Study of steady-state feature extraction algorithm based on EMD

2nd International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Huang, Xianqing^1 ; Yin, Bo^1 ; Zhang, Rui^2 ; Wei, Zhiqiang^1

College of Information Science and Engineering, Ocean University of China, Qingdao, China^1

Qingdao Haier Smart Technology RandD Co. Ltd., Qingdao, China^2

关键词: Anti-interference;    Empirical Mode Decomposition;    Experimental comparison;    Frequency domains;    Nonintrusive load monitoring;    Steady state features;    Time domain features;    Voltage fluctuations;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/490/6/062036/pdf
DOI  :  10.1088/1757-899X/490/6/062036

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The accuracy of appliance identification is mainly determined by the selection of features in Non-Intrusive Load Monitoring (NILM). The time domain features extracted based on the appliance steady-state depends highly on the stable voltage. This paper proposes a frequency domain features extraction method, which applies the empirical mode decomposition (EMD) principle. The combination of frequency domain features and time domain features can effectively reduce the impact of voltage fluctuations on the accuracy of electrical identification. Through experimental comparison, it is proved that this method can solve time domain features overlapping, with higher anti-interference ability and robustness, especially for the non-resistive electronic loads.