Battery pack health degree judgment method and system and storage medium

Abstract

The embodiment of the invention discloses a battery pack health degree judgment method and system and a storage medium. The health degree judgment method comprises the steps that current data, first characterization data and second characterization data of single batteries are acquired; based on the first characterization data, the anomaly detection model obtains a judgment threshold value; obtaining first health degree information based on the judgment threshold and the second representation data; determining a vehicle state based on the current data; when the vehicle state is a charging state, taking the first health degree information as the health degree information of the battery pack; and when the vehicle state is a driving state, obtaining representation data dispersion based on the representation data, generating second health degree information based on the representation data dispersion and the first health degree information, and taking the second health degree information as the health degree information of the battery pack. Firstly, the vehicle state is distinguished, then the health degree information of the battery pack is obtained according to the anomaly detection model and the representation data dispersion, and the effect of detecting the health degree of the battery pack at any time is achieved.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to the technical field of power battery systems, and specifically to a battery pack health determination method, system, and storage medium. Background Art

[0002] With the widespread application of new energy vehicles in the transportation field, the health status of power batteries, as their core components, has become increasingly important. The health of the battery not only directly affects the service life and performance of the battery system, but is also closely related to the safe operation of the vehicle and the personal safety of passengers. Once the power battery is in an abnormal state, its safety will drop sharply, which will affect the normal use of the vehicle and even cause serious safety accidents, resulting in safety hazards and economic losses.

[0003] Power batteries are usually composed of multiple battery cells connected in series or in parallel. There may be certain differences between each cell, which will significantly affect the overall performance and safety of the battery pack. Since the performance of the battery system does not change linearly during use, it is usually necessary to test the capacity of the battery cells regularly. The actual capacity of each battery cell in the fully charged and fully discharged state is measured through charge and discharge cycles, and the differences between them are compared, and then appropriate treatment is carried out to eliminate hidden dangers.

[0004] However, the fully charged and fully discharged states are ideal states for judging the health status. In actual applications, it is impossible to detect battery cells in an unhealthy state at any time, causing the power battery to work in an abnormal state for a long time, accelerating the reduction of the safety of the power battery. Summary of the invention

[0005] The embodiments of this specification provide a battery pack health determination method, system and storage medium, which first distinguish the vehicle status, and then obtain the battery pack health information based on the abnormal detection model and the discreteness of the characterization data, so as to achieve the effect of detecting the battery pack health at any time, thereby avoiding the battery system from being used in an unhealthy state and causing irreversible damage to the power battery system. The technical solution is as follows: In a first aspect, an embodiment of the present specification provides a method for determining the health of a battery pack, wherein the battery pack is applied to a new energy vehicle and includes a plurality of battery cells, including: Acquire the current data, the first characterization data, and the second characterization data corresponding to each battery cell within a preset time and varying with time; Acquire a determination threshold based on first characterization data corresponding to each battery cell and varying with time within a preset time and an abnormality detection model; Acquire first health information corresponding to each battery cell based on a determination threshold and second characterization data corresponding to each battery cell and changing over time within a preset time; Determine the vehicle state based on the time-varying current data corresponding to each battery cell within a preset time, wherein the vehicle state is a charging state or a driving state; When the vehicle is in a charging state, the first health information corresponding to each battery cell is used as the health information of the battery pack; When the vehicle state is in the driving state, the discreteness of the characterization data corresponding to each battery cell is obtained based on the first characterization data or the second characterization data corresponding to each battery cell and changing with time within a preset time, and the second health information corresponding to each battery cell is generated based on the discreteness of the characterization data corresponding to each battery cell and the first health information, and the second health information corresponding to each battery cell is used as the health information of the battery pack.

[0006] As a preferred solution, the first characterization data includes one or two types of data among SOC data, voltage data, and temperature data, and the second characterization data includes other types of data among SOC data, voltage data, and temperature data except the types included in the first characterization data.

