直流输电线路发生早期绝缘故障时电流波动小、故障现象不明显,难以快速识别以采取保护措施,光伏电站线路拓扑结构复杂,不易准确定位故障发生位置。该文提出一种连续小波变换和混合神经网络模型结合的方法,可在尽可能短的时间完成故障识别与定位。该方法首先利用连续小波变换对暂态零模电流信号提取二维时频矩阵特征,压缩为彩色图像;然后,将图像送入神经网络模型中进行训练。该混合神经网络模型通过结合卷积神经网络和门控循环单元,提高识别精度并减少训练时间。最后,为验证本方法的优势,在高噪声环境下选取4条直流输电线路分别进行4种时频分析方法、3种神经网络模型仿真对比后,又对早期绝缘故障单独进行识别仿真试验,结果表明该方法可有效识别出早期绝缘故障并定位至发生线路,且具有较强的抗噪能力。
Abstract
When an early insulation fault occurs in a DC transmission line, the current fluctuation is small and the fault phenomenon is not obvious, so it is difficult to quickly identify and take protective measures. The topology of the photovoltaic power station line is complex, and it is difficult to accurately locate the fault location. In this paper, a method combining continuous wavelet transform and hybrid neural network model is proposed to identify and locate faults in the shortest possible time. The method first uses continuous wavelet transform to extract two-dimensional time-frequency matrix features from the transient zero-mode current signal, compresses it into a color image, and then sends the image to a neural network model for training. This hybrid neural network model improves recognition accuracy and reduces training time by combining convolutional neural networks and gated recurrent units. Finally, in order to verify the advantages of this method, four HVDC transmission lines are selected in a high noise environment to carry out four time-frequency analysis methods and three neural network model simulation comparisons, and then a separate simulation test is carried out to identify early insulation faults. The results show that this method can effectively identify the early insulation fault and locate the line where it occurs, and has strong anti-noise ability.
关键词
光伏电站 /
绝缘 /
小波变换 /
直流输电 /
神经网络模型 /
电气故障定位
Key words
PV power station /
insulation /
wavelet transform /
DC transmission /
neural network model /
electric fault location
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 吴春华, 胡雅, 李智华, 等. 基于SSTDR的光伏系统直流母线电弧故障在线检测与定位[J]. 中国电机工程学报, 2020, 40(8): 2725-2735.
WU C H, HU Y, LI Z H, et al.On-line detection and location of DC bus arc faults in PV systems based on SSTDR[J]. Proceedings of the CSEE, 2020, 40(8): 2725-2735.
[2] 权文杰, 童晓阳, 张广骁. 基于S变换行波能谱矩阵相似度的柔性直流单端保护方案[J]. 电力系统自动化, 2022, 46(7): 178-186.
QUAN W J, TONG X Y, ZHANG G X.Single-end flexible DC protection scheme based on similarity of S-transform energy spectrum matrix of traveling wave[J]. Automation of electric power systems, 2022, 46(7): 178-186.
[3] 陈田田, 李银红. 基于电压折射波幅值正负差异的柔性直流电网两段式行波保护[J]. 电力系统自动化, 2022, 46(3): 129-136.
CHEN T T, LI Y H.Two-section traveling wave protection for flexible DC grid based on positive and negative difference of voltage refractive wave amplitude[J]. Automation of electric power systems, 2022, 46(3): 129-136.
[4] 戴志辉, 李毅然, 焦彦军, 等. 耐受高阻和强噪声的柔直配电线路保护原理[J]. 高电压技术, 2022, 48(10): 3966-3974.
DAI Z H, LI Y R, JIAO Y J, et al.Protection scheme for flexible DC distribution lines with high resistance and strong noise endurance ability[J]. High voltage engineering, 2022, 48(10): 3966-3974.
[5] 高淑萍, 段必聪, 宋国兵, 等. 基于暂态电流故障分量的直流配电网单极故障选线方法[J]. 太阳能学报, 2022, 43(3): 141-146.
