CN118191604A

CN118191604A - Method, apparatus, device, medium and program product for predicting battery health

Info

Publication number: CN118191604A
Application number: CN202211609804.2A
Authority: CN
Inventors: 王兴成
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2022-12-14
Filing date: 2022-12-14
Publication date: 2024-06-14

Abstract

The application discloses a method, a device, equipment, a medium and a program product for predicting battery health, and relates to the technical field of battery management. The method comprises the following steps: acquiring health degree attenuation curves of the rechargeable battery under a plurality of test temperature conditions; in the current battery health degree detection period, the current use times and the current health degree corresponding to the current rechargeable battery are obtained; based on the health degree attenuation curves respectively corresponding to the multiple test temperature conditions, curve parameter fitting is carried out on the current use times and the current health degree to obtain a health degree prediction curve; determining the corresponding predicted health degree of the rechargeable battery when the number of times of use reaches a preset number; based on the relationship between the predicted health and the required health, the future health detection period of the rechargeable battery is adjusted. By the method, the future health detection period can be timely adjusted by predicting the battery health of the rechargeable battery, so that the attenuation slowing strategy is performed on the rechargeable battery in advance.

Description

Method, apparatus, device, medium and program product for predicting battery health

Technical Field

The embodiment of the application relates to the technical field of battery management, in particular to a method, a device, equipment, a medium and a program product for predicting battery health.

Background

Rechargeable batteries are widely used to power electrical devices such as: the battery Health (SOH) Of a rechargeable battery is a key factor for determining the usable time Of the rechargeable battery, such as charging a mobile phone, charging an electric car, and the like.

In the related art, the corresponding designated number of times of use when the battery health of the rechargeable battery is in the health decay state is generally predicted according to the current number of times of use of the rechargeable battery, and when the number of times of use of the rechargeable battery reaches the designated number of times of use, the decay rate of the battery health is slowed down by reducing the battery voltage.

However, in the related art, as the habit of using the device by different users is different, the battery health degree of the rechargeable battery reaches the health degree attenuation state before the specific use times are not reached, so that the attenuation and slowing strategy is started later, the strategy effect is poor, and the battery use efficiency of the rechargeable battery is lower.

Disclosure of Invention

The embodiment of the application provides a method, a device, equipment, a medium and a program product for predicting the health degree of a battery, which can timely adjust the future health degree detection period by predicting the health degree of the battery of the rechargeable battery, so as to carry out attenuation slowing strategy on the rechargeable battery in advance. The technical scheme is as follows:

in one aspect, a method for predicting battery health is provided, the method comprising:

acquiring health degree attenuation curves of the rechargeable battery under a plurality of test temperature conditions, wherein the health degree attenuation curves are used for indicating attenuation change rules of the health degree of the rechargeable battery along with the use times under the test temperature conditions;

in a current battery health degree detection period, acquiring current use times and current health degrees corresponding to the rechargeable battery, wherein the current use times are used for indicating battery cycle times corresponding to the situation that the discharge quantity of the rechargeable battery reaches a preset discharge quantity, and the current health degrees are used for indicating the current electric quantity accommodating capacity of the rechargeable battery;

Performing curve parameter fitting on the current use times and the current health degree based on the health degree attenuation curves respectively corresponding to the plurality of test temperature conditions to obtain a health degree prediction curve;

Based on the health degree prediction curve, predicting and analyzing the future health degree of the rechargeable battery, and determining the corresponding predicted health degree of the rechargeable battery when the number of times of use is preset;

and adjusting a future health detection period of the rechargeable battery based on the relation between the predicted health and the required health, wherein the required health is a preset battery health corresponding to the preset use times.

In another aspect, there is provided a device for predicting battery health, the device comprising:

The acquisition module is used for acquiring health degree attenuation curves of the rechargeable battery under a plurality of test temperature conditions, wherein the health degree attenuation curves are used for indicating the attenuation change rule of the health degree of the rechargeable battery along with the use times under the test temperature conditions;

The acquisition module is further configured to acquire, in a current battery health detection period, a current usage number and a current health corresponding to the rechargeable battery, where the current usage number is used to indicate a battery cycle number corresponding to when a discharge amount of the rechargeable battery reaches a preset discharge amount, and the current health is used to indicate a current electric quantity holding capability of the rechargeable battery;

The fitting module is used for performing curve parameter fitting on the current use times and the current health degree based on the health degree attenuation curves respectively corresponding to the plurality of test temperature conditions to obtain a health degree prediction curve;

The analysis module is used for carrying out predictive analysis on the future health of the rechargeable battery based on the health prediction curve and determining the corresponding predicted health of the rechargeable battery when the number of times of use reaches a preset number;

And the adjustment module is used for adjusting the future health detection period of the rechargeable battery based on the relation between the predicted health and the required health, wherein the required health is a preset battery health corresponding to the preset use times.

In another aspect, a computer device is provided, where the computer device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a set of codes, or a set of instructions, where the at least one instruction, the at least one program, the set of codes, or the set of instructions are loaded and executed by the processor to implement a method for predicting battery health according to any one of the embodiments of the present application.

In another aspect, a computer readable storage medium is provided, in which at least one instruction, at least one program, a set of codes, or a set of instructions is stored, the at least one instruction, the at least one program, the set of codes, or the set of instructions being loaded and executed by a processor to implement a method for predicting battery health according to any one of the embodiments of the application described above.

In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electric vehicle reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the electric vehicle performs the method of predicting the battery health according to any one of the above embodiments.

The technical scheme provided by the embodiment of the application has the beneficial effects that at least:

after the corresponding health degree attenuation curves of the rechargeable battery under different test temperature conditions are obtained, curve parameter fitting is carried out on the current use times and the current health degree of the rechargeable battery according to a plurality of health degree attenuation curves in the current battery health degree detection period, so that a health degree prediction curve of the rechargeable battery in the current battery health degree detection period is obtained, the predicted health degree of the rechargeable battery is determined according to the health degree prediction curve, and finally, the future health degree detection period of the rechargeable battery is adjusted in real time according to the relation between the predicted health degree and the preset required health degree, so that the attenuation slowing strategy can be formulated in time later. That is, by means of the current use times and the current health degree of the rechargeable battery, the health degree prediction curve can be obtained in real time, the health degree detection period can be adjusted in advance according to different battery health degree states of the rechargeable battery, the related attenuation slowing strategy can be formulated conveniently later, the efficiency of slowing down the attenuation state of the battery of the rechargeable battery is improved, and the usable time of the rechargeable battery is prolonged effectively.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of a method for predicting battery health according to an exemplary embodiment of the present application;

FIG. 2 is a flowchart of a method for predicting battery health provided by an exemplary embodiment of the present application;

FIG. 3 is a flowchart of a method of predicting battery health according to another exemplary embodiment of the present application;

FIG. 4 is a schematic diagram of a health decay curve under different test temperature conditions provided by an exemplary embodiment of the present application;

FIG. 5 is a schematic diagram of health prediction curve generation provided by an exemplary embodiment of the present application;

FIG. 6 is a schematic diagram of a health prediction curve corresponding to different actual usage parameters according to an exemplary embodiment of the present application;

FIG. 7 is a flowchart of a method for predicting battery health provided by an exemplary embodiment of the present application;

Fig. 8 is a block diagram showing a structure of a battery health prediction apparatus according to an exemplary embodiment of the present application;

Fig. 9 is a block diagram illustrating a structure of a battery health prediction apparatus according to another exemplary embodiment of the present application;

fig. 10 is a block diagram of a computer device according to an exemplary embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

First, terms involved in the present application are explained.

