Lithium iron battery system equalization method, device, equipment, storage medium and program product
By using the SOC prediction model based on the decision tree algorithm in the iron lithium battery system, the SOC and minimum SOC of a single battery are accurately estimated, which solves the problem of errors in the selection of balance points in the prior art, and improves the capacity consistency and charge and discharge capacity of the battery system.
Patent Information
- Application Number
- CN202411617605.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-02-28
Smart Images
Figure CN119542579A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of battery equalization, and in particular to a method, device, equipment, storage medium and program product for equalizing an iron-lithium battery system based on a decision tree algorithm. Background Art
[0002] Power batteries are composed of many independent battery cells. Due to the inconsistency of the battery cells themselves and the difference in the ambient temperature, after a period of use, the battery cells will have some capacity differences. This capacity difference affects the life and usability of the battery pack, and active or passive balancing must be performed. Therefore, the battery management system will balance the battery while monitoring the voltage and temperature of the battery. Most battery systems use passive balancing to balance the battery system. The difficulty in balancing is the selection of the balancing point, and the battery working environment and historical operating conditions have a great impact on the capacity and voltage of the battery, which also brings many challenges to the selection of the balancing voltage point.
[0003] Most of the existing technologies use the voltage difference of the battery to select the appropriate single cell voltage point for balancing. However, the working environment and historical working conditions of the battery have a great influence on the battery voltage. In addition, the voltage difference of the iron-lithium battery in the plateau period is very small. Simply using the voltage difference cannot reflect the capacity difference of the battery. This will lead to the wrong selection of the voltage point for balancing. In this way, balancing will not only fail to make the battery box tolerance consistent, but will increase the capacity difference, causing the battery box charge and discharge capacity to become smaller. Summary of the invention
[0004] The purpose of the present invention is to overcome the shortcomings and defects of the prior art and to provide a method, device, equipment, storage medium and program product for balancing an iron-lithium battery system.
[0005] A first aspect of the present invention provides a method for balancing an iron-lithium battery system, comprising the steps of:
[0006] When the iron-lithium battery system is in use, the SOC prediction model based on the decision tree is used to estimate the SOC of the single battery of the iron-lithium battery system in real time to obtain the minimum SOC of the single battery;
[0007] According to the comparison result between the difference between the target single cell SOC and the minimum single cell SOC and the preset threshold, the balancing process of the target single cell is controlled to be turned on or off.
[0008] The SOC prediction model is trained by the following steps:
[0009] Conducting a working condition test on the lithium iron battery system, during which the battery data required for model training is collected to obtain a training set and a test set; using the training set to train the constructed decision tree model, and then using the test set to verify it, to obtain an SOC prediction model;
[0010] Among them, the battery data includes voltage data and temperature data of the single cell of the iron-lithium battery system, current data of the iron-lithium battery system, SOC value of the iron-lithium battery system reported by the BMS system, and current value passing through the single cell; preferably, the battery data comes from data at the charging end of the iron-lithium battery system.
[0011] Among them, before the operating condition test of the iron-lithium battery system is carried out, the iron-lithium battery system is fully charged, and then the operating condition test is carried out until the minimum single cell voltage reaches the preset voltage and the operating condition test is stopped, and then the iron-lithium battery system is charged to reach the cut-off voltage; and this process is repeated; preferably, when charging the iron-lithium battery system, the charging current is selected according to the charging rate in the charging rate table.
[0012] The operating condition test is carried out at different temperatures, and the temperature range is -10°C to 18°C; preferably, when the model is verified with a test set, the variance of the prediction accuracy is used to judge the single cell SOC prediction error.
[0013] The SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V.
[0014] When the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value.
[0015] The SOC prediction model is introduced into the BMS system of the iron-lithium battery system to estimate the SOC of the single battery of the iron-lithium battery system.
[0016] A second aspect of the present invention provides a lithium iron battery system balancing device, comprising:
[0017] The single cell minimum SOC estimation module is used to estimate the single cell SOC of the iron-lithium battery system in real time using the SOC prediction model formed based on the decision tree during the use of the iron-lithium battery system to obtain the single cell minimum SOC;
[0018] A calculation and judgment module is used to calculate the difference between the target single cell SOC and the minimum single cell SOC and compare it with a preset threshold;
[0019] The balancing start and stop module is used to control the start or stop of the balancing process of the target single cell battery according to the comparison result of the difference between the target single cell battery SOC and the minimum single cell battery SOC and the preset threshold.
[0020] According to a third aspect of the present invention, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described when executing the computer program.
[0021] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program implements the steps of the method described when executed by a processor.
