基于核密度估计分类器的变换器故障诊断方法
|
摘要
现有变换器的故障诊断过程需训练大量的故障样本才能实现故障的识别和定位,但故障数据获取困难且训练过程复杂。针对这一问题,提出一种结合基于Mallat(快速递推算法)的三次B样条小波分析与核密度估计算法。该方法首先采用基于Mallat的三次B样条小波分析方法对变换器的输出电压进行预处理,加强抗噪声能力并降低数据维度;其后,基于核密度估计的分类器对故障进行识别和定位。所提方法在故障辨识阶段无需故障样本仅对正常样本进行训练便能准确识别故障样本,且在故障定位阶段仅需训练少量故障样本就能实现故障的定位,具有抗干扰能力强、实现简单、诊断率高的优点。仿真和实验验证了所提方法的可行性和有效性。
Existing fault diagnosis of converters needs to train a large number of fault samples to realize fault identification and location, but fault data acquisition is difficult and the training process is complicated. This paper presents an algorithm combining quadratic B spline wavelet analysis based on Mallat(fast recursive algorithm) and kernel density estimation to solve above problems. Firstly, the output voltage of the converter is pre-processed with quadratic B spline wavelet analysis based on Mallat to enhance anti-noise ability and reduce data dimension. Then, the classifier based on kernel density estimation is used to identify and locate fault samples. The proposed method can identify fault samples accurately without fault samples in fault identification stage, and only a few number of fault samples in fault location stage need to train for realizing fault location. The method has advantages of high reliability, simple implementation and high classification performance. Simulation and experiment verify feasibility and effectiveness of the proposed method.
Existing fault diagnosis of converters needs to train a large number of fault samples to realize fault identification and location, but fault data acquisition is difficult and the training process is complicated. This paper presents an algorithm combining quadratic B spline wavelet analysis based on Mallat(fast recursive algorithm) and kernel density estimation to solve above problems. Firstly, the output voltage of the converter is pre-processed with quadratic B spline wavelet analysis based on Mallat to enhance anti-noise ability and reduce data dimension. Then, the classifier based on kernel density estimation is used to identify and locate fault samples. The proposed method can identify fault samples accurately without fault samples in fault identification stage, and only a few number of fault samples in fault location stage need to train for realizing fault location. The method has advantages of high reliability, simple implementation and high classification performance. Simulation and experiment verify feasibility and effectiveness of the proposed method.
引文
[1]候虚虚,秦岭,熊俊峰,等.光伏-蓄电池联合供电水泵系统用集成式单管DC/DC变换器[J].电网技术,2018,42(1):210-219.Hou Xuxu,Qin Ling,Xiong Junfeng,et al.Single-switch integrated DC/DC converter for photovoltaic-battery-powered water pumping system[J].Power System Technology,2018,42(1):210-219(in Chinese).
[2]刘闯,李伟,孙佳俊.一种应用于电动汽车快速充电站的高频隔离双级功率变换器[J].电网技术,2017,41(5):1636-1643.Liu Chuang,Li Wei,Sun Jiajun.A high-frequency-isolation twopower-stage converter applied in electric vehicle fast charging station[J].Power System Technology,2017,41(5):1636-1643(in Chinese).
[3]任磊,韦徵,龚春英,等.电力电子电路功率器件故障特征参数提取技术综述[J].中国电机工程学报,2015,35(12):3089-3101.Ren Lei,Wei Zheng,Gong Chunying,et al.Fault feature extraction techniques for power devices in power electronic converters:a review[J].Proceedings of the CSEE,2015,35(12):3089-3101(in Chinese).
[4]成庶,李蔚,陈特放,等.整流器主电路开路故障诊断及容错控制研究[J].电工技术学报,2016,31(13):26-35.Cheng Shu,Li Wei,Chen Tefang,et al.Research on open-circuit fault diagnosis and fault-tolerant control scheme for rectifier main circuits[J].Transactions of China Electrotechnical Society,2016,31(13):26-35(in Chinese).
[5]黄科元,刘静佳,黄守道,等.永磁直驱系统变流器开路故障诊断方法[J].电工技术学报,2015,30(16):129-136.Huang Keyuan,Liu Jingjia,Huang Shoudao,et al.Converters opencircuit fault diagnosis methods research for direct-driven permanent magnet wind power system[J].Transactions of China Electrotechnical Society,2015,30(16):129-136(in Chinese).
[6]Abari I,Lahouar A,Hamouda M,et al.Fault detection methods for three-level NPC inverter based on DC-bus electromagnetic signatures[J].IEEE Transactions on Industrial Electronics,2018,65(7):5224-5236.
[7]耿乙文,李伟,王凯.一种三相光伏并网逆变器故障诊断方法[J].电工技术学报,2014,29(S1):203-209.Geng Yiwen,Li Wei,Wang Kai.A fault diagnosis method for three-phase photovoltaic grid-connected inverter[J].Transactions of China Electrotechnical Society,2014,29(S1):203-209(in Chinese).
