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

Lithium-ion battery state of charge estimation method based on fusion of deep belief network and Kalman filter

A deep belief network and Kalman filter technology, applied in the measurement of electricity, measurement devices, measurement of electrical variables, etc., can solve the problems of low SOC estimation accuracy and model parameter identification of lithium-ion batteries

Active Publication Date: 2020-08-04
HARBIN INST OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the low accuracy of traditional methods for estimating the SOC of lithium-ion batteries in actual working conditions, but there are modeling problems and model parameter identification problems in battery model-based methods, thereby providing a lithium-ion battery for dynamic working conditions State of Charge Estimation Method

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-ion battery state of charge estimation method based on fusion of deep belief network and Kalman filter
  • Lithium-ion battery state of charge estimation method based on fusion of deep belief network and Kalman filter
  • Lithium-ion battery state of charge estimation method based on fusion of deep belief network and Kalman filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] combine Figure 4 This embodiment will be specifically described with Table 1. In this embodiment, four sets of sample data sets of the NASA PCoE random working condition data set are selected to estimate the state of charge of the battery.

[0049] Step 1: Extract the voltage, current, temperature and SOC data of the battery from the battery test data, and normalize the extracted data to [0, 1] to obtain a normalized data set.

[0050] Step 2: Divide the normalized data set into the No. 1 input vector X at time k according to the following formula k (1) , the second input vector X k (2) and the output vector Y k ; The number one input vector X at the time k k (1) , the second input vector X k (2) and the output vector Y k The expressions of are as follows:

[0051] x k (1) =[v k ,...,v k-m ,i k ,...,i k-n ,t k ,...,t k-p ],

[0052] x k (2) =[v k ,...,v k-m ,i k ,...,i k-n ,t k ,...,t k-p ,SOC k-1 ],

[0053] Y k =[SOC k ],

[0054] Amo...

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 provides a lithium ion battery charge state estimation method based on depth belief network and Kalman filtering, relates to the technical field of battery management, and aims at solving the problem of a conventional method. The lithium ion battery charge state estimation method starts from the current, voltage and temperature parameters capable of being directly measured in practical operation of the battery; a lithium ion battery SOC estimation model is built. The depth belief network in depth study is used for estimating the lithium ion battery SOC; the depth belief network and a Kalman filtering method are merged to obtain a fused lithium ion battery SOC estimation model. Compared with the prior art, the SOC estimation method based on a data driving method can perform feature extraction according to historical data obtained according to the practical work of the battery; then, the system error is inspected by combining with the filtering method, so that the relativeprecise SOC estimation value is obtained.

Description

technical field [0001] The invention belongs to the technical field of battery management, and in particular relates to an online estimation method for the state of charge of a lithium-ion battery. Background technique [0002] Due to its high specific energy, high working voltage, wide temperature range, low self-discharge rate, long cycle life and good safety, lithium-ion batteries are widely used in mobile phones, notebook computers and electric vehicles, and gradually expanded to Military communications, navigation, aviation, aerospace and other fields have gradually become key and supporting technologies in many important fields in the future. [0003] Battery state of charge (State of Charge, SOC) is an important key parameter in the lithium-ion battery management system. Accurate estimation of the lithium-ion battery SOC can ensure the efficiency of the battery and improve the safety of the system. Therefore, it is of great significance to accurately estimate the SOC...

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 Patents(China)
IPC IPC(8): G01R31/382G01R31/387
Inventor 刘大同彭宇李律宋宇晨彭喜元
Owner HARBIN INST OF TECH