CN-122017585-A - Battery peak power determination method and related equipment

CN122017585ACN 122017585 ACN122017585 ACN 122017585ACN-122017585-A

Abstract

The embodiment of the application provides a method for determining battery peak power and related equipment, belonging to the technical field of power batteries. The embodiment can combine the real-time terminal voltage, battery capacity, total battery capacity and battery capacity change value of the power battery, output the peak power value through the peak power prediction model, realize the acquisition of the battery peak power value after continuous use, the electric equipment using the power battery can timely carry out power adjustment according to the peak power value, maintain the power supply function of the power battery, and prolong the service life of the battery.

Inventors

ZHENG LINFENG
TANG XIN
SHEN WENJING
WANG JIE
Nian Muxin
ZHANG HAICHUAN
LV ZHIJIAN
HU DENGPING
LIN XUN

Assignees

深圳技术大学

Dates

Publication Date: 20260512
Application Date: 20260202

Claims (10)

1. A method of determining peak power of a battery, the method comprising: Acquiring operation data of a power battery in the current charge and discharge process, and determining working parameters of the power battery by utilizing the operation data, wherein the working parameters at least comprise terminal voltage, battery capacity, total battery capacity and battery capacity change values of the power battery; And inputting the working parameters into a peak power prediction model, and acquiring a peak power value of the power battery, wherein the power prediction model is used for determining the peak power value of the power battery in the current charge and discharge process according to the input mapping relation between the working parameters and the peak power.
2. The method of claim 1, further comprising obtaining a peak power prediction model; The obtaining the peak power prediction model includes: Test data of the power battery in the cyclic charge and discharge processes under different working conditions are obtained, wherein the test data comprise terminal voltage, current value, battery capacity and peak power; Determining a battery capacity increment of the power battery according to the test data; And establishing a peak power prediction model taking the terminal voltage, the current value, the battery capacity and the battery capacity increment as model inputs by using a Gaussian process regression algorithm, wherein the peak power is the peak power prediction model output by the model.
3. The method of claim 2, wherein determining the battery capacity delta of the power battery based on the test data comprises: Acquiring test data in a plurality of cyclic charge and discharge processes, and determining adjacent test data in a charge and discharge process adjacent to the current charge and discharge process; And determining the battery capacity increment of the power battery by utilizing a five-point three-time smoothing algorithm and combining the adjacent test data.
4. The method of claim 2, wherein the covariance function of the peak power prediction model is a Matern/2 kernel function.
5. The method of claim 2, wherein the prior distribution of the peak power prediction model is a zero-mean gaussian process.
6. The method of claim 2, wherein after said establishing a peak power prediction model using said terminal voltage, said current value, said battery capacity, and said battery capacity delta as model inputs and said peak power as model output using a gaussian process regression algorithm, said method further comprises: And performing performance evaluation on the trained prediction model, wherein the evaluation indexes at least comprise average absolute error, average relative error and decision coefficient.
7. A battery peak power determination apparatus, the apparatus comprising: The power battery charging and discharging device comprises an acquisition module, a charging and discharging module and a charging and discharging module, wherein the acquisition module is used for acquiring operation data of a power battery in the current charging and discharging process, and determining working parameters of the power battery by utilizing the operation data, wherein the working parameters at least comprise terminal voltage, battery capacity, total battery capacity and battery capacity change values of the power battery; The power prediction module is used for determining the peak power value of the power battery in the current charge and discharge process according to the input mapping relation between the working parameter and the peak power.
8. An electronic device comprising a memory storing a computer program and a processor implementing the method of any of claims 1 to 6 when the computer program is executed by the processor.
9. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the method of any one of claims 1 to 6.

Description

Battery peak power determination method and related equipment Technical Field The application relates to the technical field of power batteries, in particular to a battery peak power determination method and related equipment. Background The power battery is widely applied to various fields such as portable electronic equipment, wearable equipment, electric automobiles, commercial energy storage systems, aerospace, military and the like due to the characteristics of high energy density, light weight, repeated charging and low self-discharge rate, and becomes an ideal choice in various application scenes. However, the performance of the power battery is gradually deteriorated due to factors such as cyclic charge and discharge, high temperature, overcharge, overdischarge, and the like, and is accompanied by a great potential safety hazard. The performance degradation of the power battery may be accompanied by a decrease in various parameters, affecting the normal use of the power battery, and it is difficult for a device powered by the power battery to quickly determine specific parameters of the power battery, and a power shortage may occur. In summary, the technical problems in the related art are to be improved. Disclosure of Invention The embodiment of the application mainly aims to provide a battery peak power determining method and related equipment, so as to confirm specific battery parameters of a power battery after continuous use, thereby being convenient for the equipment to adjust a power supply strategy in time and maintaining normal power supply. To achieve the above object, an aspect of an embodiment of the present application provides a method for determining peak power of a battery, including: Acquiring operation data of a power battery in the current charge and discharge process, and determining working parameters of the power battery by utilizing the operation data, wherein the working parameters at least comprise terminal voltage, battery capacity, total battery capacity and battery capacity change values of the power battery; And inputting the working parameters into a peak power prediction model, and acquiring a peak power value of the power battery, wherein the power prediction model is used for determining the peak power value of the power battery in the current charge and discharge process according to the input mapping relation between the working parameters and the peak power. In some embodiments, the method further comprises obtaining a peak power prediction model; The obtaining the peak power prediction model includes: Test data of the power battery in the cyclic charge and discharge processes under different working conditions are obtained, wherein the test data comprise terminal voltage, current value, battery capacity and peak power; Determining a battery capacity increment of the power battery according to the test data; And establishing a peak power prediction model taking the terminal voltage, the current value, the battery capacity and the battery capacity increment as model inputs by using a Gaussian process regression algorithm, wherein the peak power is the peak power prediction model output by the model. In some embodiments, the determining the battery capacity increment of the power battery according to the test data comprises: Acquiring test data in a plurality of cyclic charge and discharge processes, and determining adjacent test data in a charge and discharge process adjacent to the current charge and discharge process; And determining the battery capacity increment of the power battery by utilizing a five-point three-time smoothing algorithm and combining the adjacent test data. In some embodiments, the covariance function of the peak power prediction model is a Matern/2 kernel function. In some embodiments, the prior distribution of the peak power prediction model is a zero-mean gaussian process. In some embodiments, after said using a gaussian process regression algorithm to build a peak power prediction model with said terminal voltage, said current value, said battery capacity and said battery capacity delta as model inputs, said peak power being a model output, said method further comprises: And performing performance evaluation on the trained prediction model, wherein the evaluation indexes at least comprise average absolute error, average relative error and decision coefficient. To achieve the above object, another aspect of the embodiments of the present application provides a battery peak power determining apparatus, including: The power battery charging and discharging device comprises an acquisition module, a charging and discharging module and a charging and discharging module, wherein the acquisition module is used for acquiring operation data of a power battery in the current charging and discharging process, and determining working parameters of the power battery by utilizing the operation data, wherein the working parameters at least comprise termi