State Of Health (SOH): the battery usage performance state, that is, the percentage between the current capacity of the battery and the capacity of the factory, is expressed as a general capacity of 100% and a capacity of 0% when the battery is completely discarded.

Battery Cycle number (Cycle): refers to a complete charge-discharge cycle, and when the battery reaches a complete charge cycle, the cycle number of the battery is increased by one. In this embodiment, considering that a user does not form a complete cycle every time the user uses the mobile phone in real life, a discharge amount threshold is set, for example: when the preset discharge amount reaches 50%, and when the discharge amount of the mobile phone used by the user reaches 50%, the number of times of primary battery circulation is generated, namely the number of times of use in the embodiment of the application.

The battery is used as an energy storage device and is widely applied to scenes such as mobile phones, electric automobiles, power grid assistance, high-rate quick charging stations and the like. In the field of intelligent terminals, rechargeable batteries are often used to charge equipment in combination with a charger, wherein the rechargeable batteries comprise nickel-cadmium batteries, nickel-hydrogen batteries, lithium ion batteries, lead storage batteries and lithium iron batteries. Therefore, the rechargeable battery is built in the above-described specific device.

Taking a lithium ion battery as an example, in the field of intelligent terminals (such as the field of intelligent mobile phones), how to slow down the decay rate of the service life of the lithium ion battery is always a hot spot of research, and currently applied decay slowing strategies predict a target cycle number according to the actual battery cycle number of the current lithium ion battery, so that a strategy of cyclically reducing the voltage of the lithium ion battery is executed when the service frequency of the lithium ion battery reaches the target cycle number, but when the service frequency of the lithium ion battery reaches the target cycle number, a certain degree of abnormal health decay phenomenon occurs in the lithium ion battery, so that the execution process of the decay slowing strategy is lagged, and the efficiency of slowing down the health decay state of the lithium ion battery is lower.

According to the method for predicting the health degree of the rechargeable battery, the health degree prediction curve of the rechargeable battery can be obtained according to the current use state of the rechargeable battery, so that the health degree detection period of the rechargeable battery is adjusted, the attenuation slowing strategy can be executed on the rechargeable battery in advance in the health degree detection period, and the strategy execution efficiency is improved. Referring to fig. 1, a schematic diagram of a method for predicting the health of a battery according to an exemplary embodiment of the present application is shown, and as shown in fig. 1, a rechargeable battery is built in a designated device, and a health decay curve 110 of the rechargeable battery under a plurality of test temperature conditions is obtained through a battery aging cycle test. In the current battery health detection period, current use parameters 120 of the rechargeable battery in the current period are acquired, including the current use times and the current health, and curve parameter fitting is performed on the current use parameters 120 of the rechargeable battery according to the health decay curve 110, so as to obtain a health prediction curve 130. The future health of the rechargeable battery is predicted and analyzed according to the health prediction curve 130, the predicted health 140 corresponding to the rechargeable battery when the number of times of use is preset in the current battery health detection period is determined, the future health detection period 160 of the rechargeable battery is adjusted according to the relation between the predicted health 140 and the preset required health 150, and the future health detection period is adjusted again in the next health detection period, so that the health detection period is adjusted in real time according to different use states of the rechargeable battery, and the health attenuation state of the rechargeable battery is predicted.

Referring to fig. 2, a flowchart of a method for predicting the battery health according to an exemplary embodiment of the present application is shown, and the method includes the following steps, as shown in fig. 2.

Step 210, obtaining health degree attenuation curves of the rechargeable battery corresponding to the plurality of test temperature conditions.

The health degree attenuation curve is used for indicating the attenuation change rule of the health degree of the rechargeable battery along with the use times under the test temperature condition.

Illustratively, the rechargeable battery is built in the above-mentioned designated device and is a power supply device for charging the designated device in cooperation with a charger.

The health degree attenuation curve is a curve corresponding to the health degree attenuation of the rechargeable battery along with the increase of the use times under the test temperature condition. That is, the curve parameters corresponding to the health degree decay curve are the number of times of use and the battery health degree, respectively.

Optionally, the health degree attenuation curves respectively corresponding to different test temperature conditions are different; or the health degree attenuation curves corresponding to at least two test temperature conditions are the same, which is not limited.

Illustratively, the higher the temperature, the faster the rate of decay in the health of the rechargeable battery as the number of uses of the rechargeable battery increases.

Optionally, the acquiring manner of the health degree attenuation curve includes at least one of the following acquiring manners:

1. by designing a battery aging experiment, using the charge and discharge theoretical knowledge of the rechargeable battery, and taking the test temperature as a variable quantity to carry out charge and discharge measurement on the rechargeable battery, a plurality of battery health degree values which respectively correspond to different times of use under the test temperature condition are obtained, and a corresponding health degree attenuation curve under the test temperature condition is generated after fitting the plurality of battery health degree values;

2. Acquiring historical health degree attenuation data of a plurality of reference batteries of the same model as the rechargeable battery in a historical time period, wherein the historical health degree attenuation data refer to historical battery health degrees respectively corresponding to the reference batteries along with the increase of the use times under the historical temperature condition, so that health degree attenuation curves respectively corresponding to different historical temperature conditions are generated according to the historical health degree attenuation data respectively corresponding to the plurality of reference batteries and the historical temperature condition;

3. And (3) pre-training a battery attenuation prediction model, inputting the battery parameters of the rechargeable battery and a plurality of test temperature conditions into the battery attenuation prediction model, and outputting to obtain health degree attenuation curves corresponding to the plurality of test temperature conditions respectively.

It should be noted that the above-mentioned method for obtaining the health decay curve is merely an illustrative example, and the embodiment of the present application is not limited thereto.

In this embodiment, the health decay curves under a plurality of different test temperature conditions refer to experimental use parameters of the rechargeable battery.

In this embodiment, when the health of the rechargeable battery is reduced, the rechargeable battery starts to age. Therefore, the health decay curve may also be referred to as an aging curve of the rechargeable battery.

Step 220, in the current battery health degree detection period, the current use times and the current health degree corresponding to the current rechargeable battery are obtained.

The current use times are used for indicating the corresponding battery cycle times when the discharge quantity of the rechargeable battery reaches the preset discharge quantity, and the current health degree is used for indicating the current electric quantity accommodating capacity of the rechargeable battery.

