In the low-voltage distribution network, it is difficult to determine the moment of electric shock and distinguish the types of electric shock by detecting the total leakage current. In order to solve the problems, a recognition method of electric shock based on artificial intelligence is proposed in this paper. The constructed adaptive threshold is used to detect the mutation amount of the total leakage current, which achieves the purpose of determining the moment of electric shock. And then, according to the different waveform characteristics of living and non-living bodies after electric shock, the electric shock accidents are classified. The results show that the proposed method can effectively detect electric shock signals and has reference value for the development of a new generation of residual current protectors.
Comment submit