| 2,171 | 0 | 115 |
| 下载次数 | 被引频次 | 阅读次数 |
随着新型电力系统规模的扩大与运行方式的复杂化，高效精准的故障诊断技术对保障系统安全稳定运行至关重要。近年来，机器学习和大语言模型技术的快速发展，为新型电力系统的故障诊断提供了新的理论与方法支撑。文章系统综述了机器学习和大语言模型技术在新型电力系统故障诊断中的研究进展，对比分析相关方法的应用特点，总结相应的技术挑战，并且梳理未来研究方向。文章通过系统性的技术分析和梳理，旨在为新型电力系统构建高效、鲁棒、可解释的智能故障诊断体系提供理论参考与技术路径。
Abstract：[Objective] Modern power systems are rapidly evolving, characterized by an exponential increase in equipment volume, highly complex network topologies, and continuously changing operating conditions. Traditional fault diagnosis methods, relying on expert knowledge and threshold-based judgment, now face technical bottlenecks, including limited real-time performance, high misjudgment rates, and difficulties in multimodal data fusion. Developing intelligent diagnostic technologies based on machine learning, artificial intelligence, big data mining, and multisource information fusion has therefore become essential for achieving accurate fault identification and rapid fault location. [Methods] Recent advances in machine learning and large language models(LLMs) have opened new paths for fault diagnosis. Deep-learning-based architectures can integrate time-series operational data with multisource monitoring signals, extract cross-modal fault correlation features, and analyze fault propagation paths under dynamic coupling relationships. Transfer learning and federated learning help mitigate data silos and improve cross-regional diagnostic generalization. Supervised learning technology enhances anomaly detection robustness in small-sample scenarios. Meanwhile, LLMs can incorporate domain knowledge graphs through knowledge distillation, perform semantic reasoning and multicriteria collaborative decision-making, and support the development of diagnostic systems that combine data-driven learning with knowledge-informed causal inference. [Results] This article systematically reviews recent research progress in machine learning and LLM-based fault diagnosis technologies for new-type power systems, compares the characteristics of representative approaches, summarizes the key challenges in their practical application, and finally, outlines future research directions. [Conclusion] The work provides theoretical insights and technical pathways for building efficient, robust, and interpretable intelligent fault diagnosis systems for new power systems through systematic technical analysis and sorting.
[1]别朝红,卞艺衡,张理寅,等.新型电力系统应对极端事件的风险防范与应急管理关键技术[J].中国电机工程学报,2024, 44(18):7049–7068.BIE Z H, BIAN Y H, ZHANG L Y, et al. Key technologies of risk prevention and emergency management against extreme events for new power systems[J]. Proceedings of the CSEE,2024, 44(18):7049–7068.(in Chinese)
[2]舒印彪,张正陵,汤涌,等.新型电力系统构建的若干基本问题[J].中国电机工程学报, 2024, 44(21):8327–8341.SHU Y B, ZHANG Z L, TANG Y, et al. Fundamental issues of new-type power system construction[J]. Proceedings of the CSEE, 2024, 44(21):8327–8341.(in Chinese)
[3]文继锋,刘子俊,周专,等.新型电力系统下高渗透新能源接入的次同步振荡问题研究[J].太阳能学报, 2024, 45(11):50–60.WEN J F, LIU Z J, ZHOU Z, et al. Research on sub-synchronous oscillation issues of high penetration renewable energy access under new power systems[J]. Acta Energiae Solaris Sinica,2024, 45(11):50–60.(in Chinese)
