Method, device, equipment and storage medium for predicting state of charge value of vehicle battery

Abstract

The method, device, equipment and storage medium for predicting the state of charge value of an automotive battery provided by this application obtain the current battery health, current battery temperature and current battery open-circuit voltage value of the automotive battery when it is detected that the vehicle is powered on. The predicted state of charge value of the automotive battery at present is determined according to the current battery health, current battery temperature and current battery open-circuit voltage value, and then the state of charge of the automotive battery is updated based on the predicted state of charge value. Since the influence of battery health, battery temperature and battery open-circuit voltage value on the state of charge is fully considered when determining the predicted state of charge value, the obtained predicted state of charge value is closer to the true value, improving the accuracy of state of charge prediction.

Description

Technical Field

[0001] This application relates to the technical field of automotive batteries, and particularly to a method, device, equipment and storage medium for predicting the state of charge value of an automotive battery. Background Art

[0002] In recent years, electric vehicles have been developing rapidly. The power battery is the only power source for electric vehicles, so effective management of the battery is particularly important. At present, the inaccurate display of the remaining mileage on the instrument large screen seriously affects the user experience. The reason is that the state of charge value of the battery, that is, the SOC value, is estimated inaccurately. Therefore, accurately estimating the battery SOC value can improve the accuracy of the remaining mileage displayed on the screen and provide guiding opinions for functions such as the balance, charge and discharge management of the BMS. Therefore, how to accurately estimate the SOC value of the battery has become an urgent technical problem to be solved. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method, device, equipment and storage medium for predicting the state of charge value of an automotive battery to solve the above technical problems.

[0004] On the one hand, a method for predicting the state of charge value of an automotive battery is provided. The method includes:

[0005] When it is detected that the vehicle is powered on, obtain the current battery health, the current battery temperature, and the current battery open-circuit voltage value of the automotive battery;

[0006] Determine the current state of charge prediction value of the automotive battery according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value;

[0007] Update the state of charge of the automotive battery based on the state of charge prediction value.

[0008] In one embodiment, the determining the current state of charge prediction value of the automotive battery according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value includes:

[0009] Input the current battery health, the current battery temperature, and the current battery open-circuit voltage value into a preset target prediction model to obtain the current state of charge prediction value of the automotive battery; the target prediction model is a model obtained by training an initial state of charge value prediction model with a sample data set, and the sample data set includes multiple data groups, and each data group is composed of a historical battery health, a historical battery temperature, a historical battery open-circuit voltage value, and a historical battery state of charge value.

[0010] In one embodiment, the initial state of charge value prediction model includes a convolutional neural network model.

[0011] In one embodiment, the convolutional neural network model includes an input layer, a convolutional layer, a fully connected layer, and an output layer connected in sequence. Training the initial prediction model of the state of charge value using the sample data set includes:

[0012] Input the sample data set into the input layer, perform convolution processing through the convolutional layer, input the sample data set after convolution processing into the fully connected layer, and output by the output layer;

[0013] Adjust the weights of each neuron in the fully connected layer through the cross-entropy loss function, and stop training to obtain the target prediction model until the preset convergence condition is met.

[0014] In one embodiment, updating the state of charge of the vehicle battery based on the predicted state of charge value includes:

[0015] Obtain the current static duration of the vehicle and the target state of charge value; the current static duration is the duration between the vehicle's last power-off and the current power-on; the target state of charge value is the state of charge value of the vehicle's battery at the time of the current power-on or the state of charge value of the vehicle's battery at the time of the last power-off;

[0016] When it is determined that the vehicle meets the preset state of charge value update condition based on the current static duration and the target state of charge value, update the target state of charge value based on the predicted state of charge value.

[0017] In one embodiment, when it is determined that the vehicle meets the preset state of charge value update condition based on the current static duration and the target state of charge value, updating the target state of charge value based on the predicted state of charge value includes:

[0018] When the current static duration is greater than the preset duration threshold, update the current static count of the vehicle, and obtain the absolute value between the predicted state of charge value and the target state of charge value; the static count is the number of occurrences of the target static event, and the target static event is an event where the static duration between the vehicle switching from the power-off state to the power-on state is greater than the preset duration threshold;

[0019] If the absolute value is greater than the preset state of charge threshold, obtain the first state of charge value, update the target state of charge value based on the first state of charge value, and reset the current static count of the vehicle to 0; the first state of charge value is the predicted state of charge value.

