特征模式分解的局部放电信号特征提取算法

Partial Discharge Signal Feature Extraction Algorithm Based on Feature Pattern Decomposition

摘要

针对设备噪声及外界环境干扰的耦合作用下, 掩盖或扭曲了真实的局部放电信号, 增加了特征提取难度的问题, 提出了基于特征模式分解的局部放电信号特征提取算法。 采用小波变换分析信号主要边缘, 求出各尺度与邻近尺度间的相关系数, 消除局部放电信号噪声。 采用变分模态分解法分解放电信号, 计算固有模态分量的多尺度熵, 进一步滤除干扰; 结合核主成分分析法降维输入信号的特征参数, 计算出频段投影序列的能量、 模值和绝对均值, 完成特征提取。 实验证明, 所提算法可有效提取局部放电特征, 提供详尽故障信息, 确保设备稳定运行。

Abstract

Under the coupling effect of equipment noise and external environmental interference, the real partial discharge signal is masked or distorted, which increases the difficulty of feature extraction. Therefore, a partial discharge signal feature extraction algorithm based on feature pattern decomposition is proposed. Using wavelet transform to analyze the main edges of the signal, calculate the correlation coefficients between each scale and adjacent scales, and eliminate the noise of partial discharge signals. Using the variational mode decomposition method to decompose the discharge signal, calculating the multi-scale entropy of the intrinsic mode components, and further filtering out interference; Combining the kernel principal component analysis method to reduce the feature parameters of the input signal, calculate the energy, modulus, and absolute mean of the frequency band projection sequence to complete feature extraction. Experimental results have shown that the proposed algorithm effectively extracts partial discharge features, provides detailed fault information, and ensures stable operation.

关键词

特征模式分解 / 局部放电信号 / 小波变换 / 特征提取 / 相关系数

Key words

feature pattern decomposition / partial discharge signal / wavelet transform / feature extraction / correlation coefficient

参考文献

[1] 赵仕策, 赵洪山, 曲岳晗, 等. 基于虚拟通道延拓的局部放电信号压缩采样方法[J]. 电工技术学报, 2023, 38(12): 3366-3378.

[2] ZHAO S C, ZHAO H S, QU Y H, et al. Compressed Sampling of Partial Discharge Signal Based on Virtual Channel Extension[J]. Transactions of China Electrotechnical Society, 2023, 38(12): 3366-3378.

[3] YEO J, JIN H, MOR A R, et al. Localisation of Partial Discharge in Power Cables through Multi-Output Convolutional Recurrent Neural Network and Feature Extraction[J]. IEEE Transactions on Power Delivery, 2023, 38(1): 177-188.

[4] 高宝琪, 马捍超, 毕艳冰, 等. 深度信念网络下的高压电缆局部放电信号捕捉[J]. 哈尔滨理工大学学报, 2023, 28(2): 92-98.

[5] GAO B Q, MA H C, BI Y B, et al. Partial Discharge Signal Capture of High Voltage Cable under Deep Belief Network[J]. Journal of Harbin University of Science and Technology, 2023, 28(2): 92-98.

[6] DJORDJE D. Extraction of Partial Discharge Signal in Predominant VHF Range in the Presence of Strong Noise in Power Transformer[J]. Electrical Engineering, 2023, 105(5): 3001-3018.

[7] 尚海昆, 李宇才, 林伟. 基于EWT-MQE的变压器局部放电特征提取[J]. 电力系统保护与控制, 2022, 50(14): 161-171.

[8] SHANG H K, LI Y C, LIN W. Partial Discharge Feature Extraction of a Transformer Based on EWT-MQE[J]. Power System Protection and Control, 2022, 50(14): 161-171.

[9] 江友华, 朱毅轩, 杨兴武, 等. 基于Hankel-SVD-CEEMDAN改进阈值的局部放电特征提取方法[J]. 电网技术, 2022, 46(11): 4557-4567.

[10] JIANG Y H, ZHU Y X, YANG X W, et al. Hankel-SVD-CEEMDAN Improved Threshold Partial Discharge Feature Extraction Method[J]. Power System Technology, 2022, 46(11): 4557-4567.

[11] 杨攀烁, 贾文阁, 刘森, 等. 基于小波变换和灰度-梯度共生矩阵的局部放电特征提取及识别[J]. 科学技术与工程, 2023, 23(27): 11673-11680.

[12] YANG P S, JIA W G, LIU S, et al. Feature Extraction and Recognition of Partial Discharge Based on Wavelet Transform and GGCM[J]. Science Technology and Engineering, 2023, 23(27): 11673-11680.

[13] 代少升, 任忠, 赖智颖, 等. 基于PRPD图谱多特征融合的局部放电类型识别研究[J]. 重庆邮电大学学报(自然科学版), 2022, 34(3): 373-382.