[4]蒲天骄,赵琦,王新迎.电力人工智能技术研究框架、应用现状及展望[J/OL].电网技术, 1–21[2025-05-14]. http://kns.cnki.net/kcms/detail/11.2410.tm.20241024.1500.002.html.PU T J, ZHAO Q, WANG X Y, Technology framework,application status and prospects on electric power artificial intelligence[J/OL]. Grid Technology, 1–21[205-05-14], http://kns.cnki.et/kcms/detail/11.2410.tm.20241024.1500.002.html.(in Chinese)
[5]龚立,王先培,田猛,等.电力信息物理系统韧性的概念与提升策略研究进展[J].电力系统保护与控制, 2023, 51(14):169–187.GONG L, WANG X P, TIAN M, et al. Concepts and research progress on enhancement strategies for cyber physical power system resilience[J]. Power System Protection and Control,2023, 51(14):169–187.(in Chinese)
[6]周晓华,冯雨辰,陈磊,等.改进秃鹰搜索算法优化SVM的变压器故障诊断研究[J].电力系统保护与控制, 2023, 51(8):118–126.ZHOU X H, FENG Y C, CHEN L, et al. Transformer fault diagnosis based on SVM optimized by the improved bald eagle search algorithm[J]. Power System Protection and Control,2023, 51(8):118–126.(in Chinese)
[7]袁钰林,郑运鸿,游一民,等.基于随机森林与长短时记忆神经网络的真空接触器故障诊断方法研究[J].高压电器,2022, 58(5):103–111.YUAN Y L, ZHENG Y H, YOU Y M, et al. Research on fault diagnosis method of vacuum contactor based on R-LSTM model[J]. High Voltage Apparatus, 2022, 58(5):103–111.(in Chinese)
[8]郭建勋,刘晓博,吕金淼,等.基于WPE-BA-CNN模型的输电线路放电声纹特征识别方法[J].智慧电力, 2025, 53(3):92–98.GUO J X, LIU X B, LU J M, et al. Discharge voiceprint feature recognition method for transmission lines based on WPE-BA-CNN model[J]. Smart Power, 2025, 53(3):92–98.(in Chinese)
[9]李康,李爽,高小永,等.多变量时序标记Transformer及其在电潜泵故障诊断中的应用[J].控制与决策, 2025, 40(4):1145–1153.LI K, LI S, GAO X Y, et al. Multivariate time series tokenized transformer and its application in fault diagnosis of electric submersible pump[J]. Control and Decision, 2025, 40(4):1145–1153.(in Chinese)
[10]王小君,窦嘉铭,刘曌,等.可解释人工智能在电力系统中的应用综述与展望[J].电力系统自动化, 2024, 48(4):169–191.WANG X J, DOU J M, LIU Z, et al. Review and prospect of explainable artificial intelligence and its application in power systems[J]. Automation of Electric Power System, 2024, 48(4):169–191.(in Chinese)
[11]郑尚直,仲林林,王同磊,等.基于改进半监督阶梯网络的有载分接开关故障诊断方法[J].电力工程技术, 2023, 42(2):197–205.ZHENG S Z, ZHONG L L, WANG T L, et al. Fault diagnosis method for OLTC based on improved semi-supervised ladder networks[J]. Electric Power Engineering Technology, 2023,42(2):197–205.(in Chinese)
[12]陈戈,张俊勃,彭颖,等.基于决策空间裁剪强化学习的连锁故障调切结合紧急控制[J].电力系统自动化, 2025, 49(6):144–156.ZHANG G, ZHANG J B, PENG Y, et al. Emergency control combined with adjustment and tripping against cascading failures based on decision space pruning reinforcement learning[J]. Automation of Electric Power Systems, 2025, 49(6):144–156.(in Chinese)
[13]蒲天骄,乔骥,赵紫璇,等.面向电力系统智能分析的机器学习可解释性方法研究(一):基本概念与框架[J].中国电机工程学报, 2023, 43(18):7010–7030.PU T J, QIAO J, ZHAO Z X, et al. Research on interpretable methods of machine learning applied in intelligent analysis of power system(partⅠ):Basic concept and framework[J].Proceedings of the CSEE, 2023, 43(18):7010–7030.(in Chinese)
[14]陈晓红,傅文润,刘朝明,等.人工智能大模型在电力设备运维场景中的应用探讨[J].中国工程科学, 2025, 27(1):180–192.CHEN X H, FU W R, LIU Z M, et al. Application of artificial intelligence large language model in power equipment operation and maintenance[J]. Chinese Engineering Science, 2025, 27(1):180–192.(in Chinese)
