电网故障处置信息自适应理解框架及关键技术

doi:10.11930/j.issn.1004-9649.202401026

摘要/Abstract

摘要：

为了提升电网故障处置响应能力，提出一种故障处置信息自适应理解框架，该框架基于所构建的多任务协同理解模型和故障处置知识图谱识别电网故障告警、运行状态、操作指令等信息，自适应推理生成故障处置操作策略。通过建立故障处置信息理解模型评价指标和试验数据集，验证了故障处置信息理解框架和多任务协同理解模型的有效性。

关键词: 故障处置, 多任务协同, 知识图谱, 自适应推理

Abstract:

In order to improve the response capacity of power grid fault disposal, an adaptive understanding framework of fault disposal information is proposed. The framework is based on the constructed multi-task collaborative understanding model and the fault disposal knowledge graph to identify the power grid fault alarm, operation status, operation instruction and other information, and the fault disposal operation strategy is generated by reasoning adaptively. By establishing the evaluation index system and test data set of fault disposal information, the experimental effect of the adaptive understanding framework of fault disposal information and multi-task collaborative understanding model are verified.

Key words: fault disposal, multi-task collaborative, knowledge graph, adaptive reasoning

田波, 张越, 蒙飞, 单连飞, 高海洋, 田坤, 乔咏田. 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.

Bo TIAN, Yue ZHANG, Fei MENG, Lianfei SHAN, Haiyang GAO, Kun TIAN, Yongtian QIAO. Adaptive Understanding Framework and Key Technology of Power Grid Fault Disposal Information[J]. Electric Power, 2024, 57(7): 188-195.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202401026

https://www.electricpower.com.cn/CN/Y2024/V57/I7/188

图/表 9

图 1 电网故障处置信息自适应理解框架

Fig.1 The adaptive understanding framework of fault disposal information

图 2 BERT模型结构

Fig.2 Structure of BERT model

图 3 故障处置信息多任务协同理解模型结构

Fig.3 Structure of fault disposal information multi-task collaborative understanding model

图 4 故障处置知识图谱形态

Fig.4 The form of fault disposal knowledge graph

表 1 部分故障处置试验数据

Table 1 Partial fault disposal test data

序号	操作意图	操作意图表述
1	调阅电网负荷曲线	查询宁夏电网负荷曲线
2	查询有功出力	查询常胜变有功
3	查询机组备用出力	查询大坝电厂#1机备用出力
4	打开有功曲线	打开中宁二厂有功曲线
···	···	···
22	打开厂站图	打开常胜变厂站图
23	查询事故预案	查询大侯双回线跳闸预案
24	打开潮流图	打开宁夏电网潮流图

表 2 部分故障处置信息标记数据

Table 2 Partial fault disposal information label data

序号	操作意图表述	标记意图	标记槽位
1	查询大侯I线有功曲线	open_active_power_ output_curve	大侯I线
2	查询宁夏电网功率曲线	open_grid_load_curve	宁夏电网
···	···	···	···
17560	查询昭沂直流潮流	query_trend_size	昭沂直流

图 5 故障处置信息意图识别效果

Fig.5 Identification effect of fault disposal information intention

表 3 故障处置信息多任务协同理解模型识别效果

Table 3 Recognition effect of fault disposal information multi-task collaborative understanding model 单位：%

样本集	精准率	召回率	F₁值
训练样本	99.96	99.96	99.96
验证样本	99.95	99.95	99.95
测试样本	99.02	99.31	99.16

表 4 各模型评价指标计算结果

Table 4 Calculation results of evaluation indicators for each model 单位：%

模型	精准率	召回率	F₁值
BERT-CRF	99.02	99.31	99.16
BiLSTM-CRF	97.99	98.40	98.19
DPCNN+IDCNN	91.47	92.21	91.84
TextCNN+BiLSTM-CRF	97.80	98.14	97.97

