CN118024953A - Management method, program product and battery management system for vehicle power battery - Google Patents
Management method, program product and battery management system for vehicle power battery Download PDFInfo
- Publication number
- CN118024953A CN118024953A CN202410348572.2A CN202410348572A CN118024953A CN 118024953 A CN118024953 A CN 118024953A CN 202410348572 A CN202410348572 A CN 202410348572A CN 118024953 A CN118024953 A CN 118024953A
- Authority
- CN
- China
- Prior art keywords
- battery
- diffusion
- power battery
- equalization
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 35
- 238000009792 diffusion process Methods 0.000 claims abstract description 68
- 238000010801 machine learning Methods 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The present disclosure relates to a management method for a power battery of a vehicle, wherein the management method includes at least the steps of: acquiring data of a plurality of state parameters of each battery cell of the power battery; generating a battery diffusion index according to the data in combination with a machine learning algorithm model, wherein the battery diffusion index is used for analyzing the battery diffusion risk of the power battery; when it is determined that there is a battery diffusion problem based on the battery diffusion index, corresponding equalization control measures are implemented. The disclosure also relates to a corresponding computer program product and a battery management system for a vehicle. The power battery health condition can be accurately estimated, and the occurrence of the battery diffusion phenomenon can be timely predicted, so that the performance attenuation of the power battery can be reliably avoided, and the service life of the power battery can be prolonged.
Description
Technical Field
The present disclosure relates to the field of battery management, and more particularly, to a method for managing a power battery for a vehicle. The disclosure also relates to a corresponding computer program product and a corresponding battery management system for a vehicle.
Background
In recent years, with the development of technology and the rise of environmental awareness, electric vehicles have received increasing attention. The power battery as a main energy source of the electric vehicle has the advantages of environmental protection, energy conservation, stability and the like.
In order to meet the energy and power demands of a vehicle traveling, a power battery generally includes a battery pack composed of a plurality of battery cells that form a battery pack in a serial-parallel connection. As the number of charge and discharge increases, each cell of the battery pack is attenuated to various degrees, so that there is a difference in performance and state of each cell, which is also called a cell diffusion phenomenon, which may cause a decrease in the overall energy density, safety, and service life of the power battery.
At present, detection measures based on temperature or current exist for the battery diffusion phenomenon, but the detection measures cannot timely and accurately predict the battery diffusion problem.
BRIEF SUMMARY OF THE PRESENT DISCLOSURE
It is therefore an object of the present disclosure to propose an improved management method for a power battery of a vehicle, by which the health condition of the power battery can be accurately estimated, and the occurrence of a battery diffusion phenomenon can be timely predicted, thereby reliably avoiding performance degradation of the power battery, extending the service life of the power battery, and also providing additional protection against damage of a battery cell due to overcharge or overdischarge and reducing maintenance costs. It is also an object of the present disclosure to propose a corresponding computer program product and a corresponding battery management system for a vehicle.
According to a first aspect of the present disclosure, there is provided a management method for a power battery of a vehicle, wherein the management method includes at least the steps of:
s1: acquiring data of a plurality of state parameters of each battery cell of the power battery;
S2: generating a battery diffusion index according to the data in combination with a machine learning algorithm model, wherein the battery diffusion index is used for analyzing the battery diffusion risk of the power battery;
S3: when it is determined that there is a battery diffusion problem based on the battery diffusion index, corresponding equalization control measures are implemented.
Within the framework according to the present disclosure, the "risk of battery diffusion" is understood as the possibility of non-negligible inconsistencies between the individual cells of the power battery, which lead to a decrease in the energy density, safety and service life of the power battery as a whole, and even to the damage of the cells due to overcharging or overdischarging, which are always present and which increase gradually with an increase in the number of times of charge and discharge of the power battery; by "battery diffusion problem" is understood that a non-negligible inconsistency has occurred between the individual cells of the power battery, which should be eliminated as soon as possible in order to avoid irreversible damage to the power battery. Here, when the battery diffusion risk increases to some extent, it can be determined that there is a battery diffusion problem inside the power battery.
Compared with the prior art, in the management method for the power battery of the vehicle, the machine learning algorithm model is utilized to comprehensively analyze a plurality of state parameters of each battery cell of the power battery and generate corresponding battery diffusion indexes, the battery diffusion indexes represent battery diffusion risks of the power battery, when a battery diffusion problem is predicted based on the battery diffusion indexes, corresponding equalization control measures are implemented to eliminate inconsistency among the battery cells and actively prevent and reduce battery diffusion phenomena, so that the cycle operation times of the power battery can be increased, damage to the battery cells due to overcharge or overdischarge can be prevented, and performance attenuation of the power battery and service life of the power battery can be avoided cost-effectively.
