Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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

A life prediction and regression model technology, applied in special data processing applications, computer-aided design, design optimization/simulation, etc., can solve problems such as poor generalization ability, inability to fully consider the non-stationary problem of capacity data, and insufficient prediction stability , to achieve the effects of improving accuracy, reducing data complexity and instability, and improving prediction accuracy and robustness

Inactive Publication Date: 2021-05-04
SHANGHAI MARITIME UNIVERSITY
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Lithium battery residual life prediction method based on multi-scale integrated regression model
  • Lithium battery residual life prediction method based on multi-scale integrated regression model
  • Lithium battery residual life prediction method based on multi-scale integrated regression model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be described in further detail below with reference to the accompanying drawings.

[0047] The present invention proposes a method for predicting the remaining life of a lithium battery based on a multi-scale integrated regression model, such as figure 1 Shown is the concrete flowchart of the present invention, comprises the following steps:

[0048] (1) Preprocessing lithium battery data: Divide the lithium battery data into three stages: charging, discharging, and impedance, and then filter out the discharging stage to extract the lithium battery capacity degradation data, and use the lithium battery capacity degradation data at time 1,...,t as In the training set, the lithium battery capacity degradation data after time t+1 is used as the prediction data set, where t represents the current moment;

[0049] Preprocess lithium battery data according to step (1). The lithium battery capacity degradation data comes from the NASA Research Cente...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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 ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/20G06F119/04
CPCG06F30/20G06F2119/04
Inventor 王冉周雁翔胡雄顾邦平石如玉后麒麟
Owner SHANGHAI MARITIME UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products