Method for predicting battery state of health of vehicle, and electronic device and storage medium

Abstract

A method for predicting the battery state of health of a vehicle, and an electronic device and a storage medium. The method comprises: acquiring vehicle parameter information of a vehicle at an nth moment (S110), wherein the vehicle parameter information comprises operating parameters of the vehicle and parameter information of a battery pack, and n is an integer greater than or equal to 1; acquiring multi-dimensional feature data at an (n-1)th moment, wherein the multi-dimensional feature data comprises battery state-of-health data at the (n-1)th moment (S120); on the basis of the vehicle parameter information at the nth moment and the multi-dimensional feature data at the (n-1)th moment, calculating multi-dimensional feature data at the nth moment (S130); and on the basis of the multi-dimensional feature data at the nth moment and the battery state-of-health data at the (n-1)th moment, determining the battery state of health at the nth moment on the basis of a preset prediction model (S140).

Description

Predictive methods for vehicle battery health, electronic devices, and storage media

[0001] This application claims priority to Chinese Patent Application No. 202510425713.0, filed with the Chinese Patent Office on April 3, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of battery testing technology, such as a method for predicting the health of a vehicle battery, electronic devices, and storage media. Background Technology

[0003] Batteries are widely used in automobiles, electronic mobile devices, and other fields. Due to the cyclic use of batteries, irreversible physical or chemical changes occur inside the battery, and the battery's health gradually declines with use. Therefore, to ensure the safe operation of batteries, it is necessary to test their health. Technical issues

[0004] The battery testing technologies in this field have poor predictive ability for battery health and low accuracy. Solution

[0005] According to one aspect of this application, a method for predicting the health of a vehicle battery is provided, comprising:

[0006] Obtain the vehicle parameter information at time n; the vehicle parameter information includes the vehicle's operating parameters and the battery pack's parameter information; n is an integer greater than or equal to 1;

[0007] Obtain multidimensional feature data at time n-1, including battery health data at time n-1;

[0008] Calculate the multidimensional feature data at time n based on the vehicle parameter information at time n-1 and the multidimensional feature data at time n-2.

[0009] Based on the multidimensional feature data at time n and the battery health data at time n-1, the battery health at time n is determined using a pre-defined prediction model.

[0010] According to another aspect of this application, an electronic device is provided, comprising:

[0011] At least one processor; and

[0012] A memory that is communicatively connected to at least one processor; wherein,

[0013] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the vehicle battery health prediction method in any embodiment of this application.

[0014] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the vehicle battery health prediction method in any embodiment of this application. Beneficial effects

[0015] In some embodiments of this application, by acquiring vehicle parameter information at time n and multidimensional feature data at time n-1, both vehicle operating parameters and battery pack parameter information can be obtained simultaneously, providing more comprehensive data. Therefore, this application exhibits better accuracy and precision in predicting battery health. Furthermore, this application is not limited to any type of battery when predicting battery health and is applicable to various battery types such as lithium iron phosphate, ternary lithium batteries, lithium iron manganese oxide, and lithium cobalt oxide, demonstrating high applicability. Attached Figure Description

[0016] Figure 1 is a flowchart of a method for predicting the health of a vehicle battery according to some implementations of this application;

[0017] Figure 2 is a flowchart of another method for predicting vehicle battery health according to some implementations of this application;

[0018] Figure 3 is a flowchart of an implementation method of S132 provided according to some implementation methods of this application;

[0019] Figure 4 is a flowchart of another method for predicting vehicle battery health according to some implementations of this application;

[0020] Figure 5 is a flowchart of an implementation method of S135 provided according to some implementation methods of this application;

[0021] Figure 6 is a flowchart of another method for predicting vehicle battery health according to some implementations of this application;

[0022] Figure 7 is a flowchart of another method for predicting vehicle battery health according to some implementations of this application;

[0023] Figure 8 is a schematic diagram of the structure of an electronic device provided according to some implementations of this application. Embodiments of the present invention

[0024] This application provides a method for predicting vehicle battery health. Figure 1 is a flowchart of a method for predicting vehicle battery health provided in this application. Referring to Figure 1, the method includes:

[0025] S110. Obtain the vehicle parameter information at time n.

