光伏组件热斑效应故障的知识表达及图谱构建

doi:doi:10.19912/j.0254-0096.tynxb.2024-0786

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

光伏组件热斑效应故障的知识表达及图谱构建

更新时间：2025-10-22

- 光伏组件热斑效应故障的知识表达及图谱构建
- Vol. 46, Issue 9, Pages: 538-546(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0786
  CLC： TM615
- Published Online：14 October 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
[J]. 2025, 46(9): 538-546.
DOI：

[J]. 2025, 46(9): 538-546. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0786.

摘要

提出一种构建热斑故障知识图谱的方法。首先对热斑故障知识表达进行规范化

收集相关文本信息制作语料库。其次通过改进的RoBERTa-BiLSTM-MHA-CRF模型对热斑故障知识进行实体识别

并在此基础上使用BERT模型进行关系抽取

最终将两部分的结果进行信息整合

构建出一张完整的热斑故障知识图谱。实验结果表明

所提出的实体识别模型对热斑故障知识的实体识别精度达到96.02%

召回率为93.56%

F1值达到94.77%。该方法能够精准构建光伏组件热斑故障知识图谱

可为光伏组件的智能化故障诊断提供可能性

同时也可为后续应用提供有力支撑。

Abstract

This paper proposes a method for constructing a knowledge graph for hot-spot failures. First

the hot-spot failure knowledge representation is standardized

and relevant text information is collected to create a corpus. Secondly

an improved RoBERTa-BiLSTM-MHA-CRF model is used to identify entities related to hot-spot failures. Based on this

the BERT model is used for relationship extraction. Finally

the results of these two parts are integrated to construct a complete hot-spot failure knowledge graph. Experimental results show that the proposed entity recognition model achieves an accuracy of 96.02% for hot-spot failure knowledge

a recall rate of 93.56%

and an F1 value of 94.77%. This method precisely constructs a knowledge graph for hot spot faults in photovoltaic modules

enabling intelligent fault diagnosis of PV modules and offering strong support for subsequent applications.

关键词

Keywords

references

伊纪禄, 刘文祥, 马洪斌, 等. 太阳电池热斑现象和成因的分析[J]. 电源技术, 2012, 36(6): 816-818.

王道累, 李超, 李明山, 等. 基于深度卷积神经网络的光伏组件热斑检测[J]. 太阳能学报, 2022, 43(1): 412-417.

王道累, 李明山, 姚勇, 等. 改进SSD的光伏组件热斑缺陷检测方法[J]. 太阳能学报, 2023, 44(4): 420-425.

蔡洁聪, 吕洪坤, 朱凌云, 等. 光伏发电站热斑检测技术综述[J]. 电源技术, 2021, 45(5): 683-685.

王道累, 姚从荣, 李超, 等. 光伏组件热斑效应智能化检测的综述及展望[J]. 太阳能学报, 2024, 45(5): 527-536.

俞伊丽, 张展耀, 接晓霞, 等. 基于知识图谱与SCD文件的智能变电站二次检修安全措施自动生成技术研究[J]. 电力系统保护与控制, 2024, 52(2): 129-142.

武霁阳, 李强, 陈潜, 等. 知识图谱框架下基于深度学习的HVDC系统故障辨识[J]. 电力系统保护与控制, 2023, 51(20): 160-169.

黄简, 杨程, 冯天波, 等. 面向风电机组运维的知识图谱构建研究与应用[J]. 电力系统保护与控制, 2024, 52(8): 167-177.

ZHANG P F, LI T R, WANG G Q, et al.Multi-source information fusion based on rough set theory: a review[J]. Information fusion, 2021, 68: 85-117.

YANG X, ZHANG H W, CAI J F.Deconfounded image captioning: a causal retrospect[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(11): 12996-13010.

蔡莉, 王淑婷, 刘俊晖, 等. 数据标注研究综述[J]. 软件学报, 2020, 31(2): 302-320.

YUN W, ZHANG X, LI Z D, et al.Knowledge modeling: a survey of processes and techniques[J]. International journal of intelligent systems, 2021, 36(4): 1686-1720.

张吉祥, 张祥森, 武长旭, 等. 知识图谱构建技术综述[J]. 计算机工程, 2022, 48(3): 23-37.

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.

CHUNG Y A, ZHU C G, ZENG M.SPLAT: speech-language joint pre-training for spoken language understanding[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, 2021: 1897-1907.

CHO K, VAN MERRIENBOER B, GULCEHRE C, et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP). Doha, Qatar, 2014: 1724-1734.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

信息融合的NRP-AlexNet-SENet风电齿轮箱故障诊断

Related Author

龙霞飞

何志成

曾进辉

周凌

梁凯

伍席文

王育欣

张志

Related Institution

School of New Energy, Shenyang Institute of Engineering

Liaoning Solar Energy Research and Application Co., Ltd.

School of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, China

Xi’an Dishan Vision Technology Limited Company, Xi’an 712044, China

College of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China

AI问答

⁰