CN116299006A

CN116299006A - Method, device, equipment and storage medium for predicting health condition of battery pack

Info

Publication number: CN116299006A
Application number: CN202310084903.1A
Authority: CN
Inventors: 郭东旭; 韩雪冰; 卢兰光; 欧阳明高
Original assignee: Tsinghua University
Current assignee: Tsinghua University
Priority date: 2023-01-18
Filing date: 2023-01-18
Publication date: 2023-06-23

Abstract

The application relates to a method, a device, equipment and a storage medium for predicting the health condition of a battery pack. The method comprises the following steps: acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and each sampling current of the battery pack in the process of charging the battery pack in each target historical time period; determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period and the first charge state and the second charge state corresponding to each battery cell; training the initial prediction model according to battery parameters and actual health conditions corresponding to each target historical time period to obtain a target prediction model, and determining the health conditions of the battery pack to be predicted in the charging time period according to the battery parameters and the target prediction model corresponding to the battery pack to be predicted in the charging time period. By adopting the method, the accuracy of the health condition prediction of the battery pack can be improved.

Description

Method, device, equipment and storage medium for predicting health condition of battery pack

Technical Field

The present disclosure relates to the field of new energy technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting a health status of a battery pack.

Background

With the rapid development of new energy technology, the power battery pack has the advantages of higher voltage, higher energy density, good cycle performance and the like, and is widely applied to new energy vehicles. The long-term use of the new energy vehicle also causes the battery pack to age, so that the user experience is worse and worse, even the new energy vehicle is failed, and the current Health condition (State of Health, SOH) of the power battery pack is necessary to be known in the aspects of recovery, echelon utilization and the like of the power battery pack.

In the conventional technology, according to the information such as the current, the open-circuit voltage, the temperature and the like of the battery pack in each charging process of the battery pack, the corresponding total charging capacity of the battery pack from the first charging to the current charging completion is determined, so that the total charging capacity can be obtained by accumulating the charging capacity of each charging. Thereafter, a target SOH value may be determined based on the total charge capacity and a predetermined capacity change threshold. When some of the information such as the current, the open circuit voltage and the temperature of the battery pack is missing, calculation errors are caused, and the determined target SOH value is inaccurate.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, apparatus, device, and storage medium for predicting the health of a battery pack that can improve the accuracy of predicting the health of a power battery.

In a first aspect, the present application provides a method for predicting a health condition of a battery pack. The method comprises the following steps:

acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and sampling currents obtained by sampling currents of the battery pack in the process of charging the battery pack in each target historical time period;

determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period, the first charge state and the second charge state corresponding to each battery cell;

training an initial prediction model according to battery parameters corresponding to each target historical time period and the actual health condition to obtain a target prediction model;

and determining the health condition of the battery pack to be predicted in the charging time period according to the battery parameters corresponding to the battery pack to be predicted in the charging time period and the target prediction model.

In one embodiment, the determining the actual health condition of the battery pack in each target historical period according to each sampling current corresponding to each target historical period, the first state of charge corresponding to each battery cell, and the second state of charge includes:

determining the accumulated electric quantity of the battery pack corresponding to each target historical time period according to each sampling current corresponding to each target historical time period;

determining the state of charge variation corresponding to each battery cell according to the first state of charge and the second state of charge corresponding to each battery cell;

and determining the actual health condition of the battery pack in each target historical time period according to the accumulated electric quantity of the battery pack in each target historical time period and the state of charge variation of each battery cell.

In one embodiment, determining the actual health condition of the battery pack in each target historical time period according to the accumulated electric quantity of the battery pack in each target historical time period and the state of charge variation of each battery cell includes:

determining the monomer capacity of each battery monomer in each target historical time period according to the state of charge variation corresponding to each battery monomer and the accumulated electric quantity corresponding to each target historical time period;

And determining the actual health condition of the battery pack in each target historical time period according to the monomer capacity of each battery monomer, the second charge state and the rated capacity of the battery pack in each target historical time period.

In one embodiment, the determining the cell capacity of each of the battery cells according to the state of charge variation corresponding to each of the battery cells and the accumulated electric quantity corresponding to each of the target historical time periods includes:

determining a first ratio between the accumulated electric quantity corresponding to each target historical time period and the state of charge variation corresponding to each battery cell;

and determining the monomer capacity of each battery monomer according to the first ratio corresponding to each battery monomer in each target historical time period.

