| 220 | 8 | 24 |
| 下载次数 | 被引频次 | 阅读次数 |
为实现低压配电网故障快速检测，提出基于数据驱动的检测方法。在边缘终端建立梯度提升决策树（Gradient Boosting Decision Tree，GBDT），以配电网中三相电压及三相电流作为输入特征，通过输出结果判断配电网是否发生故障。初步分析后，数据上传至区域主站，通过多头自注意力机制和GBDT算法完成故障分类和定位。边缘终端和区域主站协同工作，提升了检测效率。通过在33节点、0.4 kV配电网系统中进行仿真测试，验证了该方法的有效性和可靠性。
Abstract：In order to achieve rapid fault detection in low voltage distribution network, a data-driven detection method is proposed in this paper. Gradient Boosting Decision Tree (GBDT) is established at the edge terminal, using three-phase voltage and current in the distribution network as input features, and whether a fault has occurred in the distribution network can be determined through the output results. After preliminary analysis, the data is uploaded to the regional master station, and fault classification and localization are completed through the multi-head self-attention mechanism and GBDT algorithm. The collaboration between edge terminals and regional master stations improves the detection efficiency. The effectiveness and reliability of this method are verified through simulation test in 0.4 kV distribution network system with 33-node.
[1] 刘凯诚, 钟鸣, 曾平良, 等.考虑分布式可再生电源和储能的智能配电网可靠性评估综述[J].电测与仪表, 2021, 58(7):1-11.LIU Kaicheng, ZHONG Ming, ZENG Pingliang, et al.Review on reliability assessment of smart distribution networks considering distributed renewable energy and energy storage[J].Electrical Measurement & Instrumentation, 2021, 58(7):1-11.
[2] 曹文斌, 徐静, 王利, 等.时域反演算法在配电网故障定位的建模和仿真[J].智慧电力, 2020, 48(12):79-83.CAO Wenbin, XU Jing, WANG Li, et al.Modeling and Simulation of Fault Location with Time Reversal Algorithm in Distribution Network[J].Smart Power, 2020, 48(12):79-83.
[3] 曾祥君, 刘玉玲, 喻锟, 等.改进的配电网对地参数谐振测量方法[J].电力科学与技术学报, 2020, 35(3):3-11.ZENG Xiangjun, LIU Yuling, YU Kun, et al.An improved resonance measurement method of grounded parameters for distribution networks[J].Journal of Electric Power Science and Technology, 2020, 35(3):3-11.
[4] 董晓峰, 苏义荣, 吴健, 等.支撑城市能源互联网的主动配电网方案设计及工程示范[J].中国电机工程学报, 2018, 38(增刊1):75-85.DONG Xiaofeng, SU Yirong, WU Jian, et al.Scheme Design and Engineering Demonstration of Active Distribution Network Supporting City Energy Internetwork[J].Proceedings of the CSEE, 2018, 38(S1):75-85.
[5] 李英超.基于多电容接地方式的低压直流微电网故障定位[J].电力系统及其自动化学报, 2023, 35(4):59-67.LI Yingchao.Fault Location for Low-Voltage DC Microgrid Based on Multi-Capacitor Grounding Scheme[J].Proceedings of the CSU-EPSA, 2023, 35(4):59-67.
[6] 叶远波, 蔡翔, 谢民, 等.配电网单相接地故障快速选相方法研究[J].电力系统保护与控制, 2021, 49(3):96-103.YE Yuanbo, CAI Xiang, XIE Min, et al.Fault phase fast detection of the single-phase-to-ground fault in a power distribution network[J].Power System Protection and Control, 2023, 35(4):59-67.
[7] 陈银峰, 帅萌, 高胜强, 等.基于配电自动化系统的单相接地定位技术研究[J].机电信息, 2019(24):10-11, 13.
[8] 刘科研, 董伟杰, 肖仕武, 等.基于电压数据SVM分类的有源配电网故障判别及定位[J].电网技术, 2021, 45(6):2369-2379.LIU Keyan, DONG Weijie, XIAO Shiwu, et al.Fault Identification and Location of Active Distribution Network Based on SVM Classification of Voltage Data[J].Power System Technology, 2021, 45(6):2369-2379.
[9] 洪翠, 付宇泽, 郭谋发, 等.改进多分类支持向量机的配电网故障识别方法[J].电子测量与仪器学报, 2019, 33(1):7-15.HONG Cui, FU Yuze, GUO Moufa, et al.Identification method of distribution network faults based on improved multiclassification support vector machine[J].Journal of Electronic Measurement and Instrumentation, 2019, 33(1):7-15.