[0022] A fifth aspect of the present invention provides a computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of the described method are implemented.
[0023] The present invention uses an SOC prediction model based on a decision tree to predict the SOC of a single cell, fully considers the impact of the battery's historical operating conditions, estimates the capacity difference between the single cells in the battery system, and can select batteries with higher capacity to start balancing, which can effectively improve the capacity consistency of the battery system and increase the charge and discharge capacity of the battery system. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 It is a flow chart of a method for balancing an iron-lithium battery system according to an embodiment of the present invention.
[0025] Figure 2 It is a schematic diagram of a specific implementation flow of the iron-lithium battery system balancing method according to an embodiment of the present invention.
[0026] Figure 3 This is the SOC prediction effect diagram when there is no BMS SOC data and system current data.
[0027] Figure 4 This is the SOC prediction error diagram when there is no BMS SOC data and system current data.
[0028] Figure 5 It is a diagram of SOC prediction effect of an embodiment of the present invention.
[0029] Figure 6 is an SOC prediction error diagram of an embodiment of the present invention.
[0030] Figure 7 It is a structural principle diagram of an iron-lithium battery system equalization device according to an embodiment of the present invention.
[0031] Figure 8 It is a structural principle diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0032] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0033] See also Figure 1 As shown, an iron-lithium battery system balancing method in an embodiment of the present invention includes the following steps:
[0034] S1. When the iron-lithium battery system is in use, the SOC prediction model based on the decision tree is used to estimate the SOC of the single battery of the iron-lithium battery system in real time to obtain the minimum SOC of the single battery;
[0035] S2. According to the comparison result between the difference between the target single cell SOC and the minimum single cell SOC and the preset threshold value, control to start or stop the balancing process of the target single cell.
[0036] The SOC prediction model is trained by the following steps:
[0037] Conducting a working condition test on the lithium iron battery system, during the working condition test (DST), collecting battery data required for model training to obtain a training set and a test set; using the training set to train the constructed decision tree model, and then using the test set to verify it, to obtain an SOC prediction model;
[0038] In this application, after the operating condition test is completed, the battery data obtained during the test process is sorted out, and the battery data obtained from the test is processed into a data set and divided into a training set and a test set. The training set data is used to train the constructed decision tree model, and the test data set is used to verify the accuracy of the trained model.
[0039] In the embodiment of the present application, all factors that may affect the SOC of the power battery are comprehensively considered. Therefore, the battery data may include voltage data and temperature data of the single cell of the iron-lithium battery system, current data of the iron-lithium battery system, the SOC value of the iron-lithium battery system reported by the BMS system, and the current value passing through the single cell (used to calculate the SOC of the single cell).
[0040] Among them, the current data of the battery system and the battery system SOC value data reported by the BMS system play a relatively important role in the SOC prediction of the single cell. The current data can identify the change trend and speed of the SOC. The positive current indicates that the battery system is discharging and the SOC change is a downward trend. The negative current indicates that the battery system is charging and the SOC change is an upward trend. The larger the current, the faster the SOC changes, and the smaller the current, the smaller the SOC changes. The battery system SOC value reported by the BMS system has a great similarity with the SOC value of the single cell in the SOC prediction of the single cell. The reference cell voltage and cell temperature data can reflect the characteristics of the single cell SOC. When the data vector set eliminates the two key parameters in the model-the battery system SOC value and the battery system current data reported by the BMS system, the MSE of the model increases significantly to 0.0161, and the predicted result deviates greatly from the true value, and the prediction error increases significantly. For specific effects, please refer to the attached Figure 3 The SOC prediction effect diagram without BMS SOC data and system current data, and Figure 4 The SOC prediction error diagram without BMS SOC data and system current data is shown in the figure. After adding these two data sets, the MSE of the model is reduced to 0.0011, and the prediction result is close to the true value with an error within 5%. For the prediction effect, please refer to the attached Figure 5 , 6 As shown, it can be seen that these two influencing factors have an important impact on the accuracy of the model.
[0041] Since the voltage difference at the charging end of the iron-lithium battery system is large, in order to obtain a more accurate SOC estimate for better control / shutdown balancing, in the embodiment of the present application, the battery data selected from the charging end of the iron-lithium battery system is used as the data set for training and verifying the decision tree model.
[0042] In an embodiment of the present application, before performing an operating condition test on the lithium iron battery system, it is necessary to fully charge the lithium iron battery system, and then perform an operating condition test until the minimum single cell voltage reaches a preset voltage (such as 3.4V) and then stop the operating condition test. Then, the lithium iron battery system is charged to reach the cut-off voltage. This process is repeated, and battery data is collected during the process to obtain a training set and a test set.