[0026] Vehicle parameter information includes vehicle operating parameters and battery pack parameters. Vehicle operating parameters may include data such as mileage and operating time. Battery pack parameters may include information such as charging temperature, charge level, and voltage. n is an integer greater than or equal to 1. The nth time is the time when the vehicle parameter information is obtained for the nth time.

[0027] For example, information can be proactively acquired at various times when battery health prediction is needed, or it can be automatically acquired every 500 kilometers (km) or every month of vehicle operation for subsequent battery health prediction. Vehicle parameter information can be obtained through a cloud server. The cloud server provides powerful computing capabilities, and vehicle parameter information can be stored in the cloud server in the form of State of Health (SOH) tags, and multi-dimensional feature data can be calculated through the cloud server. Therefore, SOH tags can be used to reflect detailed vehicle parameter information. When extracting or processing data, data can be collected by extracting SOH tags, resulting in more efficient data collection.

[0028] S120. Obtain the multidimensional feature data at time n-1, including the battery health data at time n-1.

[0029] Multidimensional feature data can be calculated from vehicle parameter information, and the multidimensional feature data at time n-1 can be used to reflect the vehicle parameter information at time n-1. For example, the multidimensional feature data at time n-1 can be obtained from the vehicle parameter information at time n-1 and the multidimensional feature data at time n-2.

[0030] For example, the battery health data at time 0 can be a preset initial health value. If the battery is brand new at this time, the preset initial health value can be 100%.

[0031] S130. Calculate the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1.

[0032] The multidimensional feature data at time n-1 includes the battery health data at time n-1. The multidimensional feature data at time n can be calculated based on the vehicle parameter information at time n and the multidimensional feature data at time n-1. It should be noted that the multidimensional feature data at time n calculated in this step does not include the battery health data at time n.

[0033] S140. Based on the multidimensional feature data at time n and the battery health data at time n-1, determine the battery health at time n based on the preset prediction model.

[0034] In some embodiments, the preset prediction model includes models such as extreme gradient boosting (XGBoost) and gradient boosting tree (GBT). Multidimensional feature data and battery health data serve as inputs to the preset prediction model, while battery health is the output.

[0035] After inputting the multidimensional feature data at time n and the battery health data at time n-1 into the preset prediction model, the preset prediction model can output the battery health at time n. The data input to the preset prediction model includes the vehicle's operating parameters and battery pack parameter information at time n, as well as the battery health data at time n-1. This allows the preset prediction model to generate battery health data based on rich data. Because of the diverse input data, the preset prediction model can perform more comprehensive data processing, thereby improving the accuracy of the output data.

[0036] The technical solution provided in this application, by acquiring vehicle parameter information at time n and multi-dimensional feature data at time n-1, can simultaneously obtain vehicle operating parameters and battery pack parameter information, providing more comprehensive data information. Therefore, this application has better accuracy and precision in predicting battery health. Furthermore, this application is not limited to battery type when predicting battery health and is applicable to various types of batteries such as lithium iron phosphate, ternary lithium batteries, lithium iron manganese oxide, and lithium cobalt oxide, exhibiting high applicability.

[0037] Based on the above embodiments, optionally, S110, obtaining the vehicle parameter information at time n, includes: obtaining the vehicle's operating parameters and battery pack parameter information at time n. The vehicle's operating parameters include: the vehicle's mileage and operating time. The battery pack parameter information includes: the battery pack's real-time charging temperature, the battery pack's real-time fast charging capacity, the battery pack's real-time slow charging capacity, and the voltage of all individual cells.

[0038] The vehicle's mileage is the total distance traveled by the vehicle after it has been put into operation. The vehicle's operating time is the continuous operating time after the vehicle is started.

[0039] For example, there can be multiple sampling points between different times, and the vehicle collects vehicle parameter information at each sampling point. For instance, the vehicle can collect vehicle parameter information every 10 seconds (s). When it is necessary to obtain the vehicle's mileage, the mileage can be obtained through the cumulative mileage field. When it is necessary to obtain the vehicle's running time, the running time can be obtained through the running time of the vehicle at each sampling point.