Illustratively, the battery health detection period refers to a period in which the current battery health of the rechargeable battery is detected immediately when the number of battery cycles of the rechargeable battery reaches a specified number of intervals. In one example, the battery health detection period is 50 times apart, and each time the battery cycle number of the rechargeable battery reaches a multiple of 50 (e.g., 100 times, 150 times, 200 times, etc.), the battery health of the rechargeable battery is detected.

Illustratively, the current battery health detection period refers to a period corresponding to when the number of times the current rechargeable battery is used reaches a specified number of times interval.

In some embodiments, the current usage number refers to the number of battery cycles of the rechargeable battery at the current time, and the discharge amount is the usage amount of the rechargeable battery, for example: the current charge of the rechargeable battery is 70%, and the discharge of the rechargeable battery is 30%. The preset discharge amount is a specified discharge amount preset for determining the number of battery cycles of the rechargeable battery. Such as: when the discharge amount of the rechargeable battery reaches 30%, the battery cycle number of the rechargeable battery is increased by one, and if the current discharge amount of the rechargeable battery reaches 100 times, the current use number is 100 times.

In some embodiments, the current health refers to the battery health of the rechargeable battery at the current number of uses. The capacity of the rechargeable battery is a percentage between the current capacity of the rechargeable battery and the capacity of the rechargeable battery when the rechargeable battery is used for a certain number of times.

Illustratively, in the current battery health detection period, a battery electricity meter is used for detecting the rechargeable battery, and the current use times and the current health of the rechargeable battery at the current moment are obtained.

The battery power meter, also referred to as a battery power indicator, predicts how long a rechargeable battery will still provide power under prescribed operating conditions. In this embodiment, the specified working condition is the condition of the rechargeable battery in the current practical use process.

In this embodiment, the current number of uses and the current health degree belong to actual use parameters of the rechargeable battery.

And 230, performing curve parameter fitting on the current use times and the current health degree based on the health degree attenuation curves respectively corresponding to the plurality of test temperature conditions to obtain a health degree prediction curve.

Schematically, as the health degree attenuation curves corresponding to the test temperature conditions are obtained in advance, the health degree prediction curve corresponding to the rechargeable battery at the current moment is located between the health degree attenuation curves corresponding to the two test temperature conditions in the test temperature conditions. Wherein, these two test temperature conditions are determined according to the current number of uses and the current health.

In some embodiments, the two test temperature conditions are respectively used as a first test temperature condition and a second test temperature condition, wherein the health degree attenuation curve corresponding to the first test temperature condition is a first attenuation curve, and the health degree attenuation curve corresponding to the second test temperature condition is a second attenuation curve.

Illustratively, curve parameter fitting refers to determining a curve parameter according to a proportional relationship between a plurality of detected health degrees and a current health degree after determining the detected health degrees corresponding to the health degree attenuation curve according to the current use times, so as to generate a health degree prediction curve according to the curve parameter.

Optionally, the obtaining manner of the health degree prediction curve includes at least one of the following obtaining manners:

1. Determining detection health degrees corresponding to the current use times from a plurality of health degree attenuation curves according to the current use times of the rechargeable battery, and determining a first health degree and a second health degree which are matched with the health degree of the battery from the plurality of detection health degrees, wherein the health degree attenuation curve corresponding to the first health degree is used as a first attenuation curve, the health degree attenuation curve corresponding to the second health degree is used as a second attenuation curve, and the health degree attenuation curve is generated according to the proportional relation among the first health degree, the current health degree and the second health degree;

2. According to the current temperature condition of the rechargeable battery at the current moment, a first test temperature condition and a second test temperature condition which are matched with the current temperature condition are determined from a plurality of test temperature conditions, and curve parameter fitting is carried out on the current health degree and the current use times through a first attenuation curve corresponding to the first test temperature condition and a second attenuation curve corresponding to the second test temperature condition, so that a health degree prediction curve corresponding to the actual use parameters is generated.

It should be noted that the above-mentioned method for obtaining the health degree prediction curve is merely an illustrative example, and the embodiment of the present application is not limited thereto.

Optionally, the health prediction curve is entirely between the first decay curve and the second decay curve; or the part of the line segment on the health degree prediction curve is completely between the first attenuation curve and the second attenuation curve, but the part of the line segment is outside the first attenuation curve and the second attenuation curve, which is not limited.

In some embodiments, the first and second decay curves that it adapts to are different as the current number of uses and current health are different.

In some embodiments, the corresponding health prediction curves may or may not be the same as the current time is not used. That is, the health prediction curve varies with the current health and the number of times of use.

And 240, carrying out predictive analysis on the future health of the rechargeable battery based on the health prediction curve, and determining the corresponding predicted health of the rechargeable battery when the number of times of use reaches a preset number.

Illustratively, the future health refers to a battery health corresponding to a future time starting from the current time as the starting time.

Schematically, after the health degree prediction curve corresponding to the current moment is obtained, the predicted health degree of the rechargeable battery when the number of times of use is preset is determined according to the health degree prediction curve. In one example, when the current usage number is 100 times, the predicted health of the rechargeable battery is 91% after the health prediction curve when the current health is 95% is determined, and the preset usage number is 300 times according to the health prediction curve.

In some embodiments, the predicted health may vary from one health prediction curve to another.

Illustratively, the predicted health refers to the future health corresponding to the health prediction curve determined according to the actual usage parameters at the current time, that is, the predicted health is related to the current number of uses and the current health.

Optionally, the preset number of uses is determined according to the current health degree, such as: if the current health degree is 95%, and the current use times are 100 times, the preset use times are 300 times, and the following is further provided: if the current health degree is 90%, the current use times are 100 times, and the preset use times are 200 times; or the preset number of times of use is a preset fixed number of times.

In an alternative scheme, after the health degree prediction curve of the current moment is obtained, firstly, the predicted health degree is determined, and the preset use times are determined according to the predicted health degree. Such as: after the health degree prediction curve at the current moment is obtained, the predicted health degree is determined to be 80%, and the preset use times corresponding to the predicted health degree of 80% are determined to be 500 according to the health degree prediction curve.

In an alternative scheme, after the health degree prediction curve of the current moment is obtained, the preset use times are determined first, and the predicted health degree is determined according to the preset use times. Such as: after the health degree prediction curve at the current moment is obtained, the preset use time is determined to be 800 times, and the predicted health degree corresponding to 800 times is determined to be 85% according to the health degree prediction curve.

Step 250, based on the relationship between the predicted health and the required health, the future health detection period of the rechargeable battery is adjusted.

The required health degree is a preset battery health degree corresponding to a preset use number.

Schematically, the required health degree refers to the health degree of the rechargeable battery corresponding to the preset use times according to the factory setting conditions of the rechargeable battery. Such as: the factory setting of the rechargeable battery is that the battery health degree is 80% when the use times reach 800 times under the condition of 20 ℃.

Schematically, since there is a certain difference between the actual use condition of the rechargeable battery and the departure setting condition, there is a certain difference between the health degree prediction curve generated according to the actual use parameter at the current time and the standard health degree curve under the departure setting condition.

In some embodiments, the future health detection period refers to a subsequent health detection period starting with the current health detection period of the rechargeable battery.

