电能质量扰动识别的小波压缩感知方法
|
摘要
为改善基于小波电能质量信号扰动识别中存在数据量大、识别率不高的不足,提出一种电能质量扰动识别的小波压缩感知新方法。该方法首先确定扰动信号在小波域中的稀疏性,利用小波压缩感知降维,获得少量测量数据,应用正交匹配追踪算法求取各层稀疏系数组成稀疏矩阵;然后提取稀疏系数的最大值、标准差、峭度等组成特征向量,输入神经网络系统训练并实现分类识别。该方法具有采样数据少、处理方便、特征提取简单等特点。仿真结果表明,针对典型的7类单一扰动和复合扰动信号,所提方法在理想环境下识别率分别达到99.50%和99.43%,噪声环境下识别率分别达到97%和98%以上,拥有较强的鲁棒性和较好的准确性。
To overcome the disadvantages in the power quality signal disturbance recognition based on wavelet transform,such as a large amount of data and a low accuracy rate,a novel power quality disturbance recognition method based on wavelet compressive sensing is proposed. First,the sparsity of disturbance signal in wavelet domain is determined. Second,wavelet compressive sensing is used to reduce dimensions,and a few measurement data can be obtained. Then,the sparsity coefficient in every layer can be obtained by orthogonal matching pursuit(OMP)algorithm to form a sparsity matrix. Finally,eigenvectors are formed by the extracted maximum,standard deviation,kurtosis,etc.,and they are further input into the neural network system for training so as to classify and identify the types of disturbance signal. This method is featured by less sampling data,easy process,and simple extraction of characteristics,etc.Simulation results demonstrate that the recognition rates obtained using the proposed method for seven typical single and mixed disturbance signals reach 99.50% and 99.43% respectively in an ideal environment,and above 97% and98% respectively in a noisy environment,showing stronger robustness and better accuracy.
To overcome the disadvantages in the power quality signal disturbance recognition based on wavelet transform,such as a large amount of data and a low accuracy rate,a novel power quality disturbance recognition method based on wavelet compressive sensing is proposed. First,the sparsity of disturbance signal in wavelet domain is determined. Second,wavelet compressive sensing is used to reduce dimensions,and a few measurement data can be obtained. Then,the sparsity coefficient in every layer can be obtained by orthogonal matching pursuit(OMP)algorithm to form a sparsity matrix. Finally,eigenvectors are formed by the extracted maximum,standard deviation,kurtosis,etc.,and they are further input into the neural network system for training so as to classify and identify the types of disturbance signal. This method is featured by less sampling data,easy process,and simple extraction of characteristics,etc.Simulation results demonstrate that the recognition rates obtained using the proposed method for seven typical single and mixed disturbance signals reach 99.50% and 99.43% respectively in an ideal environment,and above 97% and98% respectively in a noisy environment,showing stronger robustness and better accuracy.
引文
[1]杨洪耕,肖先勇,刘俊勇(Yang Honggeng,Xiao Xianyong,Liu Junyong).电能质量问题的研究和技术进展(一)--电能质量一般概念(Issues and technology assessment on power quality,Part1:General concepts on power quality)[J].电力自动化设备(Electric Power Automation Equipment),2003,23(10):1-4.
[2]陈雷,郑德忠,廖文喆(Chen Lei,Zheng Dezhong,Liao Wenzhe).基于压缩感知的含扰动电能质量信号压缩重构方法(Method based on compressed sensing for compression and reconstruction of power quality signals with disturbances)[J].电工技术学报(Transactions of China Electrotechnical Society),2016,31(8):163-171.
[3]杨烁,曹思扬,戴朝华,等(Yang Suo,Cao Siyang,Dai Chaohua,et al).电能质量扰动信号时频原子分解的进化匹配追踪算法(Evolutionary matching pursuit based time-frequency atom decomposition for power quality disturbance signals)[J].电力系统保护与控制(Power System Protection and Control),2015,43(16):79-86.