In one embodiment, the determining the actual health of the battery pack in each of the target historical periods according to the cell capacity of each of the battery cells, the second state of charge, and the rated capacity of the battery pack in each of the target historical periods includes:

determining the battery pack capacity of the battery pack in each target historical time period according to the monomer capacity of each battery monomer and the second charge state in each target historical time period;

Determining a second ratio of a battery pack capacity of the battery pack to a rated capacity of the battery pack for each of the target historical periods;

and determining the actual health condition of the battery pack in each target historical time period according to the second ratio corresponding to each target historical time period.

In one embodiment, the method further comprises:

acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and a battery pack temperature in the process of charging the battery pack in each historical time period;

determining a second difference value between the second state of charge and the first state of charge of each battery cell corresponding to each historical time period;

determining a target difference value according to the minimum second difference value corresponding to each battery cell in each historical time period;

and if the target difference value is greater than the preset state of charge difference value threshold value and the temperature of the battery pack is within the preset temperature range, taking the historical time period corresponding to the minimum second difference value as the target historical time period.

In one embodiment, the battery parameters include the following:

the driving mileage of the electric vehicle corresponding to the battery pack before the battery pack is charged;

Maximum monomer voltage, minimum monomer voltage, maximum monomer temperature and minimum monomer temperature at the beginning of charging corresponding to each target historical time period;

maximum monomer voltage, minimum monomer voltage, maximum monomer temperature and minimum monomer temperature at the end of charging corresponding to each target historical time period;

maximum monomer voltage, minimum monomer voltage, maximum monomer temperature, minimum monomer temperature corresponding to each of the target historical time periods.

In a second aspect, the present application also provides a device for predicting a health condition of a battery pack. The device comprises:

the first acquisition module is used for acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and sampling currents obtained by sampling currents of the battery pack in the process of charging the battery pack in each target historical time period;

the first determining module is used for determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period, the first charge state and the second charge state corresponding to each battery cell;

the training module is used for training the initial prediction model according to the battery parameters corresponding to each target historical time period and the actual health condition to obtain a target prediction model;

And the second determining module is used for determining the health condition of the battery pack to be predicted in the charging time period according to the battery parameters corresponding to the battery pack to be predicted in the charging time period and the target prediction model.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

According to the method, the device, the equipment and the storage medium for predicting the health condition of the battery pack, in the process of charging the battery pack in each target historical time period, the first charge state of each battery cell in the battery pack at the beginning of charging, the second charge state of each battery cell at the end of charging and each sampling current obtained by sampling the current of the battery pack are obtained, the actual health condition of the battery pack in each target historical time period is determined according to each sampling current corresponding to each target historical time period, the first charge state and the second charge state corresponding to each battery cell, and then the initial prediction model is trained according to the battery parameters corresponding to each target historical time period and the actual health condition to obtain the target prediction model, and finally the health condition of the battery pack to be predicted in the charging time period is determined according to the battery parameters corresponding to the battery pack to be predicted and the target prediction model. In the conventional technology, a target SOH value is determined according to a total charge capacity and a predetermined capacity change threshold, and when some information in the information such as a current, an open circuit voltage, and a temperature of the battery pack is missing, a calculation error is caused, so that the determined target SOH value is inaccurate. In the method, the actual SOH value of the target historical time period is calculated, the target prediction model is trained through the actual SOH value and the battery parameter, and the SOH value error of the battery pack is predicted through the target prediction model because the actual SOH value error of the calculated target historical time period is smaller, and the prediction accuracy of the target prediction model obtained through training according to the actual SOH value and the battery parameter is higher, so that the SOH value error of the battery pack is smaller, and the accuracy of SOH value prediction of the battery pack is improved.