[15]张俊,徐箭,许沛东,等.人工智能大模型在电力系统运行控制中的应用综述及展望[J].武汉大学学报（工学版）, 2023,56(11):1368–1379.ZHANG J, XU J, XU P D, et al. Overview and prospect of application of artificial intelligence large model in power system operation control[J]. Journal of Wuhan University(Engineering Edition), 2023, 56(11):1368–1379.(in Chinese)
[16]丁俐夫,陈颖,肖谭南,等.基于大语言模型的新型电力系统生成式智能应用模式初探[J].电力系统自动化, 2024,48(19):1–13.DING L F, CHEN Y, XIAO T N, et al. Exploration of generative intelligent application mode for new power systems based on large language models[J]. Automation of Electric Power Systems,2024, 48(19):1–13.(in Chinese)
[17]孙国强,史学恒,罗哲清,等.基于专家知识与大语言模型混合增强的水电站告警智能诊断[J/OL].电力建设, 1–18[2025-05-09]. http://kns.cnki.net/kcms/detail/11.2583.tm.20250430.1707.015.html.SUN G Q, SHI X H, LUO Z Q, et al. Intelligent diagnosis of hydroelectric power station alarm based on hybrid-augmentation of expert knowledge and large language model[J/OL]. Electric Power Construction, 1–18[2025-05-09]. http://kns.cnki.net/kcms/detail/11.2583.tm.20250430.1707.015.html.(in Chinese)
[18]孙秋野,张瑞霞,陈东岳.大模型技术赋能电力系统的应用及技术路线展望[J/OL].电力系统自动化, 1–22[2025-05-09].http://kns.cnki.net/kcms/detail/32.1180.TP.20250317.1811.006.html.SUN Q Y, ZHANG R X, CHEN D Y. Application and route prospect of empowering power systems with large language models[J/OL]. Automation of Electric Power System, 1–22[2025-05-09]. http://kns.cnki.net/kcms/detail/32.1180.TP.20250317.1811.006.html.
[19]解骞,郑胜瑜,刘兴华,等.基于IIVY-SVMD-MPE-SVM的开关柜局部放电故障识别[J].实验技术与管理, 2025, 42(4):26–36.XIE Q, ZHENG S Y, LIU X H, et al. Partial discharge fault identification of switchgear based on IIVY-SVMD-MPE-SVM[J]. Experimental Technology and Management, 2025, 42(4):26–36.(in Chinese)
[20]ABO-KHALIL A G,LEE D C. DC-link capacitance estimation in AC/DC/AC PWM converters using voltage injection[J]. IEEE Transactions on Industry Applications, 2008, 44(5):1631–1637.
[21]黄友锐,沈玉轩,徐善永.融合机器学习的永磁同步电机数字孪生故障诊断技术研究[J].电测与仪表, 2025, 62(2):181–187.HUANG Y R, SHEN Y X, XU S Y. Research on digital twin fault diagnosis technology of permanent magnet synchronous motor integrating machine learning[J]. Electric Measurement and Instrumentation, 2025, 62(2):181–187.(in Chinese)
[22]刘新,常英贤,孙莉莉,等.基于深度学习的电网网络攻击检测研究[J].自动化仪表, 2022, 43(12):81–85, 91.LIU X, CHANG Y X, SUN L L, et al. Research on grid network attack detection based on deep learning[J]. Process Automation Instrumentation, 2022, 43(12):81–85, 91.(in Chinese)
[23]孟井煜枫,杨禄铭,饶晨晖,等.基于粒子群优化随机森林的风电主轴承故障诊断[J].微特电机, 2025, 53(2):74–78.MENG J Y Y, YANG L M, RAO C H, et al. Fault diagnosis of wind turbine main bearings based on particle swarm optimization and random forest[J]. Small Special Electrical Machines, 2025,53(2):74–78.(in Chinese)
[24]闫泽玉,杨洋,刘云鹏,等.基于神经监督决策树算法的多感知GIS局部放电识别[J].中国电机工程学报, 2024, 44(14):5821–5833.YAN Z Y, YANG Y, LIU Y P, et al. Multi-aware GIS partial discharge identification based on neural supervision decision tree[J]. Proceedings of the CSEE, 2024, 44(14):5821–5833.(in Chinese)