[0020] In one embodiment, after obtaining the absolute value between the predicted state of charge value and the target state of charge value, the method further includes:

[0021] If the absolute value is less than or equal to the preset state of charge threshold, obtain the current number of times the vehicle has been stationary, and compare the current number of times the vehicle has been stationary with the preset number of stationary times threshold;

[0022] If the current number of times the vehicle has been stationary is greater than or equal to the preset number of stationary times threshold, obtain a second state of charge value, update the target state of charge value based on the second state of charge value, and reset the current number of times the vehicle has been stationary to 0; the second state of charge value is the average of the predicted state of charge value and the target state of charge value.

[0023] On the other hand, a device for predicting the state of charge value of an automotive battery is provided, including:

[0024] An acquisition module, configured to obtain the current battery health, the current battery temperature, and the current battery open-circuit voltage value of the automotive battery when it is detected that the vehicle is powered on;

[0025] A determination module, configured to determine the current predicted state of charge value of the automotive battery according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value;

[0026] An update module, configured to update the state of charge of the automotive battery based on the predicted state of charge value.

[0027] On the other hand, an electronic device is provided, including a processor and a memory, where a computer program is stored in the memory, and the processor executes the computer program to implement any of the above methods.

[0028] On the other hand, a computer-readable storage medium is provided, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by at least one processor, any of the above methods is implemented.

[0029] The method, device, equipment, and storage medium for predicting the state of charge value of an automotive battery provided by this application obtain the current battery health, the current battery temperature, and the current battery open-circuit voltage value of the automotive battery when it is detected that the vehicle is powered on, determine the current predicted state of charge value of the automotive battery according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value, and then update the state of charge of the automotive battery based on the predicted state of charge value. Since the influence of battery health, battery temperature, and battery open-circuit voltage value on the state of charge is fully considered when determining the predicted state of charge value, the obtained predicted state of charge value is closer to the true value, improving the accuracy of state of charge prediction. Description of the Drawings

[0030] Figure 1 It is a schematic flowchart of a method for predicting the state of charge value of an automotive battery provided in the first embodiment of the present application;

[0031] Figure 2 It is the corresponding relationship of the measured battery temperature, SOC, and battery open-circuit voltage value when the battery health is 100% provided in the first embodiment of the present application;

[0032] Figure 3 It is the first schematic flowchart for updating the state of charge of an automotive battery provided in the first embodiment of the present application;

[0033] Figure 4 It is the second schematic flowchart for updating the state of charge of an automotive battery provided in the first embodiment of the present application;

[0034] Figure 5 It is the third schematic flowchart for updating the state of charge of an automotive battery provided in the first embodiment of the present application;

[0035] Figure 6 It is a schematic flowchart of a method for predicting the state of charge value of an automotive battery provided in the second embodiment of the present application;

[0036] Figure 7 It is a schematic structural diagram of a device for predicting the state of charge value of an automotive battery provided in the third embodiment of the present application;

[0037] Figure 8 It is a schematic structural diagram of an electronic device provided in the fourth embodiment of the present application. Detailed Embodiments

[0038] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0039] Embodiment 1:

[0040] The embodiment of the present application provides a method for predicting the state of charge value of an automotive battery, which can be applied to an electronic device. The electronic device can be set on an automobile. Specifically, please refer to Figure 1 as shown, and includes the following steps:

[0041] S11: When it is detected that the vehicle is powered on, obtain the current battery health, the current battery temperature, and the current battery open-circuit voltage value of the automotive battery.

[0042] S12: Determine the current state of charge prediction value of the automotive battery according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value.

[0043] S13: Update the state of charge of the vehicle battery based on the predicted state of charge value.

[0044] Next, the specific process of the above steps will be described in detail.

[0045] The electronic device can periodically monitor and record the battery health, battery temperature, and battery open-circuit voltage value of the vehicle. In this way, when it is detected that the vehicle is powered on, the latest current battery health, current battery temperature, and current battery open-circuit voltage value can be obtained for the vehicle battery.

[0046] For step S12, the current battery health, current battery temperature, and current battery open-circuit voltage value can be input into a preset target prediction model to obtain the predicted state of charge value of the vehicle battery at present.