[0040] Therefore, the vehicle's mileage is the sum of the mileage between all sampling points, and the vehicle's running time is the sum of the running time between each sampling point.

[0041] The real-time charging temperature of the battery pack is the temperature of the battery pack collected at each sampling point during charging. The real-time fast charging amount of the battery pack is the sum of the fast charging amounts at each sampling point during charging. The real-time slow charging amount of the battery pack is the sum of the slow charging amounts at each sampling point during charging. The voltage of each individual cell is the voltage of each individual cell within the battery pack when it is fully charged.

[0042] This application embodiment provides richer data for predicting battery health by acquiring vehicle operating parameters and battery pack parameter information, greatly improving the accuracy of battery health prediction and achieving better prediction results.

[0043] Based on the above embodiments, optionally, S130, calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1 includes: calculating the vehicle mileage data at time n based on the vehicle's mileage at time n and the vehicle mileage data from the multidimensional feature data at time n-1.

[0044] In some embodiments, the multidimensional feature data includes vehicle mileage data, which may include the vehicle's mileage and average daily mileage. Both the vehicle's mileage and average daily mileage are negatively correlated with battery health. For example, the higher the vehicle's mileage and the higher the average daily mileage, the lower the battery health.

[0045] Figure 2 is a flowchart of another method for predicting vehicle battery health provided in an embodiment of this application. Referring to Figure 2, based on the above embodiments, optionally, the vehicle mileage data at time n is calculated based on the vehicle mileage data at time n-1 and the multi-dimensional feature data at time n-1, including:

[0046] S131. Obtain the vehicle's mileage at time n-1.

[0047] S132. Based on the vehicle's mileage at time n and time n-1, calculate the vehicle's mileage between time n and time n-1 and the average daily mileage.

[0048] In some embodiments, vehicle mileage data includes mileage traveled and average daily mileage. The mileage traveled between time n and time n-1 is obtained by subtracting the mileage traveled at time n-1 from the mileage traveled at time n-1. The average daily mileage traveled between time n and time n-1 is then obtained by dividing the mileage traveled between time n and time n-1 by the total number of days between time n and time n-1.

[0049] Figure 3 is a flowchart of an implementation method of S132 provided in an embodiment of this application. Referring to Figure 3, based on the above embodiments, optionally, S132, calculating the vehicle's mileage and average daily mileage between time n and time n-1 based on the vehicle's mileage at time n and time n-1, includes:

[0050] S1321. Calculate the vehicle's mileage between time n and time n-1 based on the difference between the vehicle's mileage at time n and time n-1.

[0051] The mileage traveled by the vehicle at time n is the total mileage traveled by the vehicle from time 0 to time n, and the mileage traveled by the vehicle at time n-1 is the total mileage traveled by the vehicle from time 0 to time n-1. By subtracting the mileage traveled by the vehicle at time n from the mileage traveled by the vehicle at time n-1, the mileage traveled by the vehicle between time n and time n-1 can be obtained.

[0052] S1322. Based on the time difference between time n and time n-1, calculate the cumulative number of days for the vehicle between time n and time n-1.

[0053] The two sampling times can be any times. By comparing the difference between time n and time n-1, and converting the difference to 24-hour (h) format, the cumulative number of days between time n and time n-1 can be obtained.

[0054] S1323. Calculate the average daily mileage based on the ratio of mileage driven to the number of days accumulated.

[0055] The average daily mileage can be obtained by dividing the distance traveled by the vehicle between time n and time n-1 by the cumulative number of days. The average daily mileage is the vehicle's average mileage per day between time n and time n-1.

[0056] This application realizes the calculation of vehicle mileage data by acquiring and calculating mileage and average daily mileage, thus enriching the multidimensional feature data.

[0057] Based on the above embodiments, optionally, S130, calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1, further includes: calculating the vehicle operation data at time n based on the vehicle's running time at time n and the vehicle operation data of the multidimensional feature data at time n-1.

[0058] In some embodiments, the multidimensional feature data also includes vehicle operation data, which may include the vehicle's operating time. Vehicle operating time is the time between two points in time when the vehicle starts up. That is, the longer the vehicle's operating time, the longer the start-up time, and the more electricity it consumes. Therefore, an increase in vehicle operating time can also affect battery health.

