Electric vehicle charging status monitoring and safety warning method based on deep learning

In order to ensure the safe and reliable operation of electric vehicle charging and prevent the fire of electric vehicles while charging, an electric vehicle charging status monitoring and safety warning method was proposed based on convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU). Firstly, CNN was used to deeply mine the normal charging history data of electric vehicles to extract their deep features, and BiGRU was used to fully analyze and utilize the deep features to construct a temperature prediction model of electric vehicles. Next, the evaluation criteria of the prediction model output accuracy were developed and used to evaluate accuracy of the prediction model output. Then, the temperature residual analysis of the model prediction values by sliding window was performed to determine the appropriate safety warning thresholds and rules. Finally, the temperature prediction model satisfying the requirements was applied to the real-time charging of electric vehicles for safety warning experiments. The experimental results show that the CNN-BiGRU model has higher prediction accuracy and prediction effect compared with other prediction models, and the sliding window analysis method can provide safety warning for temperature abnormalities in the charging process of electric vehicles in advance. © 2023 Editorial Department of Electric Machines and Control. All rights reserved.