基于数据融合的智能化小区建筑电气谐波检测  

Detection of Electrical Harmonics in Intelligent Residential Buildings Based on Data Fusion

作　　者：尹峰 YIN Feng(Zibo Architecture Design and Research Institute Co.,Ltd.,Zibo 255000,Shandong,China)

机构地区：[1]淄博市建筑设计研究院有限公司,山东淄博255000

出　　处：《建筑节能（中英文）》2023年第2期87-91,共5页Building Energy Efficiency

摘　　要：为提高对智能化小区建筑供电的质量,并获得理想的谐波检测结果,提出基于数据融合的智能化小区建筑电气谐波检测方法研究。利用多传感器采集建筑电气观测信号,将观测信号与噪声信号混合建立融合矩阵,输出融合的多传感器信号;利用Fast-ICA算法获取多传感器信号的分离矩阵,输入谐波检测源信号,得到分离的谐波检测源信号。最后利用滑窗迭代DFT算法实现建筑电气谐波的有效检测。实验结果表明,该方法可对多传感器所采集混合信号进行有效分离,获取精准的谐波电流输出结果。研究区域的谐波电流含有率较高,总谐波畸变率高达38.64%,表明本研究方法具有一定应用价值,可对建筑电气谐波进行准确检测。In order to improve the quality of power supply for intelligent residential buildings and obtain ideal harmonic detection results,a research method for electrical harmonic detection of intelligent residential buildings based on data fusion is proposed.The multi-sensors are utilized to collect building electrical observation signals,the observation signals and noise signals are mixed to establish a fusion matrix,and the fused multi-sensor signals are output;the Fast-ICA algorithm is applied to obtain the separation matrix of multi-sensor signals,inputting the harmonic detection source signal,and getting the separated harmonic detection source signal.Finally,the sliding window iterative DFT algorithm is used to realize the effective detection of building electrical harmonics.The experimental results show that the method can effectively separate the mixed signals collected by multi-sensors and obtain accurate harmonic current output results.The harmonic current content rate in the research area is high,and the total harmonic distortion rate is as high as 38.64%,which shows that the method in this paper has certain application value and can accurately detect building electrical harmonics.

关 键 词：数据融合 智能化 建筑电气 谐波检测 混合矩阵 信号分离 

分 类 号：TU85[建筑科学] TM714[电气工程—电力系统及自动化]