[0043] When charging the lithium iron battery system, the current during charging is selected according to the charging rate in the charging rate table, such as usually 0.1C, 0.2C, 0.3C, 0.5C.
[0044] In the embodiment of the present application, the operating condition test is carried out at different temperatures, and the different temperature range is -10°C to 18°C. It can be carried out at corresponding temperatures within this range, such as -10°C, 5°C, 25°C, 40°C, 45°C, and 48°C. Since the voltage of the lithium iron battery has a plateau period, in the specific implementation, it is necessary to avoid the plateau period when collecting data so as to better establish the relationship between the single cell voltage and the single cell SOC.
[0045] In the embodiment of the present application, when the test set is used to verify the model, the variance of the prediction accuracy is used to judge the SOC prediction error of the single cell battery. For example, when the variance of the prediction accuracy is <0.002 and the SOC prediction error is below 8%, it is considered that the SOC prediction model formed based on the decision tree can be used. Otherwise, it is necessary to perform noise analysis on the test data or increase the scale of the test data and train again until it meets the requirements.
[0046] In the embodiment of the present application, since the charging terminal voltage difference of the iron-lithium battery system is large, the SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V (that is, the maximum limit voltage of the iron-lithium battery).
[0047] In the embodiment of the present application, when the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value, such as 20%, or other percentage values, but is not limited thereto. The preset threshold is the battery balancing point, which can be determined based on experience and is selected or determined when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V, and balancing is turned on.
[0048] In the embodiment of the present application, after the decision tree model is trained and the SOC prediction model is formed, when the iron-lithium battery system is balanced, the SOC prediction model is imported into the BMS system of the iron-lithium battery system for use, that is, the SOC prediction model is written into the BMS system, and the BMS system uses the established SOC prediction model to estimate the SOC of the single cell, and then performs battery balancing based on the single cell SOC estimation result.
[0049] In an embodiment of the present application, the SOC prediction model matches the vector (x1, x2, x3, ..., xn-1, xn) in the data set vector (x1, x2, x3, ..., xn-1, xn, y) based on a decision tree algorithm to obtain a prediction result vector y, where vector y is the SOC of the single cell, and vector (x1, x2, x3, ..., xn-1, xn) is a plurality of factors affecting vector y; by determining the vector (x1, x2, x3, ..., xn-1, xn) through the trained SOC prediction model, the result vector y, i.e., the estimated SOC of the single cell, can be obtained.
[0050] Specifically, when applied, the data set required for decision tree model training can be obtained according to the battery data, such as X = {x0 = time, x1 = vol, x2 = temp, x3 = sys_current, x4 = soc} for algorithm data, algorithm label Y = {SOC1, SOC2...SOCn}, that is, the SOC value of each single cell, which can be calculated by the current value (current) and time passing through the single cell according to the ampere-hour integral formula. X and Y are divided into training set and test set, and brought into the training model for training and accuracy verification, and finally an SOC prediction model that meets the accuracy requirements is obtained; the trained SOC prediction model is stored in the model variable, and the SOC value of the single cell is predicted through the model.predict function.
[0051] The construction and generation of the decision tree of the SOC prediction model can adopt existing methods, such as the classic decision tree algorithm C4.5. The following takes the classic decision tree algorithm C4.5 as an example to briefly describe the decision tree generation process.
[0052] Create or load a training data set: To create a data set, use the open() function to open a file and load a data set; decision trees are generally generated using a recursive method. When writing a recursive function, consider the end condition first: There are two conditions for the end of generating a decision tree: one is that the divided data all belong to one class, and the other is that all features have been used. In the second end case, the divided data may not all belong to one class. In this case, the classification of this sub-data set needs to be determined based on the majority voting criterion.
[0053] The function that uses a decision tree to classify input is also a recursive function. The classification function requires three parameters: a decision tree, a feature list, and data to be classified. The feature list is a bridge between the decision tree and the data to be classified. The feature of the decision tree obtains its index through the feature list, and then accesses the value of the feature in the data to be classified through the index.
[0054] Under non-end conditions, first select the feature with the largest information gain, and then classify it; at the beginning of classification, record the classified features in the decision tree, and then delete the feature in the feature label set, indicating that the feature has been used. According to the selected features, the data set is divided into several sub-datasets, and then the sub-datasets are used as parameters to recursively create a decision tree, and finally a complete decision tree is generated. Finally, the prediction accuracy of the generated decision tree is verified, and the prediction accuracy of the decision tree is evaluated using variance and MSE. The smaller the MSE, the higher the prediction accuracy of the SOC prediction model based on the decision tree.
