Lithium battery hot process space time modeling method based on dual-LS-SVM

A modeling method, lithium battery technology, applied in electrical digital data processing, character and pattern recognition, special data processing applications, etc., can solve problems such as difficult temperature distribution

Inactive Publication Date: 2018-11-02
GUANGDONG UNIV OF TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Estimating the temperature distribution online is very diffic...

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 hot process space time modeling method based on dual-LS-SVM
  • Lithium battery hot process space time modeling method based on dual-LS-SVM
  • Lithium battery hot process space time modeling method based on dual-LS-SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] The spatio-temporal modeling method of thermal process of lithium battery based on dual LS-SVM in this embodiment:

[0094] Step 1, build a lithium battery charge and discharge control platform, such as figure 1 , figure 2 As shown, a plurality of temperature sensors 2 are evenly arranged on the surface of the lithium battery 1, and the temperature data collected by each temperature sensor 2 is transmitted to the host computer 4 by the data acquisition device 3. The lithium battery 1 and the battery test cabinet 5 Electrically connected, the battery test cabinet 5 provides an input signal to the lithium battery 1 Make the lithium battery 1 cycle to charge and discharge;

[0095] Step two, such as image 3 As shown, the upper computer 4 counts the temperature data of all temperature sensors 2, and obtains the time-space data of the temperature distribution of the lithium battery 1 under the condition of cycle charging and discharging with time, and defines the time-...

Embodiment 2

[0175] This example validates the proposed modeling method by conducting real-time experiments. The lithium battery 1 used is a 60Ah lithium iron phosphate battery purchased from a battery manufacturer in Shenzhen, China. This battery uses lithium iron phosphate as its positive electrode material, and has been successfully put into use in electric vehicles. Its basic parameters are shown in Table 1. Considering a flat prismatic 60Ah LiFePO 4 / graphite battery, a 2D thermal model is considered because the temperature variation along the thickness of the battery cell is negligible.

[0176]

[0177]

[0178] Table 1

[0179] The 60Ah lithium iron phosphate battery is a soft pack structure, and the top of the battery is the positive and negative tabs of the battery. The material used for the positive electrode tab is aluminum sheet, and the material used for the negative electrode tab is copper sheet. Its internal structure is a laminated structure, which is composed of m...

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 hot process space time modeling method based on dual-LS-SVM. The method comprises the steps that S1, a lithium battery charge/discharge control platform is set up; S2, space time data of a lithium battery under a cyclic charge/discharge condition is obtained, wherein according to the space time data, temperature distribution changes along with time; S3, anupper computer learns a set of space primary functions representing space nonlinear characteristics, through utilization of a PCA algorithm (namely, a principal component analysis algorithm); S4, theupper computer decomposes an ordinary differential equation ai(t) into two nonlinear modules g(.) and h(.) through utilization of a Galerkin method; and S5, the upper computer carries out series connection on two least squares support vector machines (LS-SVMs) to form a dual-LS-SVM model, thereby approaching to the nonlinear modules g(.) and h(.). The method is used for online estimation of LIBs temperature distribution. The two least squares support vector machines (LS-SVMs) are connected in series to form the dual-LS-SVM model, thereby simulating a distributed parameter system comprising two inherent coupling nonlinearities. The method is relatively effective in the performance approximate aspect of the two inherent coupling nonlinearities. The model precision is high.

Description

technical field [0001] The invention relates to the field of lithium battery thermal process modeling, in particular to a dual LS-SVM-based spatiotemporal modeling method for lithium battery thermal process. Background technique [0002] Electric vehicles (EV) and hybrid electric vehicles (HEV) are considered as solutions to current energy and environmental issues due to oil consumption. As energy storage and conversion components, battery systems are crucial in electric and hybrid electric vehicle technology. However, battery technology advancements for EVs and HEVs are not only affected by materials, but also constrained by their management systems. A comprehensive and accurate battery management system (BMS) is essential to maximize battery life, efficiency and safety. [0003] Lithium-ion batteries (LIBs) are becoming increasingly popular as energy sources for electric and hybrid vehicles due to their high specific energy and high energy density. The safety, lifetime,...

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): G06F17/50G06K9/62
CPCG06F30/367G06F18/2411
Inventor 杨海东徐康康
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products