Optimal charging current estimation method based on neural network model

Abstract

The invention discloses an optimal charging current estimation method based on a neural network model. The optimal charging current estimation method comprises the steps of: (1) acquiring a neural network thermal model; (2) configuring a charging current range according to the model of a vehicle to be charged, wherein the upper bound of the charging current range is the maximum charging current, and the lower bound of the charging current range is the minimum charging current; (3) configuring parameters of an evaluation function, wherein the parameters of the evaluation function include allowable longest charging time, allowable shortest charging time, allowable maximum temperature, allowable minimum temperature, an evaluation weight of a temperature function and an evaluation weight of a time function; (4) and acquiring an optimal current according to the charging current range, the parameters of the evaluation function and the neural network thermal model, and regarding the optimal current as an initial charging current. The optimal charging current estimation method is high in adaptivity and flexible, can adapt to charging initial states of different battery packs, can estimate the optimal charging current in the current state, and ensures that the situations of overlong charging time and overhigh charging temperature cannot occur.

Description

technical field [0001] The invention belongs to the field of electric vehicles, and more specifically relates to a method for estimating an optimal charging current based on a neural network model. Background technique [0002] Charging technology is one of the key technologies in electric vehicle technology. Therefore, the choice of charging current is of great significance. A reasonable charging current can not only ensure the safety of charging, but also shorten the charging time, control the charging temperature so that it does not get out of control, avoid excessive aging of the battery during charging, and improve the service life of the battery pack. [0003] At present, the charging method of electric vehicles is basically charging with a fixed charging current. This method has a single charging mode, is not flexible enough, and cannot well adapt to the initial charging state of different battery packs, such as different ambient temperatures at the beginning of char...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects of the prior art, the purpose of the present invention is to provide a method for estimating the optimal charging current based on the neural network model, aiming at solving the problem of charging current with a fixed charging current in the prior art, which easily causes the difference between the charging current and the actual demand. In case of mismatch, the charging time is too long, the charging temperature is too high, and the battery aging is getting worse

Images