Method and device for determining state of charge of vehicle battery, equipment and medium

Abstract

The embodiment of the invention discloses a method, device and equipment for determining the state of charge of a vehicle battery and a medium. The method comprises the steps that first charging and discharging data and a first state-of-charge value of a first battery of a target vehicle at the current moment are acquired; based on a corresponding relation between a second battery of the candidate vehicle and a pre-trained battery state-of-charge prediction model, determining a target state-of-charge prediction model corresponding to the first battery, and inputting the first charging and discharging data into the target state-of-charge prediction model to obtain a second state-of-charge value of the first battery at the current moment; under the condition that the deviation between the first state-of-charge value and the second state-of-charge value does not exceed a preset deviation threshold value, the second state-of-charge value is sent to a target vehicle, so that the target vehicle determines a target state-of-charge value of the first battery at the current moment based on the first state-of-charge value and the second state-of-charge value, therefore, the state of charge of the vehicle battery can be obtained accurately.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer processing technology, and more particularly to a method, apparatus, device, and medium for determining the state of charge of a vehicle battery. Background Art

[0002] A vehicle's battery's state of charge (SOC) is a key parameter for evaluating the remaining available charge in a vehicle's battery. It reflects the percentage of the battery's total capacity (0% to 100%). Essentially a battery's "charge meter," it directly impacts range predictions, charge and discharge strategies, and battery health management, making it a key technical indicator for vehicles.

[0003] The ampere-hour integration method is commonly used to determine the vehicle battery's state of charge (SOC). This method integrates the battery's charge and discharge current over time to estimate the battery's dynamic SOC. However, the ampere-hour integration method requires high current sampling accuracy. If the battery is charged and discharged for extended periods, significant accumulated errors will occur, resulting in low SOC accuracy. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for determining the state of charge of a vehicle battery, so as to more accurately obtain the state of charge of the vehicle battery, thereby improving the accuracy of the state of charge of the vehicle battery.

[0005] According to one aspect of the present invention, a method for determining the state of charge of a vehicle battery is provided, which is applied to a cloud. The method includes:

[0006] Obtaining first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle;

[0007] Determining a target state of charge prediction model corresponding to the first battery based on a correspondence between a second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, inputting the first charge and discharge data into the target state of charge prediction model, and obtaining a second state of charge value of the first battery at the current moment;

[0008] When a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, the second state of charge value is sent to the target vehicle, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

[0009] According to another aspect of the present invention, a device for determining the state of charge of a vehicle battery is provided.

[0010] The device includes:

[0011] a first data acquisition module, configured to acquire first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle;

[0012] a second data acquisition model for determining a target state of charge prediction model corresponding to the first battery based on a correspondence between a second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, inputting the first charge and discharge data into the target state of charge prediction model, and obtaining a second state of charge value of the first battery at a current moment;

[0013] and a state of charge determination module, configured to send the second state of charge value to the target vehicle when a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the state of charge of a vehicle battery as described in any one of the embodiments of the present disclosure.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement any method for determining the state of charge of a vehicle battery according to the present invention when executed.

[0019] The technical solution of an embodiment of the present invention obtains the first charge and discharge data and first state of charge value of the first battery of a target vehicle at the current moment; the first state of charge value is calculated by the target vehicle's internal battery management system. Furthermore, based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, a target state of charge prediction model corresponding to the first battery is determined. The first charge and discharge data is input into the target state of charge prediction model to obtain the second state of charge value of the first battery at the current moment. This achieves a one-to-one adaptation between the vehicle and the prediction model, improving the accuracy of vehicle battery state of charge prediction. If the deviation between the first and second state of charge values does not exceed a preset deviation threshold, the second state of charge value is sent to the target vehicle, allowing the target vehicle to determine the target state of charge value of the first battery at the current moment based on the first and second state of charge values. The technical solution of an embodiment of the present invention solves the technical problem of low accuracy in calculating vehicle battery state of charge using the ampere-hour integration method in related technologies, achieving more accurate determination of vehicle battery state of charge, thereby improving vehicle battery state of charge accuracy.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0022] Figure 1 A schematic flow chart of a method for determining the state of charge of a vehicle battery provided by an embodiment of the present invention;

[0023] Figure 2 A schematic flow chart of a method for determining the state of charge of a vehicle battery provided by an embodiment of the present invention;

