Method, device and medium for effective battery charging data identification based on deep learning

Abstract

The embodiments of the present invention disclose a method, device and medium for identifying effective battery charging data based on deep learning. The method includes: acquiring a charging data curve during the charging process of the whole vehicle; using a plurality of sliding windows of different sizes to slide on the charging data curve, and after each sliding of each sliding window, according to the charging data in the window The data curve calculates the data confusion degree and the data change trend, and then summarizes the total data confusion degree and the total data change trend corresponding to each sliding window; extracts the characteristics of the total data confusion degree and the total data change trend; The features of the degree of confusion and the change trend of the total data are input to the deep learning model, and the valid or invalid identification result output by the deep learning model is obtained. This embodiment can realize fast and automatic identification of effective battery charging data.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of deep learning and data identification, and in particular, to a method, device and medium for identifying effective battery charging data based on deep learning. Background technique [0002] At present, the online accurate estimation of electric vehicle power batteries is a major problem in the industry. When consumers buy and use electric vehicles, the core concerns include range and economy, which corresponds to an accurate prediction of the available battery capacity. The research on battery life prediction is mainly based on the capacity data obtained under constant current conditions. However, in the actual operation of electric vehicles, due to the extremely complex operating conditions of the vehicle, the capacity data of the constant current discharge phase cannot be obtained. Considering that the charging process of the whole vehicle is usually relatively standardized, and...

AI Technical Summary

Problems solved by technology

[0003] In practical applications, due to the complex environment in which the vehicle is located, affected by temperature fluctuations, the charging method of the charging pile, the accuracy of the battery sensor, and the aging degree of the battery itself, it may cause charging data packet loss or data confusion and errors. As a result, the quality of the charging segment data is uneven, and the charging segment data cannot be used to predict the usable life of the battery

Images