Abstract: A charging state analysis method of an electric vehicle based on electrical characteristic sequence analysis is provided. The method includes following steps: step S1, obtaining voltage sampling data and current sampling data of the electric vehicle during charging; step S2, setting a time interval, so as to divide the voltage sample data and the current sampling data obtained in step S1 into multiple data sets; step S3, calculating an electrical characteristic vector of each time interval; step S4. adding the calculation results of Step S3 to a temperature sensing value T, and generate an electrical characteristic sequence of whole charging cycle; step S5, inputting the electrical characteristic sequence of the electric vehicle into a trained TRNN in sequence to obtain corresponding results; if the result is 1, it is normal; if the result is 0, it is abnormal.

Abstract: The invention discloses a charging state analysis method of a electric vehicle based on electrical characteristic sequence analysis. The method includes following steps: step S1, obtaining voltage sampling data and current sampling data of the electric vehicle during charging; step S2, setting a time interval, so as to divide the voltage sample data and the current sampling data obtained in step S1 into multiple data sets; step S3, calculating an electrical characteristic vector of each time interval; step S4. adding the calculation results of Step S3 to a temperature sensing value T, and generate an electrical characteristic sequence of whole charging cycle; step S5, inputting the electrical characteristic sequence of the electric vehicle into a trained Time Recurrent Neural Network (TRNN) in sequence to obtain corresponding results; if the result is 1, it means normal; if the result is 0, it means abnormal.

Abstract: A non-intrusive load identification method based on the Power Fingerprint characteristics of the load is provided. The method includes: S1, collecting Power Fingerprint characteristic data of several loads of the same type; S2, after preprocessing Power Fingerprint characteristic data of load, establishing convolution neural network based on attention mechanism to learn load characteristics; S3, using sliding time window algorithm to realize load switching event detection, In order to extract the change of electrical data of user bus before and after the switching event, the non-intrusive load identification problem is converted into the single load identification problem; S4, the load identification is realized, and the extracted electrical information features of single load are identified using the trained model.