[0024] Figure 3 A schematic flow chart of an optional embodiment of a method for determining the state of charge of a vehicle battery provided by an embodiment of the present invention;

[0025] Figure 4 A schematic structural diagram of a device for determining the state of charge of a vehicle battery provided by an embodiment of the present invention;

[0026] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. 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 necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0030] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0031] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0033] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0034] Figure 1 This is a flow chart of a method for determining the state of charge of a vehicle battery provided by an embodiment of the present invention. This embodiment is applicable to the case of estimating the state of charge of a vehicle. The method can be executed by a vehicle battery state of charge determination device. The vehicle battery state of charge determination device can be implemented in the form of hardware and / or software. The vehicle battery state of charge determination device can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method for determining the state of charge of a vehicle battery of this embodiment is applied to the cloud and includes the following steps:

[0035] S110. Obtain first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle.

[0036] Among them, the target vehicle can be understood as a vehicle for which battery state of charge estimation is required. In an embodiment of the present invention, the target vehicle may include at least one of a pure electric vehicle, a plug-in hybrid electric vehicle, an extended-range electric vehicle, a fuel cell vehicle, a hybrid electric vehicle, etc. The state of the target vehicle may be a starting state, a driving state, a charging state, or a stationary state. In an embodiment of the present invention, the number of target vehicles may be one, two, or more than two. The first battery can be understood as the battery of the target vehicle. The first charge and discharge data can be understood as the charge and discharge data of the first battery at the current moment. In an embodiment of the present invention, the charge and discharge data may include at least the voltage and current of the battery. The first state of charge value can be understood as the state of charge value of the first battery at the current moment calculated by the internal battery management system of the target vehicle.

[0037] In an embodiment of the present invention, obtaining first charge and discharge data of a first battery of a target vehicle at a current moment includes: receiving the first charge and discharge data of the first battery at a current moment sent by the target vehicle. In an embodiment of the present invention, obtaining a first state of charge value of the first battery of a target vehicle at a current moment includes: receiving the first state of charge value of the first battery at a current moment sent by the target vehicle.

[0038] S120. Based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, determine a target state of charge prediction model corresponding to the first battery, input the first charge and discharge data into the target state of charge prediction model, and obtain a second state of charge value of the first battery at the current moment.

[0039] Among them, the candidate vehicle can be understood as a vehicle for which the vehicle battery state of charge value can be estimated. In actual applications, the number of candidate vehicles is usually multiple. The second battery can be understood as the battery of the candidate vehicle. The correspondence between the candidate vehicle and the battery state of charge prediction model is one-to-one. That is, one candidate vehicle corresponds to one battery state of charge prediction model. In other words, a corresponding battery state of charge prediction model is pre-trained for each candidate vehicle so as to predict the state of charge value of the second battery of the candidate vehicle through the battery state of charge prediction model. In an embodiment of the present invention, a battery state of charge prediction model can be used to predict the state of charge value of the second battery of the candidate vehicle corresponding to the battery state of charge prediction model based on battery charging and discharging data. The target state of charge prediction model can be understood as a model in the battery state of charge prediction model used to predict the state of charge value of the target vehicle. The second state of charge value can be understood as the state of charge value of the first battery at the current moment calculated by the target state of charge prediction model.

[0040] Specifically, based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery SOC prediction model, a battery SOC prediction model corresponding to the first battery is determined, i.e., a target SOC prediction model corresponding to the first battery is determined. The first charge and discharge data can then be input into the target SOC prediction model to obtain a prediction of the SOC value of the first battery at the current moment, thereby obtaining the second SOC value of the first battery at the current moment.

[0041] S130. When a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, send the second state of charge value to the target vehicle, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

[0042] In the embodiment of the present invention, the preset deviation threshold can be set according to actual needs and is not specifically limited herein, for example, 0.05, 0.01, or 0.005. The target SOC value can be understood as the SOC value of the first battery at the current moment determined by the target vehicle based on the first SOC value and the second SOC value.

[0043] Specifically, a difference is calculated between the first SOC value and the second SOC value to obtain a deviation between the first SOC value and the second SOC value. If the deviation between the first SOC value and the second SOC value does not exceed a preset deviation threshold, the second SOC value may be sent to the target vehicle, so that the target vehicle determines a target SOC value for the first battery at a current moment based on the first SOC value and the second SOC value.