In some embodiments, the interval of future health detection periods is adjusted based on the distance between the predicted health and the required health.

In one example, the predicted health degree corresponding to the preset usage frequency is 85% and the required health degree is 90%, and the specified interval frequency corresponding to the current health degree detection period is 50 times, and the specified interval frequency is adjusted to 30 times, namely, after the usage frequency is increased by 30 times from the current usage frequency, the next health degree detection period is the next health degree detection period.

In another example, the predicted health degree corresponding to the preset usage number is 85% and the required health degree is 80%, and the specified interval number corresponding to the current health degree detection period is 50, and the specified interval number is adjusted to 80, that is, after the usage number is increased by 80 from the current usage number, the next health degree detection period is the next health degree detection period.

In this embodiment, the further the distance between the required health degree and the predicted health degree is, the larger the adjustment range of the future health degree detection period is.

In summary, according to the method for predicting the health of the battery provided by the embodiment, after the health decay curves of the rechargeable battery corresponding to the rechargeable battery under different test temperature conditions are obtained, curve parameter fitting is performed on the current use times and the current health of the rechargeable battery according to the plurality of health decay curves in the current battery health detection period, so that the health prediction curve of the rechargeable battery in the current battery health detection period is obtained, the predicted health of the rechargeable battery is determined according to the health prediction curve, and finally, the future health detection period of the rechargeable battery is adjusted in real time according to the relation between the predicted health and the preset required health, so that the decay slowing strategy can be formulated in time later. That is, by means of the current use times and the current health degree of the rechargeable battery, the health degree prediction curve can be obtained in real time, the health degree detection period can be adjusted in advance according to different battery health degree states of the rechargeable battery, the related attenuation slowing strategy can be formulated conveniently later, the efficiency of slowing down the attenuation state of the battery of the rechargeable battery is improved, and the usable time of the rechargeable battery is prolonged effectively.

In some embodiments, the first health degree and the second health degree adapted to the current health degree are determined by means of interval analysis, and referring to fig. 3, a flowchart of a method for predicting the health degree of a battery according to an exemplary embodiment of the present application is shown, and as shown in fig. 3, the current method includes the following steps.

Step 310, obtaining health degree attenuation curves of the rechargeable battery corresponding to the plurality of test temperature conditions.

Schematically, different test temperature conditions are set through a battery aging experiment, charging and discharging processes are respectively carried out on the rechargeable battery under the different test temperature conditions according to the theoretical charge and discharge knowledge, and a curve of health degree attenuation of the rechargeable battery along with the increase of the use times of the rechargeable battery under the different test temperature conditions is obtained and is used as a health degree attenuation curve corresponding to the different test temperature conditions.

In this embodiment, by setting as many test temperature conditions as possible, it is ensured that the health degree decay curves corresponding to the test temperature conditions can be determined through the battery aging experiment.

Referring to fig. 4, a schematic diagram of a health degree attenuation curve under different test temperature conditions according to an exemplary embodiment of the present application is shown, and as shown in fig. 4, a schematic diagram 400 of a health degree attenuation curve 400 is currently shown, where the test temperature conditions are two test temperature conditions of 25 degrees celsius and 45 degrees celsius, and the health degree attenuation curve 410 at 25 degrees celsius and the health degree attenuation curve 420 at 45 degrees celsius are included.

In this embodiment, it is known that the battery health of the rechargeable battery decays faster with increasing number of uses as the test temperature condition is higher.

Step 320, in the current battery health detection period, the current usage number and the current health corresponding to the current rechargeable battery are obtained.

Optionally, the current battery health detection period is obtained by adjusting a relationship between a predicted health and a required health obtained according to a health prediction curve in a previous battery health detection period; or the current battery health degree detection period is a preset fixed detection period when the rechargeable battery is set in a factory, namely the current battery health degree detection period is not regulated in period because of a health degree prediction curve, and the method is not limited.

Optionally, the current battery health detection period refers to a corresponding designated time when the number of times of use of the rechargeable battery reaches a designated number of times (or reaches a designated battery health); or the current battery health detection period refers to a random time within a period of time after the number of times of use of the rechargeable battery reaches a specified number of times (or reaches a specified battery health).

In some embodiments, the current number of uses and the current health of the rechargeable battery at the current time is obtained by a battery electricity meter.

Schematically, as shown in fig. 4, a current health degree and actual usage parameter coordinate point 430 corresponding to the current usage number are marked in a health degree attenuation curve diagram 400 as (300, 92), where 300 represents the current usage number (Cycle), and 92 represents the current health degree (SOH).

Step 330, obtaining a plurality of detected healthiness corresponding to the current usage times and the corresponding health decay curves under the plurality of test temperature conditions.

The detection health degree is used for indicating the health degree corresponding to the battery health degree when the health degree attenuation curve reaches the current use times.

Schematically, after the current use times and the current health degrees of the rechargeable battery are obtained, determining the detected health degrees respectively corresponding to the plurality of health degree attenuation curves in the current use times according to the current use times. That is, detecting the health degree refers to obtaining the health degree value corresponding to the health degree decay curve according to the current use times.

Step 340, performing interval analysis on the plurality of detected healthsof the current healthsof, and determining a first healthsof and a second healthadaptive to the current healthsof.

Wherein the current health is within a health range between the first health and the second health.

Illustratively, after the plurality of detected health degrees are obtained, a section analysis is performed on the plurality of detected health degrees according to a numerical relationship between the current health degree and the plurality of detected health degrees, wherein the section analysis refers to determining two detected health degrees so as to generate a section range which is an adaptive current health degree range. The two detected healthdegrees are taken as a first healthdegree and a second healthdegree.

In some embodiments, two detected wellness levels closest to the current wellness level are selected from the plurality of detected wellness levels, and one detected wellness level is greater than the current wellness level and one detected wellness level is less than the current wellness level.

Illustratively, as shown in fig. 4, since the current number of uses is 300, the detected health 411 on the health decay curve 410 is determined to be 94 according to the current number of uses, and the detected health 421 on the health decay curve 420 is determined to be 87 according to the current number of uses. Among them, since the detected health degree 411 and the detected health degree 421 are the closest to the current health degree among the plurality of detected health degrees, the detected health degree 411 is taken as the first health degree (SOH 1) and the detected health degree 421 is taken as the second health degree (SOH 2).

And 350, analyzing the regional proportion of the current health degree based on the first health degree and the second health degree to obtain a health degree prediction curve.

Illustratively, the area ratio analysis refers to determining that the current health level is in a ratio relationship between the first health level and the second health level, such as: the current health is intermediate, i.e. halfway between, the first and second health; another example is: the current health is in one third of the second health between the first health and the second health.

In some embodiments, a reference prediction curve is obtained by performing a region scale analysis of the current health based on the first health and the second health.

Illustratively, the first health degree and the second health degree are subjected to regional proportion analysis on the current health degree to obtain a proportion analysis result, and then the relationship among the current health degree, the current use times and the proportion analysis result is obtained, so that a reference prediction curve is generated, and a generation formula of the reference prediction curve is referred to as first.

