Vehicle battery health degree prediction method and storage medium

Abstract

The invention discloses a vehicle battery health degree prediction method and a storage medium. The vehicle battery health degree prediction method comprises the steps of obtaining a first battery parameter of a storage battery based on a first sensor deployed on the storage battery of a target vehicle, and determining a second battery parameter of the target vehicle battery based on the first battery parameter; determining predicted health degree information of the storage battery according to the first battery parameter, the second battery parameter and a battery health degree prediction model; under the condition that the predicted health degree information is smaller than or equal to a first preset threshold value, generating prompt information, and sending the prompt information to the target terminal; wherein the prompt information is used for reminding the user to replace the storage battery, so that the health degree prediction of the battery is realized, and the accuracy of the health degree prediction of the battery is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of storage batteries, and in particular to a method for predicting the health of a vehicle battery and a storage medium. Background Art

[0002] With the development of intelligence and networking, the number of necessary electronic and electrical equipment in vehicles is increasing. The increase in power consumption of vehicle equipment places higher and higher requirements on battery performance, and battery health prediction is particularly important.

[0003] In the existing technology, the health of the battery is predicted by collecting data such as the battery's voltage, current and temperature. However, there is a lack of in-depth analysis of the data such as voltage, current and temperature, resulting in low accuracy in battery health prediction. Summary of the Invention

[0004] The present invention provides a vehicle battery health prediction method and storage medium to obtain battery health information and improve the accuracy of battery health prediction.

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

[0006] Acquiring a first battery parameter of the battery based on a first sensor disposed on the battery of the target vehicle, and determining a second battery parameter of the battery of the target vehicle based on the first battery parameter;

[0007] Determining predicted health information of the battery based on the first battery parameter, the second battery parameter, and a battery health prediction model;

[0008] When the predicted health information is less than or equal to the first preset threshold, a prompt message is generated and sent to the target terminal; wherein the prompt message is used to remind the user to replace the battery.

[0009] According to another aspect of the present invention, a device for predicting vehicle battery health is provided, the device comprising:

[0010] a first battery parameter and a second battery parameter obtaining module, configured to obtain a first battery parameter of the battery based on a first sensor disposed on the battery of the target vehicle, and determine a second battery parameter of the battery of the target vehicle based on the first battery parameter;

[0011] a predicted health information determination module, configured to determine predicted health information of the battery based on the first battery parameter, the second battery parameter, and a battery health prediction model;

[0012] The prompt information generation module is used to generate prompt information when the predicted health information is less than or equal to a first preset threshold, and send the prompt information to the target terminal; wherein the prompt information is used to remind the user to replace the battery.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute a method for predicting vehicle battery health according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions. The computer instructions are used to enable a processor to implement a vehicle battery health prediction method according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein the computer program implements a vehicle battery health prediction method according to any embodiment of the present invention when executed by a processor.

[0019] The technical solution of the embodiment of the present invention obtains the first battery parameter of the battery by deploying a first sensor on the battery of the target vehicle, and determines the second battery parameter of the target vehicle battery based on the first battery parameter, so as to obtain more comprehensive battery parameters and provide comprehensive data support for subsequent analysis and processing; determines the predicted health information of the battery according to the first battery parameter, the second battery parameter and the battery health prediction model, thereby realizing the prediction of the battery health; when the predicted health information is less than or equal to the first preset threshold, generates a prompt message for reminding the user to replace the battery, and sends the prompt message to the target terminal, thereby reducing the possibility of vehicle failure due to battery failure, solving the problem of low accuracy of battery health prediction in the prior art, and improving the accuracy of battery health prediction.

[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 This is a flowchart of a method for predicting vehicle battery health provided by Example 1 of the present invention;

[0023] Figure 2 This is a flowchart of a method for training a battery health prediction model provided in Example 2 of the present invention;

[0024] Figure 3 This is a flow chart of a method for predicting vehicle battery health provided by an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of data flow in a battery health prediction process provided by an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a vehicle battery health prediction device provided by the third embodiment of the present invention;

[0027] Figure 6 This is a structural diagram of an electronic device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] 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.