Illustratively, the status parameter is selected from the group consisting of: impedance, current, terminal voltage, temperature, cycle life; and/or the data includes historical data and real-time data.
Illustratively, the power cell is determined to have a cell diffusion problem when the cell diffusion index exceeds a preset threshold.
Illustratively, the machine learning algorithm model is pre-trained by: and taking the state parameters of each battery cell of the power battery with the determined battery diffusion problem as input, taking the battery diffusion index allocated to the battery diffusion problem as output, and establishing a mapping relation between the state parameters and the battery diffusion index.
Illustratively, the machine learning algorithm model is one of the following models: bayesian models, decision tree models, support vector machine models, logistic regression models, neural network models.
The equalization control means may comprise an active equalization means, which is implemented by an external equalization circuit with an energy storage device, or a passive equalization means, which is implemented by an internal equalization circuit with an equalization chip.
Illustratively, the management method further includes step S4: the state parameters of the respective battery cells are re-detected after the equalization control measures are implemented to verify the accuracy of the battery diffusion index generated in step S2 and the validity of the equalization control measures implemented in step S3.
Illustratively, the verification result of step S4 is fed back to the machine learning algorithm model to further train and optimize the machine learning algorithm model.
In step S3, a warning message about the battery diffusion problem is additionally given to the driver of the vehicle, for example.
According to a second aspect of the present disclosure, there is provided a computer program product comprising a computer program, wherein the computer program, when executed by one or more processors, is capable of performing the management method according to the present disclosure.
According to a third aspect of the present disclosure, there is provided a battery management system for a vehicle, wherein the battery management system includes:
-a detection unit configured to detect a plurality of state parameters of respective battery cells of a power battery for a vehicle;
-a control unit obtaining the status parameters from the detection unit and configured to implement the management method according to the present disclosure with the computer program product of the present disclosure to achieve equalization of the battery cells.
Drawings
The principles, features and advantages of the present disclosure may be better understood by describing the present disclosure in more detail with reference to the drawings. The drawings include:
FIG. 1 illustrates a schematic flow chart of a method of managing a power battery for a vehicle according to one exemplary embodiment of the present disclosure;
Fig. 2 shows a schematic block diagram of a battery management system for a vehicle according to an exemplary embodiment of the present disclosure.
Detailed Description
In order to make the technical problems, technical solutions and advantageous technical effects to be solved by the present disclosure more apparent, the present disclosure will be further described in detail with reference to the accompanying drawings and a plurality of exemplary embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the present disclosure.
The present specification provides method operational steps as described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution.
Fig. 1 shows a schematic flow chart of a management method for a power battery of a vehicle according to an exemplary embodiment of the present disclosure. The vehicle may be an electric vehicle or a hybrid vehicle. The power battery comprises at least one battery pack with a plurality of battery cells, which form a battery pack in series or parallel as required.
As shown in fig. 1, the management method of the power battery for the vehicle includes at least the steps of:
S1: acquiring data of a plurality of state parameters of each battery cell of the power battery, wherein the state parameters can reflect the performance and the state of the battery cell from different angles respectively;
S2: generating a battery diffusion index according to the acquired data about the state parameters in combination with a machine learning algorithm model, wherein the battery diffusion index is used for analyzing the battery diffusion risk of the power battery, wherein the larger the generated battery diffusion index is, the higher the battery diffusion risk of the power battery is and the greater the inconsistency among battery monomers or the greater the tendency of the inconsistency to occur, and particularly when the battery diffusion index exceeds a preset threshold value, the battery diffusion problem of the power battery is determined;
s3: when it is determined that there is a battery diffusion problem based on the battery diffusion index, corresponding equalization control measures are implemented to actively eliminate inconsistencies between the battery cells.
Therefore, the machine learning algorithm model can be utilized to comprehensively analyze a plurality of state parameters of each battery cell of the power battery and generate corresponding battery diffusion indexes, the battery diffusion risk of the power battery is judged according to the battery diffusion indexes, and corresponding equalization control measures are implemented to eliminate inconsistency among the battery cells and actively prevent and reduce the battery diffusion phenomenon, so that the performance attenuation of the power battery is avoided and the service life of the power battery is prolonged.
For example, the state parameter of each cell may be selected from the group of: impedance, current, terminal voltage, temperature, cycle life. With the increase of the charge and discharge times, the state parameters of the battery cells are changed. Here, the terminal voltage and current may reflect the charge and discharge states of the battery cell, while the temperature and impedance may reflect the chemical reaction conditions inside the battery cell, and the cycle life may reflect the decay rate of the battery cell. In particular, all these state parameters are taken into account in combination to more accurately analyze the cell diffusion risk of the power cell. Of course other state parameters that the person skilled in the art deems interesting are also contemplated. The data acquired in step S1 regarding the state parameters of the battery cells may include real-time data for displaying the current state of the battery cells and history data for displaying the state parameter change conditions of the battery cells, such as a terminal voltage change rate or a temperature change curve, and the battery diffusion risk of the power battery may be more comprehensively analyzed by comprehensively considering the real-time data and the history data.
