基于语义增强的电网故障处置预案匹配方法

doi:10.11930/j.issn.1004-9649.202408023

摘要/Abstract

摘要：

为提升电网故障处置预案匹配效率和准确率，提出了基于语义增强的电网故障处置预案匹配方法。首先，通过微调基于变换器双向编码器表征（bidirectional encoder representations from transformers，BERT）模型的超参数，将故障处置预案中多调度对象实体表征为可计算词向量，并接入条件随机场（conditional random field，CRF）模型识别调度对象实体类别；然后，基于残差向量-字词嵌入向量-编码向量（residual vector-embedding vector-encoded vector，RE2）计算电网故障信息和调度对象的语义距离，建立基于BERT-CRF-RE2的电网故障处置预案匹配模型；最后，通过某地区电网数据进行验证。结果表明，所提模型有效解决了预案匹配准确率低的问题。

关键词: 电网故障处置, 预案匹配, 语义增强, 多调度对象

Abstract:

In order to improve the matching efficiency and accuracy of grid fault handling plan, a semantic enhancement-based grid fault handling plan matching method is proposed. Firstly, the multi-dispatch objects entities in the fault handling plan are characterized as computable word vectors by fine-tuning the hyperparameters of the bidirectional encoder representations from transformers (BERT) model, and integrated into the conditional random field (CRF) model to identify the dispatch objects entity categories. And then, the semantic distance between the grid fault information and dispatch objects are computed based on the residual vector-embedding vector-encoded vector (RE2), and a grid fault handling plan matching model is established based on BERT-CRF-RE2. Finally, through validation of the data of a regional power grid, the proposed model effectively solves the problem of low plan matching accuracy rate.

Key words: power grid fault handling, plan matching, semantic enhancement, multi-scheduling object

蒙飞, 李江鹏, 李涛, 徐建忠, 高海洋, 乔咏田. 基于语义增强的电网故障处置预案匹配方法[J]. 中国电力, 2025, 58(4): 237-244.

MENG Fei, LI Jiangpeng, LI Tao, XU Jianzhong, GAO Haiyang, QIAO Yongtian. Matching Method for Power Grid Fault Handling Plan Based on Semantic Enhancement[J]. Electric Power, 2025, 58(4): 237-244.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202408023

https://www.electricpower.com.cn/CN/Y2025/V58/I4/237

图/表 9

图 1 BERT-CRF模型结构

Fig.1 BERT-CRF model structure

图 2 RE2模型结构

Fig.2 RE2 model structure

图 3 基于BERT-CRF-RE2的电网故障处置预案匹配方法基本流程

Fig.3 Basic flow of BERT-CRF-RE2 based grid fault handling plan matching method

表 1 电网故障处置预案实体标记示例

Table 1 Power grid fault handling plan entity labeling example

字符序列	X	X	机	组	1	0	0	0	k	V	电	压	下	降	用	X	X	线
标签序列	B-U	I-U	I-U	I-U	B-L	I-L	I-L	I-L	I-L	I-L	O	O	O	O	O	B-A	I-A	I-A
实体类型	机组	机组	机组	机组	电压等级	电压等级	电压等级	电压等级	电压等级	电压等级						线路	线路	线路

表 2 测试样本上的调度对象实体识别结果

Table 2 The dispatch object entity recognition results on test samples 单位：%

实体类型	P	R	F₁
地区	95.85	95.85	95.85
机构	95.83	100.00	97.87
机组	100.00	96.51	98.22
线路	97.78	97.78	97.78
母线	100.00	97.06	98.51
变压器	100.00	97.44	98.70
开关	92.31	95.71	94.14
刀闸	93.64	97.95	95.75
状态	96.49	95.27	95.88
电压等级	95.17	95.83	95.50

图 4 各模型的输出损失随着训练轮数的变化

Fig.4 Variation of output loss for each model with the number of training rounds

图 5 各模型的准确率Acc随着训练轮数的变化

Fig.5 Variation of accuracy for each model with the number of training rounds

图 6 各模型的AUC值随着训练轮数的变化

Fig.6 Variation of AUC values for each model with the number of training rounds

表 3 不同文本匹配模型性能对比

Table 3 Performance comparison of different text matching models

模型	A_cc/%	A_UC	t/ms
ABCNN	86.03	0.8569	19.8
BiMPM	90.84	0.8872	24.2
DSSM	93.77	0.9061	26.0
RE2	95.92	0.9369	14.7