[0047] The target prediction model in the embodiment of the present application can be a model obtained by training the initial prediction model of the state of charge value using a sample data set. Among them, the sample data set includes multiple data groups, and each data group is composed of historical battery health, historical battery temperature, historical battery open-circuit voltage value, and historical battery state of charge value.

[0048] The battery temperature has a great influence on the "battery open-circuit voltage value - battery state of charge value" curve, and the battery health has a great influence on the battery open-circuit voltage value at high SOC of the battery. Therefore, in the embodiment of the present application, the influence of battery health, battery temperature, and battery open-circuit voltage value on the state of charge is fully considered, and the state of charge of the vehicle battery is predicted based on these three parameters.

[0049] First, the historical battery health, historical battery temperature, historical battery open-circuit voltage value, and historical battery state of charge value can be obtained through experiments. For example, for each battery health, the battery open-circuit voltage value can be measured when the battery temperature is at a certain temperature and the SOC value is at a certain value. Please refer to Figure 2 as shown Figure 2 It represents the open-circuit voltage value measured when the battery health is 100%, the battery temperature is in the range of -40°C to 50°C (a measurement point can be set every 5°C), and the SOC is in the range of 0 to 1 (a measurement point can be set every 0.02). According to this method, when the battery health is in the range of 100% - 80% (a measurement point can be set every 2%), the battery temperature is in the range of -40°C to 50°C (a measurement point can be set every 5°C), and the SOC is in the range of 0 to 1 (a measurement point can be set every 0.02), the open-circuit voltage value can be measured.

[0050] It should be noted that in some embodiments, multiple sets of battery health, battery temperature, battery open-circuit voltage values, and battery state of charge values measured through experiments can be directly used as a sample data set for training. In other embodiments, the battery temperature, battery open-circuit voltage values, battery health, and battery state of charge values measured through experiments can be normalized respectively, and the normalized battery temperature, battery open-circuit voltage values, battery health, and battery state of charge values are used as the historical battery temperature, the historical battery open-circuit voltage values, the historical battery health, and the historical battery state of charge values for model training.

[0051] Exemplarily, the data measured through experiments can be normalized in the following manner:

[0052]

[0053]

[0054]

[0055] The battery health, battery temperature, and battery open-circuit voltage values measured through experiments are stored in the database; each battery health, each battery temperature, and each battery open-circuit voltage value measured through experiments are normalized in the above manner. That is, for the parameter to be processed, the difference between it and the minimum value of the parameter in the database is divided by the difference between the maximum value and the minimum value of the parameter in the database.

[0056] Where SOH' is the normalized battery health, SOH is the battery health measured through experiments, Min(SOH) is the minimum value of battery health in the database, Max(SOH) is the maximum value of battery health in the database; T' is the normalized battery temperature, T is the battery temperature measured through experiments, Min(T) is the minimum value of battery temperature in the database, Max(T) is the maximum value of battery temperature in the database; OCV' is the normalized battery open-circuit voltage value, OCV is the battery open-circuit voltage value measured through experiments, Min(OCV) is the minimum value of open-circuit voltage in the database, Max(OCV) is the maximum value of open-circuit voltage in the database.

[0057] It should be noted that the initial prediction model of the state of charge value in the embodiments of the present application can be a convolutional neural network model. Among them, the convolutional neural network model includes an input layer, a convolutional layer, a fully connected layer, and an output layer connected in sequence. During the training process, the sample data set is used to train the initial prediction model of the state of charge value, including:

[0058] The sample data set is input into the input layer, and after being subjected to convolutional processing by the convolutional layer, the sample data set after convolutional processing is input into the fully connected layer and output by the output layer;

[0059] Adjust the weights of each neuron in the fully connected layer through the cross-entropy loss function until the preset convergence condition is met, and then stop the training to obtain the target prediction model.

[0060] The preset convergence condition in the embodiments of the present application can be flexibly set by developers. For example, it can be set to reach a preset number threshold of training times, or the output of the loss function is within a preset loss threshold.

[0061] It should be noted that the initial prediction model of the state of charge value in the embodiments of the present application can also be other models. For example, it can be a ternary formula model SOH' = F(SOH', T', OCV''), which is fitted based on the historical data measured in experiments to obtain the target prediction model. The target prediction model obtained thereby is also a ternary formula model.

