Abstract: Provided are an attenuated virus of a flavivirus virus and the use thereof. The attenuated virus comprises a polyadenylic acid (poly(A)) sequence, wherein the polyadenylic acid (poly(A)) is used for replacing a part of the nucleotide sequence of a 3? untranslated region (3?UTR) of the flavivirus virus, so that the 3? untranslated region (3?UTR) of the attenuated virus obtained after the part of the nucleotide sequence of the flavivirus virus is replaced at least retains a 3?-end stem loop region (3?SL). The attenuated virus can be used for preparing safe and effective attenuated vaccine strains.

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: The invention discloses a non-invasive load decomposition method, which includes: step 1, obtaining the power fingerprint information of each load; step 2, clustering the operating state of loads through the clustering algorithm, calculate statistical values of each cluster, and encoding the operating state of electrical appliances; step 3, establishing a hidden Markov model with multiple-parameters and calculating the model parameters; step 4, performing state recognition based on Viterbi algorithm and obtaining predicted state sequence; step 5, according to the predicted state sequence and the statistical values of each cluster, decomposing the load power based on the maximum likelihood estimation principle; step 6, outputting the state sequence and power decomposition results. The invention solves the conventional load identification algorithm problems, such as complex model, insufficient use of electrical features and low accuracy of unknown information.

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.