Open AccessMulti-state household appliance identification based on neural network
Author(s) -
Ying Zhang,
Jiali Xu,
Zehua Du,
Xifeng Dong
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/768/6/062069
Subject(s) - identification (biology) , state (computer science) , convolutional neural network , computer science , cluster analysis , process (computing) , artificial neural network , construct (python library) , artificial intelligence , machine learning , data mining , algorithm , botany , biology , programming language , operating system
In the current non-intrusive load monitoring process, the states switching of some multi-state appliances is difficult to be correctly identified by the switch event detection method, and the energy consumption statistics due to poor multi-state identification of the electrical appliances are not accurate. This paper proposes a multi-state household appliance load identification method based on convolutional neural network and clustering model. First, a convolutional neural network is used to construct an appliance type identification model. Then, a multi-state identification model is established to identify the state of different multi-state appliances. The experimental results show that the proposed method achieves multi-state identification of electrical appliances and has good engineering and practical value.