[0062] For step S13, please refer to Figure 3 as shown, it may include the following sub-steps:

[0063] S131: Obtain the current static duration of the vehicle and the target state of charge value of the battery.

[0064] The current static duration of the vehicle is the duration between the vehicle's most recent power-off and the current power-on; the target state of charge value is the state of charge value of the battery when the vehicle is powered on this time or the state of charge value of the battery when the vehicle was powered off last time.

[0065] S132: When it is determined that the vehicle meets the preset state of charge value update condition based on the current static duration and the target state of charge value, update the target state of charge value based on the state of charge prediction value.

[0066] The state of charge value update condition can be flexibly set by developers. In an optional implementation manner, for sub-step S132, please refer to Figure 4 as shown, it may include the following sub-steps:

[0067] S1320: When the current static duration is greater than the preset duration threshold, update the current static count of the vehicle, and obtain the absolute value between the state of charge prediction value and the target state of charge value.

[0068] The static count is the occurrence count of the target static event, and the target static event is an event where the static duration between the vehicle's power-off state and power-on state is greater than the preset duration threshold.

[0069] S1322: If the absolute value is greater than the preset state of charge threshold, obtain the first state of charge value, update the target state of charge value based on the first state of charge value, and reset the current static count of the vehicle to 0; the first state of charge value is the state of charge prediction value.

[0070] In this embodiment, when the current static duration is greater than the preset duration threshold and the absolute value between the predicted state of charge value and the target state of charge value is greater than the preset state of charge threshold, it is determined that the vehicle meets the preset condition for updating the state of charge value. Otherwise, it can be determined that the vehicle currently does not meet the preset condition for updating the state of charge value, and the state of charge of the vehicle battery is not updated. That is, the currently recorded state of charge value of the vehicle remains the target state of charge value.

[0071] For sub-step S132, please refer to Figure 5 As shown, after sub-step S1320, the following sub-steps may further be included:

[0072] S1321: If the absolute value is less than or equal to the preset state of charge threshold, obtain the current static times of the vehicle, and compare the current static times of the vehicle with the preset static times threshold.

[0073] S1323: If the current static times of the vehicle is greater than or equal to the preset static times threshold, obtain the second state of charge value, update the target state of charge value based on the second state of charge value, and reset the current static times of the vehicle to 0; the second state of charge value is the average value of the predicted state of charge value and the target state of charge value.

[0074] If it is determined that the current static times of the vehicle is less than the preset static times threshold after step S1321, the state of charge of the vehicle battery may not be updated. That is, the currently recorded state of charge value of the vehicle remains the target state of charge value.

[0075] It should be noted that the electronic device can record the static times. After the vehicle is switched from the power-off state to the power-on state for the first time, if it is determined that the corresponding static duration is greater than the preset duration threshold, the static times is set to 1. Whenever it is monitored that the vehicle is switched from the power-off state to the power-on state and it is determined that the corresponding static duration is greater than the preset duration threshold, the static times is incremented by 1 based on the recorded static times as the current static times of the vehicle. After monitoring that the target state of charge value is updated, the static times of the vehicle is reset to 0 again.

[0076] Finally, it should also be noted that the preset duration threshold, the preset state of charge threshold, and the preset static times threshold in the embodiments of the present application can all be set by developers according to user requirements, or can be customized by users. For example, the preset duration threshold can be set to 2h, 2.5h, 3h, 3.5h, etc., the preset state of charge threshold can be set to 0.03, 0.05, 0.10, etc., and the preset static times threshold can be set to 4, 5, 6, etc.

[0077] It should be understood that although the steps in the above flowcharts are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in rotation with at least a part of other steps or sub-steps or stages of other steps.

[0078] Embodiment 2:

[0079] To better understand the solution provided in this application, an embodiment of this application provides a more specific prediction of the state of charge value of an automotive battery. Please refer to Figure 6 as shown, including:

[0080] S601: When the vehicle is powered on, read the current static duration t of the vehicle, the state of charge SOC0 of the battery, the battery temperature T, the open-circuit voltage value OCV of the battery, the state of health SOH of the battery, and the current static count N of the vehicle.

[0081] Assume that the preset duration threshold in the embodiment of this application is 3h, the preset static count threshold is 5, and the preset state of charge threshold is 0.03. It should be understood that the setting method in the embodiment of this application does not constitute a limitation on the preset duration threshold, the preset static count threshold, and the preset state of charge threshold. In other embodiments, the preset duration threshold, the preset state of charge threshold, and the preset static count threshold can also be other values.