Drawings

FIG. 1 is an internal block diagram of a computer device provided in an embodiment of the present application;

fig. 2 is a flow chart of a method for predicting a health condition of a battery pack according to an embodiment of the present disclosure;

FIG. 3 is a graph of a fitting effect of a model training result provided in an embodiment of the present application;

fig. 4 is a flowchart of a method for predicting a health condition of a battery pack in a charging period according to an embodiment of the present disclosure;

fig. 5 is a flow chart of a method for determining an actual health status of a battery pack according to an embodiment of the present disclosure;

FIG. 6 is a second flowchart of a method for determining an actual health status of a battery pack according to an embodiment of the present disclosure;

fig. 7 is a flow chart of a method for determining a cell capacity of a battery cell according to an embodiment of the present disclosure;

FIG. 8 is a third flow chart of a method for determining an actual health status of a battery pack according to an embodiment of the present disclosure;

FIG. 9 is a flowchart of a method for determining a target historical time period according to an embodiment of the present disclosure;

fig. 10 is a block diagram of a battery pack health prediction apparatus according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The embodiment provided by the application can be applied to the computer device shown in fig. 1, and referring to fig. 1, fig. 1 is an internal structure diagram of the computer device provided in the embodiment of the application. The computer device may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a resource scaling method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, as shown in fig. 2, fig. 2 is a flow chart of a method for predicting the health condition of a battery pack according to an embodiment of the present application, and the method is applied to the computer device in fig. 1 for illustration, and includes the following steps:

s201, acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and sampling currents obtained by sampling currents of the battery pack in the process of charging the battery pack in each target historical time period.

The state of charge (SOC) is a ratio of a remaining capacity of a battery pack after the battery pack is used for a period of time or is left unused for a long period of time to a capacity of a full charge state of the battery pack, the battery pack is composed of battery cells, and each battery cell corresponds to a first state of charge and a second state of charge.

In the process of charging the battery pack in each historical time period, a first cell voltage of each battery cell in the battery pack at the beginning of charging, a second cell voltage at the end of charging and each sampling current obtained by sampling the current of the battery pack are stored on the computer device; and after determining the target historical time period, acquiring a first single voltage of each battery cell in the battery pack at the beginning of charging, a second single voltage at the end of charging and each sampling current obtained by sampling the current of the battery pack in the process of charging the battery pack in each target historical time period. The cell voltage values are approximated to open circuit voltage values (Open circuit voltage, OCV), each type of battery pack is provided with an OCV-SOC table, the table records the charge states of the battery packs corresponding to the open circuit voltage values of the battery packs, and the charge states corresponding to the first cell voltage value are taken as a first charge state and the charge states corresponding to the second cell voltage value are taken as a second charge state according to the OCV-SOC table corresponding to the battery packs.

S202, determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period and the first charge state and the second charge state corresponding to each battery cell.

According to the sampling currents corresponding to each target historical time period, the first charge state and the second charge state corresponding to each battery cell, the cell capacity of each battery cell and the battery pack capacity of the battery pack are obtained through calculation, and then the SOH value of the battery pack in each target historical time period is obtained according to the cell capacity of each battery cell and the battery pack capacity, and reflects the actual health condition of the battery pack.

And S203, training the initial prediction model according to the battery parameters and the actual health conditions corresponding to each target historical time period to obtain a target prediction model.

The initial prediction model is a machine learning model or an artificial intelligence algorithm model, and for example, a random forest (random forest), gradient descent (gradient regression), support Vector Regression (SVR), CNN, RNN, and the like may be selected as the initial prediction model.

In an exemplary embodiment, the battery parameter corresponding to each target historical time period is input as a characteristic value into an initial prediction model, the model parameter is continuously adjusted according to the mean square error between the output value of the initial prediction model corresponding to each target historical time period and the actual health condition value, and when the mean square error between the model output value and the actual health condition value is minimum, the model corresponding to the minimum mean square error is taken as the target prediction model. Fig. 3 is a graph of a fitting effect of a model training result provided in an embodiment of the present application.

S204, determining the health condition of the battery pack to be predicted in the charging time period according to the battery parameters and the target prediction model corresponding to the battery pack to be predicted in the charging time period.