[0044] Optionally, the deviation between the first state of charge value and the second state of charge value may be calculated using the following formula:

[0045]

[0046] Among them, SOC pre_n It can be expressed as the second state of charge value. n It can be expressed as a first state of charge value. N can represent the total number of battery sampling points.

[0047] In an embodiment of the present invention, the second state of charge value is sent to the target vehicle so that the target vehicle determines the target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value. Specifically, the second state of charge value may be sent to the target vehicle so that the target vehicle corrects the second state of charge value based on the first state of charge value to obtain a corrected state of charge value, that is, the target state of charge value of the first battery at the current moment.

[0048] As a vehicle's battery ages over time, it can also age. Therefore, even if the same model previously met the prediction accuracy requirements, it may no longer be applicable after the battery ages. Therefore, the model needs to be updated. In the disclosed embodiments, there are multiple ways to update the battery state of charge prediction model.

[0049] As an optional implementation of the embodiment of the present disclosure, the battery state of charge prediction model is updated. When the deviation between the first state of charge value and the second state of charge value exceeds a preset deviation threshold, the battery state of charge prediction model can be updated to achieve automatic updating of the battery state of charge prediction model, that is, irregular updating, thereby improving the accuracy of the vehicle battery state of charge.

[0050] As another optional implementation of the embodiment of the present disclosure, the battery state of charge prediction model is updated by configuring an operation in response to an update time for the battery state of charge prediction model, obtaining model update time information of the battery state of charge prediction model, and updating the battery state of charge prediction model based on the model update time information to achieve regular updates of the model. Specifically, the model update time information can be an update frequency, for example, iteratively updating the model every month. The update frequency can be set according to the actual use of the vehicle.

[0051] In an embodiment of the present invention, there are multiple ways to update the battery state of charge prediction model. For example, a new training sample data set can be obtained; and the battery state of charge prediction model can be retrained using the new training sample data set. Alternatively, a new training sample data set can be obtained; and a pre-built initial network model can be retrained using the new training sample data set. It should be noted that the start time of the time period corresponding to the charge and discharge data in the new training sample data set is the end time of the time period corresponding to the charge and discharge data in the training sample data set in the previous model training, and the start time of the time period corresponding to the charge and discharge data in the training sample data set in the previous model training is earlier than the end time of the time period corresponding to the charge and discharge data in the training sample data set in the previous model training.

[0052] The technical solution of an embodiment of the present invention obtains the first charge and discharge data and first state of charge value of the first battery of a target vehicle at the current moment; the first state of charge value is calculated by the target vehicle's internal battery management system. Furthermore, based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, a target state of charge prediction model corresponding to the first battery is determined. The first charge and discharge data is input into the target state of charge prediction model to obtain the second state of charge value of the first battery at the current moment. This achieves a one-to-one adaptation between the vehicle and the prediction model, improving the accuracy of vehicle battery state of charge prediction. If the deviation between the first and second state of charge values does not exceed a preset deviation threshold, the second state of charge value is sent to the target vehicle, allowing the target vehicle to determine the target state of charge value of the first battery at the current moment based on the first and second state of charge values. The technical solution of an embodiment of the present invention solves the technical problem of low accuracy in calculating vehicle battery state of charge using the ampere-hour integration method in related technologies, achieving more accurate determination of vehicle battery state of charge, thereby improving vehicle battery state of charge accuracy.

[0053] Figure 2A flow chart of a method for determining the state of charge of a vehicle battery provided in an embodiment of the present invention, based on the aforementioned embodiment, optionally, before determining the target state of charge prediction model corresponding to the first battery based on the correspondence between the second battery of the candidate vehicle and the pre-trained battery state of charge prediction model, the method further includes: for each second battery of the candidate vehicle, obtaining a training sample set corresponding to the second battery, wherein the training sample set includes training sample data and an expected output result corresponding to the training sample data, the training sample data is the second charge and discharge data of the second battery at a preset historical moment, and the expected output result is the third state of charge value of the second battery at the preset historical moment; inputting the training sample data into a pre-constructed initial network model to obtain a model output result corresponding to the training sample data; and adjusting the network parameters of the initial network model based on the model output result and the expected output result to obtain a battery state of charge prediction model corresponding to the second battery. Technical features identical or similar to those in the aforementioned embodiments are not repeated here. Figure 2 As shown, the method for determining the state of charge of a vehicle battery of this embodiment is applied to the cloud and specifically includes the following steps:

[0054] S210 . For each second battery of the candidate vehicle, obtain a training sample set corresponding to the second battery, wherein the training sample set includes training sample data and expected output results corresponding to the training sample data.