[0082] S602: Determine whether t > 3h holds. If so, go to S604; if not, go to S603.

[0083] S603: Do not update the SOC value.

[0084] S604: Calculate SOC cal .

[0085] In step S604, the state of charge prediction value SOC cal .

[0086] S605: Reset the current static count of the vehicle to N + 1.

[0087] S606: Determine whether abs(SOC cal -SOC0)>0.03 holds. If so, go to S607; if not, go to S609.

[0088] Wherein, SOC0 represents the target state of charge value. In the embodiment of the present application, the specific state of charge prediction value SOC cal The method of determining the target state of charge value SOC0 can refer to the content in the first embodiment, which will not be repeated here.

[0089] S607: Update SOC, update the state of charge of the vehicle battery to SOC cal .

[0090] S608: Reset the number of times the vehicle has been stationary N=0.

[0091] S609: Is N≥5 true? If so, go to S610; if not, go to S603.

[0092] S610: Update SOC, update the state of charge of the vehicle battery to (SOC cal +SOC0) / 2.

[0093] S611: Reset the number of times the vehicle has been stationary N=0.

[0094] Embodiment three:

[0095] Based on the same inventive concept, the present application embodiment provides a device for predicting the state of charge value of a vehicle battery, see Figure 7 As shown, it should be understood that the function of the charge state value prediction device of the automobile battery can refer to the description above, and in order to avoid repetition, the detailed description is appropriately omitted here.

[0096] The device for predicting the state of charge value of a vehicle battery includes at least one software functional unit that can be stored in a memory in the form of software or firmware or fixed in the operating system of the device. Specifically, the device for predicting the state of charge value of a vehicle battery includes:

[0097] The acquisition module 701 is used to acquire the current battery health, current battery temperature and current battery open circuit voltage value of the vehicle battery when the vehicle is powered on;

[0098] A determination module 702 is used to determine a current state of charge prediction value of the vehicle battery according to the current battery health, the current battery temperature and the current battery open circuit voltage value;

[0099] The updating module 703 is used to update the state of charge of the vehicle battery based on the state of charge prediction value.

[0100] It should be noted that, for the sake of brevity, the contents described in the above embodiments will not be repeated in this embodiment.

[0101] Embodiment 4:

[0102] This embodiment provides an electronic device, which can be integrally arranged on an automobile. Please refer to Figure 8 As shown, the electronic device includes a processor 801 and a memory 802. A computer program is stored in the memory 802. The processor 801 and the memory 802 communicate through a communication bus. The processor 801 executes the computer program to implement the steps of the method in the above embodiment, which will not be elaborated here. It can be understood that Figure 8 The structure shown is only for illustration. The terminal may also include more or fewer components than those shown in Figure 8 or have a different configuration from that shown in Figure 8 It should be noted that the terminal in the embodiment of the present application can be arranged on an automobile.

[0103] The processor 801 can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 801 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0104] The memory 802 can include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0105] This embodiment also provides a computer-readable storage medium, such as a floppy disk, an optical disc, a hard disk, a flash memory, a USB flash drive, an SD card, an MMC card, etc. One or more programs for implementing the above steps are stored in the computer storage medium. These one or more programs can be executed by one or more processors 801 to implement the steps of the method in the above embodiment, which will not be elaborated here.

[0106] It should be noted that the illustrations provided in this embodiment only schematically illustrate the basic concept of the present invention. Therefore, only the components related to the present invention are shown in the drawings, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the layout type of the components may also be more complex. The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the conditions for the implementation of the present invention. Therefore, they do not have any substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention. At the same time, the terms such as "upper", "lower", "left", "right", "middle", and "one" cited in this specification are only for the convenience of clear description and are not used to limit the scope of implementation of the present invention. The change or adjustment of their relative relationships, without substantial change in the technical content, should also be regarded as the scope of implementation of the present invention.