In connection with the above description, after determining the target prediction model, if the health condition of the battery pack in a certain charging period needs to be predicted, the battery parameters corresponding to the charging period of the battery pack to be predicted are input into the target prediction model, and the output value of the target prediction model is the health condition of the battery pack to be predicted in the charging period, and fig. 4 is a flow chart of a method for predicting the health condition of the battery pack in the charging period provided by the embodiment of the present application. As shown in fig. 4, first, a target historical time period is determined from each historical charging time period of a charging packet, an actual SOH value of the battery packet in each target historical time period is determined according to each sampling current corresponding to each target historical time period, a first state of charge corresponding to each battery cell and a second state of charge corresponding to each battery cell, then, according to battery parameters corresponding to each target historical time period and the actual SOH value, an initial prediction model is trained to obtain a target prediction model, and finally, according to battery parameters corresponding to the charging time period of the battery packet to be predicted and the target prediction model, the SOH value of the battery packet to be predicted in the charging time period is determined.

In the method for predicting the health condition of the battery pack, the first charge state of each battery cell in the battery pack at the beginning of charging, the second charge state at the end of charging and each sampling current obtained by sampling the current of the battery pack are obtained in the process of charging the battery pack in each target historical time period; determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period and the first charge state and the second charge state corresponding to each battery cell; training the initial prediction model according to battery parameters and actual health conditions corresponding to each target historical time period to obtain a target prediction model; and determining the health condition of the battery pack to be predicted in the charging time period according to the battery parameters and the target prediction model corresponding to the battery pack to be predicted in the charging time period. In the conventional technology, a target SOH value is determined according to a total charge capacity and a predetermined capacity change threshold, and when some information in the information such as a current, an open circuit voltage, and a temperature of the battery pack is missing, a calculation error is caused, so that the determined target SOH value is inaccurate. In the method, an actual SOH value of a target historical time period is calculated, and a target prediction model is trained through the actual SOH value and battery parameters. Because the calculated actual SOH value error of the target historical time period is smaller, and further the prediction accuracy of the target prediction model obtained by training according to the actual SOH value and the battery parameters is higher, the SOH value error of the battery pack predicted by the target prediction model is smaller, and the SOH value prediction accuracy of the battery pack is improved.

Fig. 5 is a schematic flow chart of a method for determining an actual health condition of a battery pack according to an embodiment of the present application, which relates to how to determine an actual health condition of a battery pack in each target historical period according to each sampling current corresponding to each target historical period, and a first state of charge and a second state of charge corresponding to each battery cell, where, based on the embodiment, as shown in fig. 3, the step S202 includes:

s501, determining the accumulated electric quantity of the battery pack corresponding to each target historical time period according to each sampling current corresponding to each target historical time period.

The sampling current is the current of the battery pack corresponding to each sampling time in the target historical time period, and the accumulated electric quantity is the accumulated charging electric quantity of the battery pack from the beginning of charging to the end of charging in each target historical time period.

For example, the start time of the target history period is set to t ₀ The end time of the target history period is set to T, and the sampling current of the target history period is set to I _t If the accumulated electric quantity of the battery pack corresponding to the target historical time period is set to be delta Q, the delta Q can be calculated by an ampere-hour integration method, and the formula is as follows:

S502, determining the state of charge variation corresponding to each battery cell according to the first state of charge and the second state of charge corresponding to each battery cell.

Illustratively, the first state of charge corresponding to cell i in the battery pack for the target historical period T1 is recorded as

The second state of charge is recorded as +.>

The state of charge change Δsoc corresponding to each battery cell i ⁱ Can be expressed by the following relation:

s503, determining the actual health condition of the battery pack in each target historical time period according to the accumulated electric quantity corresponding to each target historical time period and the state of charge variation corresponding to each battery cell.

The above embodiments are described by taking the target historical time period T1 as an example, and according to the accumulated electric quantity Δq of the battery pack corresponding to the target historical time period T1 and the state of charge variation Δsoc of each battery cell ⁱ The actual health of the battery pack during the target historical period T1 is determined.

In the embodiment of the application, the accumulated electric quantity of the battery pack corresponding to each target historical time period is determined according to each sampling current corresponding to each target historical time period, the change amount of the electric charge state corresponding to each battery cell is determined according to the first electric charge state and the second electric charge state corresponding to each battery cell, and the actual health condition of the battery pack in each target historical time period is determined according to the accumulated electric quantity of the battery pack corresponding to each target historical time period and the change amount of the electric charge state corresponding to each battery cell, so that preconditions are provided for determining a target prediction model.