Equation one:

wherein SOH represents the current health degree, SOH1 represents the first health degree, SOH2 represents the second health degree, F (x) represents a first decay curve corresponding to the first health degree, g (x) represents a second decay curve corresponding to the second health degree, and F (x) represents a reference prediction curve.

Illustratively, as shown in FIG. 4, a health prediction curve 440 is currently obtained according to equation one.

In this embodiment, a curve relationship between the current health degree and the current usage frequency is obtained through the first formula, and the health degree prediction curve is a curve relationship between the usage time length of the rechargeable battery and the current health degree, so that parameter conversion is further required to be performed after the battery usage time length of the current rechargeable battery is obtained, thereby generating the health degree prediction curve. Namely, the battery use time of the rechargeable battery is obtained; obtaining an attenuation coefficient based on the battery use duration and the current use times of the rechargeable battery; and performing parameter conversion on the reference prediction curve based on the attenuation coefficient to obtain a health degree prediction curve.

In this embodiment, after the battery usage time length at the current time of the rechargeable battery is obtained, the attenuation coefficient is determined according to the battery usage time length and the current usage times, and please refer to formula two.

Formula II:

Wherein k represents the attenuation coefficient, T represents the battery use duration, and Cycle represents the current use times.

In this embodiment, after the attenuation coefficient is obtained, parameter conversion is performed on the reference prediction curve through the attenuation coefficient, so as to generate the health degree prediction curve.

Schematically, the current times of the rechargeable battery are different along with the difference of the current battery health degree detection period, so that the current health degree is different, and therefore, the generated health degree prediction curves are also different under the condition that the actual use parameters are different.

Schematically, as shown in fig. 5, a schematic diagram of generating a health degree prediction curve according to an exemplary embodiment of the present application is shown, and as shown in fig. 5, a health degree attenuation curve interface diagram 500 is currently displayed, where the health degree attenuation curve interface diagram includes a health degree attenuation curve 510 at 25 degrees celsius and a health degree attenuation curve 520 at 45 degrees celsius. In the current battery health detection period, the current usage frequency of the rechargeable battery is 800 times, the current health is 86%, so that the actual usage parameter coordinate point 530 is (800, 86), and the health prediction curve is 540 according to the formula one and the formula two. As can be seen from fig. 5, although the current health level is located between the first health level and the second health level, there is a portion of the health prediction curve that lies outside the health decay curve 510 and the health decay curve 520.

Therefore, in the case that the actual usage parameters of the rechargeable battery at the current time are different, the generated health detection curves are also different, and referring to fig. 6, a schematic diagram of different health prediction curves corresponding to the different actual usage parameters provided by an exemplary embodiment of the present application is shown, as shown in fig. 6, a health prediction curve interface diagram 600 is currently displayed, where the health prediction curve 610 is a health prediction curve generated by the rechargeable battery at (300, 94), and the health prediction curve 620 is a health prediction curve generated by the rechargeable battery at (800, 86). The health degree prediction curves under different use conditions are different due to different use habits of users.

Step 360, obtaining the preset number of times of use.

Illustratively, the preset number of uses is a number of uses preset according to a health degree prediction curve, wherein the preset number of uses is greater than the current number of uses.

And 370, acquiring the predicted health degree corresponding to the preset use times based on the health degree prediction curve.

Schematically, after obtaining the predicted health degree prediction curve corresponding to the preset use times and the current time, determining the predicted health degree corresponding to the preset use times according to the health degree prediction curve, for example: after the corresponding health degree prediction curve with the current use times of 300 times is obtained, the preset use times of 600 times are obtained, so that the corresponding battery health degree is 85% when the preset use times of 600 times are determined according to the health degree prediction curve.

Step 380, based on the relationship between the predicted health and the required health, the future health detection period of the rechargeable battery is adjusted.

In some embodiments, a required health profile is obtained; obtaining the required health degree based on the required health degree curve and the preset use times; acquiring a health degree deviation between the current health degree and the required health degree; and adjusting future health detection periods of the rechargeable battery based on the health deviation to obtain n future health detection periods, wherein n is a positive integer.

Illustratively, the required health curve refers to a standard health curve configured according to battery parameters of the rechargeable battery at factory setting, such as: the required health degree curve set by the rechargeable battery in factory setting is that the battery health degree is 80% when the use times reach 800 times under the condition that the temperature condition is 25 ℃.

In some embodiments, after obtaining the required health degree curve of the rechargeable battery, determining the required health degree corresponding to the preset number of uses according to the required health degree curve, for example: after the required health degree curve of the rechargeable battery is obtained, the corresponding required health degree is 88% when the preset use time is 600 times.

Illustratively, after the required health degree is obtained, a health degree deviation between the required health degree and the current health degree is determined, so that the interval of the future health degree detection period of the rechargeable battery is adjusted according to the health degree deviation.

In this embodiment, after the required health degree is obtained, it is determined that the health degree deviation between the required health degree and the current health degree is 88% -85% =3%, and therefore, the current health degree is lower than the required health degree by 3%, so that the interval of the future health degree detection period of the rechargeable battery is shortened from 50 times set in advance to 30 times.

In this embodiment, if the current health is higher than the required health, the interval of the future health detection period of the rechargeable battery will be enlarged, and if the current health is lower than the required health, the interval of the future health detection period of the rechargeable battery will be shortened. The magnitude of the expansion/contraction is positively correlated with the magnitude of the health deviation.

In step 390, the current health and the current number of uses are obtained in the ith future health detection period.

Wherein i is more than 0 and less than or equal to n, and i is an integer.

Illustratively, after the interval of the future health detection period is adjusted by the current health detection period, the i future health detection period is taken as the current health detection period in the i future health detection period after the use times reach the interval, and the current health and the current use times are determined.

Step 3100, obtaining a predicted health degree corresponding to the preset usage number in the jth future health degree detection period based on the current health degree and the current usage number.

Wherein i < j is less than or equal to n and j is an integer.

Schematically, in the above embodiment, curve parameter fitting is performed on the health degree attenuation curves corresponding to the different test temperature conditions according to the current health degree and the current use times, so as to generate the health degree prediction curve corresponding to the ith future health degree detection period.

After the health degree prediction curve is obtained, the predicted health degree corresponding to the preset use times is determined according to the health degree prediction curve by obtaining the preset use times. Notably, the predicted health is a predicted health determined from actual use parameters (current health and current number of uses) in the i-th future health detection period. In this embodiment, the predicted health belongs to the battery health in the jth future health detection period, wherein the jth future health detection period is located after the ith future health detection period.

In step 3110, the required health for the preset number of uses in the jth future health detection period is obtained based on the required health curve.

Illustratively, according to the required health degree curve, determining the required health degree corresponding to the preset use times in the jth future health degree detection period.

Step 3120, determining that the rechargeable battery is in a state of health decay during the j-th future health detection period in response to the health deviation between the predicted health and the required health reaching a preset health threshold during the j-th future health detection period.

