Open AccessIdentification of electrical equipment based on two-dimensional time series characteristics of power
Author(s) -
Dongning Jia,
Xin Huang,
Zehua Du,
Ruixue Li,
Kexin Li
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/6/062019
Subject(s) - normalization (sociology) , computer science , residual , electric power , data set , electrical equipment , electricity , identification (biology) , real time computing , power network , power (physics) , electric power system , data mining , reliability engineering , artificial intelligence , engineering , electrical engineering , algorithm , physics , botany , quantum mechanics , sociology , anthropology , biology
Non-intrusive load monitoring provides real-time monitoring of the operational status of individual devices in the home and provides detailed power usage data. In this paper, a deep neural network structure with residual module and Batch Normalization layer is proposed for the problem that it is difficult to extract complete features. The new method of converting power data into two-dimensional image is used to identify electricity device. Finally, the accuracy rate of the test in the data set containing 21 kinds of electrical equipment is 97.2%. The experimental results show that the method has high recognition for a large number of household electrical equipment, especially for appliances with multiple states and fewer samples rate.