[0055] Specifically, when implementing the lithium battery system balancing technology of the present invention, the following can be done: Figure 2The process shown in the figure is to first determine the parameters of the model, then build the required model, and train the model with the collected battery data, that is, use the training set to train the model. After the training is completed, it is determined whether the model has achieved the accuracy. If not, continue training until the target accuracy is achieved, and then the model can be tested. When testing the model, first use the model to predict the SOC of the single cell to obtain the minimum SOC of the single cell. When the difference between the SOC of the single cell and the minimum (low) SOC of the single cell is greater than 20%, turn on the balancing, otherwise turn off the balancing; if the difference is greater than 20%, it is considered that the string of single cells has reached the balancing condition and the string of single cells is selected as the balancing point. The 20% threshold is determined based on the project experience value.
[0056] See also Figure 7 As shown, in the second aspect of the embodiment of the present invention, there is provided an iron-lithium battery system balancing device, including: a single cell minimum SOC estimation module, which is used to estimate the single cell SOC of the iron-lithium battery system in real time by using an SOC prediction model formed based on a decision tree during use of the iron-lithium battery system, so as to obtain the single cell minimum SOC; a calculation and judgment module, which is used to calculate the difference between the target single cell SOC and the single cell minimum SOC and compare it with a preset threshold; and a balancing start and stop module, which is used to control the start of the target single cell balancing process or the end of the balancing process according to the comparison result of the difference between the target single cell SOC and the single cell minimum SOC and the preset threshold.
[0057] In an embodiment of the present application, after the decision tree model training is completed and the SOC prediction model is formed, when the iron-lithium battery system is balanced, the SOC prediction model can be imported into the BMS system of the iron-lithium battery system for use, that is, the SOC prediction model is written into the BMS system of the iron-lithium battery system, and the BMS system of the iron-lithium battery system uses the established SOC prediction model to estimate the SOC of the single cell, and then performs battery balancing processing based on the single cell SOC estimation result.
[0058] In the embodiment of the present application, since the charging terminal voltage difference of the iron-lithium battery system is large, the SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V (that is, the maximum limit voltage of the iron-lithium battery).
[0059] In the embodiment of the present application, when the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value, such as 20%, or other percentage values, but is not limited thereto. The preset threshold is the battery balancing point, which can be determined based on experience and is selected or determined when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V, and balancing is turned on.
[0060] The iron-lithium battery system balancing device of the embodiment of the present invention performs a balancing control process on the battery system in accordance with the technical steps of the iron-lithium battery system balancing of the embodiment of the present invention. For the specific contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method.
[0061] See also Figure 8 As shown, in the third aspect of the embodiment of the present invention, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the iron-lithium battery system balancing method when executing the computer program. For the contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method. The computer device can be a terminal, and its internal structure can be as follows Figure 8 As shown, it includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used 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 the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a battery system balancing method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0062] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0063] In the embodiment of the present application, the electronic device may be a BMS system of an iron-lithium battery system. When in use, the trained SOC prediction model may be imported into the BMS system of the iron-lithium battery system to estimate the SOC of a single cell, and then perform battery balancing based on the estimated SOC result of the single cell.
[0064] In the embodiment of the present application, since the charging terminal voltage difference of the iron-lithium battery system is large, the SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V (that is, the maximum limit voltage of the iron-lithium battery).
[0065] In the embodiment of the present application, when the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value, such as 20%, or other percentage values, but is not limited thereto. The preset threshold is the battery balancing point, which can be determined based on experience and is selected or determined when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V, and balancing is turned on.
[0066] The computer device of the embodiment of the present invention, in the process of balancing the battery system, follows the technical steps of balancing the iron-lithium battery system of the embodiment of the present invention. For the specific contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method.
[0067] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the iron-lithium battery system balancing method are implemented. For the contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method.
[0068] In an embodiment of the present application, the computer program formed by the SOC prediction model is stored in a computer-readable storage medium. After the decision tree model training is completed and the SOC prediction model is formed, the SOC prediction model is stored in a computer-readable storage medium as a computer program, and the processing device calls it to estimate the SOC of the single cell battery, and then perform battery balancing processing based on the single cell SOC estimation result.
[0069] In the embodiment of the present application, since the charging terminal voltage difference of the iron-lithium battery system is large, the SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V (that is, the maximum limit voltage of the iron-lithium battery).
[0070] In the embodiment of the present application, when the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value, such as 20%, or other percentage values, but is not limited thereto. The preset threshold is the battery balancing point, which can be determined based on experience and is selected or determined when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V, and balancing is turned on.