[0107] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0108] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for predicting the state of charge value of an automotive battery, characterized in that, Including: When it is detected that the vehicle is powered on, obtain the current battery health, the current battery temperature, and the current battery open-circuit voltage value of the vehicle battery; Determine the predicted state of charge value of the vehicle battery at present according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value; Update the state of charge of the vehicle battery based on the predicted state of charge value; The updating the state of charge of the vehicle battery based on the predicted state of charge value includes: Obtain the current static duration of the vehicle and the target state of charge value; the current static duration is the duration between the last power-off and the current power-on of the vehicle; the target state of charge value is the state of charge value of the vehicle battery at the time of the current power-on or the state of charge value of the vehicle battery at the time of the last power-off; When the current static duration is greater than a preset duration threshold, update the current static count of the vehicle, and obtain the absolute value of the difference between the predicted state of charge value and the target state of charge value; the static count is the occurrence count of the target static event, and the target static event is an event in which the static duration between the vehicle switching from the power-off state to the power-on state is greater than the preset duration threshold; If the absolute value is greater than the preset state of charge threshold, obtain the first state of charge value, update the target state of charge value based on the first state of charge value, and reset the current static count of the vehicle to 0; the first state of charge value is the predicted state of charge value.

2. The method for predicting the state of charge value of an automotive battery according to claim 1, wherein The determining the predicted state of charge value of the vehicle battery at present according to the current battery health, the current battery temperature, and the current battery open-circuit voltage value includes: Input the current battery health, the current battery temperature, and the current battery open-circuit voltage value into a preset target prediction model to obtain the predicted state of charge value of the vehicle battery at present; the target prediction model is a model obtained by training a state of charge value initial prediction model with a sample data set, and the sample data set includes a plurality of data groups, and each data group is composed of a historical battery health, a historical battery temperature, a historical battery open-circuit voltage value, and a historical state of charge value.

3. The method for predicting the state of charge value of an automotive battery according to claim 2, characterized in that, The state of charge value initial prediction model includes a convolutional neural network model.

4. The method for predicting the state of charge value of an automotive battery according to claim 3, characterized in that, The convolutional neural network model includes an input layer, a convolutional layer, a fully connected layer, and an output layer connected in sequence. The training the state of charge value initial prediction model with the sample data set includes: Input the sample data set into the input layer, perform convolutional processing through the convolutional layer, input the sample data set after convolutional processing into the fully connected layer, and output by the output layer; Adjust the weights of each neuron in the fully connected layer through a cross-entropy loss function until the preset convergence condition is met, and then stop training to obtain the target prediction model.

5. The method for predicting the state of charge value of an automotive battery according to claim 1, wherein, After obtaining the absolute value of the difference between the predicted state of charge value and the target state of charge value, it further includes: If the absolute value is less than or equal to the preset state of charge threshold, obtain the current static count of the vehicle, and compare the current static count of the vehicle with a preset static count threshold; If the current number of static stops of the vehicle is greater than or equal to the preset static stop number threshold, obtain a second state of charge value, update the target state of charge value based on the second state of charge value, and reset the current number of static stops of the vehicle to 0; the second state of charge value is the average of the predicted state of charge value and the target state of charge value.

6. A state of charge value prediction device for an automotive battery, characterized in that, Comprising: An obtaining module, configured to obtain the current battery health, the current battery temperature, and the current battery open circuit voltage value of the vehicle battery when it is detected that the vehicle is powered on; A determining module, configured to determine the predicted state of charge value of the vehicle battery currently according to the current battery health, the current battery temperature, and the current battery open circuit voltage value; An updating module, configured to obtain the current static stop duration of the vehicle and the target state of charge value of the battery; the current static stop duration is the duration between the last power-off of the vehicle and the current power-on; The target state of charge value is the state of charge value of the vehicle battery when the vehicle is powered on this time or the state of charge value of the vehicle battery when the vehicle was powered off last time; when the current static stop duration is greater than the preset duration threshold, update the current number of static stops of the vehicle, and obtain the absolute value of the difference between the predicted state of charge value and the target state of charge value; the number of static stops is the number of occurrences of a target static stop event, and the target static stop event is an event in which the static stop duration between the vehicle switching from the power-off state to the power-on state is greater than the preset duration threshold; if the absolute value is greater than the preset state of charge threshold, obtain a first state of charge value, update the target state of charge value based on the first state of charge value, and reset the current number of static stops of the vehicle to 0; the first state of charge value is the predicted state of charge value.

7. An electronic device, characterized in that, Comprising a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method according to any one of claims 1-5 is implemented.

Images