The preset health degree threshold is a preset health degree threshold, and is used for determining whether the health degree deviation between the predicted health degree and the required health degree in j health degree detection periods reaches the health degree threshold or not, which indicates whether the rechargeable battery reaches a health degree attenuation state or not, and specifically please refer to a formula III.

And (3) a formula III: delta SOH < f (Cycle _pre)-g(Cycle_pre)

Wherein Delta SOH represents a preset health degree threshold, f (Cycle _pre) represents a required health degree corresponding to a jth future health degree detection period, and g (Cycle _pre) represents a predicted health degree corresponding to the jth future health degree detection period.

In step 3130, a degradation mitigation strategy for the rechargeable battery is determined based on the state of health degradation.

Wherein the decay slowing strategy is used for indicating to slow down the health decay speed of the rechargeable battery.

Illustratively, when the battery health of the rechargeable battery is determined to be in a health decay state in the jth future health detection period, a corresponding decay slowing strategy of the rechargeable battery is formulated in advance. That is, when it is determined that the battery health of the rechargeable battery is in the health decay state in the jth future health detection period, a decay mitigation strategy is performed on the rechargeable battery from the ith future health detection period.

In this embodiment, the attenuation slowing policy is to slow down the speed of the attenuation of the battery health degree as the usage frequency increases in the subsequent future health degree detection period.

In this embodiment, the voltage of the rechargeable battery is reduced as a damping strategy.

In this embodiment, after a plurality of detected healthdegrees are obtained, a manner of performing interval analysis on the plurality of detected healthdegrees is performed, so that a first healthdegree and a second healthdegree adapted to the current healthdegree are determined, and a healthdegree prediction curve corresponding to the current healthdegree is generated according to the first healthdegree and the second healthdegree, so that the generated healthdegree prediction curve accords with the actual use state of the rechargeable battery at the current moment, and the reality and accuracy of the healthdegree prediction curve are improved.

In this embodiment, the attenuation coefficient is determined by obtaining the battery usage time of the rechargeable battery, and then the reference prediction curve is subjected to parameter conversion by the attenuation coefficient, so that the health degree prediction curve is finally generated, the attenuation rule of the battery health degree of the current rechargeable battery can be displayed through the curve relationship between the battery usage time of the rechargeable battery and the battery health degree, and the intuitiveness of the health degree prediction curve is improved.

In this embodiment, by acquiring the preset number of uses and acquiring the predicted health degree corresponding to the preset number of uses according to the health degree prediction curve, the health degree attenuation state of the rechargeable battery can be predicted in advance.

In this embodiment, by predicting the deviation of the health degree between the health degree and the required health degree, the attenuation slowing policy of the rechargeable battery is formulated in advance, so that the attenuation slowing efficiency of the rechargeable battery can be improved, and the battery service life of the rechargeable battery can be prolonged.

Referring to fig. 7, a flowchart of a method for predicting the health of a battery according to an exemplary embodiment of the application is shown, and the method includes the following steps.

Step 71, obtaining health degree attenuation curves corresponding to the three test temperature conditions respectively.

In this embodiment, taking three test temperature conditions under a plurality of test temperature conditions as an example, the health degree attenuation curves corresponding to the three test temperature conditions are obtained through a battery aging experiment.

And step 72, performing formula fitting on the health degree attenuation curves corresponding to the three test temperature conditions respectively.

In this embodiment, three health decay curves are fitted by formulas, and the fitting results are stored in the first decay curve (cycle 1), the second decay curve (cycle 2), and the third decay curve (cycle 3) in the battery electricity meter.

Step 73, obtaining the current use times and the current health degree of the lithium ion battery in the current health degree detection period.

In this embodiment, the current state of health (SOH) and the current number of uses (Cycle) of the lithium ion battery are obtained using the battery electricity meter during the current state of health detection period.

And step 74, determining the detection health degrees respectively corresponding to the three health degree attenuation curves according to the current health degree and the current use times.

In this embodiment, according to the current usage times, the detected healthness corresponding to each of the three healthness attenuation curves at the current usage times is determined, which are respectively a first detected healthness (SOH 1) corresponding to the first healthness attenuation curve, a second detected healthness (SOH 2) corresponding to the second healthness attenuation curve, and a third detected healthness (SOH 3) corresponding to the third healthness attenuation curve. The health degree attenuation curve corresponding to the first detection health degree is a first attenuation curve, the health degree attenuation curve corresponding to the second detection health degree is a second attenuation curve, and the health degree attenuation curve corresponding to the third detection health degree is a third attenuation curve _.

Step 75, performing interval analysis on the current health degree according to the plurality of detected health degrees.

In this embodiment, the interval analysis is performed on the current health degree according to the three detected health degrees, and the first health degree and the second health degree adapted to the current health degree are determined.

In the following, a total of four cases are discussed.

(1) SOH1 < SOH2, steps 76 to 78 are performed.

(2) SOH2 < SOH3, steps 76 to 78 are performed.

(3) SOH1 < SOH, step 79 is performed.

(4) SOH 3> SOH, step 710 is performed.

Step 76, obtaining a reference prediction curve according to formula one.

For the above case (1), when the first health degree is SOH1 and the second health degree is SOH2, substituting the SOH1 and SOH2 and the first attenuation curve corresponding to the first detected health degree and the second attenuation curve corresponding to the second detected health degree according to the above formula one to obtain the reference prediction curve corresponding to the lithium ion battery at the current moment.

For the above case (2), when the first health degree is SOH2 and the second health degree is SOH3, substituting the second attenuation curve corresponding to the SOH2 and SOH3 and the second detection health degree and the third attenuation curve corresponding to the third detection health degree into the first equation to obtain the reference prediction curve corresponding to the lithium ion battery at the current moment.

It is noted that, since the first health degree and the second health degree corresponding to the case 1 and the case 2 are different, respectively, the reference prediction curves generated by the respective cases are also different.

Step 77, obtaining attenuation coefficients.

And (3) aiming at the condition (1), acquiring the battery use duration of the lithium ion battery in the current health detection period, and determining the attenuation coefficient k between the battery use duration and the current use times through the formula II.

And (3) aiming at the condition (2), acquiring the battery use duration of the lithium ion battery in the current health detection period, and determining the attenuation coefficient k between the battery use duration and the current use times through the formula II.

Step 78, obtaining a health prediction curve.

For the above case (1), the reference prediction curve is subjected to parameter conversion according to the attenuation coefficient, and a health degree prediction curve is generated.

And (2) performing parameter conversion on the reference prediction curve according to the attenuation coefficient to generate a health degree prediction curve.

Step 79, taking the first decay curve as a health prediction curve.

Aiming at the condition (3), the method shows that the current lithium ion battery has good attenuation state, and no subsequent attenuation state early warning is needed, so that the first attenuation curve is directly used as a health degree prediction curve.

And step 710, taking the second attenuation curve as a health degree prediction curve.

Aiming at the condition (4), the current lithium ion battery needs to perform battery attenuation state early warning, so the second attenuation curve is used as a health degree prediction curve.