Fig. 6 is a second flowchart of a method for determining an actual health condition of a battery pack according to an embodiment of the present application, where the embodiment relates to how to determine, according to an accumulated electric quantity of the battery pack corresponding to each target historical time period and a state of charge change amount of each battery cell, a possible implementation of the actual health condition of the battery pack in each target historical time period, and on the basis of the foregoing embodiment, as shown in fig. 6, the step S503 includes:

s601, determining the monomer capacity of each battery monomer in each target historical time period according to the state of charge variation corresponding to each battery monomer and the accumulated electric quantity corresponding to each target historical time period.

The single capacity is the battery capacity of each battery single in the battery pack.

ExampleThe battery capacity of each battery cell in each target historical time period is determined according to the state of charge variation corresponding to each battery cell and the accumulated electric quantity corresponding to each target historical time period, and the target historical time period T1 is taken as an example, and the battery capacity is determined according to the state of charge variation delta SOC corresponding to the battery cell i ⁱ And determining the monomer capacity of each battery monomer i in the target historical time period T1 together with the accumulated electric quantity delta Q of the battery pack.

S602, determining the actual health condition of the battery pack in each target historical time period according to the monomer capacity, the second charge state and the rated capacity of the battery pack of each battery monomer in each target historical time period.

In this embodiment, it should be noted that, first, the battery pack capacity of the battery pack needs to be determined according to the monomer capacity and the second charge state of each battery monomer in each target historical period, and then, the actual health condition of the battery pack in each target historical period needs to be determined according to the battery pack capacity and the rated capacity of the battery pack in each target historical period.

In this embodiment of the present application, the monomer capacity of each battery monomer in each target historical period is determined according to the state of charge variation corresponding to each battery monomer and the accumulated electric quantity corresponding to each target historical period, and the actual health condition of the battery pack in each target historical period is determined according to the monomer capacity of each battery monomer in each target historical period, the second state of charge and the rated capacity of the battery pack. The actual health condition of the battery pack is determined by the capacity of the battery cells.

Fig. 7 is a flow chart of a method for determining a single-cell capacity of a battery cell according to an embodiment of the present application, where the embodiment relates to a possible implementation manner of determining a single-cell capacity of each battery cell according to a state-of-charge variation corresponding to each battery cell and an accumulated electric quantity corresponding to each target historical time period, and on the basis of the foregoing embodiment, as shown in fig. 7, the foregoing S601 includes:

S701, determining a first ratio between the accumulated electric quantity corresponding to each target historical time period and the state of charge change quantity corresponding to each battery cell.

To target toDescribing a historical time period T1 as an example, determining a first ratio Q between the accumulated electric quantity delta Q corresponding to the target historical time period T1 and the state of charge variation corresponding to each battery cell _i1 The formula is as follows:

s702, determining the monomer capacity of each battery monomer according to the first ratio corresponding to each battery monomer in each target historical time period.

For example, let the cell capacity corresponding to each battery cell i in the target history period T1 be Q _i Q can be as follows _i1 The corresponding cell capacity of each battery cell i in the target historical time period T1 is Q _i 。

Alternatively, q may also be _i1 Multiplying the product of the first preset coefficient as Q _i The present embodiment is not limited herein.

In the embodiment of the application, the first ratio between the accumulated electric quantity corresponding to each target historical time period and the state of charge variation corresponding to each battery cell is determined, and the cell capacity of each battery cell is determined according to the first ratio corresponding to each battery cell in each target historical time period, so that preconditions are provided for determining the health condition of the battery pack.

Fig. 8 is a third flowchart of a method for determining an actual health condition of a battery pack according to an embodiment of the present application, where the embodiment relates to how to determine, according to a cell capacity of each cell, a second state of charge, and a rated capacity of the battery pack in each target historical period, an actual health condition of the battery pack in each target historical period, and on the basis of the embodiment, as shown in fig. 8, the step S602 includes:

s801, determining the battery pack capacity of the battery pack in each target historical time period according to the monomer capacity and the second charge state of each battery monomer in each target historical time period.