[0007] As a preferred solution, the determination threshold is obtained based on the first characterization data corresponding to each battery cell and the abnormality detection model that changes with time within a preset time, including: Acquire a value coverage interval range of the first characterization data based on the first characterization data corresponding to each battery cell and varying with time within a preset time; Based on the anomaly detection model and the numerical coverage interval range of the first characterization data, a corresponding decision threshold is output.

[0008] As a preferred solution, the method of judging the vehicle state based on the time-varying current data corresponding to each battery cell within a preset time includes: Determine the vehicle status based on the magnitude and change of the current data corresponding to each battery cell over time within a preset time; When all current data are constant and not zero, the vehicle is judged to be in a charging state; When all current data have changed, it is determined that the vehicle state is in the driving state.

[0009] As a preferred solution, the step of obtaining the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell and varying with time within a preset time includes: Get vehicle speed data within a preset time; The discreteness of the characterization data corresponding to each battery cell is obtained based on the vehicle speed data within a preset time and the first characterization data or the second characterization data corresponding to each battery cell and changing with time.

[0010] As a preferred solution, the method of obtaining the discreteness of the characterization data corresponding to each battery cell based on the vehicle speed data within a preset time and the first characterization data or the second characterization data corresponding to each battery cell and varying with time includes: When the vehicle speed data within the preset time is zero, the voltage dispersion of each battery cell is obtained based on the voltage data corresponding to each battery cell that varies with time; When the vehicle speed data within the preset time is not zero, the temperature dispersion of each battery cell is obtained based on the temperature data corresponding to each battery cell that changes with time.

[0011] As a preferred solution, the step of obtaining the voltage dispersion of each battery cell based on the voltage data corresponding to each battery cell that varies with time includes: Based on the voltage data corresponding to each battery cell that changes with time, obtaining the voltage data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time, so as to obtain the voltage dispersion of each battery cell; The step of obtaining the temperature dispersion of each battery cell based on the temperature data corresponding to each battery cell and varying with time includes: Based on the temperature data corresponding to each battery cell that changes with time, the temperature data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time are obtained to obtain the temperature dispersion of each battery cell.

[0012] As a preferred solution, the step of obtaining the voltage dispersion of each battery cell based on the voltage data corresponding to each battery cell that varies with time includes: For any battery cell, based on the voltage data corresponding to each battery cell that changes with time, obtain the change amount of the voltage data corresponding to the battery cell in different unit times to obtain the voltage dispersion of the battery cell; Repeat the above steps until the voltage dispersion of each battery cell is obtained; The step of obtaining the temperature dispersion of each battery cell based on the temperature data corresponding to each battery cell and varying with time includes: For any battery cell, based on the temperature data corresponding to each battery cell that changes with time, obtain the variation of the temperature data corresponding to the battery cell in different unit times to obtain the temperature dispersion of the battery cell; Repeat the above steps until the temperature dispersion of each battery cell is obtained.

[0013] In a second aspect, an embodiment of the present specification provides a battery pack health determination system, the battery pack being applied to a new energy vehicle and comprising a plurality of battery cells, including a data acquisition module, a first processing module, a first determination module, a state recognition module, a second processing module, a second determination module and a health output module; The data acquisition module acquires the current data, the first characterization data, and the second characterization data corresponding to each battery cell over a preset time. The first processing module acquires a determination threshold based on first characterization data corresponding to each battery cell and the abnormality detection model that varies with time within a preset time period; The first judgment module acquires first health information corresponding to each battery cell based on a judgment threshold and second characterization data corresponding to each battery cell and changing with time within a preset time; The state recognition module determines the vehicle state based on the current data corresponding to each battery cell and changing with time within a preset time, and the vehicle state is a charging state or a driving state; The second processing module, when the vehicle state is the driving state, obtains the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell that changes with time within a preset time; The second judgment module generates second health information corresponding to each battery cell based on the discreteness of the characterization data corresponding to each battery cell and the first health information; The health output module uses the first health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in a charging state; and uses the second health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in a driving state.