[10] 贾志成, 张智晟, 刘远龙, 等.基于RS-SVM算法的配电网故障诊断方法[J].广东电力, 2019, 32(9):107-114.JIA Zhicheng, ZHANG Zhisheng, LIU Yuanlong, et al.Fault Diagnosis Method Based on RS-SVM Algorithm for Power Distribution Network[J].Guangdong Electric Power, 2019, 32(9):107-114.
[11] 任鞅, 张无名, 杨磊, 等.基于大数据驱动的配电网故障诊断与探索性预测模型[J].电工技术, 2022(8):116-118.REN Yang, ZHANG Wuming, YANG Lei, et al.Distribution network fault diagnosis and exploratory prediction model based on big data drive[J].Electric Engineering, 2022(8):116-118.
[12] 耿继朴, 蒋锦霞, 郑晓燕, 等.基于大数据驱动的配电网故障风险预警方法[J].电力信息与通信技术, 2022, 20(7):41-49.GENG Jipu, JIANG Jinxia, ZHENG Xiaoyan, et al.Distribution network fault risk early warning method based on big data[J].Electric Power Information and Communication Technology, 2022, 20(7):41-49.
[13] 胡朝力, 周刚, 张知宇, 等.基于数据驱动的多模型故障诊断[J].电子产品世界, 2022, 29(11):22-27.HU Zhaoli, ZHOU Gang, ZHANG Zhiyu, et al.Fault diagnosis based on data-driven with different models[J].Qutlook of Electronic Technology, 2022, 29(11):22-27.
[14] 李玮, 刘勃, 张莉, 等.基于数据驱动的电网用户侧故障主动研判技术研究与应用[J].电子设计工程, 2022, 30(6):33-37.LI Wei, LIU Bo, ZHANG Li, et al.Research and application of active research and judgment technology of power grid user side fault based on data driven[J].Electronic Design Engineering, 2022, 30(6):33-37.
[15] 林洪, 王寒, 张康伟, 等.基于改进粒子群算法的配电网故障区段定位[J].电气技术与经济, 2023(1):56-59.LIN Hong, WANG Han, ZHANG Kangwei, et al.Distribution network fault location based on improved particle swarm optimization algorithm[J].Electrical Equipment and Economy, 2023(1):56-59.
[16] 张莲, 张尚德, 贾浩, 等.基于改进鲸鱼算法的配电网故障区段定位[J].浙江电力, 2022, 41(12):63-70.ZHANG Lian, ZHANG Shangde, JIA Hao, et al.Fault location of distribution network hierarchical model based on improved whale algorithm[J].Zhejiang Electric Power, 2022, 41(12):63-70.
[17] 李碧桓, 李知艺, 鞠平.基于随机矩阵理论的低压配电网边-云协同故障检测方法[J].中国电机工程学报, 2022, 42(1):25-37.LI Bihuan, LI Zhiyi, JU Ping.An Edge-Cloud Collaborative Fault Detection Method for Low-Voltage Distribution Networks Based on Random Matrix Theory[J].Proceedings of the CSEE, 2022, 42(1):25-37.
[18] 唐明珠, 赵琪, 龙文, 等.基于梯度提升决策树的风电机组齿轮箱故障检测[J].湖南电力, 2019, 39(6):52-56, 60.TANG Mingzhu, ZHAO Qi, LONG Wen, et al.Fault Detection Based on Gradient Boosting Decision Tree for Wind Turbine Gearbox[J].Hunan Electric Power, 2019, 39(6):52-56, 60.
[19] 陈宏, 邓芳明, 吴翔, 等.基于梯度提升决策树的电力电子电路故障诊断[J].测控技术, 2017, 36(5):9-12, 20.CHEN Hong, DENG Fangming, WU Xiang, et al.Fault Diagnosis of Power Electronics Circuit Based on Gradient Boosting Decision Tree[J].Measurement & Control Technology, 2017, 36(5):9-12,20.
[20] 王庆龙, 严小恺, 王禹夫, 等.智能电表电源不同环境温度下模块的可靠性分析[J].环境适应性和可靠性, 2022, 40(6):51-54.WANG Qinglong, YAN Xiaokai, WANG Yufu, et al.Reliability analysis of smart meter power supply module under different[J].Environmental Adaptability & Reliability, 2022, 40(6):51-54.