[0059] Figure 4 is a flowchart of another method for predicting vehicle battery health provided in an embodiment of this application. Referring to Figure 4, based on the above embodiments, optionally, the vehicle operation data at time n is calculated based on the vehicle's running time at time n and the vehicle operation data of the multidimensional feature data at time n-1, including:

[0060] S133. Obtain the vehicle's running time at time n-1.

[0061] S134. Based on time n and time n-1, calculate the cumulative number of days for the vehicle between time n and time n-1.

[0062] S135. Based on the vehicle's running time at time n and time n-1 and the cumulative number of days between time n and time n-1, calculate the percentage of daily non-running time of the vehicle between time n and time n-1.

[0063] In some embodiments, vehicle operation data includes the percentage of time not running each day. The running time of the vehicle between time n and time n-1 is obtained by subtracting the running time of the vehicle at time n-1 from the running time at time n-1. The non-running time of the vehicle between time n and time n-1 is obtained by subtracting the running time between time n and time n-1 from the total time between time n and time n-1. The percentage of time not running each day is obtained by dividing the non-running time by the total accumulated time of the days. The percentage of time not running each day is the ratio of the vehicle's non-running time to the total time of the day.

[0064] The technical solution provided in this application does not limit the execution order of steps S131 and S133. After step S120, step S131 can be executed first, or step S133 can be executed first.

[0065] Figure 5 is a flowchart of an implementation method of S135 provided in an embodiment of this application. Referring to Figure 5, based on the above embodiments, optionally, S135, calculating the percentage of daily non-running time of the vehicle between time n and time n-1 based on the vehicle's running time at time n and time n-1 and the cumulative number of days between time n and time n-1, includes:

[0066] S1351. Calculate the vehicle's non-running time based on the difference between the total duration corresponding to the accumulated days and the total duration of the vehicle's running time between time n and time n-1.

[0067] The running time of the vehicle at time n is the total running time of the vehicle from time 0 to time n, and the running time of the vehicle at time n-1 is the total running time of the vehicle from time 0 to time n-1. By subtracting the running time of the vehicle at time n from the running time of the vehicle at time n-1, the running time of the vehicle between time n and time n-1 can be obtained.

[0068] The vehicle's non-running time can be obtained by subtracting the total duration corresponding to the cumulative number of days between time n and time n-1 from the total running time.

[0069] S1352. Calculate the percentage of daily non-running time of the vehicle between time n and time n-1 based on the ratio of the vehicle's non-running time to the cumulative number of days.

[0070] The percentage of time a vehicle is not in operation between time n and time n-1 can be obtained by dividing the total time corresponding to the cumulative number of days between time n and time n-1.

[0071] Based on the above embodiments, optionally, S130, calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1, further includes: calculating the battery charging data at time n based on the real-time fast charging amount of the battery pack, the real-time slow charging amount of the battery pack, the voltage of all individual cells, the real-time charging temperature of the battery pack from time n-1 to time n, and the battery charging data of the multidimensional feature data at time n-1.

[0072] In some embodiments, the multidimensional feature data also includes battery charging data. As the number of vehicle charging cycles increases, different charging methods and temperatures can lead to varying degrees of decrease in battery health. Therefore, it is necessary to monitor data such as the battery pack's charging amount and charging temperature to obtain a more accurate battery health assessment using battery charging data.

[0073] Figure 6 is a flowchart of another method for predicting vehicle battery health provided in an embodiment of this application. Referring to Figure 6, based on the above embodiments, optionally, the battery charging data at time n is calculated based on the real-time fast charging amount of the battery pack at time n, the real-time slow charging amount of the battery pack, the voltage of all individual cells, the real-time charging temperature of the battery pack from time n-1 to time n, and the battery charging data of the multi-dimensional feature data at time n-1, including:

[0074] S136. Obtain the voltage of all individual cells in the battery charging data at time n-1.

[0075] When obtaining the voltage of all individual cells, it is only necessary to obtain the voltage of each individual cell inside the battery pack when the battery pack is fully charged.

