基于卷积双向长短期记忆网络的微网继电保护故障诊断技术

杨志淳; 闵怀东; 杨帆; 雷杨; 胡伟; 陈鹤冲

doi:10.19912/j.0254-0096.tynxb.2023-1431

PDF(1374 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (1) : 420-428. DOI: 10.19912/j.0254-0096.tynxb.2023-1431

基于卷积双向长短期记忆网络的微网继电保护故障诊断技术

杨志淳, 闵怀东, 杨帆, 雷杨, 胡伟, 陈鹤冲

作者信息 +

FAULT DIAGNOSIS TECHNOLOGY OF RELAY PROTECTION IN MICROGRID BASED ON CONVOLUTIONAL BIDI-RECTIONAL LONG SHORT-TERM MEMORY NETWORK

Yang Zhichun, Min Huaidong, Yang Fan, Lei Yang, Hu Wei, Chen Hechong

Author information +

文章历史 +

摘要

分布式电源种类和容量不断提升的微网运行方式复杂、故障特征微弱,现有的继电保护装置故障诊断方法无法满足保护需求。提出一种基于卷积双向长短期记忆网络的微网继电保护故障诊断技术。首先,分析多能源互补微网系统架构,对采集的三相电流数据进行预处理,提高后续模型对数据的学习效率;然后,融合卷积神经网络和双向长短期记忆网络提出卷积双向长短期记忆网络的微网继电保护故障诊断方法,提取三相电流数据长序列和局部序列特征实现故障分类、故障定位,融合注意力机制,重点关注对故障诊断有影响的特征,提高故障诊断准确率;最后经过RTDS实时仿真系统进行验证,实验结果表明,所提方法故障诊断精度高、计算时间短,同卷积神经网络、长短期记忆网络、人工神经网络相比,故障分类准确率分别提升8.53%、9.62%、11.45%,故障定位准确率分别提升7.47%、10.61%、10.85%,验证所提方法的有效性与先进性。

Abstract

The operation mode of microgrids with continuously increasing types and capacities of distributed power sources is complex and the fault characteristics are weak. The existing fault diagnosis methods for relay protection devices cannot meet the protection requirements. A fault diagnosis technique for relay protection in microgrid based on convolutional bidirectional Long short-term memory network is proposed. First, analyze the architecture of the multi energy complementary microgrid system, preprocess the collected three-phase current data, and improve the learning efficiency of the subsequent model on the data; Then, combining Convolutional neural network and bi-directional Long short-term memory network, a fault diagnosis method for micro network relay protection based on convolutional bidirectional Long short-term memory network is proposed. Long sequence and local sequence features of three-phase current data are extracted to achieve fault classification and fault location. The fusion attention mechanism focuses on features that have an impact on fault diagnosis, and improves the accuracy of fault diagnosis; Finally, the RTDS real-time simulation system is used to verify the experimental results. The experimental results show that the proposed method has high fault diagnosis accuracy and short calculation time. Compared with Convolutional neural network, long short-term memory network and artificial neural network, the accuracy of fault classification is increased by 8.53%, 9.62% and 11.45% respectively, and the accuracy of fault location is increased by 7.47%, 10.61% and 10.85%, which verifies the effectiveness and progressiveness of the proposed method.

导出引用

杨志淳, 闵怀东, 杨帆, 雷杨, 胡伟, 陈鹤冲. 基于卷积双向长短期记忆网络的微网继电保护故障诊断技术[J]. 太阳能学报. 2025, 46(1): 420-428 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1431

Yang Zhichun, Min Huaidong, Yang Fan, Lei Yang, Hu Wei, Chen Hechong. FAULT DIAGNOSIS TECHNOLOGY OF RELAY PROTECTION IN MICROGRID BASED ON CONVOLUTIONAL BIDI-RECTIONAL LONG SHORT-TERM MEMORY NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(1): 420-428 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1431