In step 711, a preset decay time point is obtained.

In this embodiment, a preset number of times of use is determined according to the health degree prediction curve, where the preset number of times of use is greater than the current number of times of use. And converting the preset use times into preset attenuation time points according to the attenuation coefficients. Wherein the predicted decay time belongs to the number of uses in a future health detection period.

Step 712, obtaining the predicted health degree corresponding to the preset decay time point according to the health degree prediction curve.

In this embodiment, according to the health degree prediction curve, the predicted health degree corresponding to the preset decay time point is determined.

In step 713, the predicted health is determined according to the preset decay threshold.

Schematically, after the predicted health degree is obtained, a required health degree curve of the lithium ion battery is obtained according to factory settings of the lithium ion battery, and the required health degree corresponding to the predicted decay time point is obtained according to the required health degree curve.

And judging whether the health degree deviation is larger than a preset health degree threshold value according to the health degree deviation between the required health degree and the predicted health degree, executing step 714 if the health degree deviation is larger than the preset health degree threshold value, adjusting the interval of the health degree detection period if the health degree deviation is not larger than the preset health degree threshold value, and repeating the steps in the next future health degree detection period to judge the health degree deviation.

And step 714, reporting the state of health attenuation of the lithium ion battery, and formulating an attenuation slowing strategy.

In this embodiment, when the deviation of the health degree between the required health degree and the predicted health degree is greater than the preset health degree threshold, it is indicated that the lithium ion battery is in a health degree attenuation state in a corresponding future health detection period, the health degree attenuation state and the corresponding future health degree detection period are reported, and a attenuation slowing strategy for reducing the voltage of the lithium ion battery is executed in advance.

In the related technical scheme, the attenuation cyclic voltage reduction strategy of the lithium ion battery is a strategy for executing delay attenuation according to the current attenuation state of the lithium ion battery, and when the delay attenuation strategy is started to be executed, the lithium ion battery has obvious attenuation conditions. If the decay curve of the service life of the lithium ion battery can be predicted in real time according to the current state of the lithium ion battery, a strategy for delaying the decay can be executed in advance for the battery with serious decay. The cycle life of the lithium ion battery can be effectively prolonged. In the current terminal equipment, the function of predicting the service life of the lithium ion battery is not realized. According to the prediction mode of the scheme, self-adaptive adjustment can be performed according to the current state of the lithium ion battery, the accuracy is high, the prediction mode can gradually approach to the real attenuation curve of the lithium ion battery, and the calculated amount is small. And the life prediction of the lithium ion battery is realized in the terminal equipment according to the current state of the lithium ion battery, the attenuation trend curve of the lithium ion battery is obtained, and a charging strategy for slowing down the life attenuation can be formulated in advance according to the attenuation trend.

Fig. 8 is a view showing a device for predicting the health of a battery according to an exemplary embodiment of the present application, as shown in fig. 8, the device including:

The obtaining module 810 is configured to obtain health degree attenuation curves of the rechargeable battery under a plurality of test temperature conditions, where the health degree attenuation curves are used to indicate attenuation change rules of health degree of the rechargeable battery along with the number of times of use under the test temperature conditions;

the obtaining module 810 is further configured to obtain, in a current battery health detection period, a current usage number and a current health of the rechargeable battery, where the current usage number is used to indicate a battery cycle number corresponding to when a discharge amount of the rechargeable battery reaches a preset discharge amount, and the current health is used to indicate a current power capacity of the rechargeable battery;

The fitting module 820 is configured to perform curve parameter fitting on the current usage times and the current health degree based on the health degree attenuation curves corresponding to the plurality of test temperature conditions, so as to obtain a health degree prediction curve;

The analysis module 830 is configured to perform predictive analysis on the future health of the rechargeable battery based on the health prediction curve, and determine a predicted health corresponding to the rechargeable battery when the number of times of use reaches a preset number;

The adjustment module 840 is configured to adjust a future health detection period of the rechargeable battery based on a relationship between the predicted health and a required health, where the required health is a preset health of the battery corresponding to the preset number of uses.

In some embodiments, as shown in fig. 9, the fitting module 820 includes:

An obtaining unit 821, configured to obtain a plurality of detected healthiness degrees corresponding to the current usage times of the corresponding healthiness degree attenuation curves under the plurality of test temperature conditions, where the detected healthiness degrees are used to indicate the battery healthiness degrees corresponding to the current usage times of the corresponding healthiness degree attenuation curves;

An analysis unit 822, configured to perform interval analysis on the plurality of detected healthiess based on the current healthiess, determine a first healthiess and a second healthiess that are adapted to the current healthiess, and the current healthiess is within a healthier range between the first healthiess and the second healthiess;

The analysis unit 822 is further configured to perform a region proportion analysis on the current health degree based on the first health degree and the second health degree, so as to obtain the health degree prediction curve.

In some embodiments, the analyzing unit 822 is further configured to perform a region scale analysis on the current health degree based on the first health degree and the second health degree to obtain a reference prediction curve; acquiring the battery use time of the rechargeable battery; obtaining an attenuation coefficient based on the battery use duration of the rechargeable battery and the current use times; and carrying out parameter conversion on the reference prediction curve based on the attenuation coefficient to obtain the health degree prediction curve.

In some embodiments, the analysis module 830 is further configured to obtain the preset number of uses; and acquiring the predicted health degree corresponding to the preset use times based on the health degree prediction curve.

In some embodiments, the analysis module 830 is further configured to obtain a required health curve; obtaining the required health degree based on the required health degree curve and the preset use times; acquiring a health degree deviation between the predicted health degree and the required health degree; and adjusting future health detection periods of the rechargeable battery based on the health deviation to obtain n future health detection periods, wherein n is a positive integer.

In some embodiments, the adjusting module 840 is further configured to obtain the current health degree and the current usage number in an i-th future health degree detection period, where i is greater than 0 and less than or equal to n and i is an integer; acquiring predicted health degrees corresponding to preset use times in a j-th future health degree detection period based on the current health degrees and the current use times, wherein i is more than or equal to j and less than or equal to n, and j is an integer; obtaining the required health degree of preset use times in a j-th future health degree detection period based on the required health degree curve; determining that the rechargeable battery is in a health decay state during a jth future health detection period in response to a health deviation between the predicted health and the required health reaching a preset health threshold during the jth future health detection period; a decay mitigation strategy for the rechargeable battery is determined based on the state of health decay, the decay mitigation strategy being used to indicate a mitigation of a rate of health decay for the rechargeable battery.

In summary, according to the device for predicting the health of the battery provided by the embodiment, after the health decay curves of the rechargeable battery corresponding to the rechargeable battery under different test temperature conditions are obtained, curve parameter fitting is performed on the current use times and the current health of the rechargeable battery according to the plurality of health decay curves in the current battery health detection period, so that the health prediction curve of the rechargeable battery in the current battery health detection period is obtained, the predicted health of the rechargeable battery is determined according to the health prediction curve, and finally, the future health detection period of the rechargeable battery is adjusted in real time according to the relation between the predicted health and the preset required health, so that the decay slowing strategy can be formulated in time later. That is, by means of the current use times and the current health degree of the rechargeable battery, the health degree prediction curve can be obtained in real time, the health degree detection period can be adjusted in advance according to different battery health degree states of the rechargeable battery, the related attenuation slowing strategy can be formulated conveniently later, the efficiency of slowing down the attenuation state of the battery of the rechargeable battery is improved, and the usable time of the rechargeable battery is prolonged effectively.

