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

Lithium battery temperature field online modeling method and system

A modeling method and temperature field technology, applied in the field of lithium battery temperature field online modeling method and system, can solve problems such as aggravating the generation of ill-conditioned matrix inversion and algorithm instability, and achieve the effect of ensuring timeliness and accurate prediction

Pending Publication Date: 2022-07-01
GUANGDONG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the forgetting factor introduced by the algorithm exacerbates the problem of ill-conditioned matrix inversion, which leads to the instability of the whole algorithm.

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 temperature field online modeling method and system
  • Lithium battery temperature field online modeling method and system
  • Lithium battery temperature field online modeling method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0102] like figure 1 As shown in the figure, an online modeling method for a temperature field of a lithium battery includes the following steps;

[0103] S1. Use the KL method to separate the space-time data in space and time, and obtain the space basis function and time coefficient respectively;

[0104] S2. Use the width learning network to train the time coefficient to obtain an offline model of the temperature field of the lithium battery;

[0105] S3. Use the incremental learning algorithm of the width learning network to update the network weight of the offline model. When the set weight value is reached, stop the update to obtain the online model of the lithium battery temperature field;

[0106] S4, reconstruct the prediction time coefficient in the online model and the space basis function obtained in step S1 to obtain a prediction model;

[0107] S5. Input the temperature field data of the lithium battery to be predicted into the prediction model, and the predicti...

Embodiment 2

[0189] like figure 2 As shown, this embodiment is similar to Embodiment 1, the difference is that this embodiment provides an online modeling system for lithium battery temperature field based on the principle of the method for the method in Embodiment 1, and the system includes a processor , and a separation module, a training module, an update module, and a reconstruction module that are communicatively connected to the processor;

[0190] The separation module uses the KL method to separate the space-time data, obtains the space basis function and the time coefficient, and uploads them to the processor, and the processor sends the time coefficient to the training module;

[0191] The training module uses the width learning network to train the time coefficient, obtains the offline model of the lithium battery temperature field, and sends it to the update module;

[0192] The update module uses the incremental learning algorithm of the width learning network to update the ...

Embodiment 3

[0198] Taking the thermal process of a 32Ah NCM ternary lithium battery as an example, the embodiments of the present invention will be explained.

[0199] There are 32 thermal sensors evenly distributed on the surface of the lithium battery. In order to fully excite the battery temperature, the input current and the generated operating voltage are used as the input signal u(t)=[I(t), U(t)], and I(t) is Input current; U(t) is the working voltage. In the case of the sample interval Δt=1s, the data of 1370s since the discharge is used, a total of 1370 groups, each group contains 32 temperature data collected by the thermal sensor.

[0200] In the initial stage, using the KL method to separate the spatiotemporal data for the temperature data y(x, t), the spatiotemporal data can be separated into spatial basis functions containing spatial information and time-related corresponding time coefficients.

[0201] When using the snapshot method to find the spatial basis function, the f...

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 temperature field online modeling method and system. The method comprises the following steps: firstly, carrying out space-time separation on space-time data by using a KL method to respectively obtain a space basis function and a time coefficient; secondly, training a time coefficient by using a width learning network to obtain an offline model of the lithium battery temperature field; and then updating the network weight of the off-line model by using an incremental learning algorithm of width learning, establishing an on-line model of the lithium battery temperature field, and finally reconstructing an obtained prediction time coefficient and a space basis function to obtain a final prediction model to predict data. According to the method, modeling is carried out on the temperature field of the lithium ion battery, and online updating is carried out on the model by using an incremental learning algorithm with excellent width learning, so that the model adapts to the time-varying behavior of the system, and the problem of temperature field prediction with unknown, nonlinear and time-varying characteristics of the system is solved.

Description

technical field [0001] The invention relates to the technical field of testing the temperature field of lithium batteries, in particular to an on-line modeling method and system for the temperature field of lithium batteries. Background technique [0002] The temperature field of the lithium battery has a great influence on the performance, service life and safety of the battery. Establishing an accurate temperature field prediction model is helpful for the monitoring, management and control of lithium battery temperature. However, the lithium-ion battery temperature field belongs to a class of time-varying distributed parameter systems. Mathematically, this type of system can be described by partial differential equations and related boundary conditions, but this type of system has time-varying and strongly nonlinear characteristics, and the system input / output, system boundary and system parameters will vary with time and space. Variety. Therefore, it is a great challen...

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): G06F30/27G06F17/18G06F17/16G06F119/08
CPCG06F30/27G06F17/18G06F17/16G06F2119/08
Inventor 徐康康谭喜杨海东印四华金熹朱成就
Owner GUANGDONG UNIV OF TECH
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