Unlock instant, AI-driven research and patent intelligence for your innovation.

Lithium battery residual life prediction method based on long-term and short-term memory network

A technology of long and short-term memory and life prediction, applied in the direction of measuring electricity, measuring devices, measuring electrical variables, etc., can solve the problems of voltage time series data noise and other problems, and achieve the effect of improving accuracy

Pending Publication Date: 2020-11-27
ZHEJIANG UNIV OF TECH
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the voltage time series data generated during the operation of lithium batteries contains certain noise, it is usually difficult to effectively correlate them with the life of lithium batteries

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 long-term and short-term memory network
  • Lithium battery residual life prediction method based on long-term and short-term memory network
  • Lithium battery residual life prediction method based on long-term and short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0059] 1) Feature extraction

[0060] Monitor the operation process of the lithium battery. According to professional experience, the time series data of the discharge voltage difference (3.8V, 3.45V) and the charging voltage difference (4.0V, 4.1V) are extracted from the charging and discharging process of the lithium battery based on the principle of equal voltage difference time series data. ) time series data.

[0061] 2) Establish model training and prediction

[0062] Standardize the selected equal voltage difference time series feature data, and then use the LSTM algorithm to establish a lithium battery RUL prediction model. The standardized discharge voltage difference (3.8V, 3.45V) time series data and charging voltage difference (4.0V, 4.1V) time series data were sent to the model for training, and RMSE was used as an indicator to evaluate the prediction results. Table 1 is a comparison of the accuracy of different algorithms for lithium battery RUL prediction, wit...

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 long-term and short-term memory network. The method comprises the following steps: 1) feature extraction: monitoring the operation process of a lithium battery, extracting voltage change time series data of the charging and discharging process of the lithium battery from the operation process, and processing the voltage change time series data in the charging and discharging process according to the principle of equal voltage difference to generate features; and 2) establishing model training and prediction: establishing a model based on an LSTM algorithm, training the model by taking the equal voltage difference time series data of the charging and discharging process extracted from the battery operationdata as the input characteristics of the model, and then using the trained model for lithium battery RUL prediction. The lithium battery residual prediction method has the advantages that the LSTM algorithm is introduced into the field of lithium battery RUL prediction, and the accuracy of lithium battery RUL prediction is effectively improved by means of the high time sequence prediction capacityof the LSTM algorithm.

Description

technical field [0001] The invention relates to the technical field of prediction of the remaining life of lithium batteries, in particular to a method for predicting the remaining life of lithium batteries based on a long-short-term memory network. Background technique [0002] As the most popular power source at present, lithium battery has many advantages: high specific energy, high working voltage, wide temperature range, low self-discharge rate, long cycle life and good safety, etc. However, as the lithium battery charge and discharge cycles continue to accumulate, the life of the lithium battery will attenuate in an oscillating manner. In the current social life where lithium batteries are used extensively, any carelessness will cause safety accidents. Therefore, it is very important to be able to effectively predict the remaining life (RUL) of lithium batteries. [0003] Generally, the prediction methods for lithium battery RUL are divided into two categories. The f...

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
IPC IPC(8): G01R31/36G01R31/388G01R31/392G01R31/396
CPCG01R31/3648G01R31/388G01R31/392G01R31/396
Inventor 马正阳程钏徐凡娄维尧杨克允沈伟健林韩波刘明威蔡姚杰
Owner ZHEJIANG UNIV OF TECH