[0014] In a third aspect, an embodiment of this specification provides an electronic device, comprising a processor and a memory; the processor is connected to the memory; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps described in the first aspect of the above embodiment.

[0015] In a fourth aspect, an embodiment of this specification provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the steps described in the first aspect of the above embodiment.

[0016] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following: after a battery pack has been used for a long time, the attenuation degree of each battery cell will be different, and the health will be completely different. If the attenuation of individual batteries is accelerated, the dynamic changes and discrete states of the characterizing data such as the battery voltage and temperature will be abnormal under the same conditions. Therefore, during the charging and operation of the battery pack, the health of the battery pack can be judged according to the changes in the characterizing data such as the battery cell voltage and temperature, and the abnormal points in the battery pack can be discovered in advance to avoid continuous deterioration of the battery. When the battery pack is not in a fully charged or fully discharged state, the battery health can also be accurately detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flowchart of a method for determining the health of a battery pack provided in an embodiment of this specification.

[0019] Figure 2 It is a voltage data curve of each battery cell at different times.

[0020] Figure 3 It is a structural schematic diagram of a battery pack health determination system provided in an embodiment of this specification.

[0021] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of this specification will be described clearly and completely below in conjunction with the drawings in the embodiments of this specification.

[0023] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0024] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present specification. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described with respect to some examples may be combined in other examples.

[0025] Due to the performance changes of the battery system during use, the existing technology mainly judges the health of the battery based on the characterization data of the battery in the full charge and full discharge state. The battery is rarely in the full charge and full discharge state, so it is impossible to make a timely health judgment to find out whether the battery system is in an unhealthy state. Continuing to use the battery in an unhealthy state will cause irreversible damage to the power battery system. In order to realize the battery health judgment at any time and timely determine the abnormal battery cells, a battery pack health judgment method, system and storage medium are proposed.

[0026] Reference Figure 1 As shown, Figure 1 A flowchart of a method for determining the health of a battery pack provided in an embodiment of this specification may include at least the following steps: Step 202: Obtain the current data, the first characterization data, and the second characterization data corresponding to each battery cell that varies with time within a preset time.

[0027] Illustratively, the first characterization data and the second characterization data are both key information for evaluating battery performance, including electrochemical performance, thermal characteristics, material properties, etc. The first characterization data and the second characterization data are used as reference variables and verification variables, respectively.

[0028] In some embodiments, the first characterization data includes one or two types of data among SOC data, voltage data, and temperature data, and the second characterization data includes other types of data among SOC data, voltage data, and temperature data except the types included in the first characterization data.

[0029] Explanatory, SOC (State of Charge) data is a parameter that describes the ratio between the current remaining power of the battery and its full charge. The correlation changes between the SOC, voltage and temperature of the battery cell are used to determine whether the battery cell is abnormal. These three types of data are key parameters in the battery management system (BMS), which are easy to obtain and highly correlated. Selecting characterization parameters different from the above types and using the same or similar battery health judgment method as this solution also falls within the scope of protection of this solution.

[0030] Exemplarily, the first characterization data is SOC data, and the second characterization data is voltage data and temperature data.

[0031] Step 204 : acquiring a determination threshold based on the first characterization data corresponding to each battery cell and the abnormality detection model that varies with time within a preset time.

[0032] Explanatory, the anomaly detection model is a pre-trained model. The battery management system continuously collects the characterization data of each battery cell during the operation of the battery pack, and establishes a large database based on all the battery data collected by the battery management system, classifies different data types, such as SOC data, voltage data, temperature data, etc., and performs data preprocessing such as naturalization, missing, abnormal, and repeated value processing. Form multiple types of characterization data sequences arranged in time series. Establish a recurrent neural network (RNN) model for long-term sequence prediction, input multiple types of characterization data sequences into the RNN model in batches for training and evaluation, and gradually improve the convergence form of the model. According to the settings when the model is built, the converged model can obtain the change of another type of characterization data based on a certain type of characterization data or the superposition of multiple types of characterization data, that is, the judgment threshold.