[4]曹思扬,戴朝华,朱云芳,等(Cao Siyang,Dai Chaohua,Zhu Yunfang,et al).一种新的电能质量扰动信号压缩感知识别方法(A novel compressed sensing-based recognition method for power quality disturbance signals)[J].电力系统保护与控制(Power System Protection and Control),2017,45(3):7-12.
[5]杨烁(Yang Shuo).电能质量扰动信号的稀疏表示/压缩采样研究(Research on Sparse Representation and Compressive Sampling of Power Quality Disturbance Singnals)[D].成都:西南交通大学电气工程学院(Chengdu:School of Electrical Engineering,Southwest Jiaotong University),2015.
[6]曹思扬(Cao Siyang).电能质量扰动信号的压缩感知研究(Research on Compressed Sensing of Power Quality Disturbance Signals)[D].成都:西南交通大学电气工程学院(Chengdu:School of Electrical Engineering,Southwest Jiaotong University),2016.
[7]黄建明,瞿合祚,李晓明(Huang Jianming,Qu Hezuo,Li Xiaoming).基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类(Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis)[J].电网技术(Power System Technology),2016,40(10):3184-3191.
[8]吴兆刚,李唐兵,姚建刚,等(Wu Zhaogang,Li Tangbing,Yao Jiangang,et al).基于小波和改进神经树的电能质量扰动分类(Power quality disturbance classification based on a wavelet and improved neural tree)[J].电力系统保护与控制(Power System Protection and Control),2014,42(24):86-92.
[9]占勇,程浩忠,丁屹峰,等(Zhan Yong,Cheng Haozhong,Ding Yifeng,et al).基于S变换的电能质量扰动支持向量机分类识别(S-transform-based classification of power quality disturbance signals by support vector machines)[J].中国电机工程学报(Proceedings of the CSEE),2005,25(4):51-56.
[10]朱玲,刘志刚,胡巧琳,等(Zhu Ling,Liu Zhigang,Hu Qiaolin,et al).基于CWD谱峭度的暂态电能质量扰动识别(Recognition of transient power quality disturbances based on CWD spectral kurtosis)[J].电力自动化设备(Electric Power Automation Equipment),2014,34(2):125-131.
[11]沈跃,刘国海,刘慧(Shen Yue,Liu Guohai,Liu Hui).随机降维映射稀疏表示的电能质量扰动多分类研究(Study on classification method of power quality disturbances based on random dimensionality reduction projection and sparse representation)[J].仪器仪表学报(Chinese Journal of Scientific Instrument),2011,32(6):1371-1376.
[12]程德强,高凌志,陈亮亮,等(Cheng Deqiang,Gao Lingzhi,Chen Liangliang,et al).自适应多尺度分块压缩感知算法(Adaptive multi-scale block compressed sensing algorithm)[J].中国图象图形学报(Journal of Image and Graphics),2017,22(9):1175-1182.
[13] Baraniuk R G. Compressive Sensing[J]. IEEE Signal Processing Magazine,2007,24(4):118-121,124.
[14] Candes E J,Wakin M B. An introduction to compressive sampling[J]. IEEE Signal Processing Magazine,2008,25(2):21-30.
[15]闫敬文,刘蕾,屈小波.压缩感知及应用[M].北京:国防工业出版社,2015.
[16] Aldroubi A,Chen Xuemei,Powell A M. Perturbations of measurement matrices and dictionaries in compressed sensing[J]. Applied and Computational Harmonic Analysis,2012,33(2):282-291.
[17]姚建刚,郭知非,陈锦攀,等(Yao Jiangang,Guo Zhifei,Chen Jinpan,et al).基于小波和BP神经网络的电能扰动分类新方法(A new approach to recognize power quality disturbances based on wavelet transform and BP neural network)[J].电网技术(Power System Technology),2012,36(5):139-144.
[2]陈雷,郑德忠,廖文喆(Chen Lei,Zheng Dezhong,Liao Wenzhe).基于压缩感知的含扰动电能质量信号压缩重构方法(Method based on compressed sensing for compression and reconstruction of power quality signals with disturbances)[J].电工技术学报(Transactions of China Electrotechnical Society),2016,31(8):163-171.