[0076] S137. Based on the real-time fast charging amount and the real-time slow charging amount of the battery pack at time n, generate the total fast charging amount and the total slow charging amount of the battery pack at time n.

[0077] In some embodiments, battery charging data includes: the total fast charging capacity of the battery pack, the total slow charging capacity of the battery pack, the average charging temperature, and the difference between the maximum and minimum voltages of all individual cells.

[0078] The real-time fast charging capacity of the battery pack at time n is the total amount of electricity charged by the battery pack via fast charging up to and including time n. The real-time slow charging capacity of the battery pack at time n is the total amount of electricity charged by the battery pack via slow charging up to and including time n. Therefore, the real-time fast charging capacity of the battery pack at time n is the same as the total fast charging capacity of the battery pack at time n; the real-time slow charging capacity of the battery pack at time n is the same as the total slow charging capacity of the battery pack at time n.

[0079] S138. Based on the sum of the real-time charging temperatures of the battery pack from time n-1 to time n, divide by the number of temperature samplings between time n-1 and time n to calculate the average charging temperature of the battery pack between time n and time n-1.

[0080] In some embodiments, multiple sampling points may be available between time n-1 and time n. For example, the vehicle may collect temperature data every 10 seconds. The average charging temperature of the battery pack between time n and time n-1 can be obtained by summing the real-time charging temperatures of each sampling and dividing by the total number of temperature samples.

[0081] S139. Based on the voltages of all individual cells at time n and time n-1, calculate the difference between the maximum and minimum voltages of all individual cells at each time between time n and time n-1; take the average of the differences between the maximum and minimum voltages of all individual cells at all times as the voltage difference.

[0082] Ideally, when a battery pack is fully charged, the voltage of each individual cell should remain the same. If the voltage of a single cell changes, its capacity may have changed. Therefore, calculating the difference between the maximum and minimum voltages of all individual cells can reflect the battery health of the battery pack.

[0083] For example, the voltage of all individual cells at time n-1 can be expressed as: The voltage of all individual cells at time n can be expressed as: Where m represents the number of individual cells; calculate the difference between the maximum and minimum voltages of all individual cells at each time step. For example, for time step k (k takes the value n-1 or n), calculate the difference between the maximum and minimum voltages of all individual cells at that time, denoted as . Then, calculate the average of the differences between the maximum and minimum voltages of all individual cells between time n-1 and time n to obtain the voltage difference. .

[0084] The technical solutions provided in this application do not limit the execution order of steps S131, S133, and S136. After step S120, step S131 may be executed first, step S133 may be executed first, or step S136 may be executed first.

[0085] Figure 7 is a flowchart of another method for predicting vehicle battery health provided in an embodiment of this application. Referring to Figure 7, based on the above embodiments, optionally, before obtaining the vehicle parameter information at time n in step S110, the following steps are included:

[0086] S150. Obtain the multidimensional feature data of the vehicle from time 0 to time n-1, and construct a multidimensional feature dataset.

[0087] Table 1 is a summary table of a multidimensional feature dataset provided in the embodiments of this application. Referring to Table 1, the driving mileage is used to represent the total driving mileage of the vehicle, the interval driving mileage is used to represent the driving mileage of the vehicle between two time points, the daily average mileage is used to represent the daily average driving mileage, the cumulative number of days is used to represent the cumulative number of days between the current time point and the initial time point, the interval cumulative number of days is used to represent the cumulative number of days between two time points, the non-running percentage is used to represent the percentage of daily non-running time between two time points, the fast charging amount is used to represent the total fast charging amount, the slow charging amount is used to represent the total slow charging amount, the voltage difference is used to represent the difference between the maximum and minimum voltages of all individual batteries between each time point, the temperature is used to represent the average charging temperature between two time points, the battery health at the previous time point is used to represent the battery health at the previous time point, and the battery health at the current time point is used to represent the battery health at the current time point.

[0088]

[0089] For example, feature engineering can be used to construct multidimensional feature datasets. Feature engineering can process and transform the original vehicle parameter information to extract features that are valuable for training and prediction of the preset prediction model, and generate multidimensional feature data to improve the performance and effectiveness of the model.

[0090] S160. Train a preset prediction model based on the multidimensional feature dataset.

