针对光伏系统直流串联电弧故障特征难以提取且算法普遍缺乏泛化性、适应性的问题,提出一种基于动态时间规整（DTW）的串联电弧故障特征提取新方法。首先计算电流信号的移动平均值（MA）来识别突变事件,采集异常信号;接着使用奇异谱分析（SSA）去除异常信号中的趋势成分,减小不同光伏系统信号之间的差异;随后,计算信号的DTW距离来提取有效特征;最后,使用特征向量的波形因子作为诊断判据,辨识出电弧、短路以及由逆变器启动、辐照度突变引起的干扰事件。实验结果表明,基于所提特征提取的电弧故障识别方法不仅速度快、特征辨识度高,而且适用于不同的逆变器系统,具有较强的适应性,综合性能优于对比方法。
Abstract
In light of challenges encountered in extracting DC series arc fault features within photovoltaic （PV） system and the observed limitations in algorithm generalization and adaptability, this study introduces a novel series arc fault feature extraction method based on dynamic time warping （DTW）. Initially, the moving average （MA） value of the current signal is calculated to identify the mutation event and collect the abnormal signal. Then, the singular spectrum analysis （SSA） is used to remove the trend component of abnormal signals and reduce the differences between different PV system signals. Following this, the DTW distance of the signal is calculated to extract the valid features. In the end, the waveform factor of the identified feature vector serves as the diagnostic criterion to identify the arc fault, short circuit fault and the interference events caused by inverter start-up and irradiance mutation. The experimental results show that the arc fault identification method based on the proposed feature extraction is not only fast and highly recognizable, but also suitable for different inverter systems, has strong adaptability, and the comprehensive performance is better than that of the comparison method.
关键词
光伏系统 /
电弧 /
故障检测 /
动态时间规整 /
奇异谱分析
Key words
photovoltaic system /
electric arcs /
fault detection /
dynamic time warping（DTW） /
singular spectrum analysis（SSA）
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] DHAR S, PATNAIK R K, DASH P K.Fault detection and location of photovoltaic based DC microgrid using differential protection strategy[J]. IEEE transactions on smart grid, 2018, 9(5): 4303-4312.
[2] 龙官微, 穆海宝, 张大宁, 等. 基于多特征融合神经网络的串联电弧故障识别技术[J]. 高电压技术, 2021, 47(2): 463-471.
LONG G W, MU H B, ZHANG D N, et al.Series arc fault detection technology based on multi-feature fusion neural network[J]. High voltage engineering, 2021, 47(2): 463-471.
[3] SIDHU T S, SACHDEV M S, SAGOO G S.Detection and location of low-level arcing faults in metal-clad electrical apparatus[C]//2001 Seventh International Conference on Developments in Power System Protection (IEE). Amsterdam, Netherlands, 2002: 157-160.
[4] XIONG Q, JI S C, ZHU L Y, et al.A novel DC arc fault detection method based on electromagnetic radiation signal[J]. IEEE transactions on plasma science, 2017, 45(3): 472-478.
[5] CHEN S, LU Q S, MENG Y, et al.Hardware implementation of series arc fault detection algorithm for different DC resistive systems[C]//2019 IEEE Holm Conference on Electrical Contacts. Milwaukee, WI, USA, 2019: 245-249.
[6] 刘璇, 熊兰, 王韵, 等. 光伏电站串联型直流电弧的检测算法与保护实验研究[J]. 太阳能学报, 2022, 43(1): 348-355.
LIU X, XIONG L, WANG Y, et al.Experimental study on detection algorithm and protection of DC series arc in photovoltaic station[J]. Acta energiae solaris sinica, 2022, 43(1): 348-355.
[7] 吴春华, 徐文新, 李智华. 光伏系统直流电弧故障检测方法及其抗干扰研究[J]. 中国电机工程学报, 2018, 38(12): 3546-3555, 14.
WU C H, XU W X, LI Z H, et al.Study on detection method and its anti-interference of DC arc fault for photovoltaic system[J]. Proceedings of the CSEE, 2018, 38(12): 3546-3555, 14.
[8] 孟羽, 陈思磊, 吴子豪, 等. 基于随机共振方法增强光伏直流故障电弧检测特征的研究[J]. 中国电机工程学报, 2022, 42(6): 2396-2407.
MENG Y, CHEN S L, WU Z H, et al.Research on feature enhancement of DC arc fault detection in photovoltaic systems based on stochastic resonance[J]. Proceedings of the CSEE, 2022, 42(6): 2396-2407.
[9] 黄雨薇, 彭道刚, 姚峻, 等. 基于SSA和K均值的TD-BP神经网络超短期光伏功率预测[J]. 太阳能学报, 2021, 42(4): 229-238.
HUANG Y W, PENG D G, YAO J, et al.Ultra-short-term photovoltaic power forecast of TD-BP neural network based on SSA and K-means[J]. Acta energiae solaris sinica, 2021, 42(4): 229-238.
[10] 肖白, 肖志峰, 姜卓, 等. 基于降噪自编码器、奇异谱分析和长短期记忆神经网络的空间电力负荷态势感知[J]. 中国电机工程学报, 2021, 41(14): 4858-4867.
XIAO B, XIAO Z F, JIANG Z, et al.Spatial load situation awareness based on denoising autoencoder, singular spectrum analysis and long short-term memory neural networks[J]. Proceedings of the CSEE, 2021, 41(14): 4858-4867.
[11] 林顺富, 詹银枫, 李毅, 等. 基于CNN-BiLSTM与DTW的非侵入式住宅负荷监测方法[J]. 电网技术, 2022, 46(5): 1973-1981.
LIN S F, ZHAN Y F, LI Y, et al.Non-intrusive residential load monitoring method based on CNN-BiLSTM and DTW[J]. Power system technology, 2022, 46(5): 1973-1981.
[12] 万书亭, 马晓棣, 陈磊, 等. 基于振动信号短时能熵比与DTW的高压断路器状态评估及故障诊断[J]. 高电压技术, 2020, 46(12): 4249-4257.
WAN S T, MA X D, CHEN L, et al.State evaluation and fault diagnosis of high-voltage circuit breaker based on short-time energy entropy ratio of vibration signal and DTW[J]. High voltage engineering, 2020, 46(12): 4249-4257.
[13] 童晓阳, 杨明杰, 张广骁. 基于改进DTW的行波波形相似性的高压直流输电线路保护方案[J]. 中国电机工程学报, 2020, 40(12): 3878-3888.
TONG X Y, YANG M J, ZHANG G X.A protection scheme for HVDC transmission line based on traveling waveform similarity using improved DTW algorithm[J]. Proceedings of the CSEE, 2020, 40(12): 3878-3888.
[14] LE V, YAO X, MILLER C, et al.Series DC arc fault detection based on ensemble machine learning[J]. IEEE transactions on power electronics, 2020, 35(8): 7826-7839.
[15] CAO Y, LI J, SUMNER M,et al.Arc fault generation and detection in DC systems[C]//2013 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC). Hong Kong, China, 2014: 1-5.
[16] KIM J C, KWAK S S.Frequency-domain characteristics of series DC arcs in photovoltaic systems with voltage-source inverters[J]. Applied sciences, 2020, 10(22): 8042.
[17] CAI X R, WAI R J.Intelligent DC arc-fault detection of solar PV power generation system via optimized VMD-based signal processing and PSO-SVM classifier[J]. IEEE journal of photovoltaics, 2022, 12(3): 1058-1077.
PDF(2594 KB)