[3]杨烁,曹思扬,戴朝华,等(Yang Suo,Cao Siyang,Dai Chaohua,et al).电能质量扰动信号时频原子分解的进化匹配追踪算法(Evolutionary matching pursuit based time-frequency atom decomposition for power quality disturbance signals)[J].电力系统保护与控制(Power System Protection and Control),2015,43(16):79-86.
[4]曹思扬,戴朝华,朱云芳,等(Cao Siyang,Dai Chaohua,Zhu Yunfang,et al).一种新的电能质量扰动信号压缩感知识别方法(A novel compressed sensing-based recognition method for power quality disturbance signals)[J].电力系统保护与控制(Power System Protection and Control),2017,45(3):7-12.
[5]杨烁(Yang Shuo).电能质量扰动信号的稀疏表示/压缩采样研究(Research on Sparse Representation and Compressive Sampling of Power Quality Disturbance Singnals)[D].成都:西南交通大学电气工程学院(Chengdu:School of Electrical Engineering,Southwest Jiaotong University),2015.
[6]曹思扬(Cao Siyang).电能质量扰动信号的压缩感知研究(Research on Compressed Sensing of Power Quality Disturbance Signals)[D].成都:西南交通大学电气工程学院(Chengdu:School of Electrical Engineering,Southwest Jiaotong University),2016.
[7]黄建明,瞿合祚,李晓明(Huang Jianming,Qu Hezuo,Li Xiaoming).基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类(Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis)[J].电网技术(Power System Technology),2016,40(10):3184-3191.
[8]吴兆刚,李唐兵,姚建刚,等(Wu Zhaogang,Li Tangbing,Yao Jiangang,et al).基于小波和改进神经树的电能质量扰动分类(Power quality disturbance classification based on a wavelet and improved neural tree)[J].电力系统保护与控制(Power System Protection and Control),2014,42(24):86-92.
[9]占勇,程浩忠,丁屹峰,等(Zhan Yong,Cheng Haozhong,Ding Yifeng,et al).基于S变换的电能质量扰动支持向量机分类识别(S-transform-based classification of power quality disturbance signals by support vector machines)[J].中国电机工程学报(Proceedings of the CSEE),2005,25(4):51-56.
[10]朱玲,刘志刚,胡巧琳,等(Zhu Ling,Liu Zhigang,Hu Qiaolin,et al).基于CWD谱峭度的暂态电能质量扰动识别(Recognition of transient power quality disturbances based on CWD spectral kurtosis)[J].电力自动化设备(Electric Power Automation Equipment),2014,34(2):125-131.
[11]沈跃,刘国海,刘慧(Shen Yue,Liu Guohai,Liu Hui).随机降维映射稀疏表示的电能质量扰动多分类研究(Study on classification method of power quality disturbances based on random dimensionality reduction projection and sparse representation)[J].仪器仪表学报(Chinese Journal of Scientific Instrument),2011,32(6):1371-1376.
[12]程德强,高凌志,陈亮亮,等(Cheng Deqiang,Gao Lingzhi,Chen Liangliang,et al).自适应多尺度分块压缩感知算法(Adaptive multi-scale block compressed sensing algorithm)[J].中国图象图形学报(Journal of Image and Graphics),2017,22(9):1175-1182.
[13] Baraniuk R G. Compressive Sensing[J]. IEEE Signal Processing Magazine,2007,24(4):118-121,124.
[14] Candes E J,Wakin M B. An introduction to compressive sampling[J]. IEEE Signal Processing Magazine,2008,25(2):21-30.
[15]闫敬文,刘蕾,屈小波.压缩感知及应用[M].北京:国防工业出版社,2015.
[16] Aldroubi A,Chen Xuemei,Powell A M. Perturbations of measurement matrices and dictionaries in compressed sensing[J]. Applied and Computational Harmonic Analysis,2012,33(2):282-291.
[17]姚建刚,郭知非,陈锦攀,等(Yao Jiangang,Guo Zhifei,Chen Jinpan,et al).基于小波和BP神经网络的电能扰动分类新方法(A new approach to recognize power quality disturbances based on wavelet transform and BP neural network)[J].电网技术(Power System Technology),2012,36(5):139-144.