基于调制宽频模态分解和局部保持投影特征融合的光伏直流电能质量扰动识别  

Identification of photovoltaic direct current power quality disturbance based on modulated broadband mode decomposition and local preserving projection feature fusion

作　　者：熊婕 朱宪宇 王娜 刘良江 李庆先 XIONG Jie;ZHU Xianyu;WANG Na;LIU Liangjiang;LI Qingxian(Hu’nan Institute of Metrology and Testing,Changsha 410018;Zhejiang Fangyuan Test Group Co.,Ltd,Hangzhou 310018)

机构地区：[1]湖南省计量检测研究院,长沙410018 [2]浙江方圆检测集团股份有限公司,杭州310018

出　　处：《电气技术》2024年第5期22-30,40,共10页Electrical Engineering

基　　金：长沙市杰出创新青年培养计划项目(kq2206066)。

摘　　要：光伏直流系统中的非线性负载可能导致直流电信号出现纹波、突变和噪声等扰动,而现有时频分析方法如变分模态分解等对光伏直流电信号进行分解时易产生误差。本文在宽带模式分解的基础上,采用基于调制差分算子的调制宽频模态分解(MBMD)对光伏直流电信号进行去噪,以减小分解误差。首先采用MBMD对直流电信号进行自适应分解,然后结合局部保持投影(LPP)算法进行特征融合,最后采用反向传播(BP)人工神经网络模型实现直流电能质量智能识别。仿真和实验分析表明,本文提出的方法可准确识别不同类型的光伏直流电能质量扰动。Nonlinear loads in photovoltaic(PV)direct current(DC)systems may introduce disturbances such as ripples,transients and noise in the DC power signal.Existing time-frequency analysis methods,such as variational mode decomposition,often lead to errors when decomposing PV DC power signals.This paper,building upon the foundation of broadband mode decomposition,employs modulated broadband mode decomposition(MBMD)with a modulation difference operator to denoise PV DC power signals,aiming to reduce decomposition errors.The proposed approach first utilizes MBMD for adaptive signal decomposition,incorporating a local preserving projection(LPP)algorithm for feature fusion.Finally,a back propagation artificial neural network model is employed for intelligent recognition of DC power quality.Simulation and experimental analysis demonstrate that the proposed method can accurately identify various types of disturbances in PV DC power.

关 键 词：调制宽频模态分解(MBMD) 复合多尺度模糊熵 局部保持投影(LPP) BP人工神经网络 直流电能质量 扰动识别 

分 类 号：TM615[电气工程—电力系统及自动化] TM711