Intelligent Fault Diagnosis Method for Photovoltaic Systems Based on Large Artificial Intelligence Models

LI Hongjun; ZHANG Lixia; HONG Jun; LI Binbin; WANG Chenjia

doi:10.13296/j.1001-1609.hva.2026.07.022

您当前的位置：

首页 >

文章列表页 >

Intelligent Fault Diagnosis Method for Photovoltaic Systems Based on Large Artificial Intelligence Models

Technical Discussion | 更新时间：2026-07-06

- Intelligent Fault Diagnosis Method for Photovoltaic Systems Based on Large Artificial Intelligence Models
- High Voltage Apparatus Vol. 62, Issue 7, Pages: 213-220(2026)
- 作者机构：
  
  中国西电集团有限公司，西安 710075
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.07.022
  CLC：
- Received：10 January 2026，
  
  Revised：2026-03-19，
  
  Published：16 July 2026
- 稿件说明：
移动端阅览
LI Hongjun, ZHANG Lixia, HONG Jun, et al. Intelligent Fault Diagnosis Method for Photovoltaic Systems Based on Large Artificial Intelligence Models[J]. High Voltage Apparatus, 2026, 62(7): 213-220.
DOI：

LI Hongjun, ZHANG Lixia, HONG Jun, et al. Intelligent Fault Diagnosis Method for Photovoltaic Systems Based on Large Artificial Intelligence Models[J]. High Voltage Apparatus, 2026, 62(7): 213-220. DOI： 10.13296/j.1001-1609.hva.2026.07.022.

摘要

本研究将大语言模型技术应用于光伏故障诊断，搭建了一套支持自然语言交互的智能故障诊断系统。系统采用数据、逻辑、响应3层协同架构，通过定时任务持续同步实时运行数据，运用统计方法完成分析，并结合负载率指标实现设备与拓扑层面的异常监测。本研究的核心创新在于引入大模型的自然语言理解能力，运维人员可直接用日常语言查询和分析故障，系统能准确识别用户需求并给出专业诊断结果。系统还采用实时数据库缓存、预计算策略与多级容错机制，在保障诊断精度的前提下，将平均响应时间控制在800 ms以内。实际应用结果表明，该系统可有效缩短故障排查周期，提升光伏电站运维效率，具备较强的工程实用价值与智能化应用效果。

Abstract

In this study

the large language model technology is used to photovoltaic fault diagnosis and an intelligent fault diagnosis system supporting natural language interaction is constructed. The system adopts a three-layer collaborative architecture consistign of data

logic and response. It continuously synchronizes real-time operational data through scheduled tasks

performs analysis using statistical methods

and integrates load rate indicators to achhieve anomaly monitoring at both equipment and topology levels. The core innovation of this study lies in introducing the natural language understanding capability of large models. Maintenance personnel can directly query and analyze faults using natural language

and the system can accurately recognize user intent and provide professional diagnostic results. Moreover

the system also uses real-time database caching

precomputation strategies

and a multilevel fault tolerance mechanism to keep the everage response time within 800 ms while ensursing diagnostic accuracy.The practical application result shows that the system can effectively shorten the fault diagnosis cycle

improve the operation and maintenance efficiency of photovoltaic power plant and possess strong engineering practial value as well as intelligent application effectiveness.

关键词

Keywords

references

谢骊骊,叶青,陈伟,等.光伏电站在线监测智能诊断系统设计与实现[J].太阳能,2017(1):16-21.

Xie Lili, Ye Qing, Chen Wei, et al. Design and implementation of an intelligent online monitoring and diagnosis system for photovoltaic power stations[J]. Solar Energy,2017(1):16-21.

陈君,王博士,肖媛,等.基于Informer模型的短期光伏发电功率预测[J].西安工程大学学报,2025,39(4):82-88.

Chen Jun, Wang Boshi, Xiao Yuan, et al. Short-term photovoltaic power forecasting based on the Informer model[J]. Journal of Xi'an Polytechnic University,2025,39(4):82-88.

曹新春,王发强.光伏发电系统MPPT算法的比较研究[J].电力科学与技术学报,2024,39(5):25-35.

Cao Xinchun, Wang Faqiang. A comparative study on MPPT algorithms for photovoltaic power generation systems[J]. Journal of Electric Power Science and Technology,2024,39(5):25-35.

孔令宽,周旭东,张经纬,等.基于大数据挖掘的光伏发电与储能电站安全智能控制系统[J].电子设计工程,2025,33(18):96-100.

Kong Lingkuan, Zhou Xudong, Zhang Jingwei, et al. Intelligent safety control system for photovoltaic power generation and energy storage stations based on big data mining[J]. Electronic Design Engineering,2025,33(18):96-100.

陈飞,苏适,徐佳宁,等.光伏发电系统自动化调度数据异常检测方法[J].电网与清洁能源,2025,41(4):128-133.