Illustratively, determining the battery pack capacity of the battery pack in each target historical period according to the cell capacity and the second charge state of each battery cell in each target historical period comprises the following steps:

determining a first product result between the monomer capacity of each battery monomer and the second charge state in each target historical time period; determining a first difference between the first preset value and the second state of charge; determining a second product result between the first difference and the cell capacities of the battery cells; and determining the battery pack capacity of the battery pack in each target historical time period according to the sum of the minimum first product result and the minimum second product result. For example, the battery pack capacity of the battery pack target history period T1 is set to Q _pack Q is then _pack The following formula can be used:

alternatively, the sum of the smallest first product result and the smallest second product result may be multiplied by a second preset coefficient to obtain the product result as the battery pack capacity of the battery pack in each target history period.

S802, a second ratio between the battery pack capacity of the battery pack and the rated capacity of the battery pack for each target history period is determined.

For example, the battery pack capacity Q of the target history period T1 is set _pack Rated capacity Q of battery pack _norm A second ratio of q ₂ Q is ₂ Can be expressed by the following relation:

s803, determining the actual health condition of the battery pack in each target historical time period according to the second ratio corresponding to each target historical time period.

The second ratio corresponding to each target history period may be taken as the actual health of the battery pack for each target history period. Introduction to the foregoing examplesA second ratio q corresponding to the target history period T1 may be calculated ₂ Actual health of battery pack as target history period T1

Alternatively, the product obtained by multiplying the second ratio corresponding to each target historical period by the third preset coefficient may be used as the actual health condition of the battery pack in each target historical period.

In this embodiment of the present application, according to the monomer capacity and the second state of charge of each battery monomer in each target historical period, the battery pack capacity of the battery pack in each target historical period is determined, the second ratio between the battery pack capacity of the battery pack in each target historical period and the rated capacity of the battery pack is determined, and according to the second ratio corresponding to each target historical period, the actual health condition of the battery pack in each target historical period is determined. Preconditions are provided for determining the target predictive model.

Fig. 9 is a flow chart of a method for determining a target historical time period according to an embodiment of the present application, where on the basis of the above embodiment, as shown in fig. 9, the method includes the following:

s901, acquiring a first state of charge of each battery cell in the battery pack at the start of charging, a second state of charge at the end of charging, and a battery pack temperature during charging the battery pack in each historical period.

S902, determining a second difference between the second state of charge and the first state of charge of each battery cell corresponding to each historical period.

S903, determining a target difference according to the minimum second difference corresponding to each battery cell in each historical time period.

S904, if the target difference value is greater than the preset state of charge difference value threshold value and the temperature of the battery pack is within the preset temperature range, taking the historical time period corresponding to the smallest second difference value as the target historical time period.

In this embodiment, in order to improve the accuracy of the target prediction model in predicting the battery health condition of the battery pack in the charging period, it is necessary to train the initial prediction model by using the actual health condition of the battery pack corresponding to the history period with a smaller error. For example, the preset state of charge difference threshold is set to 40%, the preset temperature range is set to 15 degrees to 30 degrees, and the first state of charge of each battery cell in the battery pack at the start of charging, the second state of charge at the end of charging and the battery pack temperature are obtained in the process of charging the battery pack in each historical period. And determining a second difference value between the second charge state and the first charge state of each battery cell corresponding to each historical time period. And determining a target difference value according to the minimum second difference value corresponding to each battery cell in each historical time period. And if the target difference value is greater than the preset state of charge difference value threshold value by 40 percent and the temperature of the battery pack is within the preset temperature range of 15 to 30 degrees, taking the historical time period corresponding to the smallest second difference value as the target historical time period.

In this embodiment of the present application, by acquiring a first state of charge of each battery cell in a battery pack at a start of charging, a second state of charge of each battery cell at an end of charging, and a battery pack temperature in a process of charging the battery pack in each historical period, determining a second difference value between the second state of charge and the first state of charge of each battery cell corresponding to each historical period, determining a target difference value according to a minimum second difference value corresponding to each battery cell in each historical period, and if the target difference value is greater than a preset state of charge difference value threshold, and the battery pack temperature is within a preset temperature range, taking the historical period corresponding to the minimum second difference value as the target historical period. Because the charge state difference value of the selected target historical time period is large and the battery temperature is proper, the error of the actual health condition of the battery pack in the calculated target historical time period is small, and therefore the accuracy of the actual health condition of the battery pack is improved.