[0030] Example 1

[0031] Figure 1 This is a flow chart of a method for predicting the health of a vehicle battery provided by the first embodiment of the present invention. This embodiment is applicable to the case of predicting the health of a vehicle battery. The method can be executed by a vehicle battery health prediction device, which can be implemented in the form of hardware and / or software and can be configured in a target vehicle. Figure 1 As shown, the method includes:

[0032] S110 : Acquire a first battery parameter of the battery based on a first sensor deployed on the battery of the target vehicle, and determine a second battery parameter of the battery of the target vehicle based on the first battery parameter.

[0033] The target vehicle is a vehicle equipped with a battery as an energy source or auxiliary energy source, including but not limited to traditional fuel vehicles, new energy vehicles and special vehicles. The first sensor is a sensor directly deployed on the battery, used to collect physical signals and electrochemical signals of the battery. The first sensor includes but is not limited to a voltage sensor, a current sensor, a temperature sensor and a pressure sensor. The first battery parameter is data collected by the first sensor that can reflect the real-time status of the battery. Optionally, the first battery parameter includes at least one of the battery's voltage information, current information, resistance information and temperature information. The voltage information can be measured by a voltage sensor connected in series to the battery; the current information can include charging current and discharging current, and the charging current and discharging current of the battery can be collected by connecting it in series in the charging and discharging circuit; the temperature information includes the temperature of the environment in which the battery is located, and can be collected by a temperature sensor deployed on the surface of the battery.

[0034] The second battery parameter is data obtained by deducing and calculating the first battery parameter. Optionally, the second battery parameter includes at least one of the following information: number of deep discharges, number of times the battery is not fully charged, state of charge information, and current power gain information.

[0035] The state of charge (SOC) information is the percentage of the battery's current remaining charge to its rated capacity, reflecting the battery's immediately available charge. The SOC information can be determined based on the current information in the first battery parameter. For example, the change in charge value over a preset time period can be calculated using the ampere-hour integration method, and the ratio of the change in charge value to the rated capacity can be calculated. The current SOC information can be calculated based on the initial SOC information and the ratio of the change in charge value to the rated capacity.

[0036] The deep discharge count is the cumulative number of times the battery's charge level is discharged from a high level to a low level during use. For example, the deep discharge count can be the cumulative number of times the battery's charge level is discharged from greater than or equal to 80% to less than or equal to 20%. The deep discharge count can be determined based on the SOC information and the current information in the first battery parameter. For example, a deep discharge threshold is set when the SOC information decreases from greater than or equal to 80% to less than or equal to 20%. When a single discharge process meets this deep discharge threshold, the deep discharge count is incremented by one.

[0037] The partially charged power usage count is the cumulative number of times the battery began to supply power when it was not fully charged. The partially charged power usage count can be determined based on the SOC information and the voltage and current information in the first battery parameters. For example, based on the voltage and current information in the first battery parameters, it is determined whether the battery charging process was interrupted. If the SOC information corresponding to the interruption is less than a preset threshold, the battery is determined to be partially charged, and the partially charged power usage count is incremented by 1.

[0038] The current charge gain information is the actual amount of charge added to the battery during a single charge, or the actual amount of charge lost during a single discharge. The current charge gain information can be determined based on the SOC information and the current information in the first battery parameter. Taking a single charge process as an example, the post-charge SOC information is determined based on the current information in the first battery parameter. The difference between the post-charge SOC information and the pre-charge SOC information is calculated, and the product of this difference and the rated capacity of the battery is calculated to obtain the current charge gain information.

[0039] By deploying a first sensor on the battery of the target vehicle, the first battery parameter of the battery is obtained, thereby realizing the collection of the first battery parameter; based on the first battery parameter, the second battery parameter of the target vehicle battery is determined, thereby realizing the accurate determination of the second battery parameter, providing accurate data support for subsequent analysis and processing, thereby ensuring the efficient and accurate execution of subsequent tasks.