[0055] In an embodiment of the present invention, the training sample data may be second charge and discharge data of the second battery at a preset historical moment. The expected output result may be a third state of charge value of the second battery at the preset historical moment. The preset historical moment can be set based on actual needs and is not specifically limited herein. The second charge and discharge data may be understood as the charge and discharge data of the second battery at the preset historical moment. The third state of charge value may be understood as the state of charge value of the second battery at the preset historical moment.

[0056] Specifically, for each candidate vehicle's second battery, a target database is determined for storing a training sample set for the candidate vehicle's second battery; and a training sample set corresponding to the second battery can then be obtained from the target database. In this embodiment of the present invention, obtaining a training sample set corresponding to the second battery of each candidate vehicle enables training a customized battery SOC prediction model for each candidate vehicle, making each battery SOC prediction model more tailored to the corresponding candidate vehicle, thereby improving the accuracy of the SOC value prediction for each candidate vehicle.

[0057] Based on the above embodiment, before obtaining a training sample set corresponding to the second battery of each candidate vehicle, the method further includes: displaying a first interface; wherein the first interface includes at least one vehicle identifier; in response to an identifier selection operation for at least one of the vehicle identifiers, determining the selected vehicle identifier; treating the vehicle battery corresponding to each selected vehicle identifier as a separate second battery, obtaining a charge and discharge data stream of the second battery within a preset historical period from the current moment, to obtain third charge and discharge data of the second battery at each historical moment within the preset historical period from the current moment, and using this data as training sample data. In the disclosed embodiment, data training can be selected through the interface, achieving data visualization and simplified operation.

[0058] Among them, the first interface can be understood as an interface for displaying the vehicle identification, so as to select the second battery according to needs. In the embodiment of the present disclosure, the first interface supports flexible selection of vehicles, so as to perform targeted model training and updating on the battery of the selected vehicle. The identification selection operation can be understood as an operation for selecting the vehicle identification provided by the first interface. The charge and discharge data stream can be understood as a data stream obtained by combining the charge and discharge data of the second battery within a preset historical period from the current moment. The charge and discharge data stream may include the third charge and discharge data of the second battery at each historical moment within the preset historical period from the current moment. The third charge and discharge data can be understood as the charge and discharge data of the second battery at each historical moment within the preset historical period from the current moment in the charge and discharge data stream.

[0059] Specifically, in response to a vehicle selection operation, a first interface is displayed. The first interface includes at least one vehicle identifier. In response to an identifier selection operation for at least one of the vehicle identifiers, the selected vehicle identifier is determined. Furthermore, the vehicle battery corresponding to each selected vehicle identifier can be individually used as a second battery. This allows the acquisition of a stream of charge and discharge data for the second battery within a preset historical period from the current moment, thereby obtaining third charge and discharge data for the second battery at each historical moment within the preset historical period from the current moment, which is then used as training sample data.

[0060] In an embodiment of the present invention, after obtaining the charge and discharge data stream of the second battery within a preset historical period from the current moment, the charge and discharge data stream can be divided into a training sample data set and a validation sample data set according to a preset ratio (e.g., 7:3). It is understood that after the model is trained using the training sample data set, the validation sample data set can be used to verify the accuracy of the trained model, thereby improving the accuracy of the vehicle battery state of charge prediction model in actual use.

[0061] On the basis of the above embodiment, before obtaining the charge and discharge data stream of the second battery within a preset historical period from the current moment, the method further includes: displaying a second interface, wherein the second interface includes a preset time period template for obtaining battery charge and discharge data, and the preset time period template includes a start time setting item and an end time setting item for obtaining battery charge and discharge data, wherein the end time setting item displays the current moment; and responding to a time setting operation for the start time item to obtain the charge and discharge data acquisition period of the second battery within the preset historical period from the current moment.