[8]Liu H D,Yue W J,Lan H,et al.Fault diagnosis method in controlled rectifier based on support vector machines[J].Advanced Materials Research,2011(383-390):5006-5011.
[9]Nie S,Chen Y,Pei X,et al.A DSP-based diagnostic system for DC-DC converters using the shape of voltage across the magnetic components[C]//IEEE Energy Conversion Congress and Exposition.Atlanta,Georgia,USA:IEEE,2010:1908-1915.
[10]陈丹江,叶银忠.基于多神经网络的三电平逆变器器件开路故障诊断方法[J].电工技术学报,2013,28(6):120-126.Chen Danjiang,Ye Yinzhong.Fault diagnosis of three level inverter based on multi neural network[J].Transactions of China Electrotechnical Society,2013,28(6):120-126(in Chinese).
[11]Wang T,Xu H,Han J,et al.Cascaded H-bridge multilevel inverter system fault diagnosis using a PCA and multiclass relevance vector machine approach[J].IEEE Transactions on Power Electronics,2015,30(12):7006-7018.
[12]崔江,王强,龚春英.结合小波与Concordia变换的逆变器功率管故障诊断技术研究[J].中国电机工程学报,2015,35(12):3110-3116.Cui Jiang,Wang Qiang,Gong Chunying.Inverter power switch fault diagnosis technique research based on wavelet and concordia transform[J].Proceedings of the CSEE,2015,35(12):3110-3116(in Chinese).
[13]Li W,Liu W,Wu W,et al.Fault diagnosis of star-connected auto-transformer based 24-pulse rectifier[J].Measurement,2016(91):360-370.
[14]于生宝,何建龙,王睿家,等.基于小波包分析和概率神经网络的电磁法三电平变换器故障诊断方法[J].电工技术学报,2016,31(17):102-112.Yu Shengbao,He Jianlong,Wang Ruijia,et al.Fault diagnosis of electromagnetic three-level inverter based on wavelet packet analysis and probabilistic neural networks[J].Transactions of China Electrotechnical Society,2016,31(17):102-112(in Chinese).
[15]崔江,叶纪青,陈未.一种基于M-ary支持向量机的功率变换器故障分类方法[J].中国电机工程学报,2016,36(22):6231-6237.Cui Jiang,Ye Jiqing,Chen Wei.Fault classification of power converters based on M-ary support vector machine method[J].Proceedings of the CSEE,2016,36(22):6231-6237(in Chinese).
[16]缪希仁,吴晓梅.低压系统多层级短路电流早期检测与预测[J].电工技术学报,2014,29(11):177-183.Miao Xiren,Wu Xiaomei.Early detection and prediction for shortcircuit current in a multi-level low voltage system[J].Transactions of China Electrotechnical Society,2014,29(11):177-183(in Chinese).
[17]田小静,冯雨,郭英杰,等.基于小波变换和形态学细化算法的真空电弧形态检测[J].电工技术学报,2015,30(11):110-114.Tian Xiaojing,Feng Yu,Guo Yingjie,et al.Morphological detection of vacuum switching arc based on wavelet transform and morphology edge thinning[J].Transactions of China Electrotechnical Society,2015,30(11):110-114(in Chinese).
[18]王玉平,蔡元龙.多尺度B样条小波边缘检测算子[J].中国科学,1995(4):426-437.Wang Yuping,Cai Yuanlong.Multiscale B spline wavelet edge detection operator[J].Science in China,1995(4):426-437(in Chinese).
[19]Yu L,Su Z.Application of kernel density estimation in lamb wave-based damage detection[J].Mathematical Problems in Engineering,2012(6):857-868.
[20]He Y L,Wang R,Kwong S,et al.Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis[J].Information Sciences,2014(259):252-268.
[2]刘闯,李伟,孙佳俊.一种应用于电动汽车快速充电站的高频隔离双级功率变换器[J].电网技术,2017,41(5):1636-1643.Liu Chuang,Li Wei,Sun Jiajun.A high-frequency-isolation twopower-stage converter applied in electric vehicle fast charging station[J].Power System Technology,2017,41(5):1636-1643(in Chinese).
[3]任磊,韦徵,龚春英,等.电力电子电路功率器件故障特征参数提取技术综述[J].中国电机工程学报,2015,35(12):3089-3101.Ren Lei,Wei Zheng,Gong Chunying,et al.Fault feature extraction techniques for power devices in power electronic converters:a review[J].Proceedings of the CSEE,2015,35(12):3089-3101(in Chinese).
[4]成庶,李蔚,陈特放,等.整流器主电路开路故障诊断及容错控制研究[J].电工技术学报,2016,31(13):26-35.Cheng Shu,Li Wei,Chen Tefang,et al.Research on open-circuit fault diagnosis and fault-tolerant control scheme for rectifier main circuits[J].Transactions of China Electrotechnical Society,2016,31(13):26-35(in Chinese).