[0033] Illustratively, the SOC changes of the battery cells in the battery pack will change with usage and aging, so new data must be continuously collected and the RNN must be trained, which requires constant updating and adjustment to adapt to the performance degradation of the battery.

[0034] In some embodiments, obtaining a determination threshold based on first characterization data corresponding to each battery cell and varying with time within a preset time and an abnormality detection model includes: Acquire a value coverage interval range of the first characterization data based on the first characterization data corresponding to each battery cell and varying with time within a preset time; Based on the anomaly detection model and the numerical coverage interval range of the first characterization data, a corresponding decision threshold is output.

[0035] Illustratively, because the battery pack usage conditions are not full-depth charge and discharge, and because of the special electrochemical characteristics of the battery, this factor needs to be fully considered when using the model, distinguishing between different current sizes, time relationships, SOC usage ranges and other factors, and performing conditional identification and judgment.

[0036] Explanatory, since the attenuation degree of each battery cell is different, the first characterization data corresponding to each battery cell in the preset time is different, and the change interval covered by all SOC data can be determined, such as SOC∈(10,20). The abnormal detection model outputs the change amount of other types of characterization data corresponding to the change interval, such as the change amount of voltage data, the change amount of temperature data, etc.

[0037] Battery cells have different voltage variation characteristics in different SOC ranges. During the battery charging process, as the SOC increases, the terminal voltage usually increases. However, this increase is not linear. In some SOC ranges, the voltage increase may be very slow, while in other ranges it may be very fast. During the battery discharge process, as the SOC decreases, the terminal voltage gradually decreases. Similarly, this decrease is usually nonlinear. However, as the data abundance in the large database increases, the trained anomaly detection model can converge in a smaller range of characterizing data changes, such as when SOC∈(9,12) the voltage data change is 3.0, when SOC∈(12,15) the voltage data change is 3.3, when SOC∈(15,18) the voltage data change is 3.5, when SOC∈(18,21) the voltage data change is 3.6, and the change range covered by all SOC data within the preset time is SOC∈(10,20). The anomaly detection model will output the voltage data change corresponding to multiple different SOC change ranges as the judgment threshold for separate judgments.

[0038] Step 206 : Acquire first health information corresponding to each battery cell based on the determination threshold and the second characterization data corresponding to each battery cell and varying with time within a preset time.

[0039] Illustratively, the second characterization data corresponding to each battery cell within a preset time and changing with time are divided into several segments according to the convergence degree of the abnormality detection model, and are calculated and compared with the corresponding characterization data changes. For example, the health of the battery cell that exceeds the judgment threshold is recorded as abnormal, and the rest is normal. Thus, the first health information corresponding to each battery cell is obtained.

[0040] Explanatory, similarly, the anomaly detection model can also output the temperature data change corresponding to multiple different SOC change intervals as the judgment threshold, so as to make simultaneous judgments in the two dimensions of voltage and temperature, and cross-validate to improve the accuracy of detection.

[0041] Step 208 : judging the vehicle state based on the current data corresponding to each battery cell changing with time within a preset time, where the vehicle state is a charging state or a driving state.

[0042] In some embodiments, judging the vehicle state based on the time-varying current data corresponding to each battery cell within a preset time includes: Determine the vehicle status based on the magnitude and change of the current data corresponding to each battery cell over time within a preset time; When all current data are constant and not zero, the vehicle is judged to be in a charging state; When all current data have changed, it is determined that the vehicle state is in the driving state.