[0062] Among them, the second interface can be understood as an interface for configuring the time period for obtaining battery charge and discharge data. The second interface includes a preset time period template for obtaining battery charge and discharge data. Among them, the preset time period template may include a start time setting item and an end time setting item for obtaining battery charge and discharge data. In an embodiment of the present invention, the start time setting item can be used to set the start time for obtaining battery charge and discharge data. The start time setting item may display a default time or may not display a default time. The end time setting item can be used to set the end time for obtaining battery charge and discharge data. The default time displayed by the end time setting item is the current moment. In actual applications, the time set by the start time setting item is earlier than the time set by the end time setting item.

[0063] The time setting operation can be used to set the start time item in the preset time period template. The charge and discharge data acquisition period can be understood as the time period obtained by setting the start time and end time of the start time item in the preset time period template based on the time setting operation. In embodiments of the present invention, the end time of the preset time period template can also be modified as needed, which is not specifically limited here.

[0064] Specifically, a second interface is displayed, which displays a preset time period template for acquiring battery charge and discharge data. The preset time period template displays a start time setting item and an end time setting item for acquiring battery charge and discharge data. The end time defaults to the current time. In response to a time setting operation for the start time item, the start time set for the start time item is obtained. Based on the set start time and the default current time, the preset historical period of the second battery from the current time, i.e., the charge and discharge data acquisition period, can be obtained.

[0065] Based on the above embodiment, after obtaining the charge and discharge data stream of the second battery within a preset historical period from the current moment, the method further includes determining change curve information of the third charge and discharge data and the first state of charge value of the second battery at various historical moments within the preset historical period from the current moment, and displaying the change curve information to facilitate a user's manual selection of training sample data suitable for the second battery based on the change curve information. In this embodiment of the present invention, the third charge and discharge data may include at least current, voltage, and temperature. The change curve information may be used to describe the temporal relationship between the third charge and discharge data and the first state of charge value, thereby intuitively reflecting the battery's charge and discharge behavior and predicting performance changes. Optionally, the change curve information may include first, second, and third curve information. The first curve information may be derived based on the vehicle battery's current and state of charge value, describing the temporal relationship between the vehicle battery's current and state of charge value. The second curve information may be derived based on the vehicle battery's voltage and state of charge value, describing the temporal relationship between the vehicle battery's voltage and state of charge value. The second curve information may be obtained based on the temperature and the battery state of charge value of the vehicle battery, and is used to describe the relationship between the temperature and the battery state of charge value of the vehicle battery in a time series.

[0066] Based on the above example, if there are a large number of vehicles, you can also set specific historical charge and discharge data, such as the past week or the past month, to automatically train the model and ensure model accuracy by setting an error threshold. For example, if the default training data is set to the past week, when the automatic charge and discharge data selection control is triggered, the charge and discharge data segment for the previous seven days can be obtained and divided into training and validation sample sets according to a certain ratio.

[0067] S220: Input the training sample data into a pre-built initial network model to obtain a model output result corresponding to the training sample data.

[0068] In an embodiment of the present invention, the initial network models corresponding to different candidate vehicles may be the same or different. For example, the initial network model may be a preset convolutional neural network model or a trained neural network model. The preset convolutional neural network may be any one of a fully connected network, a long short-term memory (LSTM) network, a genetic algorithm, and a support vector machine.

[0069] In an embodiment of the present invention, taking a convolutional neural network model as an example, the convolutional neural network model includes at least a fully connected layer and a convolutional layer. Training sample data and an expected output result corresponding to the training sample data are input into the convolutional neural network model to obtain a model output result corresponding to the training sample data. Specifically, second charge and discharge data of the second battery at a preset historical moment is input into the pre-constructed initial network model to obtain a predicted state of charge value of the second battery at the preset historical moment.

[0070] Because the process of learning the mapping relationship between the vehicle battery's charge and discharge data and the state of charge value through a convolutional neural network model has high data requirements, in an embodiment of the present invention, a data cleaning process is introduced to process the raw data, that is, the vehicle battery's charge and discharge data is pre-processed. Specifically, in the case of missing data and abnormalities in the charge and discharge data, the abnormal charge and discharge data can be interpolated to increase the data density, thereby improving the training effect. In addition, abnormal data in the charge and discharge data is screened out to prevent the model from learning noise information.

[0071] S230: Based on the model output result and the expected output result, adjust network parameters of the initial network model to obtain a battery state of charge prediction model corresponding to the second battery.