参考文献 25

1	莫石, 徐秋实, 卢子敬, 等. 模糊分割多目标风险框架下电网连锁故障运行风险评估[J]. 中国电力, 2024, 57 (2): 41- 48.
	MO Shi, XU Qiushi, LU Zijing, et al. Fuzzy partitioned multi-objective risk framework based operational risk assessment of cascading failure for power grid[J]. Electric Power, 2024, 57 (2): 41- 48.
2	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.
3	毕超豪, 史艳刚, 付志超, 等. 基于MMC的多端直流电网通用计算方法及拓扑优化研究[J]. 智慧电力, 2023, 51 (4): 99- 106. DOI
	BI Chaohao, SHI Yangang, FU Zhichao, et al. MMC-based general calculation method and topology optimization of DC power grid[J]. Smart Power, 2023, 51 (4): 99- 106. DOI
4	袁泉, 周海峰, 黄金满, 等. 电网故障诊断解析模型的改进二进制增益共享知识算法求解[J]. 电力系统保护与控制, 2023, 51 (24): 175- 187.
	YUAN Quan, ZHOU Haifeng, HUANG Jinman, et al. An improved binary Gaining-sharing knowledge-based algorithm for solving the analytic model of power grid fault diagnosis[J]. Power System Protection and Control, 2023, 51 (24): 175- 187.
5	程学珍, 庄学山, 孟璐莎. 基于加权模糊的时序约束Petri网电网故障诊断方法[J]. 智慧电力, 2023, 51 (11): 83- 90. DOI
	CHENG Xuezhen, ZHUANG Xueshan, MENG Lusha. Fault diagnosis method of power grid based on weighted fuzzy temporal constraint petri net[J]. Smart Power, 2023, 51 (11): 83- 90. DOI
6	王洪彬, 周念成, 黄睿灵, 等. 基于深度学习的110kV电网监控信号语义解析及态势感知模型[J]. 电力系统保护与控制, 2023, 51 (2): 160- 168.
	WANG Hongbin, ZHOU Niancheng, HUANG Ruiling, et al. 110 kV signal semantic analysis and situation awareness model based on deep learning theory for a power system monitoring system[J]. Power System Protection and Control, 2023, 51 (2): 160- 168.
7	孙端航, 李本新. 考虑风电不确定性的电网状态检修策略[J]. 东北电力大学学报, 2023, 43 (4): 65- 73.
	SUN Duanhang, LI Benxin. Condition-based maintenance scheduling for power transmission system considering wind power uncertainty[J]. Journal of Northeast Electric Power University, 2023, 43 (4): 65- 73.
8	刘育权, 宋禹飞, 梁锦照, 等. 电力设备数字化标准一体化支撑智能制造[J]. 南方电网技术, 2022, 16 (12): 46- 53.
	LIU Yuquan, SONG Yufei, LIANG Jinzhao, et al. Digital standardization integration on power equipment for intelligent manufacturing[J]. Southern Power System Technology, 2022, 16 (12): 46- 53.
9	王中行, 周元贵, 张学广. 基于人工智能算法的风电机组状态监测和故障诊断技术研究综述[J]. 东北电力大学学报, 2024, 44 (1): 42- 51.
	WANG Zhongxing, ZHOU Yuangui, ZHANG Xueguang. Review of artificial intelligence algorithms-based wind turbine condition monitoring and fault diagnosis techniques[J]. Journal of Northeast Electric Power University, 2024, 44 (1): 42- 51.
10	王福贺, 海威, 张越, 等. 电网线路故障处置智能调度机器人研究及应用[J]. 电气自动化, 2021, 43 (3): 1- 3, 23. DOI
	WANG Fuhe, HAI Wei, ZHANG Yue, et al. Research and application of intelligent dispatching robots handling grid line faults[J]. Electrical Automation, 2021, 43 (3): 1- 3, 23. DOI
11	乔骥, 王新迎, 闵睿, 等. 面向电网调度故障处理的知识图谱框架与关键技术初探[J]. 中国电机工程学报, 2020, 40 (18): 5837- 5849.
	QIAO Ji, WANG Xinying, MIN Rui, et al. Framework and key technologies of knowledge-graph-based fault handling system in power grid[J]. Proceedings of the CSEE, 2020, 40 (18): 5837- 5849.
12	郭榕, 杨群, 刘绍翰, 等. 电网故障处置知识图谱构建研究与应用[J]. 电网技术, 2021, 45 (6): 2092- 2100.
	GUO Rong, YANG Qun, LIU Shaohan, et al. Construction and application of power grid fault handing knowledge graph[J]. Power System Technology, 2021, 45 (6): 2092- 2100.
13	王骏东, 杨军, 裴洋舟, 等. 基于知识图谱的配电网故障辅助决策研究[J]. 电网技术, 2021, 45 (6): 2101- 2112.
	WANG Jundong, YANG Jun, PEI Yangzhou, et al. Distribution network fault assistant decision-making based on knowledge graph[J]. Power System Technology, 2021, 45 (6): 2101- 2112.
14	张晓华, 冯长有, 王永明, 等. 电网调控机器人设计思路[J]. 电力系统自动化, 2019, 43 (13): 1- 8. DOI