[0043] Explanatory, in the constant current state during charging, the battery characterization data changes relatively steadily, while the characterization data changes complexly in the driving state, so it is necessary to determine the state of the vehicle when the characterization data is collected, and adopt different health detection methods. When all current data are constant and not zero, it can be determined that the vehicle is in a charging state with constant current input. When the current data fluctuates, it can be determined that the vehicle is in a complex and changeable driving state. Judging the vehicle state through current data is the most intuitive and accurate, and can be directly obtained from the battery management system (BMS), and the vehicle state can also be determined by other methods. Since there is also an energy recovery function in hybrid energy vehicles, such as when the vehicle is coasting, decelerating or braking, the motor can be converted into a generator, converting the vehicle's kinetic energy into electrical energy and storing it in the battery, which is also equivalent to the charging state, but not necessarily constant current. If the vehicle state is determined by other methods, there may be problems with incorrect vehicle state judgment.

[0044] Step 210A: when the vehicle is in a charging state, the first health information corresponding to each battery cell is used as the health information of the battery pack; Illustratively, under constant current state, the battery characterization data changes relatively stably. At this time, the abnormal battery cells in the battery pack can be screened accurately enough through the abnormal detection model, so the first health information corresponding to each battery cell is directly used as the health information of the battery pack.

[0045] Step 210B, when the vehicle state is the driving state, obtain the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell that changes with time within a preset time, and generate the second health information corresponding to each battery cell based on the discreteness of the characterization data corresponding to each battery cell and the first health information, and use the second health information corresponding to each battery cell as the health information of the battery pack.

[0046] Illustratively, due to the complex changes in the characterization data under driving conditions, there may be problems of missed screening or wrong screening when screening abnormal battery cells in the battery pack through the abnormal detection model. To ensure the accuracy of the health detection, an additional health detection step is performed. The discreteness of all characterization data within a preset time is used to determine which battery cells may have abnormalities, and cross-compared with the first health information, and the health corresponding to the overlapping abnormal battery cells is recorded as abnormal, and the rest are normal. In this way, the second health information corresponding to each battery cell is obtained, which effectively eliminates the problem of wrong screening. The health corresponding to non-overlapping abnormal battery cells can also be recorded as to be determined, and the focus is on it during subsequent detection to avoid missed screening problems.

[0047] In some embodiments, based on the vehicle speed data within a preset time and the first characterization data or the second characterization data corresponding to each battery cell and varying with time, obtaining the characterization data discreteness corresponding to each battery cell specifically includes: When the vehicle speed data within the preset time is zero, the voltage dispersion of each battery cell is obtained based on the voltage data corresponding to each battery cell that changes with time; When the vehicle speed data within the preset time is not zero, the temperature dispersion of each battery cell is obtained based on the temperature data corresponding to each battery cell that changes with time.

[0048] For illustration, when the vehicle speed is zero, the vehicle may not start, wait for traffic lights, or stop temporarily. At this time, the battery pack is close to no load and is in a static state. The external environment has the least impact on the battery. The discreteness is determined based on the voltage data collected from all battery cells, and a voltage data curve of each battery cell at different times is generated. Please refer to the attached figure. Figure 2 The horizontal axis in the figure is the number of the battery cell, and the vertical axis is the voltage value. Each broken line in the figure is formed by connecting the voltage data of each battery cell at a certain moment. In this way, it is possible to intuitively see which battery cell is discrete from the overall voltage change trend of the battery pack, and determine the abnormal battery cell.

[0049] For illustration, when the vehicle speed is not zero, the vehicle is in a normal driving state. At this time, the battery pack is in a dynamic state, and the external environment has a greater impact on the battery. The discreteness is judged based on the temperature data collected from all battery cells, and a similar Figure 2 The temperature data curve of each battery cell at different times can be directly seen which battery cell is more discrete than the temperature change trend of the battery pack as a whole, and the abnormal battery cell can be identified.