[0091] A preset prediction model can be used to calculate battery health. Before running the preset prediction model, it can be trained. For example, multidimensional feature data can be aggregated into a multidimensional feature dataset, and then the preset prediction model can be trained using this dataset to improve its prediction accuracy, enabling it to output highly accurate data. After the preset prediction model is trained, the multidimensional feature data at time n and the battery health data at time n-1 can be input into the preset prediction model, which can then output the battery health at time n.

[0092] The multidimensional feature dataset provided in this application embodiment is not limited to the multidimensional feature data provided in Table 1. In other embodiments, it may also include multidimensional feature data such as the average vehicle speed and the average battery pack voltage between two time points. By adding multidimensional feature data and training a preset prediction model, the prediction accuracy of the preset prediction model can be improved, enabling the prediction model to output a battery health value with high accuracy when predicting battery health.

[0093] Based on the above embodiments, optionally, S150, obtaining the multidimensional feature data of the vehicle from time 0 to time n-1 includes: obtaining the multidimensional feature data of at least two vehicles from time 0 to time n-1; wherein, the battery health data at time 0 is a preset initial health value.

[0094] For example, during model training, in order to maximize the accuracy of the model's prediction results, multidimensional feature data of multiple vehicles can be input into the preset prediction model for model training. Through this setting, multidimensional feature data of different vehicles under different driving environments can be calculated and collected, so that the preset prediction model provided in this application embodiment can accurately predict battery health under different driving scenarios and has a good prediction effect.

[0095] For example, the battery health data in the multidimensional feature data at time 0 can be a preset initial health value. The preset initial health value is used to represent the initial health of the battery; for example, the preset initial health value can be 100%.

[0096] Figure 8 illustrates a schematic diagram of an electronic device that can be used to implement embodiments of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are illustrative.

[0097] As shown in Figure 8, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0098] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0099] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, for example, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a method for predicting the health of a vehicle battery.

[0100] In some embodiments, a method for predicting vehicle battery health may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for predicting vehicle battery health described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a method for predicting vehicle battery health by any other suitable means (e.g., by means of firmware).

[0101] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a memory system, at least one input device, and at least one output device, and transferring data and instructions to the memory system, the at least one input device, and the at least one output device.

[0102] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0103] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. Examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disc-read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT), liquid crystal display (LCD), or monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0105] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0106] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0107] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the multiple steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved.

Claims

1. A method for predicting the health of a vehicle battery, comprising: Obtain the vehicle parameter information at time n; The vehicle parameter information includes the vehicle's operating parameters and the battery pack's parameter information; n is an integer greater than or equal to 1; Obtain multidimensional feature data at time n-1, wherein the multidimensional feature data includes battery health data at time n-1; Calculate the multidimensional feature data at time n based on the vehicle parameter information at time n-1 and the multidimensional feature data at time n-2. Based on the multidimensional feature data at time n and the battery health data at time n-1, the battery health at time n is determined using a preset prediction model.

2. The method for predicting vehicle battery health according to claim 1, wherein, The acquisition of vehicle parameter information at time n includes: Obtain the vehicle's operating parameters and the battery pack's parameter information at time n; the vehicle's operating parameters include: the vehicle's mileage and the vehicle's operating time; the battery pack's parameter information includes: the battery pack's real-time charging temperature, the battery pack's real-time fast charging capacity, the battery pack's real-time slow charging capacity, and the voltage of all individual cells.

3. The method for predicting vehicle battery health according to claim 2, wherein, The step of calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1 includes: The vehicle mileage data at time n is calculated based on the vehicle mileage at time n and the vehicle mileage data of the multidimensional feature data at time n-1.

4. The method for predicting vehicle battery health according to any one of claims 1-3, wherein, The calculation of the vehicle mileage data at time n based on the vehicle's mileage at time n and the multidimensional feature data at time n-1 includes: The mileage of the vehicle at time n-1 is obtained. Based on the vehicle's mileage at time n and time n-1, calculate the vehicle's mileage and average daily mileage between time n and time n-1; the vehicle mileage data includes the mileage and the average daily mileage.