[0072] Specifically, based on the model output result and the expected output result, the function value of a preset loss function is determined; thus, the network parameters of the initial network model can be adjusted according to the function value; and the initial network model is trained with convergence of the preset loss function as the training goal to obtain a battery state of charge prediction model corresponding to the second battery. In the embodiment of the present disclosure, the loss function is pre-set and is used to measure whether the output value of the determined trained initial network model is accurate. Optionally, the loss function can be an average error function, which is used to calculate the average error between the model output result and the expected output result.

[0073] In an embodiment of the present disclosure, the initial network model is trained with convergence of the preset loss function as the training objective. Specifically, the training error of the loss function can be used as a criterion for detecting whether the loss function has currently reached convergence, such as whether the training error is less than a preset error, whether the error trend is stable, or whether the current number of iterations is equal to a preset number. If convergence conditions are met, such as when the training error of the loss function is less than a preset error or the error trend is stable, the training of the battery state of charge prediction model is complete, and iterative training can be terminated. If convergence conditions are not met, further training samples from the training sample data can be obtained to retrain the trained battery state of charge prediction model until the training error of the loss function is within a preset range. When the training error of the loss function has reached convergence, the retrained battery state of charge prediction model can be used as the trained battery state of charge prediction model corresponding to the second battery. The state of charge value of the second battery in the candidate vehicle can be determined based on the trained battery state of charge prediction model.

[0074] S240. Obtain first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle.

[0075] S250. Based on the correspondence between the second battery of the candidate vehicle and the pre-trained battery state of charge prediction model, determine the target state of charge prediction model corresponding to the first battery, input the first charge and discharge data into the target state of charge prediction model, and obtain the second state of charge value of the first battery at the current moment.

[0076] S260. When a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, sending the second state of charge value to the target vehicle, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

[0077] It should be noted that due to differences in performance between vehicles and different usage by drivers, the same model may not be applicable to all vehicles (even if the vehicles have the same battery capacity). Therefore, in an embodiment of the present invention, the model and vehicle are bound in the cloud, and the most suitable neural network model is trained for each vehicle through a "one vehicle, one model" approach to achieve targeted state of charge value prediction for the vehicle's battery.

[0078] See also Figure 3After obtaining the charge and discharge data of each candidate vehicle battery at each historical moment in the charge and discharge data stream within a preset historical period from the current moment, data cleaning processing can be performed. The cleaned data is thus divided into a training sample data set and a verification sample data set. Afterwards, for the training sample data set, the data in the training sample data set is input into the model of the preset neural network algorithm for training, thereby obtaining a vehicle model, that is, a battery state of charge prediction model corresponding to the candidate vehicle. For the verification sample data set, the data in the verification sample data set is input into the trained vehicle model for model verification to predict the deviation and visualize the deviation. Afterwards, if the predicted deviation does not exceed the preset deviation threshold, the trained vehicle model is sent to the corresponding candidate vehicle to correct the state of charge value on the vehicle side.

[0079] The technical solution of an embodiment of the present invention is to obtain a training sample set corresponding to the second battery of each candidate vehicle, wherein the training sample set includes training sample data and an expected output result corresponding to the training sample data, the training sample data is the second charge and discharge data of the second battery at a preset historical moment, and the expected output result is the third state of charge value of the second battery at the preset historical moment; the training sample data is input into a pre-constructed initial network model to obtain a model output result corresponding to the training sample data; based on the model output result and the expected output result, the network parameters of the initial network model are adjusted to obtain a battery state of charge prediction model corresponding to the second battery, thereby realizing one-to-one adaptation between the vehicle and the prediction model and improving the accuracy of the prediction of the vehicle battery state of charge value.

[0080] Figure 4 This is a schematic diagram of a device for determining the state of charge of a vehicle battery provided by an embodiment of the present invention. Figure 4As shown, the apparatus includes: a first data acquisition module 310, a second data acquisition model 320, and a state of charge determination module 330. The first data acquisition module 310 is configured to acquire first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle; the second data acquisition model 320 is configured to determine a target state of charge prediction model corresponding to the second battery of the candidate vehicle based on a correspondence between the first battery and a pre-trained battery state of charge prediction model, input the first charge and discharge data into the target state of charge prediction model, and obtain a second state of charge value of the first battery at a current moment; and the state of charge determination module 330 is configured to send the second state of charge value to the target vehicle if the deviation between the first and second state of charge values does not exceed a preset deviation threshold, so that the target vehicle determines the target state of charge value of the first battery at a current moment based on the first and second state of charge values.