In one embodiment, the battery parameters include:

and the battery pack is charged, before the battery pack is charged, the battery pack corresponds to the driving mileage of the electric vehicle, and the battery pack corresponds to the maximum single voltage, the minimum single voltage, the maximum single temperature and the minimum single temperature at the beginning of charging in each target historical time period, and corresponds to the maximum single voltage, the minimum single voltage, the maximum single temperature and the minimum single temperature at the end of charging in each target historical time period. Maximum monomer voltage, minimum monomer voltage, maximum monomer temperature, minimum monomer temperature corresponding to each target historical time period.

Alternatively, the battery pack or other parameters of the electric vehicle and the energy storage device using the battery pack may be selected as the battery parameters according to the actual situation.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a health condition prediction device of the battery pack for realizing the health condition prediction method of the battery pack. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the health status prediction device for one or more battery packs provided below may be referred to the limitation of the health status prediction method for a battery pack hereinabove, and will not be described herein.

In one embodiment, as shown in fig. 10, there is provided a health prediction apparatus 1000 of a battery pack, comprising: a first acquisition module 1001, a first determination module 1002, a training determination module 1003, and a second determination module 1004, wherein:

a first obtaining module 1001, configured to obtain a first state of charge of each battery cell in the battery pack when charging starts, a second state of charge of each battery cell when charging ends, and each sampling current obtained by sampling a current of the battery pack during each target historical period;

a first determining module 1002, configured to determine an actual health condition of the battery pack in each target historical period according to each sampling current corresponding to each target historical period, and a first state of charge and a second state of charge corresponding to each battery cell;

the training module 1003 is configured to train the initial prediction model to obtain a target prediction model according to the battery parameters and the actual health conditions corresponding to each target historical time period;

the second determining module 1004 is configured to determine a health condition of the battery pack to be predicted in the charging period according to the battery parameter corresponding to the battery pack to be predicted in the charging period and the target prediction model.

In one embodiment, the first determining module 1002 includes:

the first determining unit is used for determining the accumulated electric quantity of the battery pack corresponding to each target historical time period according to each sampling current corresponding to each target historical time period;

the second determining unit is used for determining the state of charge variation corresponding to each battery cell according to the first state of charge and the second state of charge corresponding to each battery cell;

and the third determining unit is used for determining the actual health condition of the battery pack in each target historical time period according to the accumulated electric quantity corresponding to each target historical time period of the battery pack and the state of charge variation corresponding to each battery cell.

In one embodiment, the third determining unit is specifically configured to determine, according to the state of charge change corresponding to each battery cell and the accumulated electric quantity corresponding to each target historical time period, a cell capacity of each battery cell in each target historical time period; and determining the actual health condition of the battery pack in each target historical time period according to the monomer capacity of each battery monomer, the second charge state and the rated capacity of the battery pack in each target historical time period.

In one embodiment, the third determining unit is specifically configured to determine a first ratio between the accumulated electric quantity corresponding to each target historical period and the state of charge variation corresponding to each battery cell; and determining the monomer capacity of each battery monomer according to the first ratio corresponding to each battery monomer in each target historical time period.

In one embodiment, the third determining unit is specifically configured to determine, according to the cell capacity and the second state of charge of each cell in each target historical period, a cell pack capacity of the cell pack in each target historical period; determining a second ratio between the battery pack capacity of the battery pack and the rated capacity of the battery pack for each target historical period; and determining the actual health condition of the battery pack in each target historical time period according to the second ratio corresponding to each target historical time period.

In one embodiment, the battery pack health prediction apparatus 1000 further includes:

the second acquisition module is used for acquiring a first charge state of each battery monomer in the battery pack at the beginning of charging, a second charge state at the end of charging and the temperature of the battery pack in the process of charging the battery pack in each historical time period;

a third determining module, configured to determine a second difference between a second state of charge and the first state of charge of each battery cell corresponding to each historical time period;

a fourth determining module, configured to determine a target difference according to a minimum second difference corresponding to each battery cell in each historical time period;

and a fifth determining module, configured to, if the target difference is greater than the preset state of charge difference threshold and the temperature of the battery pack is within the preset temperature range, take the historical time period corresponding to the smallest second difference as the target historical time period.

