A Detection Method of Electricity Stealing Behavior of Charging Pile Based on CNN-LSTM

With the growth of the number of electric vehicles, the demand for charging piles is increasing, and the behavior of stealing electricity is becoming more and more frequent. In order to protect the safety of power grid, it is necessary to monitor the behavior of stealing electricity effectively. In this paper, a new method based on convolution neural network and long-term and short-term memory network is proposed to detect the electricity stealing behavior of charging pile, so as to realize the purpose of anti electricity stealing of charging pile. In the stage of feature data input, the model analyzes the voltage, current and electric energy collected by the power stealing detection equipment, extracts the power stealing features by CNN and judges the features of the suspected users by LSTM, and tests the classification effect on the test set. The experimental results show that the model has high accuracy, and can meet the detection needs of the charging pile.