[21] Zhendong Z, Cheolkon J.GBDT-MO:Gradient-Boosted Decision Trees for Multiple Outputs[J].IEEE Transactions On Neural Networks and Learning Systems, 2021, 32(7):3156-3167.
[22] 王彦琦, 张强, 朱刘涛, 等.基于改进鲸鱼优化算法的GBDT回归预测模型[J].吉林大学学报(理学版), 2022, 60(2):401-408.WANG Yanqi, ZHANG Qiang, ZHU Liutao, et al.GBDT Regression Prediction Model Based on Improved Whale Optimization Algorithm[J].Journal of Jilin University(Science Edition), 2022, 60(2):401-408.
[23] 邱锡鹏.神经网络与深度学习[M].北京:机械工业出版社, 2020.
[24] 李俊卿, 胡晓东, 秦静茹, 等.基于多头注意力机制和卷积模型的超短期风电功率预测[J].电力科学与工程, 2022, 38(7):34-40.LI Junqing, HU Xiaodong, QIN Jingru, et al.Ultra-short Term Wind Oower Prediction Based on Multi-Head Attention and CNN Model[J].Electric Power Science and Engineering, 2022, 38(7):34-40.
[25] 吉兴全, 陈金硕, 张玉敏, 等.基于CNN-SVM的配电网故障分类研究[J].智慧电力, 2022, 50(1):94-100.JI Xingquan, CHEN Jinshuo, ZHANG Yumin, et al.Fault Classification in Distribution Network Based on CNN-SVM[J].Smart Power, 2022, 50(1):94-100.
[26] 秦飞翔, 朱革兰.基于LSTM-CNN机器学习的配电网故障定位方法[J].广东电力, 2021, 34(11):27-34.QIN Feixiang, ZHU Gelan.Fault Location Method for Distribution Network Based on LSTM-CNN Machine Learning[J].Guangdong Electric Power, 2021, 34(11):27-34.
[27] 朱方博, 张俊林, 王瑞驰, 等.基于SA-SAE的配电网故障分类方法[J].电气自动化, 2023, 45(2):100-102.ZHU Fangbo, ZHANG Junlin, WANG Ruichi, et al.Distribution Network Fault Classification Method Based on SA-SAE[J].Electrical Automation, 2023, 45(2):100-102.
[28] 杨旭冬, 李丁, 邹帅, 等.基于SSA-PNN算法的配电网的故障判别方法研究[J].信息与电脑, 2021, 33(20):19-21, 25.YANG Xudong, LI Ding, ZOU Shuai, et al.Research on Fault Identification Method of Distribution Network Based on SSA-PNN Algorithm[J].China Computer & Communication, 2021, 33(20):19-21, 25.
[29] 宗剑, 牟龙华, 张鑫, 等.配电网单相接地故障类型及程度的判据[J].电力系统及其自动化学报, 2004, 16(4):27-29.ZONG Jian, MOU Longhua, ZHANG Xin, et al.Criterion of Single-Phase Ground Fault Type and Its Degree for Distribution Network[J].Proceedings of the CSU-EPSA, 2004, 16(4):27-29.
[30] 李宾雄.农村10 kV配电线路单相接地故障分析[J].通信电源技术, 2019, 36(10):281-282.LI Binxiong.Analysis of Single-Phase Grounding Fault of Rural 10 kV Power Distribution Line[J].Telecom Power Technologies, 2019, 36(10):281-282.
[31] Sapountzoglou N, Raison B, Silva N.Fault Detection and Localization in LV Smart Grids[C]//Institute of Electrical and Electronics Engineers.2019 IEEE Milan PowerTech.Milan, 2019.
基本信息:
DOI：10.19929/j.cnki.nmgdljs.2023.0066
中图分类号:TM73
引用信息:
[1]杨军1,何金波1,陈晨辉1等.基于数据驱动的低压配电网故障检测方法[J].内蒙古电力技术,2023,41(05):28-34.DOI:10.19929/j.cnki.nmgdljs.2023.0066.
基金信息:
国家自然科学基金项目“计及热量迁移动态过程的电热耦合系统时空异构动态优化调度方法研究”（52007103）；国网浙江省电力有限公司台州市路桥区供电公司科技项目“基于数据驱动和终端—主站协同的低压配电网故障检测关键技术研究”（5211T223000L）