GAO S P, DUAN B C, SONG G B, et al.Single-pole fault line selection method of DC distribution network based on transient current fault component[J]. Acta energiae solaris sinica, 2022, 43(3): 141-146.
[6] 高飘, 郑晓冬, 晁晨栩, 等. 基于特定频带能量比的高压直流输电线路保护[J]. 电力系统自动化, 2022, 46(15): 136-144.
GAO P, ZHENG X D, CHAO C X, et al.High-voltage DC transmission line protection based on energy ratio of specific frequency band[J]. Automation of electric power systems, 2022, 46(15): 136-144.
[7] 杨赛昭, 向往, 张峻榤, 等. 基于人工神经网络的架空柔性直流电网故障检测方法[J]. 中国电机工程学报, 2019, 39(15): 4416-4430.
YANG S Z, XIANG W, ZHANG J J, et al.The artificial neural network based fault detection method for the overhead MMC based DC grid[J]. Proceedings of the CSEE, 2019, 39(15): 4416-4430.
[8] 王晓卫, 高杰, 吴磊, 等. 柔性直流配电网高阻接地故障检测方法[J]. 电工技术学报, 2019, 34(13): 2806-2819.
WANG X W, GAO J, WU L, et al.A high impedance fault detection method for flexible DC distribution network[J]. Transactions of China Electrotechnical Society, 2019, 34(13): 2806-2819.
[9] 薛蕙, 杨仁刚. 利用Morlet连续小波变换实现非整次谐波的检测[J]. 电网技术, 2002, 26(12): 41-44.
XUE H, YANG R G.Morlet wavelet based detection of noninteger harmonics[J]. Power system technology, 2002, 26(12): 41-44.
[10] CHUNG J Y, GULCEHRE C, CHO K H, et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv, 2014: 1412.3555.
[11] LIU W X, SONG Y B, CHEN D S, et al.Deformable object tracking with gated fusion[J]. IEEE transactions on image processing, 2019, 28(8): 3766-3777.
[12] 赵兵, 王增平, 纪维佳, 等. 基于注意力机制的CNN-GRU短期电力负荷预测方法[J]. 电网技术, 2019, 43(12): 4370-4376.
ZHAO B, WANG Z P, JI W J, et al.A short-term power load forecasting method based on attention mechanism of CNN-GRU[J]. Power system technology, 2019, 43(12): 4370-4376.
[13] 姚程文, 杨苹, 刘泽健. 基于CNN-GRU混合神经网络的负荷预测方法[J]. 电网技术, 2020, 44(9): 3416-3424.
YAO C W, YANG P, LIU Z J.Load forecasting method based on CNN-GRU hybrid neural network[J]. Power system technology, 2020, 44(9): 3416-3424.
[14] 庄一展, 刘飞, 黄艳辉, 等. 模块化串联光伏直流变换器的环形功率均衡拓扑及效率优化策略[J]. 中国电机工程学报, 2022, 42(5): 1657-1669.
ZHUANG Y Z, LIU F, HUANG Y H, et al.A circular power balancing topology with efficiency optimization strategy for modular cascaded photovoltaic DC/DC converter[J]. Proceedings of the CSEE, 2022, 42(5): 1657-1669.
[15] BAGHERZADEH H, ABEDINI M, DAVARPANAH M, et al.A novel protection scheme to detect, discriminate, and locate electric faults in photovoltaic arrays using a minimal number of measurements[J]. International journal of electrical power & energy systems, 2022, 141: 108172.
[16] YUAN S, YANG B F, ZHANG J Y.Experimental study on short-circuit current characteristics of a photovoltaic system with low voltage ride through capability under a symmetrical fault[J]. Energy reports, 2022, 8: 4502-4511.
基金
揭榜挂帅科技攻关专项（2021JH1/10400009）
PDF(2524 KB)