[14] DAI S S, REN Z, LAI Z Y, et al. Research on Partial Discharge Type Recognition Based on Multi-Feature Fusion of PRPD Map[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2022, 34(3): 373-382.

[15] 文豪, 张国治, 肖黎, 等. 基于小样本UHF信号的变压器局部放电平面定位技术研究[J]. 变压器, 2022, 59(4): 54-59.

[16] WEN H, ZHANG G Z, XIAO L, et al. Research on Localization Technology of Transformer Partial Discharge Plane Based on Small Sample UHF Signal[J]. Transformer, 2022, 59(4): 54-59.

[17] 万中一, 胡岳, 陈炳树, 等. 基于能量谱分析和DBSCAN改进算法的多源局部放电分类识别方法[J]. 高电压技术, 2023, 49(10): 4335-4344.

[18] WAN Z Y, HU Y, CHEN B S, et al. Multi-Source Partial Discharge Classification and Recognition Method Based on Energy Spectrum Analysis and DBSCAN Improved Algorithm[J]. High Voltage Engineering, 2023, 49(10): 4335-4344.

[19] XU N, GOOI H B, WANG L, et al. Loop Optimization Noise-Reduced LSTM Based Classifier for PD Detection[J]. IEEE Transactions on Industry Applications, 2023, 59(1): 392-402.

[20] 王利福, 刘屹江泽, 王燚增. 基于EEMD能量矩与ISSA-SVM算法的GIS局部放电类型识别方法[J]. 电子测量与仪器学报, 2022, 36(5): 204-212.

[21] WANG L F, LIU Y J Z, WANG Y Z. Partial Discharge Identification Method in GIS Based on EEMD Energy Moment and ISSA-SVM Algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(5): 204-212.

[22] 宁暑光, 何怡刚, 程彤彤, 等. 基于自适应S变换与截断紧致奇异值分解的局部放电源复杂染噪特征提取方法[J]. 电工技术学报, 2022, 37(15): 3951-3962.

[23] NING S G, HE Y G, CHENG T T, et al. Feature Extraction of Partial Discharge Source with Complex Noise Based on Adaptive S-Transform and Truncated Compact Singular Value Decomposition[J]. Transactions of China Electrotechnical Society, 2022, 37(15): 3951-3962.

[24] DENG Y, ZHU K, ZHAO G, et al. Efficient Partial Discharge Signal Denoising Method via Adaptive Variational Modal Decomposition for Infrared Detectors[J]. Infrared Physics and Technology, 2022, 125: 104230.

[25] HAO Y, CHEN Y, CHEN Y, et al. Partial Discharge Detection Using the Fiber-Optic Mach-Zehnder Interferometer System for XLPE Cables[J]. Electrical Engineering, 2022, 104(4): 2133-2140.

[26] 韩雪源. 基于LSTM算法的高压交联电缆线路振荡波局部放电检测方法[J]. 电机与控制应用, 2022, 49(12): 41-46, 80.

[27] HAN X Y. Oscillating Wave Partial Discharge Detection Method of High Voltage Cross-Linked Cable Line Based on LSTM Algorithm[J]. Electric Machines & Control Application, 2022, 49(12): 41-46,80.

[28] PEI S, LIU D, YE Z, et al. Optimization Scheme of Partial Discharge Location of External Insulation Based on 2-D Multiple Signal Classification Algorithm[J]. IET Science, Measurement & technology, 2023, 17(1): 11-26.

[29] 艾嘉伟, 牛海清, 陈泽铭, 等. 基于神经网络的D-S多信息融合GIL局部放电联合识别方法[J]. 高电压技术, 2022, 48(12): 4925-4932.

[30] AI J W, NIU H Q, CHEN Z M, et al. D-S Multi Information Fusion GIL Partial Discharge Joint Recognition Method Based on Neural Network[J]. High Voltage Engineering, 2022, 48(12): 4925-4932.

[31] ZHANG J W, WANG L, CHEN J H, et al. An Optical Measurement Method for Nanosecond Impulse Signal Monitoring of Partial Discharge Based on the Fabry-Perot Interferometer Sensing System[J]. Japanese Journal of Applied Physics, 2022, 61(10): 102006.

[32] 辛文成, 姚森敬, 陈浩敏, 等. 计及电磁模特高频信号的局部放电模式识别方法[J]. 电力科学与技术学报, 2022, 37(6): 108-115.

[33] XIN W C, YAO S J, CHEN H M, et al. Pattern Recognition of UHF Signals in Partial Discharge Considering Electromagnetic Model[J]. Journal of Electric Power Science and Technology, 2022, 37(6): 108-115.

基金资助

海南省教育厅基金资助项目(Hnjgzc2023-93)