[5]黄科元,刘静佳,黄守道,等.永磁直驱系统变流器开路故障诊断方法[J].电工技术学报,2015,30(16):129-136.Huang Keyuan,Liu Jingjia,Huang Shoudao,et al.Converters opencircuit fault diagnosis methods research for direct-driven permanent magnet wind power system[J].Transactions of China Electrotechnical Society,2015,30(16):129-136(in Chinese).
[6]Abari I,Lahouar A,Hamouda M,et al.Fault detection methods for three-level NPC inverter based on DC-bus electromagnetic signatures[J].IEEE Transactions on Industrial Electronics,2018,65(7):5224-5236.
[7]耿乙文,李伟,王凯.一种三相光伏并网逆变器故障诊断方法[J].电工技术学报,2014,29(S1):203-209.Geng Yiwen,Li Wei,Wang Kai.A fault diagnosis method for three-phase photovoltaic grid-connected inverter[J].Transactions of China Electrotechnical Society,2014,29(S1):203-209(in Chinese).
[8]Liu H D,Yue W J,Lan H,et al.Fault diagnosis method in controlled rectifier based on support vector machines[J].Advanced Materials Research,2011(383-390):5006-5011.
[9]Nie S,Chen Y,Pei X,et al.A DSP-based diagnostic system for DC-DC converters using the shape of voltage across the magnetic components[C]//IEEE Energy Conversion Congress and Exposition.Atlanta,Georgia,USA:IEEE,2010:1908-1915.
[10]陈丹江,叶银忠.基于多神经网络的三电平逆变器器件开路故障诊断方法[J].电工技术学报,2013,28(6):120-126.Chen Danjiang,Ye Yinzhong.Fault diagnosis of three level inverter based on multi neural network[J].Transactions of China Electrotechnical Society,2013,28(6):120-126(in Chinese).
[11]Wang T,Xu H,Han J,et al.Cascaded H-bridge multilevel inverter system fault diagnosis using a PCA and multiclass relevance vector machine approach[J].IEEE Transactions on Power Electronics,2015,30(12):7006-7018.
[12]崔江,王强,龚春英.结合小波与Concordia变换的逆变器功率管故障诊断技术研究[J].中国电机工程学报,2015,35(12):3110-3116.Cui Jiang,Wang Qiang,Gong Chunying.Inverter power switch fault diagnosis technique research based on wavelet and concordia transform[J].Proceedings of the CSEE,2015,35(12):3110-3116(in Chinese).
[13]Li W,Liu W,Wu W,et al.Fault diagnosis of star-connected auto-transformer based 24-pulse rectifier[J].Measurement,2016(91):360-370.
[14]于生宝,何建龙,王睿家,等.基于小波包分析和概率神经网络的电磁法三电平变换器故障诊断方法[J].电工技术学报,2016,31(17):102-112.Yu Shengbao,He Jianlong,Wang Ruijia,et al.Fault diagnosis of electromagnetic three-level inverter based on wavelet packet analysis and probabilistic neural networks[J].Transactions of China Electrotechnical Society,2016,31(17):102-112(in Chinese).
[15]崔江,叶纪青,陈未.一种基于M-ary支持向量机的功率变换器故障分类方法[J].中国电机工程学报,2016,36(22):6231-6237.Cui Jiang,Ye Jiqing,Chen Wei.Fault classification of power converters based on M-ary support vector machine method[J].Proceedings of the CSEE,2016,36(22):6231-6237(in Chinese).
[16]缪希仁,吴晓梅.低压系统多层级短路电流早期检测与预测[J].电工技术学报,2014,29(11):177-183.Miao Xiren,Wu Xiaomei.Early detection and prediction for shortcircuit current in a multi-level low voltage system[J].Transactions of China Electrotechnical Society,2014,29(11):177-183(in Chinese).
[17]田小静,冯雨,郭英杰,等.基于小波变换和形态学细化算法的真空电弧形态检测[J].电工技术学报,2015,30(11):110-114.Tian Xiaojing,Feng Yu,Guo Yingjie,et al.Morphological detection of vacuum switching arc based on wavelet transform and morphology edge thinning[J].Transactions of China Electrotechnical Society,2015,30(11):110-114(in Chinese).
[18]王玉平,蔡元龙.多尺度B样条小波边缘检测算子[J].中国科学,1995(4):426-437.Wang Yuping,Cai Yuanlong.Multiscale B spline wavelet edge detection operator[J].Science in China,1995(4):426-437(in Chinese).
[19]Yu L,Su Z.Application of kernel density estimation in lamb wave-based damage detection[J].Mathematical Problems in Engineering,2012(6):857-868.
[20]He Y L,Wang R,Kwong S,et al.Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis[J].Information Sciences,2014(259):252-268.