5. The method for predicting vehicle battery health according to claim 4, wherein, The step of calculating the vehicle's mileage and average daily mileage between time n and time n-1 based on the vehicle's mileage at time n and time n-1 includes: The vehicle's mileage between time n and time n-1 is calculated based on the difference between the vehicle's mileage at time n and time n-1. Based on the time difference between time n and time n-1, calculate the cumulative number of days for the vehicle between time n and time n-1; The average daily mileage is calculated based on the ratio of the mileage driven to the cumulative number of days.

6. The method for predicting vehicle battery health according to claim 1 or 2, wherein, The step of calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1 further includes: The vehicle operation data at time n is calculated based on the vehicle's running time at time n and the vehicle operation data of the multidimensional feature data at time n-1.

7. The method for predicting vehicle battery health according to claim 6, wherein, The calculation of the vehicle operation data at time n based on the vehicle's operating time at time n and the multidimensional feature data at time n-1 includes: The running time of the vehicle at time n-1; Calculate the cumulative number of days for the vehicle between time n and time n-1 based on time n. Based on the vehicle's running time at time n and time n-1 and the cumulative number of days between time n and time n-1, the percentage of daily non-running time of the vehicle between time n and time n-1 is calculated; the vehicle running data includes the percentage of daily non-running time.

8. The method for predicting vehicle battery health according to claim 7, wherein, The calculation of the percentage of daily non-running time of the vehicle between time n and time n-1, based on the vehicle's running time at time n and time n-1 and the cumulative number of days between time n and time n-1, includes: The non-running time of the vehicle is calculated based on the difference between the total duration corresponding to the accumulated number of days and the total duration of the vehicle's running time between time n and time n-1. The percentage of daily non-running time of the vehicle between time n and time n-1 is calculated based on the ratio of the vehicle's non-running time to the cumulative number of days.

9. The method for predicting vehicle battery health according to claim 1 or 2, wherein, The step of calculating the multidimensional feature data at time n based on the vehicle parameter information at time n and the multidimensional feature data at time n-1 further includes: The battery charging data at time n is calculated based on the real-time fast charging amount of the battery pack at time n, the real-time slow charging amount of the battery pack, the voltage of all individual cells, the real-time charging temperature of the battery pack from time n-1 to time n, and the battery charging data of the multi-dimensional feature data at time n-1.

10. The method for predicting vehicle battery health according to claim 9, wherein, The calculation of the battery charging data at time n, based on the real-time fast charging amount of the battery pack at time n, the real-time slow charging amount of the battery pack, the voltage of all individual cells, the real-time charging temperature of the battery pack from time n-1 to time n, and the multi-dimensional feature data at time n-1, includes: The voltage of all individual cells for which the battery charging data is obtained at time n-1; Based on the real-time fast charging amount and the real-time slow charging amount of the battery pack at time n, the total fast charging amount and the total slow charging amount of the battery pack at time n are generated. The average charging temperature of the battery pack between time n and time n is calculated by dividing the sum of the real-time charging temperatures of the battery pack from time n-1 to time n by the number of temperature samplings between time n-1 and time n. Based on the voltages of all individual cells at time n and time n-1, calculate the difference between the maximum and minimum voltages of all individual cells between time n and time n-1. The battery charging data includes: the total fast charging capacity of the battery pack, the total slow charging capacity of the battery pack, the average charging temperature, and the difference between the maximum and minimum voltages of all individual batteries.

11. The method for predicting vehicle battery health according to claim 1, further comprising, before obtaining vehicle parameter information at time n: Acquire the multidimensional feature data of the vehicle from time 0 to time n-1, and construct a multidimensional feature dataset; The preset prediction model is trained based on the multidimensional feature dataset.

12. The method for predicting vehicle battery health according to claim 11, wherein, The acquisition of the multidimensional feature data of the vehicle from time 0 to time n-1 includes: Obtain multidimensional feature data of at least two vehicles from time 0 to time n-1; The battery health data at time 0 is the preset initial health value.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for predicting the health of a vehicle battery according to any one of claims 1-12.

14. A computer-readable storage medium storing computer instructions for causing a processor to execute the method for predicting the health of a vehicle battery as described in any one of claims 1-12.

Images