[0040] In order to improve the accuracy of the first battery parameter and the second battery parameter, the data collected by the first sensor may be preprocessed.

[0041] Optionally, after obtaining the first battery parameters of the battery based on the first sensor deployed on the battery of the target vehicle, it also includes: preprocessing the first battery parameters, and updating the first battery parameters according to the preprocessing results; wherein the preprocessing includes data screening processing and / or erroneous data deletion processing.

[0042] The data collected by the first sensor includes data unrelated to battery health prediction. Data collected by the first sensor is screened to determine data relevant to battery health prediction. The data collected by the first sensor may contain erroneous data due to communication errors and sensor failures. This erroneous data is deleted from the data collected by the first sensor to obtain preprocessed first battery parameters.

[0043] Specifically, the first battery parameters are obtained by pre-processing the data collected by the first sensor by performing data screening and erroneous data deletion, thereby improving the accuracy of the first battery parameters and providing accurate data support for subsequent analysis and processing.

[0044] S120 . Determine predicted health information of the battery according to the first battery parameter, the second battery parameter, and a battery health prediction model.

[0045] The battery health prediction model is a model used for battery prediction. The battery health prediction model includes, but is not limited to, a machine learning model. The battery health prediction model can be configured as needed, without limitation. The input data of the battery health prediction model is the first battery parameter and the second battery parameter, and the output data of the battery health prediction model is the predicted health information.

[0046] Optionally, the battery health prediction model is trained using a machine learning model based on sample battery parameters and their corresponding actual battery health information. The sample battery parameters may include actual battery parameters and / or experimental battery parameters. The experimental battery parameters can be obtained by conducting actual battery usage simulation experiments. This setup has the advantage of enriching the sample data to train a more accurate battery health prediction model.

[0047] The predicted health information is a quantitative result that characterizes the future health status of the battery. The form of the predicted health information includes but is not limited to a score and a percentage.

[0048] Specifically, the first battery parameter and the second battery parameter are input into the battery health prediction model for processing to obtain predicted health information of the battery, thereby realizing the health prediction of the battery and improving the accuracy of the battery health prediction.

[0049] S130. When the predicted health information is less than or equal to a first preset threshold, generate a prompt message and send the prompt message to a target terminal; wherein the prompt message is used to remind the user to replace the battery.

[0050] Among them, the first preset threshold is a manually set health critical value for triggering a replacement reminder. The first preset threshold can be set according to the actual usage scenario and performance requirements of the battery. The prompt information is a notification content used to inform the user that the battery needs to be replaced when the predicted health information is less than or equal to the first preset threshold. The prompt information may include multiple forms, for example, it may be at least one of the forms of text information, picture information, and sound information. The target terminal is a device or platform for receiving prompt information, for example, the target terminal may include a mobile phone, a smart watch, and a car's central control screen. The target terminal can receive the prompt information through communication.

[0051] Specifically, when the predicted health information is less than or equal to a first preset threshold, a prompt message is generated and sent to the target terminal through communication. The user can replace the battery according to the prompt information received by the target terminal, providing data support for the user's decision-making, which is conducive to reducing the risk of failure of the target vehicle due to low battery health.

[0052] The technical solution of this embodiment obtains the first battery parameter of the battery based on a first sensor deployed on the battery of the target vehicle, and determines the second battery parameter of the target vehicle battery based on the first battery parameter, thereby providing comprehensive data support for subsequent analysis and processing; determines the predicted health information of the battery based on the first battery parameter, the second battery parameter and the battery health prediction model, thereby realizing the prediction of the battery health; when the predicted health information is less than or equal to a first preset threshold, generates a prompt message for reminding the user to replace the battery, and sends the prompt message to the target terminal, thereby providing data support for the user's decision-making, which is conducive to reducing the risk of failure of the target vehicle due to low battery health.