[0071] The computer program product stored on the computer-readable storage medium of the embodiment of the present invention is consistent with the technical steps of balancing the iron-lithium battery system of the embodiment of the present invention during the process of balancing control of the battery system. For specific contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method.
[0072] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of the iron-lithium battery system balancing method are implemented.
[0073] In the embodiment of the present application, the SOC prediction model is imported into the BMS system of the iron-lithium battery system for use, forming a computer program, which is executed by a processor to estimate the SOC of a single cell, and then battery balancing is performed based on the estimated SOC results of the single cell.
[0074] In the embodiment of the present application, due to the large voltage difference at the charging end of the iron-lithium battery system, the SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V (i.e., the maximum limiting voltage of the iron-lithium battery). In the embodiment of the present application, when the difference is less than the preset threshold, the balancing is turned off, and when the difference is greater than the preset threshold, the balancing is turned on; the difference is a percentage value, such as 20%, or other percentage values, not limited thereto, the preset threshold is the battery balancing point, which can be determined based on experience, and is selected or determined when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V, and the balancing is turned on.
[0075] The computer program product of the embodiment of the present invention performs a process of balancing the battery system, which is consistent with the technical steps of balancing the iron-lithium battery system of the embodiment of the present invention. For specific contents not detailed in this section, please refer to the technical contents of the iron-lithium battery system balancing method of the present invention and the contents of the specific implementation method.
[0076] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.
[0077] Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.
[0078] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0079] The basic principles and main features of the present invention and the advantages of the present invention are shown and described above. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention.
[0080] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the claims are included in the present invention.
[0081] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
Claims
1. A method for balancing a lithium iron battery system, characterized in that: Includes steps: When the iron-lithium battery system is in use, the SOC prediction model based on the decision tree is used to estimate the SOC of the single battery of the iron-lithium battery system in real time to obtain the minimum SOC of the single battery; According to the comparison result between the difference between the target single cell SOC and the minimum single cell SOC and the preset threshold, the balancing process of the target single cell is controlled to be turned on or off.
2. The iron-lithium battery system equalization method according to claim 1, characterized in that: The SOC prediction model is obtained by the following steps: Conducting a working condition test on the lithium iron battery system, during which the battery data required for model training is collected to obtain a training set and a test set; using the training set to train the constructed decision tree model, and then using the test set to verify it, to obtain an SOC prediction model; Among them, the battery data includes voltage data and temperature data of the single cell of the iron-lithium battery system, current data of the iron-lithium battery system, SOC value of the iron-lithium battery system reported by the BMS system, and current value passing through the single cell; preferably, the battery data comes from data at the charging end of the iron-lithium battery system.
3. The iron-lithium battery system equalization method according to claim 2, characterized in that: Before carrying out the working condition test on the lithium iron battery system, the lithium iron battery system is fully charged, and then the working condition test is carried out until the minimum single cell voltage reaches the preset voltage and the working condition test is stopped, and then the lithium iron battery system is charged to reach the cut-off voltage; and this process is repeated; preferably, when charging the lithium iron battery system, the charging current is selected according to the charging rate in the charging rate table.
4. The iron-lithium battery system equalization method according to claim 2, characterized in that: The working condition test is carried out at different temperatures, and the temperature range is -10℃~18℃; Preferably, when the model is verified with a test set, the variance of the prediction accuracy is used to determine the single cell SOC prediction error.
5. The iron-lithium battery system equalization method according to claim 1, characterized in that: The SOC estimation of the single cell of the iron-lithium battery system starts when the maximum single cell voltage of the iron-lithium battery system is greater than 3.6V; preferably, the SOC prediction model is imported into the BMS system of the iron-lithium battery system to estimate the SOC of the single cell of the iron-lithium battery system.
6. The iron-lithium battery system equalization method according to claim 1, characterized in that: When the difference is less than the preset threshold, balancing is turned off, and when the difference is greater than the preset threshold, balancing is turned on; the difference is a percentage value.
7. Iron-lithium battery system equalization device, characterized in that: include: The single cell minimum SOC estimation module is used to estimate the single cell SOC of the iron-lithium battery system in real time using the SOC prediction model formed based on the decision tree during the use of the iron-lithium battery system to obtain the single cell minimum SOC; A calculation and judgment module is used to calculate the difference between the target single cell SOC and the minimum single cell SOC and compare it with a preset threshold; The balancing start and stop module is used to control the start or stop of the balancing process of the target single cell battery according to the comparison result of the difference between the target single cell battery SOC and the minimum single cell battery SOC and the preset threshold.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. Computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.