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

Quantitative diagnosis method of battery micro-short circuit based on artificial neural network

A technology of artificial neural network and diagnosis method, which is applied in the field of quantitative diagnosis of battery micro-short circuit based on artificial neural network, can solve the problems of battery micro-short circuit, thermal runaway, electrode drying, etc., and achieves the effect of small online calculation and reliable diagnosis.

Active Publication Date: 2021-02-26
UNIV OF SHANGHAI FOR SCI & TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, when the voltage measurement line leaks, it will cause the external micro-short circuit of the battery; in a battery pack or battery pack composed of some battery cells, sometimes a balancing device is configured to maintain the consistency of each battery cell, but when the balancing device fails It is also very easy to cause external micro-short circuit
There are also internal micro-short circuits in the battery that are self-contained due to defects in the diaphragm inside the battery, partial drying of the electrodes, and micro-thorns on the surface of the electrode materials, which continuously consume battery power.
In the production process of the battery, if there are burrs or dust falling into the raw materials such as the current collector, then there is a hidden danger that the diaphragm will be damaged during the subsequent use of the battery, forming an internal micro-short circuit
Even if there is no manufacturing defect in the battery, in the process of using the lithium-ion battery, if it is faced with abuses such as over-discharging, over-charging, ultra-high temperature, ultra-low temperature, severe vibration, etc., the surface of the negative electrode of the battery will easily form dendritic lithium branches. crystal, which may pierce the separator and cause a micro-short circuit inside the battery
Regardless of internal micro-short circuit or external micro-short circuit, as the degree of micro-short circuit increases, the self-discharge rate of the battery will gradually increase, and the heat generation will increase, which will lead to serious safety problems such as fire and even thermal runaway.
Especially in the charging process, high temperature environment, etc., the micro-short circuit may be more uncontrollable

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
  • Quantitative diagnosis method of battery micro-short circuit based on artificial neural network
  • Quantitative diagnosis method of battery micro-short circuit based on artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to make the technical means, creative features, goals and effects of the present invention easy to understand, the following embodiments will specifically describe the artificial neural network-based battery micro-short-circuit quantitative diagnosis method of the present invention in conjunction with the accompanying drawings.

[0016] The artificial neural network-based battery micro-short circuit quantitative diagnosis method of the present invention is used for diagnosing the micro-short circuit state of the current battery. The current battery can be a single battery cell or all the battery cells in the battery pack.

[0017] figure 1 It is a flowchart of the quantitative diagnosis method for battery micro-short circuit based on artificial neural network in the embodiment of the present invention.

[0018] Such as figure 1 As shown, the diagnostic method mainly includes the following steps:

[0019] Step 1, measuring battery aging parameters of the batte...

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 battery MSC (micro short circuit) quantitative diagnosis method based on an artificial neural network, and the method is characterized in that the method comprises the steps:carrying out the charging experiment of cells which has different aging degrees and are externally connected with resistors with different resistance values under different temperatures; obtaining thecharging time in a preset voltage section; enabling three values to serve as the input sample of the artificial neural network for one time: the temperature of the cells, the aging parameters of thecells and the charging time in the preset voltage section, wherein the external resistors serve as the output samples for this time. The method obtains samples as many as possible more uniformly underthe different cell working temperatures, aging degrees and external resistance values, and then achieves the training of an MSC fault diagnosis network. The trained MSC fault diagnosis network is integrated in a conventional cell management system. In an actual application, the MSC resistance value can be outputted only if the temperature, capacity and charging time of the cell in the preset voltage section are inputted, thereby achieving the judgment of whether there is an MSC fault or not and the severity of the MSC fault.

Description

technical field [0001] The invention relates to the technical field of batteries, in particular to a method for quantitatively diagnosing battery micro-short circuits based on artificial neural networks. Background technique [0002] In various consumer electronics, power devices and other products and equipment, many batteries are used to store and provide energy, such as lithium-ion batteries, nickel-metal hydride batteries, lead-acid batteries, etc. But when the battery fails, it will affect the use and performance of the product or equipment, and even pose a threat to the safety of the product or equipment, and the battery will catch fire and explode. Battery short circuit is a common fault. Battery short circuit refers to an abnormal path in which the positive and negative poles of the battery are connected to each other with very small resistance for some reason. Battery short circuit is further divided into battery internal short circuit and external short circuit. ...

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): G01R31/367G01R31/385G01R31/392
CPCG01R31/367
Inventor 孔祥栋张振东郑岳久尹丛勃
Owner UNIV OF SHANGHAI FOR SCI & TECH