[25]陈逸龙,林萌,周士祺.基于循环神经网络的核电厂复合故障诊断方法[J].海军工程大学学报, 2025, 37(1):36–42.CHEN Y L, LIN M, ZHOU S Q. A composite fault diagnosis compound fault diagnosis method of nuclear power plant based on recurrent neural network[J]. Journal of Naval University of Engineering, 2025, 37(1):36–42.(in Chinese)
[26]王晓康,丁雷,何嘉斌,等.基于深度学习融合证据理论的电缆接头故障检测方法研究[J].绝缘材料, 2025, 58(3):125–130.WANG X K, DING L, HE J B, et al. Research on cable joint fault detecting method based on deep learning fusion evidence theory[J]. Insulating Materials, 2025, 58(3):125–130.(in Chinese)
[27]赵建伟,林雨场,陈升,等.基于CNN-LSTM算法的电力系统气象灾害故障预测方法[J].电工电能新技术, 2025, 44(3):109–118.ZHAO J W, LIN Y C, CHEN S, et al. Power system failure prediction under meteorological disasters based on CNN-LSTM neural network[J]. Advanced Technology of Electrical Engineering and Energy, 2025, 44(3):109–118.(in Chinese)
[28]李卓,谢耀滨,吴茜琼,等.基于深度学习的电力系统虚假数据注入攻击检测综述[J].电力系统保护与控制, 2024,52(19):175–187.LI Z, XIE Y B, WU Q Q, et al. Review of deep learning-based false data injection attack detection in power systems[J]. Power System Protection and Control, 2024, 52(19):175–187.(in Chinese)
[29]徐俊俊,曹冬磊,王志伟,等.内嵌物理知识学习的主动配电网态势异常信号检测与溯因[J/OL].中国电机工程学报, 1–13[2025-05-13]. https://doi.org/10.13334/j.0258-8013.pcsee.242133.XU J J, CAO D L, WANG Z W, et al. A framework of anomaly signal detection and abduction analysis in active distribution network situation based on embedded physics knowledge learning[J/OL]. Proceedings of the CSEE, 1–13[205-05-13] https://doi.org/10.13334/j.0258-8013.pcsee.242133.(in Chinese)
[30]邬洲,张军,李隆,等.基于K-means++聚类的光伏系统直流电弧故障检测研究[J].太阳能学报, 2024, 45(11):320–329.WU Z, ZHANG J, LI L, et al. Research on DC arc fault detection of PV system based on K-means++clustering[J]. Acta Energiae Solaris Sinica, 2024, 45(11):320–329.(in Chinese)
[31]谷山强,李健,汤亮亮,等.基于聚类学习方法的新型电力系统重要输电通道雷击故障特征分析研究[J/OL].电网技术,1–15[2025-05-12]. http://kns.cnki.net/kcms/detail/11.2410.TM.20241212.1001.005.html.GU S Q, LI J, TANG L L, et al. Analysis of lightning strike fault characteristics in cluster learning method of new power systems[J/OL]. Power Grid Technology, 1–15[2020-05-12] http://kns.cnki.net/kcms/detail/11.2410.TM.20241212.1001.005.html.(in Chinese)
[32]刘畅,郑涛,王志华,等.基于DBSCAN的智能变电站交流采样异常实时识别算法[J].电力系统保护与控制, 2024,52(24):140–148.LIU C, ZHENG T, WANG Z W, et al. Algorithm for real-time identification of sampling abnormalities in smart substations based on DBSCAN[J]. Power System Protection and Control,2024, 52(24):140–148.(in Chinese)
[33]陈雨娟,顾涛.基于DBSCAN与二叉决策树算法的短路故障定位方法研究[J].华北科技学院学报, 2024, 21(3):42-49.CHEN Y J, GU T. Research on short-circuit fault localization method based on DBSCAN and binary decision tree algorithm[J]. Journal of North China University of Science and Technology, 2024, 21(3):42–49.(in Chinese)
[34]黎寿涛,夏成军,钟明明,等.基于故障链聚类算法的电网关键线路辨识[J].电力工程技术, 2022, 41(1):84–92.LI S T, XIA C J, ZHONG M M, et al. Critical line identification of power grid based on fault chain clustering algorithm[J].Electric Power Engineering Technology, 2022, 41(1):84–92.(in Chinese)