中图分类号： TM732

参考文献

[1] 王红艳, 周国华, 徐顺刚, 等. 基于串联型分布式MPPT架构的直流微网系统无缝切换控制策略[J]. 电力自动化设备, 2019, 39(2): 188-195, 203.
WANG H Y, ZHOU G H, XU S G, et al.Seamless switching control strategy of DC microgrid based on cascaded distributed MPPT architecture[J]. Electric power automation equipment, 2019, 39(2): 188-195, 203.
[2] CORNEA O, ANDREESCU G D, MUNTEAN N, et al.Bidirectional power flow control in a DC microgrid through a switched-capacitor cell hybrid DC-DC converter[J]. IEEE transactions on industrial electronics, 2017, 64(4): 3012-3022.
[3] 冉金周, 李华强, 李彦君, 等. 考虑灵活性供需匹配的孤岛微网优化调度策略[J]. 太阳能学报, 2022, 43(5): 36-44.
RAN J Z, LI H Q, LI Y J, et al.Optimal scheduling of isolated microgrid considering flexible power supply and demand[J]. Acta energiae solaris sinica, 2022, 43(5): 36-44.
[4] 张伟亮, 张辉, 支娜, 等. 环形直流微电网故障分析与保护[J]. 电力系统自动化, 2020, 44(24): 105-110.
ZHANG W L, ZHANG H, ZHI N, et al.Fault analysis and protection of ring DC microgrid[J]. Automation of electric power systems, 2020, 44(24): 105-110.
[5] 程启明, 沈磊, 程尹曼, 等. 基于PR控制和滤波电感电流的微网限流新方法[J]. 太阳能学报, 2021, 42(7): 35-43.
CHENG Q M, SHEN L, CHENG Y M, et al.Microgrid current-limiting method based on pr controland filter inductance current[J]. Acta energiae solaris sinica, 2021, 42(7): 35-43.
[6] KUMAR R, SAXENA D.Fault location in distribution network using travelling waves[J]. International journal of energy sector management, 2019, 13(3): 651-669.
[7] 王圣辉, 范春菊, 姜山. 基于暂态电压比原理的直流配电网故障保护方案[J]. 电力自动化设备, 2020, 40(7): 196-203.
WANG S H, FAN C J, JIANG S.Fault protection scheme for DC distribution network based on ratio of transient voltage principle[J]. Electric power automation equipment, 2020, 40(7): 196-203.
[8] GEDDADA N, YEAP Y M, UKIL A.Experimental validation of fault identification in VSC-based DC grid system[J]. IEEE transactions on industrial electronics, 2018, 65(6): 4799-4809.
[9] ROY S, DEBNATH S.PSD based high impedance fault detection and classification in distribution system[J]. Measurement, 2021, 169: 108366.
[10] 李毓, 张增强, 罗锐, 等. 结合微电网运行方式的综合能源系统规划方法[J]. 智慧电力, 2020(6): 40-46.
LI Y, ZHANG Z Q, LUO R, et al.Integrated energy system planning method combined with microgrid operation mode[J]. Smart power, 2020(6): 40-46.
[11] 王晓东, 王若瑾, 刘颖明, 等. 基于EMD-MDT的直流微电网线路故障检测[J]. 太阳能学报, 2022, 43(11): 522-528.
WANG X D, WANG R J, LIU Y M, et al.Line fault monitoring of dc microgrid based on emd-mdt[J]. Acta energiae solaris sinica, 2022, 43(11): 522-528.
[12] QAZI A, HUSSAIN F, RAHIM N A, et al.Towards sustainable energy: a systematic review of renewable energy sources, technologies, and public opinions[J]. IEEE access, 2019, 7: 63837-63851.
[13] 米阳, 李战强, 刘红业, 等. 考虑通信故障的直流微电网多储能荷电状态动态均衡策略[J]. 电网技术, 2018, 42(10): 3282-3290.
MI Y, LI Z Q, LIU H Y, et al.State-of-charge dynamic balancing strategy for multi energy storage of DC micro-grid considering communication faults[J]. Power system technology, 2018, 42(10): 3282-3290.
[14] 孟润泉, 杜毅, 韩肖清, 等. 可变拓扑的改进型交直流混合微电网[J]. 电力系统自动化, 2020, 44(18): 147-154.
MENG R Q, DU Y, HAN X Q, et al.An improved hybrid AC/DC microgrid with variable topology[J]. Automation of electric power systems, 2020, 44(18): 147-154.
[15] 林梅芬, 陈婷, 王秋杰, 等. 一种配电网基于模型诊断的最小碰集改进算法[J]. 电力系统保护与控制, 2020, 48(8): 25-33.
LIN M F, CHEN T, WANG Q J, et al.An improved minimum set algorithm for model-based diagnosis of a distribution network[J]. Power system protection and control, 2020, 48(8): 25-33.