	ZHANG Xiaohua, FENG Changyou, WANG Yongming, et al. Design ideas of robotic dispatcher for power grid[J]. Automation of Electric Power Systems, 2019, 43 (13): 1- 8. DOI
15	李明节, 陶洪铸, 许洪强, 等. 电网调控领域人工智能技术框架与应用展望[J]. 电网技术, 2020, 44 (2): 393- 400.
	LI Mingjie, TAO Hongzhu, XU Hongqiang, et al. The technical framework and application prospect of artificial intelligence application in the field of power grid dispatching and control[J]. Power System Technology, 2020, 44 (2): 393- 400.
16	殷婕. 基于数据挖掘的输电断面动态极限传输功率在线构建方法[J]. 东北电力大学学报, 2023, 43 (1): 69- 75.
	YIN Jie. Online construction of dynamic total transfer capability of transmission interface based onData mining technology[J]. Journal of Northeast Electric Power University, 2023, 43 (1): 69- 75.
17	陈郑平, 米为民, 林静怀, 等. 电网调控操作智能助手方案探讨[J]. 电力系统自动化, 2019, 43 (22): 173- 178, 186. DOI
	CHEN Zhengping, MI Weimin, LIN Jinghuai, et al. Discussion on intelligence assistant scheme of dispatching and control operation in power grid[J]. Automation of Electric Power Systems, 2019, 43 (22): 173- 178, 186. DOI
18	张中正, 王蓓, 赵建保, 等. 基于NL2SQL实现电力数据智能交互[J]. 电网技术, 2022, 46 (7): 2564- 2571.
	ZHANG Zhongzheng, WANG Bei, ZHAO Jianbao, et al. Realization of power data intelligent interaction based on NL2SQL[J]. Power System Technology, 2022, 46 (7): 2564- 2571.
19	余建明, 刘赫, 单连飞, 等. 基于ALBERT和RE2融合模型的电网调度意图识别方法[J]. 电力系统保护与控制, 2022, 50 (12): 144- 151.
	YU Jianming, LIU He, SHAN Lianfei, et al. Method of power grid dispatch intention recognition based on ALBERT and RE2 fusion model[J]. Power System Protection and Control, 2022, 50 (12): 144- 151.
20	田园, 原野, 刘海斌, 等. 基于BERT预训练语言模型的电网设备缺陷文本分类[J]. 南京理工大学学报, 2020, 44 (4): 446- 453.
	TIAN Yuan, YUAN Ye, LIU Haibin, et al. BERT pre-trained language model for defective text classification of power grid equipment[J]. Journal of Nanjing University of Science and Technology, 2020, 44 (4): 446- 453.
21	SU J, DAI Q Y, GUERIN F, et al. BERT-hLSTMs: BERT and hierarchical LSTMs for visual storytelling[J]. Computer Speech & Language, 2021, 67, 101169.
22	ARASE Y, TSUJII J. Transfer fine-tuning of BERT with phrasal paraphrases[J]. Computer Speech & Language, 2021, 66, 101164.
23	蒋晨, 王渊, 胡俊华, 等. 基于深度学习的电力实体信息识别方法[J]. 电网技术, 2021, 45 (6): 2141- 2149.
	JIANG Chen, WANG Yuan, HU Junhua, et al. Power entity information recognition based on deep learning[J]. Power System Technology, 2021, 45 (6): 2141- 2149.
24	刘赫, 皮俊波, 宋鹏程, 等. 基于混合神经网络的电力调度文本事件抽取方法[J]. 中国电力, 2022, 55 (9): 105- 110, 120.
	LIU He, PI Junbo, SONG Pengcheng, et al. An event extraction method for power dispatching text based on hybrid neural network[J]. Electric Power, 2022, 55 (9): 105- 110, 120.
25	刘东, 张越, 皮俊波, 等. 面向电网调控信息智能检索的知识图谱构建及应用[J]. 中国电力, 2023, 56 (7): 78- 84.
	LIU Dong, ZHANG Yue, PI Junbo, et al. Construction and application of knowledge graph for intelligent retrieval of power grid dispatching and control information[J]. Electric Power, 2023, 56 (7): 78- 84.

[1]	张金营, 王哲峰, 谢华, 么长英, 闵艳丽, 王新颖. 基于知识图谱与大语言模型的电力行业知识检索分析系统研发与应用[J]. 中国电力, 2024, 57(12): 198-205.
[2]	刘东, 张越, 皮俊波, 单连飞, 刘赫, 宋鹏程, 姜涛. 面向电网调控信息智能检索的知识图谱构建及应用[J]. 中国电力, 2023, 56(7): 78-84.
[3]	皮俊波, 齐世雄, 孙文多, 楼贤嗣, 沃建栋, 张越, 姜涛, 单连飞. 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.
[4]	梅冰笑, 周金辉, 孙翔. 基于知识图谱与细胞自动机模型的配电网信息系统风险分析[J]. 中国电力, 2022, 55(10): 23-31.
[5]	李晓露, 左璇, 刘日亮, 陆一鸣, 李聪利, 林顺富. 基于形状约束语言的电网模型知识图谱验证方法[J]. 中国电力, 2022, 55(1): 119-125,228.
[6]	李新鹏, 徐建航, 郭子明, 李军良, 宁文元, 王震学. 调度自动化系统知识图谱的构建与应用[J]. 中国电力, 2019, 52(2): 70-77,157.