[0081] The technical solution of an embodiment of the present invention obtains the first charge and discharge data and first state of charge value of the first battery of a target vehicle at the current moment; the first state of charge value is calculated by the target vehicle's internal battery management system. Furthermore, based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, a target state of charge prediction model corresponding to the first battery is determined. The first charge and discharge data is input into the target state of charge prediction model to obtain the second state of charge value of the first battery at the current moment. This achieves a one-to-one adaptation between the vehicle and the prediction model, improving the accuracy of vehicle battery state of charge prediction. If the deviation between the first and second state of charge values does not exceed a preset deviation threshold, the second state of charge value is sent to the target vehicle, allowing the target vehicle to determine the target state of charge value of the first battery at the current moment based on the first and second state of charge values. The technical solution of an embodiment of the present invention solves the technical problem of low accuracy in calculating vehicle battery state of charge using the ampere-hour integration method in related technologies, achieving more accurate determination of vehicle battery state of charge, thereby improving vehicle battery state of charge accuracy.

[0082] Optionally, the vehicle battery state of charge determination device further includes: a model training module. The model training module is configured to, before determining a target state of charge prediction model corresponding to the first battery based on the correspondence between the second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, obtain, for each second battery of the candidate vehicle, a training sample set corresponding to the second battery, wherein the training sample set includes training sample data and an expected output result corresponding to the training sample data, wherein the training sample data is second charge and discharge data of the second battery at a preset historical moment, and the expected output result is a third state of charge value of the second battery at the preset historical moment; input the training sample data into a pre-constructed initial network model to obtain a model output result corresponding to the training sample data; and adjust network parameters of the initial network model based on the model output result and the expected output result to obtain a battery state of charge prediction model corresponding to the second battery.

[0083] Optionally, the vehicle battery state of charge determination device further includes a charge and discharge data stream acquisition module. The charge and discharge data stream acquisition module is configured to display a first interface before acquiring a training sample set corresponding to the second battery of each candidate vehicle; wherein the first interface includes at least one vehicle identifier; in response to an identifier selection operation for at least one of the vehicle identifiers, determine the selected vehicle identifier; treat the vehicle battery corresponding to each selected vehicle identifier as a second battery, and acquire a charge and discharge data stream of the second battery within a preset historical period from the current moment; wherein the charge and discharge data stream includes third charge and discharge data of the second battery at each historical moment within the preset historical period from the current moment.

[0084] Optionally, the vehicle battery state of charge determination device further includes a data acquisition period setting module. The data acquisition period setting module is configured to display a second interface, before acquiring the charge and discharge data stream of the second battery within a preset historical period from the current moment, wherein the second interface includes a preset period template for acquiring battery charge and discharge data, the preset period template including a start time setting item and an end time setting item for acquiring battery charge and discharge data, wherein the end time setting item displays the current moment; and in response to a time setting operation for the start time item, obtain the charge and discharge data acquisition period for the second battery within the preset historical period from the current moment.

[0085] Optionally, the vehicle battery state of charge determination device further includes an information display module. The information display module is configured to, after acquiring the charge and discharge data stream of the second battery within a preset historical period from the current moment, determine change curve information of the third charge and discharge data and the first state of charge value of the second battery at various historical moments within the preset historical period from the current moment, and display the change curve information.

[0086] Optionally, the vehicle battery state of charge determination device further includes a first model updating module, wherein the first model updating module is configured to update the battery state of charge prediction model when a deviation between the first state of charge value and the second state of charge value exceeds a preset deviation threshold.

[0087] Optionally, the vehicle battery state of charge determination apparatus further includes a second model updating module. The second model updating module is configured to obtain model update time information of the battery state of charge prediction model in response to an update time configuration operation for the battery state of charge prediction model, and to update the battery state of charge prediction model based on the model update time information.

[0088] The device for determining the state of charge of a vehicle battery provided in an embodiment of the present invention can execute the method for determining the state of charge of a vehicle battery provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0089] It is worth noting that the various units and modules included in the above-mentioned vehicle battery charge status determination device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0090] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. 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 processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0091] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the random access memory (RAM) 13. The processor 11, the read-only memory (ROM) 12, and the random access memory (RAM) 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0093] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining the state of charge of a vehicle battery.

