelligent offshore wind farm [J]. Southern Energy Construction , 2020 , 7 ( 3 ): 62 - 69 .
王艳新 , 闫静 , 王建华 , 等 . 基于多级二阶注意力孪生网络的小样本GIS局部放电诊断方法 [J]. 电工技术学报 , 2023 , 38 ( 8 ): 2255 - 2264 .
Wang Yanxin , Yan Jing , Wang Jianhua , et al . Few-shot GIS partial discharge diagnosis method based on multi-level second-order attention siamese network [J]. Transactions of China Electrotechnical Society , 2023 , 38 ( 8 ): 2255 - 2264 .
杨博 , 陈义军 , 姚伟 , 等 . 基于新一代人工智能技术的电力系统稳定评估与决策综述 [J]. 电力系统自动化 , 2022 , 46 ( 22 ): 200 - 223 .
Yang Bo , Chen Yijun , Yao Wei , et al . Review of power system stability assessment and decision-making based on new generation artificial intelligence technology [J]. Automation of Electric Power Systems , 2022 , 46 ( 22 ): 200 - 223 .
吴翰林 , 张洁 , 张骞 . 基于知识图谱的电力运维智能问答系统设计 [J]. 电力大数据 , 2025 , 28 ( 8 ): 46 - 57 .
Wu Hanlin , Zhang Jie , Zhang Qian . Design of intelligent question answering system for power operation and maintenance based on knowledge graph [J]. Power Systems and Big Data , 2025 , 28 ( 8 ): 46 - 57 .
陈俊宇 . 面向小样本场景的知识图谱问答方法研究 [D]. 成都 : 电子科技大学 , 2025 .
Chen Junyu . Research on knowledge graph question answering method for few-shot scenario [D]. Chengdu : University of Electronic Science and Technology of China , 2025 .
吴月秀 . 海上风电场运维资源调度优化研究 [D]. 天津 : 天津理工大学 , 2024 .
Wu Yuexiu . Research on optimization of operation and maintenance resource scheduling for offshore wind farms [D]. Tianjin : Tianjin University of Technology , 2024 .
朱玲芬 . 基于大数据的海上风电运维船舶智能调度研究 [J]. 科技视界 , 2026 , 16 ( 1 ): 30 - 32 .
Zhu Lingfen . Research on intelligent scheduling of offshore wind power operation and maintenance ships based on big data [J]. Science & Technology Vision , 2026 , 16 ( 1 ): 30 - 32 .
叶新红 . 海上风电智能运维技术的创新与实践 [J]. 中国高新科技 , 2025 ( 19 ): 71 - 72 .
Ye Xinhong . Innovation and practice of intelligent operation and maintenance technology for offshore wind power [J]. China High-Tech , 2025 ( 19 ): 71 - 72 .
樊启祥 , 林鹏 , 王鑫 , 等 . 海上风电全生命期资产闭环智慧管理方法及应用 [J]. 清华大学学报(自然科学版) , 2026 , 66 ( 4 ): 796 - 809 .
Fan Qixiang , Lin Peng , Wang Xin , et al . Closed-loop intelligent asset management method and application for full-life cycle offshore wind power [J]. Journal of Tsinghua University (Science and Technology) , 2026 , 66 ( 4 ): 796 - 809 .
刘岚 , 吴垠峰 , 秦小健 , 等 . 海上风电运维的技术现状及发展趋势 [J]. 中国水运 , 2022 , 22 ( 24 ): 47 - 49 .
Liu Lan , Wu Yinfeng , Qin Xiaojian , et al . Technical status and development trend of offshore wind power operation and maintenance [J]. China Water Transport , 2022 , 22 ( 24 ): 47 - 49 .
马佳星 , 肖石 , 朱永飞 , 等 . 人工智能在海上风电运维中的自主决策与智能化管理研究 [J]. 电气技术与经济 , 2024 ( 10 ): 236 - 237 .
Ma Jiaxing , Xiao Shi , Zhu Yongfei , et al . Research on autonomous decision-making and intelligent management of artificial intelligence in offshore wind power operation and maintenance [J]. Electrical Equipment and Economy , 2024 ( 10 ): 236 - 237 .
张禹方 , 袁之康 , 高硕杰 , 等 . 基于跨模态数据的变压器套管故障知识图谱构建与应用 [J]. 中国电机工程学报 , 2025 , 45 ( 22 ): 9064 - 9074 .
Zhang Yufang , Yuan Zhikang , Gao Shuojie , et al . Construction and application of knowledge graph of transformer bushing faults based on cross-modal data [J]. Proceedings of the CSEE , 2025 , 45 ( 22 ): 9064 - 9074 .
