The invention discloses a charging
pile remote metering method, and relates to the technical field of charging
pile metering, and the method comprises the steps: carrying out the stability analysis of collected charging data, screening out the charging data meeting the standard, carrying out the sampling, intercepting the data of a
constant current stage, analyzing the correlation between each parameter and the charging
electric energy, and carrying out the calculation. Setting the preset number of parameters as charging process characteristics; selecting an interval range value of a battery SOC in the
constant current stage data as a starting point and an end point of model input, constructing a feature sequence according to charging process features, setting the feature sequence as a model input
data set, and performing
binary classification model training and multi-classification model training on the basis of a deep neural network; and performing classification judgment on the charging data of the new charging
pile according to the trained dichotomy model and / or multi-classification model. By adopting the deep
neural network classification model, the charging data of the charging pile can be remotely analyzed and judged at
high frequency, and the real-time monitoring and
remote evaluation of the performance of the charging pile are realized.