[0094] In some embodiments, the method for determining the state of charge of a vehicle battery may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via a read-only memory (ROM) 12 and / or a communication unit 19. When the computer program is loaded into a random access memory (RAM) 13 and executed by the processor 11, one or more steps of the method for determining the state of charge of a vehicle battery described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the state of charge of a vehicle battery in any other appropriate manner (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described 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 products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs for implementing the methods of the present invention 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 the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0098] 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 CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0099] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0100] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0101] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0102] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining the state of charge of a vehicle battery, characterized in that: Applied to the cloud, including: Obtaining first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle; Determining a target state of charge prediction model corresponding to the first battery based on a correspondence between a second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, inputting the first charge and discharge data into the target state of charge prediction model, and obtaining a second state of charge value of the first battery at the current moment; When a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, the second state of charge value is sent to the target vehicle, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

2. The method according to claim 1, characterized in that Before determining the target state of charge prediction model corresponding to the first battery based on the correspondence between the second battery of the candidate vehicle and the pre-trained battery state of charge prediction model, the method further includes: For each of the candidate vehicles' second batteries, obtaining a training sample set corresponding to the second battery, wherein the training sample set includes training sample data and an expected output result corresponding to the training sample data, the training sample data being second charge and discharge data of the second battery at a preset historical moment, and the expected output result being a third state of charge value of the second battery at the preset historical moment; Inputting the training sample data into a pre-built initial network model to obtain a model output result corresponding to the training sample data; Based on the model output result and the expected output result, network parameters of the initial network model are adjusted to obtain a battery state of charge prediction model corresponding to the second battery.

3. The method according to claim 2, characterized in that Before acquiring a training sample set corresponding to the second battery of each candidate vehicle, the method further includes: Displaying a first interface; wherein the first interface includes at least one vehicle identification; In response to an identification selection operation for at least one of the vehicle identifications, determining the selected vehicle identification; The vehicle battery corresponding to each selected vehicle identifier is separately used as a second battery, and a charge and discharge data stream of the second battery within a preset historical period from the current moment is obtained; wherein the charge and discharge data stream includes third charge and discharge data of the second battery at each historical moment within the preset historical period from the current moment.

4. The method according to claim 3, characterized in that Before acquiring the charge and discharge data stream of the second battery within a preset historical period from the current moment, the method further includes: Displaying a second interface, wherein the second interface includes a preset time period template for obtaining battery charge and discharge data, the preset time period template including a start time setting item and an end time setting item for obtaining battery charge and discharge data, wherein the end time setting item displays the current time; In response to the time setting operation for the start time item, a charging and discharging data acquisition period of the second battery in a preset historical period from the current moment is obtained.

5. The method according to claim 3, characterized in that After acquiring the charge and discharge data stream of the second battery within a preset historical period from the current moment, the method further includes: Determine change curve information of the third charge and discharge data and the first state of charge value of the second battery at each historical moment within a preset historical period from the current moment, and display the change curve information.

6. The method according to claim 1, characterized in that The method further comprises: When a deviation between the first state of charge value and the second state of charge value exceeds a preset deviation threshold, the battery state of charge prediction model is updated.

7. The method according to claim 1, characterized in that The method further comprises: In response to an update time configuration operation for the battery state of charge prediction model, model update time information of the battery state of charge prediction model is obtained, so as to update the battery state of charge prediction model based on the model update time information.

8. A device for determining the state of charge of a vehicle battery, characterized in that: Applied to the cloud, including: a first data acquisition module, configured to acquire first charge and discharge data and a first state of charge value of a first battery of a target vehicle at a current moment; wherein the first state of charge value is calculated based on an internal battery management system of the target vehicle; a second data acquisition model for determining a target state of charge prediction model corresponding to the first battery based on a correspondence between a second battery of the candidate vehicle and a pre-trained battery state of charge prediction model, inputting the first charge and discharge data into the target state of charge prediction model, and obtaining a second state of charge value of the first battery at a current moment; and a state of charge determination module, configured to send the second state of charge value to the target vehicle when a deviation between the first state of charge value and the second state of charge value does not exceed a preset deviation threshold, so that the target vehicle determines a target state of charge value of the first battery at the current moment based on the first state of charge value and the second state of charge value.

9. An electronic device, characterized in that: It is characterized by: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the state of charge of a vehicle battery according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the state of charge of a vehicle battery according to any one of claims 1 to 7 when executed.

Images