[35]潘宣佑,李超,杨柳林,等.利用凝聚层次聚类辨识电网中脆弱输电断面[J].广西大学学报（自然科学版）, 2024, 49(5):1020–1030.PAN X Y, LI C, YANG L L, et al. Identifying vulnerable transmission sections in power grids using agglomerative hierarchical clustering[J]. Journal of Guangxi University(Natural Science Edition), 2024, 49(5):1020–1030.(in Chinese)
[36]沙志成,朱春萍,王艳.基于约束模糊聚类的电力系统扰动信号识别方法[J].自动化与仪器仪表, 2020,(2):163–166.SHA Z C, ZHU C P, WANG Y. Disturbance signal recognition method of power system based on constrained fuzzy clustering[J]. Automation&Instrumentation, 2020,(2):163–166.(in Chinese)
[37]王月海,蒋爱民,程冉,等.模拟电路故障诊断的约束聚类集成BP网络算法[J].计算机测量与控制, 2011, 19(7):1592–1595.WANG Y H, JIANG A M, CHENG R, et al. An constraint-based clustering integrated BP networks approach for analog circuit fault diagnose[J]. Computer Measurement and Control, 2011,19(7):1592–1595.(in Chinese)
[38]范士雄,赵泽宁,郭剑波,等.数据驱动的电力系统暂态稳定评估方法综述[J].中国电机工程学报, 2024, 44(9):3408–3429.FAN S X, ZHAO Z N, GUO J B, et al. Review on data-driven power system transient stability assessment technology[J].Proceedings of the CSEE, 2024, 44(9):3408–3429.(in Chinese)
[39]陈阳,陆超,刘迪,等.多故障场景下基于主动学习的暂态电压安全评估与安全裕度估计[J].武汉大学学报(工学版),2023, 56(11):1336–1346.CHEN Y, LU C, LIU D, et al. Active learning-based transient voltage safety assessment and safety margin estimation for multi-fault scenarios[J]. Journal of Wuhan University(Engineering Edition), 2023, 56(11):1336–1346.(in Chinese)
[40]邵振国,张承圣,陈飞雄,等.生成对抗网络及其在电力系统中的应用综述[J].中国电机工程学报, 2023, 43(3):987–1004.SHAO Z G, ZHANG C S, CHEN F X, et al. A review on generative adversarial networks for power system applications[J]. Proceedings of the CSEE, 2023, 43(3):987–1004.(in Chinese)
[41]王嘉宁.基于无监督学习的电力变压器声纹异常诊断方法研究[D].北京:华北电力大学（北京）, 2022.WANG J N. Research on unsupervised learning based power transformer voiceprint anomaly diagnosis method[D]. Beijing:North China Electric Power University(Beijing), 2022.(in Chinese)
[42]杨东升,吉明佳,周博文,等.基于双生成器生成对抗网络的电力系统暂态稳定评估方法[J].电网技术, 2021, 45(8):2934–2944.YANG D S, JI M J, ZHOU B W, et al. Transient stability assessment of power system based on DGL-GAN[J]. Power System Technology, 2021, 45(8):2934–2944.(in Chinese).
[43]陈徵粼,刘灏,毕天姝.基于配电网PMU的无监督电力系统扰动特征提取与分类[J].中国电机工程学报, 2024, 44(15):5858–5871.CHEN Z L, LIU H, BI T S. Unsupervised power system disturbance feature extraction and classification using PMUs in distribution network[J]. Proceedings of the CSEE, 2024, 44(15):5858–5871.(in Chinese)
[44]杨艺宁,张蓬鹤,夏睿,等.基于CT-GAN的半监督学习窃电检测方法研究[J].湖南大学学报（自然科学版）, 2024,51(6):211–222.YANG Y N, ZHANG P H, XIA R, et al. Research on semi-supervised learning detection method of electricity theft based on CT-GAN[J]. Journal of Hunan University(Natural Science Edition), 2024, 51(6):211–222.(in Chinese)
[45]陈恩光.半监督生成对抗和深度堆栈自编码网络相结合的变压器故障诊断[D].保定:华北电力大学, 2022.CHEN E G. Transformer fault diagnosis by combining semi-supervised generative adversarial and deep stacked auto-encoder networks[D]. Baoding:North China Electric Power University, 2022.(in Chinese)
[46]谭本东,杨军,赖秋频,等.基于改进CGAN的电力系统暂态稳定评估样本增强方法[J].电力系统自动化, 2019, 43(1):149–157.TAN B D, YANG J, LAI Q P, et al. Data augment method for power system transient stability assessment based on improved conditional generative adversarial network[J].Automation of Electric Power Systems, 2019, 43(1):149–157.(in Chinese).