[16] KAVI M, MISHRA Y, VILATHGAMUWA M D.High-impedance fault detection and classification in power system distribution networks using morphological fault detector algorithm[J]. IET generation, transmission & distribution, 2018, 12(15): 3699-3710.
[17] 丁芃, 朱珂, 朱裕庆, 等. 基于模型辨识的配电线路永久性故障判定方法[J]. 电工技术学报, 2019, 34(5): 1004-1012.
DING P, ZHU K, ZHU Y Q, et al.Determining the permanent fault in distribution lines based on model recognition[J]. Transactions of China Electrotechnical Society, 2019, 34(5): 1004-1012.
[18] SOBRINHO A S F, FLAUZINO R A, LIBONI L H B, et al. Proposal of a fuzzy-based PMU for detection and classification of disturbances in power distribution networks[J]. International journal of electrical power & energy systems, 2018, 94: 27-40.
[19] 杨彦杰, 陈月, 杨康. 小波包分析与神经网络的微电网线路故障诊断[J]. 自动化仪表, 2017, 38(9): 65-69, 74.
YANG Y J, CHEN Y, YANG K.Fault diagnosis for transmission line of microgrid based on wavelet packet analysis and neural network[J]. Process automation instrumentation, 2017, 38(9): 65-69, 74.
[20] 杨彦杰, 毛亚峰, 唐圣学, 等. 基于RTDS和神经网络的光储微电网线路故障诊断[J]. 可再生能源, 2018, 36(7): 1010-1016.
YANG Y J, MAO Y F, TANG S X, et al.Photovoltaic/battery micro-grid fault diagnosis based on RTDS and neural network[J]. Renewable energy resources, 2018, 36(7): 1010-1016.
[21] JIANG T T, DU C S, GUO S, et al.Microgrid fault diagnosis model based on Weighted Fuzzy Neural Petri Net[C]//2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Chongqing, China, 2020: 2361-2365.
[22] KHALAF A, AL HASSAN H A, EMES A, et al. A machine learning approach for classifying faults in microgrids using wavelet decomposition[C]//2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP). Pittsburgh, PA, USA, 2019: 1-6.
[23] MISHRA M, ROUT P K.Detection and classification of micro-grid faults based on HHT and machine learning techniques[J]. IET generation, transmission & distribution, 2018, 12(2): 388-397.
[24] YU J J Q, HOU Y H, LAM A Y S, et al. Intelligent fault detection scheme for microgrids with wavelet-based deep neural networks[J]. IEEE transactions on smart grid, 2019, 10(2): 1694-1703.
[25] 李思琦, 蒋志坚. 基于EEMD-CNN的滚动轴承故障诊断方法[J]. 机械强度, 2020, 42(5): 1033-1038.
LI S Q, JIANG Z J.Fault diagnosis method of rolling bearing based on eemd-cnn[J]. Journal of mechanical strength, 2020, 42(5): 1033-1038.
[26] ZHAO B, ZHANG X M, LI H, et al.Intelligent fault diagnosis of rolling bearings based on normalized CNN considering data imbalance and variable working conditions[J]. Knowledge-based systems, 2020, 199: 105971.
[27] 贾京龙, 余涛, 吴子杰, 等. 基于卷积神经网络的变压器故障诊断方法[J]. 电测与仪表, 2017, 54(13): 62-67.
JIA J L, YU T, WU Z J, et al.Fault diagnosis method of transformer based on convolutional neural network[J]. Electrical measurement & instrumentation, 2017, 54(13): 62-67.
[28] 赵志宏, 赵敬娇, 魏子洋. 基于BiLSTM的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(1): 95-101.
ZHAO Z H, ZHAO J J, WEI Z Y.Rolling bearing fault diagnosis based on BiLSM network[J]. Journal of vibration and shock, 2021, 40(1): 95-101.
[29] 和志强, 杨建, 罗长玲. 基于BiLSTM神经网络的特征融合短文本分类算法[J]. 智能计算机与应用, 2019, 9(2): 21-27.
HE Z Q, YANG J, LUO C L.Combination characteristics based on BiLSTM for short text classification[J]. Intelligent computer and applications, 2019, 9(2): 21-27.