[0053] Example 2

[0054] Figure 2 This is a flowchart of a method for training a battery health prediction model provided by the second embodiment of the present invention. This embodiment is a refinement of the above embodiment. On the basis of the above embodiment, the training process of the battery health prediction model is detailed. For its specific implementation, please refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 2 As shown, the method includes:

[0055] S210: Acquire actual battery parameters of batteries of multiple reference vehicles and actual health information of the batteries under the actual battery parameters.

[0056] The reference vehicle is a vehicle used to collect real battery data. The actual battery parameters are data collected from the battery of the reference vehicle, which are used to characterize the usage status of the battery. Optionally, the actual battery parameters include a third battery parameter and a fourth battery parameter. The third battery parameter includes at least one of the battery's voltage information, current information, resistance information, and temperature information, and the fourth battery parameter includes at least one of the number of deep discharges, the number of times the battery is not fully charged, the state of charge information, and the current power gain information. The actual health information is a quantitative value of the actual current health status of the battery of the reference vehicle. The form of the actual health information includes but is not limited to a fraction and a percentage.

[0057] Specifically, the actual battery parameters of the batteries of multiple reference vehicles and the actual health information of the batteries under the actual battery parameters can be obtained through a database. The database stores the actual battery parameters of different reference vehicles and the actual health information of the batteries under the actual battery parameters. By obtaining the actual battery parameters of the batteries of multiple reference vehicles and the actual health information of the batteries under the actual battery parameters, a comprehensive data basis is provided for subsequent analysis and processing.

[0058] Specifically, for each reference vehicle, the third battery parameter of the battery can be obtained based on the second sensor deployed on the battery of the reference vehicle, and the fourth battery parameter of the battery can be determined based on the third battery parameter of the battery, and the actual battery parameter of the battery can be determined based on the third battery parameter and the fourth battery parameter.

[0059] Among them, the second sensor is a hardware device deployed on the battery of the reference vehicle, which is used to collect physical signals and electrochemical signals of the battery during operation. The second sensor includes but is not limited to a voltage sensor, a current sensor, a temperature sensor and a pressure sensor. The voltage information in the third battery parameter can be measured by a voltage sensor, the current information in the third battery parameter can be measured by a current sensor, and the temperature information in the third battery parameter can be measured by a temperature sensor. The state of charge information in the fourth battery parameter can be determined based on the current information in the third battery parameter, the number of deep discharges in the fourth battery parameter can be determined based on the state of charge information and the current information in the third battery parameter, the number of partially charged times in the fourth battery parameter can be determined based on the state of charge information, the voltage information and current information in the third battery parameter, and the current power gain information in the fourth battery parameter can be determined based on the state of charge information and the current information in the third battery parameter.

[0060] Specifically, for each reference vehicle, multiple second sensors are pre-deployed, and the multiple second sensors include a voltage sensor, a current sensor, and a temperature sensor. The third battery parameter of the battery is collected by the multiple second sensors, and the fourth battery parameter of the battery is calculated based on the third battery parameter of the battery. The third battery parameter and the fourth battery parameter constitute the actual battery parameter of the battery. Subsequent analysis and processing are performed based on the actual battery parameter of the battery, providing a comprehensive data basis for subsequent analysis and processing.

[0061] Optionally, actual health information of batteries of multiple reference vehicles under actual battery parameters is obtained, specifically including: determining the remaining battery capacity information of the battery based on the actual battery parameters, and mapping the remaining battery capacity information to the actual health information of the battery based on the remaining battery capacity information and a pre-set mapping relationship.

[0062] The remaining battery capacity information is the maximum available power that the battery can release in its current state, and can be calculated using actual battery parameters. For example, the third and fourth battery parameters can be processed using an ampere-hour integration method to determine the remaining battery capacity information of the battery.

[0063] Specifically, the third battery parameter and the fourth battery parameter are processed according to the ampere-hour integration method to obtain the remaining battery capacity information of the battery. Matching is performed in a pre-set mapping relationship based on the remaining battery capacity information, and the matched health information is used as the actual health information of the battery, thereby achieving accurate determination of the actual health information of the battery and providing accurate data support for subsequent analysis and processing.