The machine learning algorithm model used in step S2 is illustratively pre-trained and stored in a control unit for implementing the management method, wherein the machine learning algorithm model is trained by taking as input the state parameters of the individual cells of the power battery having the determined battery diffusion problem, taking as output the battery diffusion index associated with the battery diffusion problem, and establishing a mapping relationship between the state parameters and the battery diffusion index. Here, a large amount of sample data is used to train the machine learning algorithm model to promote the accuracy of the machine learning algorithm model. Illustratively, the machine learning algorithm model is one of the following models: bayesian models, decision tree models, support vector machine models, logistic regression models, neural network models. Of course, other learning algorithm models that would be considered significant by those skilled in the art are also contemplated.
For example, in step S3, when it is determined that a battery diffusion problem exists, the equalization control measure implemented may be an active equalization measure that transfers the energy of the high-voltage battery cell into the low-voltage battery cell by energy transfer and has the advantage of high energy utilization and high equalization efficiency, wherein the active equalization measure is implemented by an external equalization circuit having an energy storage device, which is configured mainly in the form of a capacitor, an inductor, or a transformer. It is also possible that the equalization control means implemented are passive equalization means which keep the electrical quantities of the high-voltage battery cells and the low-voltage battery cells identical by means of a resistive discharge and have the advantage of a simple circuit and low cost, wherein the passive equalization means are implemented by an internal equalization circuit with equalization chips.
Illustratively, as shown in fig. 1, the management method optionally includes step S4: the state parameters of the respective battery cells are re-detected after the equalization control measures are implemented to verify the accuracy of the battery diffusion index generated in step S2 and the effectiveness of the equalization control measures implemented in step S3. In this case, after successful implementation of the equalization control measures, the cell diffusion index of the power cell should be reduced, in particular below a predetermined threshold value, otherwise indicating that the resulting cell diffusion index is inaccurate and/or that the implemented equalization control measures are ineffective, in which case further measures, such as deep inspection and active maintenance of the power cell, are required to avoid irreversible damage to the battery cells of the power cell.
Illustratively, the verification result of step S4 is fed back to the machine learning algorithm model to further train and optimize the machine learning algorithm model. This may adapt the machine learning algorithm model to the actual operating environment and learn based on real world data to continually improve the accuracy of the machine learning algorithm model.
In step S3, a warning message about the battery spread problem, for example, "please note that the battery spread problem is occurring and an equalization control measure is implemented", is additionally issued to the driver of the vehicle, so that the driver is informed of the health of the power battery and actively maintains the power battery when necessary.
Fig. 2 shows a schematic block diagram of a battery management system 100 for a vehicle according to an exemplary embodiment of the present disclosure. Here, the battery management system 100 is configured for intelligently managing and maintaining a power battery of a vehicle, the power battery including at least one battery pack having a plurality of battery cells connected in series-parallel.
As shown in fig. 2, the battery management system 100 includes a detection unit 10, the detection unit 10 being configured to detect a plurality of state parameters of respective battery cells of the power battery. The state parameter may be selected, for example, from the following group: impedance, current, terminal voltage, temperature, cycle life. Accordingly, the detection unit 10 may include, for example, a current sensor, a voltage sensor, a temperature sensor, and the like.
As shown in fig. 2, the battery management system 100 comprises a control unit 20, which control unit 20 is connected, e.g. communicatively connected, to the detection unit 10 and which obtains the state parameters of the individual battery cells from the detection unit 20 and is configured to implement the management method according to the present disclosure with a computer program product according to the present disclosure to achieve a balancing of the battery cells, wherein the computer program product comprises a computer program which, when executed by one or more processors, is capable of executing the management method according to the present disclosure.
The foregoing explanation of the embodiments only describes the present disclosure in the framework of the examples. Of course, the individual features of the embodiments can be freely combined with one another without departing from the framework of the disclosure, as long as they are technically meaningful.
Other advantages and alternative embodiments of the present disclosure will be apparent to those skilled in the art. Therefore, the disclosure is not to be limited in its broader aspects to the specific details, the representative structures, and illustrative embodiments shown and described. Rather, various modifications and substitutions may be made by those skilled in the art without departing from the basic spirit and scope of the disclosure.
Claims (10)
1. A method of managing a power battery for a vehicle, the method comprising at least the steps of:
s1: acquiring data of a plurality of state parameters of each battery cell of the power battery;
S2: generating a battery diffusion index according to the data in combination with a machine learning algorithm model, wherein the battery diffusion index is used for analyzing the battery diffusion risk of the power battery;
S3: when it is determined that there is a battery diffusion problem based on the battery diffusion index, corresponding equalization control measures are implemented.