[47]李宝琴,吴俊勇,强子玥,等.基于改进DCGAN的电力系统暂态稳定增强型自适应评估[J].电力系统自动化, 2022,46(2):73–82.LI B Q, WU J Y, QIANG Z Y, et al. Enhanced adaptive assessment on transient stability of power system based on improved deep convolutional generative adversarial network[J]. Automation of Electric Power Systems, 2022, 46(2):73–82.(in Chinese).
[48]赵晨浩,焦在滨,李程昊,等.基于主动迁移学习的电力系统暂态稳定自适应评估[J].中国电力, 2025, 58(1):70–77.ZHAO C H, JIAO Z B, LI C H, et al. Adaptive assessment of power system transient stability based on active transfer learning[J]. Electric Power, 2025, 58(1):70–77.(in Chinese)
[49]武锋利.基于小波变换和深度迁移学习的变压器故障自动化诊断[J].自动化与仪表, 2025, 40(2):115–118, 123.WU F L. Automatic transformer fault diagnosis based on wavelet transform and deep transfer learning[J]. Automation&Instrumentation, 2025, 40(2):115–118, 123.(in Chinese)
[50]殷孝雎,潘雪,左雁斌,等.基于迁移学习的风电机组叶片损伤检测与分析[J].太阳能学报, 2024, 45(10):506–511.YIN X J, PAN X, ZUO Y B, et al. Wind turbine blade damage detection and analysis based on transfer learning[J]. Acta Energiae Solaris Sinica, 2024, 45(10):506–511.(in Chinese)
[51]周军,王渴心,王岩.融合迁移学习与CGAN的风电集群功率超短期预测[J].电力系统及其自动化学报, 2024, 36(5):9–18.ZHOU J, WANG K X, WANG Y. Fusion of transfer learning and CGAN for ultra short-term power prediction of wind power clusters[J]. Proceedings of the CSU-EPSA, 2024, 36(5):9–18.(in Chinese)
[52]陆俊,肖琦,龚钢军,等.基于动态差分隐私的联邦学习配电台区数据异常识别[J/OL].电网技术, 1–12[2025-05-13].https://doi.org/10.13335/j.1000-3673.pst.2024.1221.LU J, XIAO Q, GONG G J, et al. Federated learning distribution area data anomaly recognition based on dynamic differential privacy[J/OL]. Power System Technology, 1–12[2025-05-13].https://doi.org/10.13335/j.1000-3673.pst.2024.1221.(in Chinese)
[53]刘晶,王晓茜,唐震,等.基于联邦分层优化学习的设备故障诊断方法[J].计算机工程与设计, 2024, 45(6):1850–1856.LIU J, WANG X Q, TANG Z, et al. Equipment fault diagnosis method based on federated hierarchical optimization learning[J]. Computer Engineering and Design, 2024, 45(6):1850–1856.(in Chinese)
[54]刘东奇,张琼,梁皓澜,等.基于联邦学习的智能电网AMI入侵检测方法研究[J].计算机科学, 2024, 51(增刊1):944–951.LIU D Q, ZHANG Q, LIANG H L, et al. Study on smart grid AMI intrusion detection method based on federated learning[J].Computer Science, 2024, 51(S1):944–951.(in Chinese)
[55]易子宸.基于联邦图网络的风电机组异常检测定位[D].秦皇岛:燕山大学, 2024.YI Z C. Wind turbine anomaly detection and localization based on federated graph network[D]. Qinghuangdao:Yanshan University, 2024.(in Chinese)
[56]陈梦实.基于语言模型的电网输变电设备缺陷语料库系统的设计与实现[D].北京:北京邮电大学, 2024.CHEN M S. Design and implementation of defect corpus system for power grid equipment[D]. Beijing:Beijing University of Posts and Telecommunications, 2024.(in Chinese)
[57]刘江.基于知识图谱的电网故障处置的研究与设计[D].北京:华北电力大学(北京), 2023.LIU J. Research and design of power grid fault disposal based on knowledge graph[D]. Beijing:North China Electric Power University(Beijing), 2023.(in Chinese)
[58]王瑞民.基于知识图谱的汽轮发电机组故障诊断研究[D].兰州:兰州理工大学, 2024.WANG R M. Research on fault diagnosis of turbine generator sets based on knowledge graph[D]. Lanzhou:Lanzhou University of Technology, 2024.(in Chinese)