[0064] S220 . Perform a usage simulation test on the experimental battery according to the actual battery parameters to obtain the experimental battery parameters and actual health information of the battery under the experimental battery parameters.

[0065] During the actual use of the battery of the reference vehicle, collecting the actual battery parameters of the battery and the actual health information of the battery under the actual battery parameters has the problem of long collection cycle and high cost. In order to reduce the collection cost and collection cycle of the actual battery parameters and the actual health information of the battery under the actual battery parameters, a simulation experiment can be conducted on the experimental battery. By simulating the use of the experimental battery, the experimental battery parameters and the actual health information of the battery under the experimental battery parameters are obtained, thereby reducing the collection cost and collection cycle of the actual battery parameters and the actual health information of the battery under the actual battery parameters. Among them, the experimental battery parameters include at least one of the information of the experimental battery, such as the number of deep discharges, the number of times it is not fully charged, the state of charge information, and the current power gain information.

[0066] As an optional implementation manner of an embodiment of the present invention, specifically, the charge and discharge curve and the ambient temperature curve of the battery are determined based on the actual battery parameters; the experimental battery is charged and discharged according to the charge and discharge curve, and the ambient temperature of the experimental battery is controlled according to the ambient temperature curve, so that the experimental battery is in a simulated usage state; when the experimental battery is in the simulated usage state, the experimental battery parameters of the experimental battery and the actual health information of the battery under the experimental battery parameters are obtained.

[0067] Among them, the charge and discharge curve is a curve that characterizes the change of voltage information and current information of the experimental battery over time during the charging or discharging process. The charge and discharge curve can be determined based on the voltage information and current information in the third battery parameter. For example, the voltage information and current information in the third battery parameter are fitted to obtain the charge and discharge curve of the experimental battery. The ambient temperature curve is a curve that characterizes the change of the ambient temperature of the experimental battery over time, reflecting the fluctuation pattern of the ambient temperature in different usage scenarios and at different times. The ambient temperature curve can be determined based on the temperature information in the third battery parameter. For example, the temperature information in the third battery parameter is fitted to obtain the ambient temperature curve of the experimental battery.

[0068] Specifically, the voltage information and current information in the third battery parameter are fitted to obtain the charge and discharge curve of the experimental battery, and the temperature information in the third battery parameter is fitted to obtain the ambient temperature curve of the experimental battery; the experimental battery is charged and discharged according to the charge and discharge curve, and the ambient temperature of the experimental battery is controlled according to the ambient temperature curve to simulate the actual usage state of the experimental battery to ensure that the simulated usage state and the actual usage state of the experimental battery are consistent; when the experimental battery is in the simulated usage state, the experimental battery parameters of the experimental battery and the actual health information of the battery under the experimental battery parameters are obtained, which is conducive to improving the authenticity and accuracy of the experimental battery parameters of the experimental battery and the actual health information of the battery under the experimental battery parameters, and provides accurate and real data support for subsequent analysis and processing.

[0069] Exemplarily, before conducting a usage simulation test on the experimental battery according to the actual battery parameters, a test bench is built. The test bench includes a charging and discharging system and an incubator. The charging and discharging system is used to perform charging and discharging operations on the battery used in the experiment. The incubator is used to provide the expected temperature environment for the battery used in the experiment, that is, to control the ambient temperature of the battery used in the experiment. During the experiment, the battery used in the experiment can be placed in the incubator. The charge and discharge curve is input into the charging and discharging system, and the ambient temperature curve is input into the incubator to put the experimental battery in a simulated usage state. By adjusting the voltage information and current information in the charging and discharging system, as well as the temperature information in the incubator, the actual usage state of the experimental battery (the battery used in the experiment) is simulated to ensure that the simulated usage state of the experimental battery is consistent with the actual usage state. When the experimental battery is in the simulated usage state, the experimental battery parameters and the actual health information of the battery under the experimental battery parameters are calculated based on the actual battery parameters.