Chen Fei, Su Shi, Xu Jianing, et al. An anomaly detection method for automated scheduling data of photovoltaic power generation systems[J]. Power System and Clean Energy,2025,41(4):128-133.

易靖.蒙能建集团光伏发电业务竞争战略研究[D].呼和浩特:内蒙古大学,2020.

Yi Jing. Research on the competitive strategy of mengnengjian group's photovoltaic power generation business[D]. Hohhot:Inner Mongolia University,2020.

周伊,肖先勇,赵清华,等.基于组合数据清洗与改进注意力机制的光伏发电功率预测[J].供用电,2024,41(10):31-37.

Zhou Yi, Xiao Xianyong, Zhao Qinghua, et al. Photovoltaic power forecasting based on combined data cleaning and improved attention mechanism[J]. Distribution & Utilization,2024,41(10):31-37.

杨海柱,刘森,张鹏,等.基于改进黏菌算法的分布式光伏发电并网规划[J].南方电网技术,2024,18(11):119-128.

Yang Haizhu, Liu Sen, Zhang Peng, et al. Integration planning of distributed photovoltaic generation based on improved slime mould algorithm[J]. Southern Power System Technology,2024,18(11):119-128.

王舒雨,李豪,马刚,等.基于TCN和DLinear的光伏发电功率多步预测模型[J].电力建设,2025,46(4):173-184.

Wang Shuyu, Li Hao, Ma Gang, et al. Multistep prediction model for photovoltaic power generation based on time convolution and DLinear[J]. Electric Power Construction,2025,46(4):173-184.

张海涛,李文娟,李雪峰,等.基于变分模态分解和时间注意力机制TCN网络的光伏发电功率预测[J].电测与仪表,2024,61 (12):156-163.

Zhang Haitao, Li Wenjuan, Li Xuefeng, et al. Photovoltaic power forecasting based on TPA-TCN model and variational modal decomposition[J]. Electrical Measurement & Instrumentation,2024,61 (12):155-163.

邓宏远,黄永章,王哲凡,等.新能源同步机对光伏发电系统静态电压稳定性的提升作用研究[J].电力电容器与无功补偿, 2024,45(2):117-125.

Deng Hongyuan, Huang Yongzhang, Wang Zhefan, et al. Research on improvement of static voltage stability of photovoltaic power generation system by new energy synchronous machine[J]. Power Capacitor & Reactive Power Compensation,2024,45(2):117-125.

辛保安.为实现“碳达峰,碳中和”目标贡献智慧和力量[J].国家电网,2021(3):2-3.

Xin Baoan. Contributing wisdom and strength to the achievement of the“carbon peak and carbon neutrality”goals[J]. State Grid, 2021(3):2-3.

马宁宁,谢小荣,贺静波,等.高比例新能源和电力电子设备电力系统的宽频振荡研究综述[J].中国电机工程学报,2020,40 (15):4719-4731.

Ma Ningning, Xie Xiaorong, He Jingbo, et al. Review of wide-band oscillation in renewable and power electronics highly integrated power systems[J]. Proceedings of the CSEE,2020,40(15):4719-4731.

李振兴,杨梓康,杨桄,等.大规模新能源送出线路继电保护关键技术探讨[J].浙江电力,2025,44(10):10-26.

Li Zhenxing, Yang Zikang, Yang Guang, et al. Key technologies for relay protection of bulk renewable energy transmission lines[J]. Zhejiang Electric Power,2025,44(10):10-26.

陈国平,董昱,梁志峰.能源转型中的中国特色新能源高质量发展分析与思考[J].中国电机工程学报,2020,40(17):5493-5505.

Chen Guoping, Dong Yu, Liang Zhifeng. Analysis and reflection on high - quality development of new energy with Chinese characteristics in energy transition[J]. Proceedings of the CSEE, 2020,40(17):5493-5505

高伟,黄俊铭.基于SSELM的光伏组件故障智能诊断方法[J].太阳能学报,2021,42(12):465-470.

Gao Wei, Huang Junming. Intelligent fault diagnosis method of photovoltaic module via sselm[J]. Acta Energiae Solaris Sinica, 2021,42(12):465-470.

邱宇鹏.基于I-V特性的光伏组件故障智能诊断研究[D].福州:福州大学,2024.

Qiu Yupeng. Research on intelligent fault diagnosis of photovoltaic modules based on I-V characteristics[D]. Fuzhou:Fuzhou University,2024.

张海珍,陈君.光伏发电系统智能诊断与预防性维护关键技术研究[C]//能源电子(终端应用)典型案例论文集,2025,243-246.

Zhang Haizhen, Chen Jun. Research on key technologies of intelligent diagnosis and preventive maintenance for photovoltaic power generation systems[C]//Typical Cases and Proceedings of Energy Electronics(Terminal Applications),2025:243-246.

刘思哲.基于深度学习的光伏系统智能故障诊断与功率预测研究[D].呼和浩特:内蒙古工业大学,2024.