2. The method of claim 1, wherein,
The state parameter is selected from the group of: impedance, current, terminal voltage, temperature, cycle life; and/or
The data includes historical data and real-time data.
3. A method of managing as set forth in claim 1 or 2, characterized in that,
And when the battery diffusion index exceeds a preset threshold value, determining that the power battery has a battery diffusion problem.
4. A method of managing as set forth in any preceding claim, characterized in that,
The machine learning algorithm model is trained in advance by: taking the state parameters of each battery cell of the power battery with the determined battery diffusion problem as input, taking the battery diffusion index allocated to the battery diffusion problem as output, and establishing a mapping relation between the state parameters and the battery diffusion index; and/or
The machine learning algorithm model is one of the following models: bayesian models, decision tree models, support vector machine models, logistic regression models, neural network models.
5. A method of managing as set forth in any preceding claim, characterized in that,
The equalization control measures comprise active equalization measures which are realized by an external equalization circuit with an energy storage device or passive equalization measures which are realized by an internal equalization circuit with an equalization chip.
6. A method of managing as set forth in any preceding claim, characterized in that,
The management method further comprises the step S4 of: the state parameters of the respective battery cells are re-detected after the equalization control measures are implemented to verify the accuracy of the battery diffusion index generated in step S2 and the validity of the equalization control measures implemented in step S3.
7. The method of claim 6, wherein,
And feeding back the verification result of the step S4 to the machine learning algorithm model so as to further train and optimize the machine learning algorithm model.
8. A method of managing as set forth in any preceding claim, characterized in that,
In step S3, a warning message about the battery spread problem is additionally issued to the driver of the vehicle.
9. A computer program product comprising a computer program, characterized in that the computer program, when executed by one or more processors, is capable of executing the management method according to any one of claims 1 to 8.
10. A battery management system (100) for a vehicle, the battery management system (100) comprising:
-a detection unit (10), the detection unit (10) being configured to be adapted to detect a plurality of state parameters of respective battery cells of a power battery for a vehicle;
-a control unit (20), the control unit (20) obtaining the status parameter from the detection unit (10) and being configured to implement the management method according to any one of claims 1 to 8 with the computer program product of claim 8, to achieve equalization of the battery cells.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410348572.2A CN118024953A (en) | 2024-03-26 | 2024-03-26 | Management method, program product and battery management system for vehicle power battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410348572.2A CN118024953A (en) | 2024-03-26 | 2024-03-26 | Management method, program product and battery management system for vehicle power battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118024953A true CN118024953A (en) | 2024-05-14 |
Family
ID=90993296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410348572.2A Pending CN118024953A (en) | 2024-03-26 | 2024-03-26 | Management method, program product and battery management system for vehicle power battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118024953A (en) |
-
2024
- 2024-03-26 CN CN202410348572.2A patent/CN118024953A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
| CN111007401A (en) | Electric vehicle battery fault diagnosis method and device based on artificial intelligence | |
| JP6635743B2 (en) | Storage battery maintenance device and storage battery maintenance method | |
| CN112186275A (en) | BMS system based on high in clouds | |
| US20230288490A1 (en) | Battery fault diagnosis method and apparatus | |
| CN115702533B (en) | Method for predicting power states of a multi-cell electrical energy storage system | |
| CN110190347A (en) | A kind of lithium battery management system applied to communication base station | |
| CN115902646B (en) | Energy storage battery fault identification method and system | |
| CN110146817A (en) | The diagnostic method of lithium battery failure | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| WO2023221587A1 (en) | Method for determining state of health of power battery of electric vehicle, and server | |
| CN114204626B (en) | Charging control method and related equipment | |
| CN114295983A (en) | Battery thermal runaway early warning method and device, vehicle, equipment and storage medium | |
| CN110931899A (en) | Fault diagnosis and failure processing system and method for lithium ion power battery pack | |
| US20220373609A1 (en) | State Value for Rechargeable Batteries | |
| CN112622676A (en) | Monitoring method and system for power battery safe charging | |
| CN112349981A (en) | Battery management system | |
| CN104882914A (en) | Multi-battery cell balancing method | |
| CN117096476B (en) | Battery grouping method and device, electronic equipment and storage medium | |
| CN103296324B (en) | Vehicle power battery pack charging method | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| Li et al. | A novel fault diagnosis method for battery energy storage station based on differential current | |
| CN118024953A (en) | Management method, program product and battery management system for vehicle power battery | |
| CN116937758B (en) | Household energy storage power supply system and operation method thereof | |
| CN114325394B (en) | Method, system, equipment and medium for estimating battery stack SOC |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |