Electric vehicle AC charging state monitoring and fault early warning method based on deep learning

Abstract

The invention designs an electric vehicle AC charging state monitoring and fault early warning method based on deep learning, and the method comprises the steps: firstly carrying out the state monitoring of various parameters of the AC charging of an electric vehicle, and storing the parameters in a database; secondly, dividing data in the database into historical data and real-time data, and preprocessing the historical data and the real-time data; then, designing a CNN-BiGRU deep learning model to fully learn normal alternating current charging historical data, constructing an AC charging prediction model of the electric vehicle, and optimizing hyper-parameters of the model by adopting a bat algorithm; then, formulating an evaluation standard of model prediction precision for judging the accuracy of model prediction, performing residual analysis on a model prediction value through a sliding window method, and determining a fault early warning threshold value and a rule suitable for AC charging of the electric vehicle; and finally, applying the trained CNN-BiGRU prediction model to real-time alternating current charging monitoring of the electric vehicle, and realizing fault early warning of the electric vehicle.

Description

technical field [0001] The invention belongs to the technical field of equipment fault early warning, and in particular relates to a deep learning-based method for monitoring the AC charging state of an electric vehicle and a fault early warning method. Background technique [0002] In recent years, with the continuous increase of the number of traditional fuel vehicles, the energy crisis and environmental pollution have become increasingly serious, and domestic and foreign countries have begun to vigorously develop the electric vehicle industry. With the continuous development of the electric vehicle industry, people pay more and more attention to the safety of electric vehicles. The scope of electric vehicle safety issues is very broad, including vehicle safety, charging safety, information security and other aspects. AC charging of electric vehicles has the advantages of low cost and prolonging the service life of power batteries. It is widely used at present, so it is v...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the safety problems existing in the early warning of AC charging faults of electric vehicles, the present invention proposes a method for monitoring and early warning of AC charging status of electric vehicles based on deep learning to solve the deficiencies of existing methods

Images