In one embodiment, the battery parameters include the following:

the method comprises the steps that the battery pack corresponds to the driving mileage of the electric vehicle before the battery pack is charged;

maximum monomer voltage, minimum monomer voltage, maximum monomer temperature, minimum monomer temperature corresponding to each target historical time period.

The respective modules in the above-described battery pack health status prediction apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

Acquiring a first charge state of each battery cell in the battery pack at the beginning of charging, a second charge state at the end of charging and sampling currents of the battery pack in the process of charging the battery pack in each target historical time period;

determining the actual health condition of the battery pack in each target historical time period according to each sampling current corresponding to each target historical time period and the first charge state and the second charge state corresponding to each battery cell;

training the initial prediction model according to battery parameters and actual health conditions corresponding to each target historical time period to obtain a target prediction model;

and determining the health condition of the battery pack to be predicted in the charging time period according to the battery parameters and the target prediction model corresponding to the battery pack to be predicted in the charging time period.

In one embodiment, the processor when executing the computer program further performs the steps of:

And determining the actual health condition of the battery pack in each target historical time period according to the accumulated electric quantity corresponding to each target historical time period of the battery pack and the state of charge variation corresponding to each battery cell.

determining the battery pack capacity of the battery pack in each target historical time period according to the monomer capacity and the second charge state of each battery monomer in each target historical time period;

Determining a second ratio between the battery pack capacity of the battery pack and the rated capacity of the battery pack for each target historical period;

acquiring a first charge state of each battery monomer in the battery pack at the beginning of charging, a second charge state at the end of charging and the temperature of the battery pack in the process of charging the battery pack in each historical time period;

determining a second difference value between the second charge state and the first charge state of each battery cell corresponding to each historical time period;

determining a target difference value according to the minimum second difference value corresponding to each battery monomer in each historical time period;

and if the target difference value is larger than the preset state of charge difference value threshold value and the temperature of the battery pack is in the preset temperature range, taking the historical time period corresponding to the smallest second difference value as the target historical time period.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method of predicting the health of a battery pack, the method comprising:

2. The method of claim 1, wherein determining the actual health of the battery pack during each of the target historical periods based on each of the sampling currents corresponding to each of the target historical periods, the first state of charge corresponding to each of the battery cells, and the second state of charge comprises:

3. The method of claim 2, wherein determining the actual health of the battery pack during each of the target historical periods based on the accumulated electrical quantity of the battery pack during each of the target historical periods and the state of charge change of each of the battery cells comprises:

and determining the actual health condition of the battery pack in each target historical time period according to the single body capacity of each battery single body, the second charge state and the rated capacity of the battery pack in each target historical time period.

4. The method of claim 3, wherein determining the cell capacity of each of the battery cells according to the state of charge change corresponding to each of the battery cells and the accumulated electricity quantity corresponding to each of the target historical time periods comprises:

and determining the monomer capacity of each battery monomer according to a first ratio corresponding to each battery monomer in each target historical time period.

5. The method of claim 3, wherein said determining the actual health of the battery pack for each of the target historical periods based on the cell capacity of each of the battery cells, the second state of charge, and the rated capacity of the battery pack for each of the target historical periods comprises:

determining a second ratio between a battery pack capacity of the battery pack and a rated capacity of the battery pack for each of the target historical periods;

6. The method according to any one of claims 1-5, further comprising:

Acquiring a first charge state of each battery monomer in the battery pack at the beginning of charging, a second charge state at the end of charging and a battery pack temperature in the process of charging the battery pack in each historical time period;

determining a second difference between the second state of charge and the first state of charge of each of the battery cells corresponding to each of the historical time periods;

and if the target difference value is larger than a preset state of charge difference value threshold value and the battery pack temperature is in a preset temperature range, taking a historical time period corresponding to the minimum second difference value as a target historical time period.

7. The method of any one of claims 1-5, wherein the battery parameters include the following parameters:

And the maximum monomer voltage, the minimum monomer voltage, the maximum monomer temperature and the minimum monomer temperature corresponding to each target historical time period.

8. A battery pack health prediction apparatus, the apparatus comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.