It should be noted that: the battery health prediction apparatus provided in the above embodiment is only exemplified by the above-mentioned division of each functional module, and in practical application, the above-mentioned functional allocation may be performed by different functional modules according to needs, i.e., the internal structure of the device is divided into different functional modules, so as to perform all or part of the functions described above. In addition, the device for predicting the battery health degree provided in the above embodiment belongs to the same concept as the method embodiment for predicting the battery health degree, and detailed implementation processes of the device are shown in the method embodiment, which is not repeated here.

Fig. 10 is a schematic diagram showing the structure of a computer device according to an exemplary embodiment of the present application.

Specifically, the present invention relates to a method for manufacturing a semiconductor device. The computer apparatus 1000 includes a central processing unit (Central Processing Unit, CPU) 1001, a system Memory 1004 including a random access Memory (Random Access Memory, RAM) 1002 and a Read Only Memory (ROM) 1003, and a system bus 1005 connecting the system Memory 1004 and the central processing unit 1001. The computer device 1000 also includes a mass storage device 1006 for storing an operating system 1013, application programs 1014, and other program modules 1015.

The mass storage device 1006 is connected to the central processing unit 1001 through a mass storage controller (not shown) connected to the system bus 1005. The mass storage device 1006 and its associated computer-readable media provide non-volatile storage for the computer device 1000. That is, the mass storage device 1006 may include a computer readable medium (not shown) such as a hard disk or compact disc read only memory (Compact Disc Read Only Memory, CD-ROM) drive.

Computer readable media may include computer storage media and communication media without loss of generality. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), electrically erasable programmable read-only memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY, EEPROM), flash memory or other solid state memory technology, CD-ROM, digital versatile disks (DIGITAL VERSATILE DISC, DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will recognize that computer storage media are not limited to the ones described above. The system memory 1004 and mass storage device 1006 described above may be referred to collectively as memory.

According to various embodiments of the application, the computer device 1000 may also operate by a remote computer connected to the network through a network, such as the Internet. I.e., the computer device 1000 may be connected to the network 1012 through a network interface unit 1011 connected to the system bus 1005, or other types of networks or remote computer systems (not shown) may be connected using the network interface unit 1011.

The memory also includes one or more programs, one or more programs stored in the memory and configured to be executed by the CPU.

The embodiment of the application also provides a computer device, which comprises a processor and a memory, wherein at least one instruction, at least one section of program, code set or instruction set is stored in the memory, and the at least one instruction, the at least one section of program, the code set or instruction set is loaded and executed by the processor to realize the training method of the image recognition model provided by each method embodiment.

Embodiments of the present application further provide a computer readable storage medium having at least one instruction, at least one program, a code set, or an instruction set stored thereon, where the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the training method of the image recognition model provided by the above method embodiments.

Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the training method of the image recognition model according to any one of the above embodiments.

Alternatively, the computer-readable storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), solid state disk (SSD, solid STATE DRIVES), or optical disk, etc. The random access memory may include resistive random access memory (ReRAM, RESISTANCE RANDOM ACCESS MEMORY) and dynamic random access memory (DRAM, dynamic Random Access Memory), among others. The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but rather, the application is to be construed as limited to the appended claims.

Claims

1. A method for predicting battery health, the method comprising:

2. The method according to claim 1, wherein the performing curve parameter fitting on the current usage number and the current health degree based on the health degree attenuation curves corresponding to the plurality of test temperature conditions to obtain a health degree prediction curve includes:

Acquiring a plurality of detection healthiness corresponding to the current use times of the corresponding health decay curves under the plurality of test temperature conditions, wherein the detection healthiness is used for indicating the battery healthiness corresponding to the current use times of the corresponding health decay curves;

Performing interval analysis on the plurality of detection healthsof the current healthdegree, and determining a first healthdegree and a second healthdegree which are matched with the current healthdegree, wherein the current healthdegree is in a healthdegree range between the first healthdegree and the second healthdegree;

And carrying out regional proportion analysis on the current health degree based on the first health degree and the second health degree to obtain the health degree prediction curve.

3. The method of claim 2, wherein performing a regional scale analysis of the current health based on the first health and the second health to obtain the health prediction curve comprises:

Performing regional proportion analysis on the current health degree based on the first health degree and the second health degree to obtain a reference prediction curve;

acquiring the battery use time of the rechargeable battery;

Obtaining an attenuation coefficient based on the battery use duration of the rechargeable battery and the current use times;

and carrying out parameter conversion on the reference prediction curve based on the attenuation coefficient to obtain the health degree prediction curve.

4. A method according to any one of claims 1 to 3, wherein said predicting the future health of the rechargeable battery based on the health prediction curve, determining the predicted health of the rechargeable battery when a predetermined number of uses is reached, comprises:

Acquiring the preset use times;

and acquiring the predicted health degree corresponding to the preset use times based on the health degree prediction curve.

5. The method of claim 4, wherein adjusting the future health detection period of the rechargeable battery based on the relationship between the predicted health and the required health comprises:

Acquiring a required health degree curve;

obtaining the required health degree based on the required health degree curve and the preset use times;

Acquiring a health degree deviation between the predicted health degree and the required health degree;

And adjusting future health detection periods of the rechargeable battery based on the health deviation to obtain n future health detection periods, wherein n is a positive integer.

6. The method of claim 5, wherein adjusting future health detection cycles of the rechargeable battery based on the health deviation, after obtaining n future health detection cycles, further comprises:

In the ith future health detection period, acquiring the current health and the current use times, wherein i is more than 0 and less than or equal to n, and i is an integer;

Acquiring predicted health degrees corresponding to preset use times in a j-th future health degree detection period based on the current health degrees and the current use times, wherein i is more than or equal to j and less than or equal to n, and j is an integer;

obtaining the required health degree of preset use times in a j-th future health degree detection period based on the required health degree curve;

Determining that the rechargeable battery is in a health decay state during a jth future health detection period in response to a health deviation between the predicted health and the required health reaching a preset health threshold during the jth future health detection period;

A decay mitigation strategy for the rechargeable battery is determined based on the state of health decay, the decay mitigation strategy being used to indicate a mitigation of a rate of health decay for the rechargeable battery.

7. A device for predicting battery health, the device comprising:

8. A computer device comprising a processor and a memory, wherein the memory has stored therein at least one program that is loaded and executed by the processor to implement the method of predicting battery health according to any one of claims 1 to 6.

9. A computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is loaded and executed by a processor to implement the method for predicting the health of a battery according to any one of claims 1 to 6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method of predicting battery health according to any one of claims 1 to 6.