韩程程 . 小样本场景下的知识图谱构建方法 [D]. 上海 : 华东师范大学 , 2024 .
Han Chengcheng . Methods for knowledge graph construction in few-shot scenarios [D]. Shanghai : East China Normal University , 2024 .
Schubert M , Berger T , Lehmann J . Ontology-based knowledge graph for wind farm operation and maintenance [J]. Renewable and Sustainable Energy Reviews , 2021 , 145 : 111089 .
Jensen A , Hansen L K , Madsen H . Knowledge graph integration for offshore wind farm maintenance optimization [J]. IEEE Transactions on Sustainable Energy , 2022 , 13 ( 2 ): 987 - 998 .
陈璐 . 基于知识关联推理的小样本目标识别技术研究 [D]. 西安 : 西安电子科技大学 , 2024 .
Chen Lu . Research on few-shot object recognition technology based on knowledge association and reasoning [D]. Xi’an : Xidian University , 2024 .
杨文涛 . 基于改进YOLOv5m的弱小目标识别方法 [J]. 计算机测量与控制 , 2022 , 30 ( 12 ): 218 - 223 .
Yang Wentao . Method of weak and small targets recognition based on improved YOLOv5m [J]. Computer Measurement & Control , 2022 , 30 ( 12 ): 218 - 223 .
潘景豪 . 基于多维度特征融合的小样本知识图谱补全模型 [D]. 广州 : 广东工业大学 , 2025 .
Pan Jinghao . A small sample knowledge map completion model based on multi-dimensional feature fusion [D]. Guangzhou : Guangdong University of Technology , 2025 .
Finn C , Abbeel P , Levine S . Model-agnostic meta-learning for fast adaptation of deep networks [C]// Proceedings of the 34th International Conference on Machine Learning , 2017 .
Hadsell R , Chopra S , Lecun Y . Dimensionality reduction by learning an invariant mapping [C]// 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2006 .
Veličković P , Cucurull G , Casanova A , et al . Graph attention networks [EB/OL]. [ 2026-02-04 ]. https://doi.org/10.48550/arXiv.1710.10903 https://doi.org/10.48550/arXiv.1710.10903 .
樊涛 , 李刚 , 马晨阳 , 等 . 考虑经济性和舒适性的海上风电运维规划优化方法 [J]. 船舶工程 , 2025 , 47 ( 4 ): 160 - 169 .
Fan Tao , Li Gang , Ma Chenyang , et al . Optimization method of offshore wind power operation and maintenance planning considering economy and comfort [J]. Ship Engineering , 2025 , 47 ( 4 ): 160 - 169 .
林雨辰 , 张新伟 , 张思航 , 等 . 融合大语言模型的台风场景下电网应急知识图谱构建方法 [J]. 清华大学学报(自然科学版) , 2026 , 66 ( 3 ): 519 - 529 .
Lin Yuchen , Zhang Xinwei , Zhang Sihang , et al . Construction method of power grid emergency knowledge graph under typhoon scenario integrating large language model [J]. Journal of Tsinghua University (Natural Science Edition) , 2026 , 66 ( 3 ): 519 - 529 .
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 - 106 .
Xie Qing , Cai Yang , Xie Jun , et al . Research on construction method and application of knowledge graph for power transformer operation and maintenance based on ALBERT [J]. Transactions of China Electrotechnical Society , 2023 , 38 ( 1 ): 95 - 106 .
毕志昊 , 姚锦涛 , 何清波 , 等 . 模式分量能量特征赋能的齿轮传动系统无监督故障溯源方法 [J]. 振动工程学报 , 2025 , 38 ( 6 ): 1344 - 1353 .
Bi Zhihao , Yao Jintao , He Qingbo , et al . Mode component energy feature-empowered unsupervised fault localization for gear transmission systems [J]. Journal of Vibration Engineering , 2025 , 38 ( 6 ): 1344 - 1353 .
唐文虎 , 牛哲文 , 赵柏宁 , 等 . 数据驱动的人工智能技术在电力设备状态分析中的研究与应用 [J]. 高电压技术 , 2020 , 46 ( 9 ): 2985 - 2999 .
Tang Wenhu , Niu Zhewen , Zhao Boning , et al . Research and application of data-driven artificial intelligence technology for condition analysis of power equipment [J]. High Voltage Engineering , 2020 , 46 ( 9 ): 2985 - 2999 .
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 ( 19 ): 164 - 175 .
Wang Shoupeng , Zhao Dongmei . Research review and prospects for power grid fault diagnosis [J]. Automation of Electric Power Systems , 2017 , 41 ( 19 ): 164 - 175 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621