[59]戴小建.光伏故障处置知识图谱构建及辅助决策研究[D].济南:山东建筑大学, 2024.DAI X J. Research on the construction of knowledge graph for photovoltaic fault disposal and auxiliary decision-making[D].Jinan:Shandong Jianzhu University, 2024.(in Chinese)
[60]杨文昊.基于多模态信息融合的故障源定位方法研究[D].绵阳:西南科技大学, 2024.YANG W H. Research on fault source localization method based on multimodal information fusion[D]. Mianyang:Southwest University of Science and Technology, 2024.(in Chinese)
[61]丁剑涛.面向电力设备缺陷数据的多模态知识图谱研究[D].西安:长安大学, 2022.DING J T. Research on multimodal knowledge graph for power equipment defect data[D]. Xi'an:Chang'an University, 2022(in Chinese)
[62]单其尚.从情感分析到变压器故障诊断的多模态融合方法迁移应用[D].南京:南京邮电大学, 2023.DAN Q S. Multimodal fusion method migration application from sentiment analysis to transformer fault diagnosis[D].Nanjing:Nanjing University of Posts and Telecommunications,2023.(in Chinese)
[63]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 P, YU T, LI L Y, 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(in Chinese)
[64]姚一杨,杜泽星,周果清,等.基于提示学习的电力设备故障多谱段融合识别方法[J].西北工业大学学报, 2025, 43(02):410–417.YAO Y Y, DU Z X, ZHOU G Q, et al. Multi-spectral fusion power equipment fault recognition based on prompt learning[J].Journal of Northwestern Polytechnical University, 2025, 43(2):410–417.(in Chinese)
[65]张昆,张永伟,吴永城,等.基于大模型的设备故障知识图谱自动构建方法[J].计算机与现代化, 2024,(11):46–53.ZHANG K, ZHANG Y W, WU Y C, et al. An LLM-based method for automatic construction of equipment failure knowledge graphs[J]. Computer and Modernization, 2024,(11):46–53.(in Chinese)
[66]黄锦.支持分级检索的设备运检领域知识图谱的研究和实现[D].北京:北京邮电大学, 2024.HUANG J. Research and implementation of knowledge graphs in the field of equipment operation and inspection that supports hierarchical retrieval[D]. Beijing:Beijing University of Posts and Telecommunications, 2024.(in Chinese)
[67]李奕霖.机理与数据协同的机电设备智能诊断方法研究[D].北京:中国石油大学（北京）, 2022.LI Y L. Research on the intelligent diagnosis of electromechanical equipment based on hybrid physics-based and data-driven models[D]. Beijing:China University of Petroleum(Beijing),2022.(in Chinese)
[68]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 G, FANG H, LIU Y P, et al. Large-model drive technology in new power system:status, challenges and prospects[J]. High Voltage Technology, 2024, 50(7):2864–2878.(in Chinese)
[69]李建鹏.知识与数据融合驱动的小样本网络故障诊断问题研究[D].南京:南京航空航天大学, 2023.LI J P. Research on few-shot network fault diagnosis driven by knowledge and data fusion[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2023.(in Chinese)
[70]周长玉,李想,焦润海,等.基于领域知识图谱的变压器故障联合推理[J].中国电机工程学报, 2025, 45(6):2160–2171.ZHOU C Y, LI X, JIAO R H, et al. Joint reasoning for transformer faults based on domain knowledge graphs[J].Proceedings of the CSEE, 2025, 45(6):2160–2171.(in Chinese)
基本信息:
DOI：10.16791/j.cnki.sjg.2025.12.007
中图分类号:TM711;TP18
引用信息:
[1]张建良,张晓洁,麻坚,等.面向新型电力系统的故障诊断技术研究进展(二)：机器学习和大语言模型技术[J].实验技术与管理,2025,42(12):54-70.DOI:10.16791/j.cnki.sjg.2025.12.007.
基金信息:
国网浙江省电力有限公司科技项目(5211JH250009); 浙江大学实验室技术研究项目(SYBJS202511); 浙江省自然科学基金项目(LMS26E070005)