参考文献 23

1	皮俊波, 齐世雄, 孙文多, 等. 基于UIE框架的电网故障处置预案实体和事件识别方法[J]. 中国电力, 2023, 56 (12): 138- 146.
	PI Junbo, QI Shixiong, SUN Wenduo, et al. Entity and event recognition method for power grid fault handling plan based on UIE framework[J]. Electric Power, 2023, 56 (12): 138- 146.
2	胡怀伟, 富英, 张越, 等. 基于自然语言理解的故障处置预案语义建模研究及应用[J]. 电力信息与通信技术, 2022, 20 (5): 68- 73.
	HU Huaiwei, FU Ying, ZHANG Yue, et al. Research and application of semantic modeling of fault handling plan based on natural language understanding[J]. Electric Power Information and Communication Technology, 2022, 20 (5): 68- 73.
3	马覃峰, 安甦, 刘明顺, 等. 光储系统电网侧故障下VSC变流器的跟网-构网型控制方法[J]. 广东电力, 2023, 36 (12): 47- 56.
	QA Qinfeng, AN Su, LIU Mingshun, et al. Control method of VSC converter for grid-following/forming operation under grid-side gaults in PV energy storage systems[J]. Guangdong Electric Power, 2023, 36 (12): 47- 56.
4	江叶峰, 孙少华, 仇晨光, 等. 电网故障处置预案文本中的命名实体识别研究[J]. 电力工程技术, 2021, (5): 177- 183.
	JIANG Yefeng, SUN Shaohua, QIU Chenguang, et al. Named entity recognition in power fault disposal preplan text[J]. Electric Power Engineering Technology, 2021, (5): 177- 183.
5	汤耀景, 林雅, 张彩友, 等. 考虑台风动态过程的电网故障路径分析方法[J]. 电网与清洁能源, 2024, 40 (2): 119- 126.
	TANG Yaojing, LIN Ya, ZHANG Caiyou, et al. Analysis method of power grid fault paths considering the dynamic process of typhoons[J]. Power System and Clean Energy, 2024, 40 (2): 119- 126.
6	赵贵中, 黄淼华. 基于BERT-BiLSTM-CRF的电力事故信息抽取方法[J]. 综合智慧能源, 2024, 46 (11): 19- 28.
	ZHAO Guizhong, HUANG Miaohua. An information extraction method for electric power accidents based on BERT-BiLSTM-CRF model[J]. Integrated Intelligent Energy, 2024, 46 (11): 19- 28.
7	肖大军, 张逸茹, 徐遐龄, 等. 基于Bert的电网故障处置预案信息抽取研究与实现[J]. 电力信息与通信技术, 2023, 21 (3): 26- 32.
	XIAO Dajun, ZHANG Yiru, XU Xialing, et al. Research and implementation of power grid fault handling plan information extraction based on bert[J]. Electric Power Information and Communication Technology, 2023, 21 (3): 26- 32.
8	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 Jianming, SHAN Lianfei, PI Junbo, et al. Analysis method of fault handling plan based on knowledge graph[J]. Electrical Automation, 2023, 45 (2): 75- 78.
9	籍雯媗, 崔建业, 冯斌, 等. 基于视觉字符增强的电力调度故障预案匹配[J]. 中国电机工程学报, 2022, 42 (15): 5439- 5447.
	JI Wenxuan, CUI Jianye, FENG Bin, et al. Power dispatching fault plan matching based on visual character enhancement[J]. Proceedings of the CSEE, 2022, 42 (15): 5439- 5447.
10	WANG B, NING J, MEI D Z, et al. Auxiliary decision technology and application of power grid fault disposal based on knowledge understanding of fault preplan[C]//2020 5th International Conference on Power and Renewable Energy (ICPRE). Shanghai, China. IEEE, 2020: 246–251.
11	HE Y P, ZHANG S H, ZHANG J P, et al. Entity recognition of power fault disposal based on attention model[C]//2022 International Conference on Machine Learning, Cloud Computing and Intelligent Mining (MLCCIM). Xiamen, China. IEEE, 2022: 26–31.
12	陈岳林, 高铸成, 蔡晓东. 基于BERT与密集复合网络的长文本语义匹配模型[J]. 吉林大学学报(工学版), 2024, 54 (1): 232- 239.