Liu Sizhe. Research on intelligent fault diagnosis and power prediction of photovoltaic systems based on deep learning[D]. Hohhot:Inner Mongolia University of Technology,2024.

王元章,李智华,吴春华.光伏系统故障诊断方法综述[J].电源技术,2013,37(9):1700-1705.

Wang Yuanzhang, Li Zhihua, Wu Chunhua. Fault diagnosis technologies for photovoltaic system[J]. Chinese Journal of Power Sources,2013,37(9):1700-1705.

Zaki S A.基于智能算法的光伏系统故障检测和诊断方法[D].北京:华北电力大学,2021.

Zaki S A. Intelligent algorithm-based fault detection and diagnosis methods for photovoltaic systems[D]. Beijing:North China Electric Power University,2021.

杨小渝,段平,杨潇,等.基于人工智能的光伏发电系统故障诊断技术分析[J].电子技术,2024,53(12):154-155.

Yang Xiaoyu, Duan Ping, Yang Xiao, et al. Analysis of fault diagnosis technology for photovoltaic power generation system based on artificial intelligence[J]. Electronic Technology,2024,53 (12):154-155.

王志强.基于智能技术的光伏发电系统故障诊断与预测分析[J].集成电路应用,2024,41(4):290-291.

Wang Zhiqiang. Analysis of fault diagnosis and prediction in photovoltaic power generation systems based on intelligent technology[J]. Applications of IC,2024,41(4):290-291.

黄东风,姚烨彬,朱正菲.浅谈国际上光伏发电故障诊断的统计分析方法[J].能源与环境,2018(5):58-59.

Huang Dongfeng, Yao Yebin, Zhu Zhengfei. Discussion on international statistical analysis methods for fault diagnosis in photovoltaic power generation[J]. Energy and Environment,2018(5):58-59.

郝海东.分布式光伏发电系统故障智能诊断技术的研究[J].家电维修,2025(10):128-130.

Hao Haidong. Research on intelligent fault diagnosis technology for distributed photovoltaic power generation systems[J]. Appliance Repairing,2025(10):128-130.

路岩.光伏设备的故障智能诊断模型设计[J].电子产品可靠性与环境试验,2022,40(5):12-16.

Lu Yan. Design of intelligent fault diagnosis model for photovoltaic equipment[J]. Electronic Product Reliability and Environmental Testing,2022,40(5):12-16.

江颖,关艳飞,刘磊.基于人工智能的光伏发电系统故障诊断与预测技术研究[J].中国设备工程,2025(14):156-158.

Jiang Ying, Guan Yanfei, Liu Lei. Research on fault diagnosis and prediction technology for photovoltaic power generation systems based on artificial intelligence[J]. China Plant Engineering,2025 (14):156-158.

刘开石,李田泽,刘东,等.基于ABC-SVM算法的光伏阵列故障诊断[J].电源技术,2021,45(9):1171-1174.

Liu Kaishi, Li Tianze, Liu Dong, et al. Fault diagnosis of PV array based on ABC - SVM algorithm[J]. Chinese Journal of Power Sources,2021,45(9):1171-1174.

陶彩霞,王旭,高锋阳.基于深度信念网络的光伏阵列故障诊断[J].中国电力,2019,52(12):105-112.

Tao Caixia, Wang Xu, Gao Fengyang. Fault diagnosis of photovoltaic array based on deep belief network[J]. Electric Power, 2019,52(12):105-112.

余玲珍,覃涛,龙道银,等. TGBA优化核极限学习机的光伏阵列故障诊断[J].激光杂志,2021,42(12):140-148.

Yu Lingzhen, Qin Tao, Long Daoyin, et al. Fault diagnosis of PV array based on TGBA optimized kernel extreme learning machine[J]. Laser Journal,2021,42(12):140-148.

Wang L, Liu Z, Zhang J. TransQwen:a domain-adapted large language model for power transformer fault diagnosis[J]. IEEE Transactions on Power Delivery,2025,40(3):1567-1578.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Variation Research on Dissolved Gas Generation of Overheating Faults in Oil-paper Insulation System

Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm

Fault Diagnosis Method of Photovoltaic Array Based on CNN-GRU

Overview of Fault Diagnosis Criteria for High Voltage Cable Metal Sheath Grounding System Based on Sheath Current

Fault Detection and Diagnosis Method of Power Transformer Based on KMME and SVDD

Related Author

ZHANG Guozhi

LIU Xiang

HUANG Yalan

YAN Weiyang

ZHANG Xiaoxing

XU Songxiao

ZHAO Junyu

ZHANG Yuanbo

Related Institution

Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment, Hubei University of Technology

State Grid Baoding Power Supply Company

School of Electrical and Electronic Engineering, North China Electric Power University

Liaoning Technical University

State Grid Beijing Power Supply Company Cable Branch

⁰