[0050] In some embodiments, obtaining the voltage dispersion of each battery cell based on the voltage data corresponding to each battery cell that varies with time includes: Based on the voltage data corresponding to each battery cell that changes with time, obtaining the voltage data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time, so as to obtain the voltage dispersion of each battery cell; The temperature dispersion of each battery cell is obtained based on the temperature data corresponding to each battery cell that varies with time, including: Based on the temperature data corresponding to each battery cell that changes with time, the temperature data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time are obtained to obtain the temperature dispersion of each battery cell.

[0051] Explanatory, with Figure 2 Take this as an example to illustrate, horizontally compare the voltage changes of each battery cell on two adjacent broken lines. Ideally, the voltage changes of each battery cell should be consistent under the same external state and at the same time. The boxed part of the figure clearly shows that the No. 12 battery cell is abnormal, and the voltage change at adjacent moments is much greater than that of other battery cells. The ratio of the difference between the voltage change of each battery cell and the average voltage change to the average voltage change is taken as the voltage dispersion corresponding to each battery cell. A battery cell with a voltage dispersion greater than the set value can be determined as abnormal health. The horizontal comparison of temperature dispersion is similar and will not be repeated.

[0052] In some other embodiments, the voltage dispersion of each battery cell is obtained based on the voltage data corresponding to each battery cell that varies with time, including: For any battery cell, based on the voltage data corresponding to each battery cell that changes with time, obtain the change amount of the voltage data corresponding to the battery cell in different unit times to obtain the voltage dispersion of the battery cell; Repeat the above steps until the voltage dispersion of each battery cell is obtained; The temperature dispersion of each battery cell is obtained based on the temperature data corresponding to each battery cell that varies with time, including: For any battery cell, based on the temperature data corresponding to each battery cell that changes with time, obtain the variation of the temperature data corresponding to the battery cell in different unit times to obtain the temperature dispersion of the battery cell; Repeat the above steps until the temperature dispersion of each battery cell is obtained.

[0053] Explanatory, also with Figure 2 Take an example to illustrate, vertically compare the difference between the voltage changes of the same battery cell at different times, that is, the difference between the spacings of the corresponding positions of the same battery cell on the adjacent broken lines. Ideally, the voltage changes of each battery cell will not mutate under the same external state and at the same time. The difference between the voltage change of any battery cell in different unit time and the average voltage change of the battery cell in the preset time is taken as the ratio of the average voltage change as the voltage dispersion corresponding to each battery cell. A battery cell with a voltage dispersion greater than the set value can be determined as abnormal health. The vertical comparison of temperature dispersion is similar and will not be repeated.

[0054] Illustratively, all characterization data within a preset time can be compared horizontally and vertically simultaneously, and abnormal battery cells determined by the two methods can be cross-compared to identify unhealthy battery cells in the battery pack as comprehensively as possible, and further cross-verification can be performed to eliminate misscreening problems.

[0055] The technical solution of the present invention is not limited to the field of vehicle energy, but also includes all fields where power batteries can be used, such as energy storage, ships, photovoltaics, etc. This method can be used to judge the health of batteries.

[0056] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0057] See next Figure 3 , Figure 3 A schematic diagram of the structure of a battery pack health determination system provided in an embodiment of this specification is shown.

[0058] like Figure 3 As shown, a battery pack health judgment system 300, the battery pack is applied to a new energy vehicle and includes a plurality of battery cells, including a data acquisition module 301, a first processing module 302, a first judgment module 303, a state recognition module 304, a second processing module 305, a second judgment module 306 and a health output module 307; The data acquisition module 301 acquires the current data, the first characterization data, and the second characterization data corresponding to each battery cell over a preset time. The first processing module 302 acquires a determination threshold based on first characterization data corresponding to each battery cell and the abnormality detection model that varies with time within a preset time period; The first judgment module 303 acquires first health information corresponding to each battery cell based on a judgment threshold and second characterization data corresponding to each battery cell and changing with time within a preset time. A state identification module 304 determines a vehicle state based on the current data corresponding to each battery cell over time within a preset time, and the vehicle state is a charging state or a driving state; The second processing module 305, when the vehicle state is the driving state, obtains the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell that changes with time within a preset time; A second judgment module 306 generates second health information corresponding to each battery cell based on the discreteness of the characterization data corresponding to each battery cell and the first health information; The health output module 307 uses the first health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in the charging state; and uses the second health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in the driving state.