	CHEN Yuelin, GAO Zhucheng, CAI Xiaodong. Long text semantic matching model based on BERT and dense composite network[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54 (1): 232- 239.
13	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 Bo, ZHANG Yue, MENG Fei, et al. Adaptive understanding framework and key technology of power grid fault disposal information[J]. Electric Power, 2024, 57 (7): 188- 195.
14	杨祎, 崔其会, 秦佳峰, 等. 改进BERT的故障案例智能匹配方法[J]. 山东电力技术, 2022, 49 (2): 47- 53.
	YANG Yi, CUI Qihui, QIN Jiafeng, et al. Intelligent matching method for fault cases based on improve BERT[J]. Shandong Electric Power, 2022, 49 (2): 47- 53.
15	陈蕾, 郑伟彦, 余慧华, 等. 基于BERT的电网调度语音识别语言模型研究[J]. 电网技术, 2021, 45 (8): 2955- 2961.
	CHEN Lei, ZHENG Weiyan, YU Huihua, et al. Language model for speech recognition of power grid dispatching based on BERT[J]. Power System Technology, 2021, 45 (8): 2955- 2961.
16	贾骏, 杨强, 付慧, 等. 基于电力设备大数据的预训练语言模型构建和文本语义分析[J]. 中国电机工程学报, 2023, 43 (3): 1027- 1036.
	JIA Jun, YANG Qiang, FU Hui, et al. Research on pre-training language model construction and text semantic analysis based on power equipment big data[J]. Proceedings of the CSEE, 2023, 43 (3): 1027- 1036.
17	朱丹丹, 贾勇勇, 周前. 考虑负荷聚合商资源灵活度的荷源协调优化调度方法[J]. 浙江电力, 2024, 43 (4): 12- 20.
	ZHU Dandan, JIA Yongyong, ZHOU Qian. A load-source coordinated scheduling method based on resource flexibility of load aggregators[J]. Zhejiang Electric Power, 2024, 43 (4): 12- 20.
18	伏绍鑫, 张路, 唐翰峰, 等. 考虑柔性电热负荷的区域综合能源系统低碳经济调度[J]. 电力科技与环保, 2023, 39 (5): 417- 428.
	FU Shaoxin, ZHANG Lu, TANG Hanfeng, et al. Low-carbon economic dispatch of community integrated energy system consid-ering flexible electric heating load[J]. Electric Power Technology and Environmental Protection, 2023, 39 (5): 417- 428.
19	杨旭, 王瑞, 余畅文, 等. 基于改进灰狼优化算法的分布式能源系统优化调度[J]. 内蒙古电力技术, 2023, 41 (1): 26- 33.
	YANG Xu, WANG Rui, YU Changwen, et al. Optimal scheduling of distributed energy system based on improved grey wolf optimization algorithm[J]. Inner Mongolia Electric Power, 2023, 41 (1): 26- 33.
20	钟永洁, 王紫东, 左建勋, 等. 计及多时段尺度与地域分层的多能互补系统经济调度[J]. 综合智慧能源, 2024, 46 (4): 52- 59. DOI
	ZHONG Yongjie, WANG Zidong, ZUO Jianxun, et al. Economic dispatch of multi-energy complementary system considering multi-time-scale and regional stratification[J]. Integrated Intelligent Energy, 2024, 46 (4): 52- 59. DOI
21	胡怡然, 夏芳. 基于自注意力机制与BiLSTM的短文本匹配模型[J]. 武汉科技大学学报, 2023, 46 (1): 75- 80.
	HU Yiran, XIA Fang. A short text matching model using self-attention mechanism and BiLSTM[J]. Journal of Wuhan University of Science and Technology, 2023, 46 (1): 75- 80.
22	邵冠宇, 王慧芳, 吴向宏, 等. 基于依存句法分析的电力设备缺陷文本信息精确辨识方法[J]. 电力系统自动化, 2020, 44 (12): 178- 185. DOI
	SHAO Guanyu, WANG Huifang, WU Xianghong, et al. Precise information identification method of power equipment defect text based on \nDependency parsing[J]. Automation of Electric Power Systems, 2020, 44 (12): 178- 185. DOI
23	陈鑫, 李伟康, 洪宇, 等. 面向问句复述识别的多卷积自交互匹配方法研究[J]. 中文信息学报, 2019, 33 (10): 99- 108, 118.
	CHEN Xin, LI Weikang, HONG Yu, et al. A multi-convolution self-interaction method for question paraphrase identification[J]. Journal of Chinese Information Processing, 2019, 33 (10): 99- 108, 118.