基于一阶自卷积Kaiser窗的分频段谐波检测DFT算法  

Segmented DFT Algorithm for Harmonic Detection Based on1st-order Self-convolution Kaiser Window

作　　者：谢业强 王钢[1] 曾德辉 XIE Yeqiang;WANG Gang;ZENG Dehui(School of Electric Power Engineering,South China University of Technology,Guangzhou,Guangdong 510641,China;Guangzhou Jiayuan Electric Power Technology Co.,Ltd.,Guangzhou,Guangdong 510610,China)

机构地区：[1]华南理工大学电力学院,广东广州510641 [2]广州嘉缘电力科技有限公司,广东广州510610

出　　处：《广东电力》2021年第6期79-88,共10页Guangdong Electric Power

基　　金：广东省自然科学基金项目(2018A030310354)。

摘　　要：电力电子化电力系统的谐波带宽大幅拓宽,存在较多弱谐波分量,易产生混叠现象。传统傅里叶算法虽适合宽频信号检测,但存在严重的频谱泄漏和栅栏效应缺陷,谐波检测精度不高。为此,在研究自卷积运算对窗函数旁瓣性能影响的基础上,针对谱线插值算法的频率估计误差累积缺陷和全相位数据预处理算法的栅栏效应加剧问题,通过一阶自卷积运算实现两者的优势互补,提出基于一阶自卷积Kaiser窗的谐波检测离散傅里叶变换(discrete Fourier transformation,DFT)算法。同时,为降低宽频信号的检测时间,对宽频信号划分频段,提出分频段的电力谐波检测DFT算法,降低高频段的检测时间,提高计算速度。仿真表明,所提分频段算法适合宽频信号检测,能有效克服基频频率波动和噪声干扰,具有较高的谐波参数测量精度和稳定性。The harmonic bandwidth of power electronic systems has been greatly expanded,and there are many weak harmonic components,which are prone to aliasing.Although the traditional Fourier algorithm is suitable for wide-band signal detection,it has serious spectrum leakage and fence effect,resulting in low harmonic detection accuracy.Based on the study of the influence of self-convolution operation on the sidelobe performance of the window function,this paper focuses on the frequency estimation error accumulation defect of the spectral interpolation algorithm and the increase of the fence effect of the all-phase data preprocessing algorithm.The complementary advantages of the spectral interpolation algorithm and the all-phase data preprocessing algorithm are realized through the first-order self-convolution operation,and an DFT harmonic detection algorithm based on 1st-order Kaiser self-convolution window is proposed.At the same time,by segmented the broadband signal,a segmented power harmonic detection DFT algorithm is proposed,which effectively reduces the detection time in the wide frequency bands.In the case of ensuring the detection accuracy,the calculation speed of the detection algorithm based on a 1st-order Kaiser self-convolution window is improved.Simulation shows that the proposed segmented algorithm is suitable for wide-band signal detection,can effectively overcome fundamental frequency fluctuations and noise interference.The harmonic parameter measurement has high accuracy and high stability.

关 键 词：一阶自卷积Kaiser窗 谱线插值 全相数据预处理 谐波分析 离散傅里叶变换 

分 类 号：TM935[电气工程—电力电子与电力传动]