[0059] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the health judgment system 300, since it is basically similar to the embodiment of the health judgment method, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the health judgment method.

[0060] See also Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0061] like Figure 4 As shown, the electronic device 400 may include: at least one processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0062] The communication bus 402 may be used to realize the connection and communication among the above-mentioned components.

[0063] The user interface 403 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0064] The network interface 404 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0065] Among them, the processor 401 may include one or more processing cores. The processor 401 uses various interfaces and lines to connect the various parts of the entire electronic device 400, and executes various functions and processes data of the electronic device 400 by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the processor 401 can be implemented in at least one hardware form of DSP, FPGA, and PLC. The processor 401 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 401, and it can be implemented separately through a chip.

[0066] Among them, the memory 405 may include RAM or ROM. Optionally, the memory 405 includes a non-transitory computer-readable medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be at least one storage device located away from the aforementioned processor 401. The memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a health judgment application. The processor 401 can be used to call the health judgment application stored in the memory 405 and execute the steps of the health judgment method mentioned in the above-mentioned embodiment.

[0067] The embodiments of this specification also provide a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes one or more steps in the above-mentioned health determination method embodiment. If the component modules of the above-mentioned electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0068] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by the computer or a data storage device such as a server or data center that contains one or more available media integrations. Available media may be magnetic media (eg, floppy disks, hard disks, tapes), optical media (eg, digital versatile discs (DVD)), or semiconductor media (eg, solid state drives (SSD)).

[0069] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0070] The above embodiments are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. A method for judging the health of a battery pack, wherein the battery pack is applied to a new energy vehicle and comprises a plurality of battery cells, characterized in that: include: Acquire the current data, the first characterization data, and the second characterization data corresponding to each battery cell within a preset time and varying with time; Acquire a determination threshold based on first characterization data corresponding to each battery cell and varying with time within a preset time and an abnormality detection model; Acquire first health information corresponding to each battery cell based on a determination threshold and second characterization data corresponding to each battery cell and changing over time within a preset time; Determine the vehicle state based on the time-varying current data corresponding to each battery cell within a preset time, wherein the vehicle state is a charging state or a driving state; When the vehicle is in a charging state, the first health information corresponding to each battery cell is used as the health information of the battery pack; When the vehicle state is in the driving state, the discreteness of the characterization data corresponding to each battery cell is obtained based on the first characterization data or the second characterization data corresponding to each battery cell and changing with time within a preset time, and the second health information corresponding to each battery cell is generated based on the discreteness of the characterization data corresponding to each battery cell and the first health information, and the second health information corresponding to each battery cell is used as the health information of the battery pack.

2. A method for determining the health of a battery pack according to claim 1, characterized in that: The first characterization data includes one or two types of data among SOC data, voltage data, and temperature data, and the second characterization data includes other types of data among SOC data, voltage data, and temperature data except the types included in the first characterization data.

3. A method for determining the health of a battery pack according to claim 2, characterized in that: The method of obtaining the determination threshold based on the first characterization data corresponding to each battery cell and changing with time within a preset time and the abnormality detection model includes: Acquire a value coverage interval range of the first characterization data based on the first characterization data corresponding to each battery cell and varying with time within a preset time; Based on the anomaly detection model and the numerical coverage interval range of the first characterization data, a corresponding decision threshold is output.

4. A method for determining the health of a battery pack according to claim 3, characterized in that: The method of judging the vehicle state based on the current data corresponding to each battery cell and varying with time within a preset time includes: Determine the vehicle status based on the magnitude and change of the current data corresponding to each battery cell over time within a preset time; When all current data are constant and not zero, the vehicle is judged to be in a charging state; When all current data have changed, it is determined that the vehicle state is in the driving state.

