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

Transformer-based deep learning battery state of charge (SOC) estimation system and method

A technology of battery state of charge and deep learning, applied in neural learning methods, measuring electricity, measuring electrical variables, etc., can solve problems such as single factor, lack of feedback correction ability, and decreased prediction accuracy

Active Publication Date: 2021-11-19
杭州宇谷科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is simple and easy to implement, but has strong limitations
The main reason is that the factors considered in the ampere-hour integral method model are single and lack feedback correction capabilities. As the number of battery usage increases, the estimation accuracy drops sharply

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
  • Transformer-based deep learning battery state of charge (SOC) estimation system and method
  • Transformer-based deep learning battery state of charge (SOC) estimation system and method
  • Transformer-based deep learning battery state of charge (SOC) estimation system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] to combine figure 1 As shown, the present embodiment provides a Transformer-based deep learning battery state-of-charge estimation system, which includes:

[0050] A fully connected neural network, which is used to process the battery feature sequence R and the battery initial state sequence S and output it to;

[0051] Transformer neural network, which is used to process and output the battery charging and discharging process sequence T;

[0052] linear fusion layer, which is used to output and output Stitching and weighted calculations are performed to obtain the predicted battery SOC, ;as well as

[0053] output layer, which is used to output .

[0054] In this embodiment, the battery characteristic sequence R, the battery initial state sequence S and the battery charging and discharging process sequence T can be constructed simultaneously.

[0055] Among them, the battery characteristic sequence R represents the inherent characteristics of the battery, su...

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 relates to the technical field of battery SOC online prediction, in particular to a Transformer-based deep learning battery SOC estimation system and method. The system comprises a full-connection neural network which is used for processing and outputting a battery characteristic sequence R and a battery initial state sequence S; a Transformer neural network which is used for processing and outputting the battery charging and discharging process sequence T; a linear fusion layer which is used for carrying out splicing and weighted calculation on the output and the output so as to obtain a predicted battery SOC; and an output layer for outputting. The method is realized based on the system. According to the system, online prediction of the SOC of the battery can be better realized.

Description

technical field [0001] The invention relates to the technical field of battery SOC online prediction, in particular to a Transformer-based deep learning battery state-of-charge estimation system and method. Background technique [0002] Lithium batteries have the advantages of high energy storage density, long service life, low self-discharge rate, light weight, and environmental protection. They have been widely used in various daily life scenarios such as mobile phones, laptop computers, power tools, and new energy vehicles. Among them, the state of charge (SOC) is a key indicator during battery use. Accurately estimating the state of charge is of great significance in preventing overcharge and overdischarge, improving battery energy utilization, and ensuring the safety and stability of the battery system, and provides the necessary conditions for subsequent optimization of vehicle energy distribution. If the state of charge of the battery cannot be accurately measured, t...

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): G06F30/27G06F17/16G06N3/04G06N3/08G01R31/367G01R31/382
CPCG06F30/27G06F17/16G06N3/08G01R31/367G01R31/382G06N3/045
Inventor 肖劼胡雄毅余为才
Owner 杭州宇谷科技股份有限公司