Lithium battery residual life prediction method based on multi-scale integrated regression model

Abstract

The invention discloses a lithium battery residual life prediction method based on a multi-scale integrated regression model. The method comprises the following steps: firstly, decomposing a lithium battery capacity signal into a plurality of intrinsic mode components (IMF) by using empirical mode decomposition (EMD), fully mining detail features of different scales, and pointedly processing battery capacity regeneration and random fluctuation problems; then, adopting a parallel integration framework, respectively adopting two sub-learners of Gaussian process regression (GPR) and logistic regression (LR) for prediction aiming at the change rules and characteristics of the decomposed components with different scales, and better sensing the characteristics of the different components by utilizing the characteristics of the two sub-learners; and finally, integrating output results of the sub-learners to obtain the predicted residual life of the lithium battery. According to the method, regeneration and fluctuation characteristics in the battery capacity can be effectively sensed, high adaptability to all data is achieved, and higher prediction precision and generalization ability are achieved.

Description

technical field [0001] The invention relates to the technical field of lithium battery life prediction, in particular to a lithium battery remaining life prediction method based on an integrated regression model. [0002] technical background [0003] Lithium batteries are widely used in electric vehicles, ships, consumer electronics and other fields due to their advantages such as high output voltage, wide operating temperature range, long cycle life and safety performance. For example, Toyota, BYD and other automobile companies use lithium batteries. At the same time, lithium batteries have also expanded to aerospace and military communications, becoming the third generation of satellite energy storage batteries. However, during the use of lithium batteries, the performance gradually degrades and the service life gradually shortens, which directly affects the use of equipment and may even cause equipment failure. Therefore, in order to improve the reliability and safety of ...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of non-stationary capacity data caused by the local capacity regeneration phenomenon in the process of lithium battery performance degradation that cannot be fully considered in the features extracted by a single scale, as well as the poor generalization ability and insufficient prediction stability in the single prediction model, The present invention proposes a lithium battery remaining life prediction method based on a multi-scale integrated regression model, so as to accurately predict lithium battery capacity regeneration and random fluctuation trends, thereby improving the accuracy of lithium battery remaining life prediction

Images