5. A method for determining the health of a battery pack according to claim 4, characterized in that: The method of obtaining the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell and changing with time within a preset time includes: Get vehicle speed data within a preset time; The discreteness of the characterization data corresponding to each battery cell is obtained based on the vehicle speed data within a preset time and the first characterization data or the second characterization data corresponding to each battery cell and changing with time.

6. A method for determining the health of a battery pack according to claim 5, characterized in that: The method of obtaining the discreteness of the characterization data corresponding to each battery cell based on the vehicle speed data within a preset time and the first characterization data or the second characterization data corresponding to each battery cell and changing with time includes: When the vehicle speed data within the preset time is zero, the voltage dispersion of each battery cell is obtained based on the voltage data corresponding to each battery cell that varies with time; When the vehicle speed data within the preset time is not zero, the temperature dispersion of each battery cell is obtained based on the temperature data corresponding to each battery cell that changes with time.

7. A method for determining the health of a battery pack according to claim 6, characterized in that: The step of obtaining the voltage dispersion of each battery cell based on the voltage data corresponding to each battery cell and varying with time includes: Based on the voltage data corresponding to each battery cell that changes with time, obtaining the voltage data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time, so as to obtain the voltage dispersion of each battery cell; The step of obtaining the temperature dispersion of each battery cell based on the temperature data corresponding to each battery cell and varying with time includes: Based on the temperature data corresponding to each battery cell that changes with time, the temperature data changes corresponding to all battery cells corresponding to multiple unit time lengths within a preset time are obtained to obtain the temperature dispersion of each battery cell.

8. A method for determining the health of a battery pack according to claim 6, characterized in that: The step of obtaining the voltage dispersion of each battery cell based on the voltage data corresponding to each battery cell and varying with time includes: For any battery cell, based on the voltage data corresponding to each battery cell that changes with time, obtain the change amount of the voltage data corresponding to the battery cell in different unit times to obtain the voltage dispersion of the battery cell; Repeat the above steps until the voltage dispersion of each battery cell is obtained; The step of obtaining the temperature dispersion of each battery cell based on the temperature data corresponding to each battery cell and varying with time includes: For any battery cell, based on the temperature data corresponding to each battery cell that changes with time, obtain the variation of the temperature data corresponding to the battery cell in different unit times to obtain the temperature dispersion of the battery cell; Repeat the above steps until the temperature dispersion of each battery cell is obtained.

9. A battery pack health judgment system, wherein the battery pack is applied to a new energy vehicle and comprises a plurality of battery cells, characterized in that: It includes a data acquisition module, a first processing module, a first judgment module, a state recognition module, a second processing module, a second judgment module and a health output module; The data acquisition module acquires the current data, the first characterization data, and the second characterization data corresponding to each battery cell over a preset time. The first processing module acquires a determination threshold based on first characterization data corresponding to each battery cell and the abnormality detection model that varies with time within a preset time period; The first judgment module obtains first health information corresponding to each battery cell based on a judgment threshold and second characterization data corresponding to each battery cell and changing with time within a preset time; The state recognition module determines the vehicle state based on the current data corresponding to each battery cell and changing with time within a preset time, and the vehicle state is a charging state or a driving state; The second processing module, when the vehicle state is the driving state, obtains the discreteness of the characterization data corresponding to each battery cell based on the first characterization data or the second characterization data corresponding to each battery cell that changes with time within a preset time; The second judgment module generates second health information corresponding to each battery cell based on the discreteness of the characterization data corresponding to each battery cell and the first health information; The health output module uses the first health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in a charging state; and uses the second health information corresponding to each battery cell as the health information of the battery pack when the vehicle is in a driving state.

10. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the steps of a battery pack health determination method as described in any one of claims 1-8.

Images