[0070] S230 : Training a neural network model based on actual battery parameters, experimental battery parameters, and their corresponding actual health information to obtain a battery health prediction model.

[0071] Among them, the neural network model includes but is not limited to the convolutional neural network model and the transformer model. The neural network model can be selected according to the needs and is not limited here. The actual battery parameters and experimental battery parameters are input into the neural network model for processing. The model parameters of the neural network model are adjusted according to the experimental battery parameters and their corresponding actual health information until the neural network model reaches a convergence state, and the battery health prediction model is obtained, thereby realizing the training of the battery health prediction model.

[0072] As an optional implementation manner of an embodiment of the present invention, specifically: each group of actual battery parameters and experimental battery parameters are used as sample input data; the sample input data is input into a pre-established neural network model for processing to obtain predicted health information corresponding to the sample input data; the model parameters of the neural network model are adjusted based on the actual health information and the predicted health information to obtain a battery health prediction model.

[0073] The sample input data is the data set used to train the neural network model, including actual battery parameters and experimental battery parameters. The input data of the neural network model are actual battery parameters and experimental battery parameters, and the output data of the neural network model is the predicted health information.

[0074] Specifically, each group of actual battery parameters and experimental battery parameters is used as sample input data, and multiple sample input data are input into a pre-established neural network model for processing to obtain predicted health information corresponding to each sample input data. The loss of the neural network model is calculated according to the preset loss function, the actual health information and the predicted health information, and a loss threshold is set in advance. When the loss function of the neural network model is greater than the preset threshold, the model parameters of the neural network model are adjusted until the loss function of the neural network model is less than or equal to the preset threshold, and the training of the neural network model is terminated. Alternatively, when the loss function converges, the training of the neural network model is terminated, and the trained neural network model is used as a battery health prediction model, thereby realizing the training of the battery health prediction model, which is beneficial to improving the accuracy of the prediction of the battery health prediction model.

[0075] Optionally, S230 further includes: performing normalization processing on the sample input data, and inputting the normalized sample input data into a pre-established neural network model for processing.

[0076] In order to reduce the impact of the dimensions of different data in the sample input data and improve the convergence speed of the neural network model, the sample input data can be normalized and the normalized sample input data can be input into a pre-established neural network model for processing.

[0077] For example, see Figure 3 , Figure 3 This is a flow chart of a method for predicting vehicle battery health provided by an embodiment of the present invention. The method includes the following steps:

[0078] (1) User usage data is collected through battery sensors and T-boxes and uploaded to the cloud. The telematics box (T-box) is a key component in the Internet of Vehicles system, used to enable communication and data exchange between the vehicle and the outside world. The user usage data is the second battery parameter or the fourth battery parameter in the embodiments of the present invention.

[0079] (2) Use Python software tools to process data and construct battery charge and discharge curves and ambient temperature curves.

[0080] (3) Build a test bench for simulating battery operating conditions and establish a data sample library.

[0081] (4) Build and train artificial neural network prediction models based on data sample libraries.

[0082] (5) Deploy the model to the cloud to predict battery health in real time.

[0083] (6) Determine whether the battery life has reached the threshold.

[0084] (7) When the battery life reaches the threshold, it is sent to the user's mobile phone to remind the user to replace the battery; when the battery life does not reach the threshold, the battery health is continued to be predicted.

[0085] For example, see Figure 4 , Figure 4 This diagram illustrates the data flow during a battery health prediction process, as provided by an embodiment of the present invention. During this process, battery data passes through the battery sensor, the T-box (Telematic Box, an intelligent vehicle-mounted terminal in the connected vehicle system), a cloud-based battery health prediction model, and the user terminal.

[0086] The technical solution of this embodiment provides a comprehensive data basis for subsequent analysis and processing by obtaining the actual battery parameters of the batteries of multiple reference vehicles and the actual health information of the batteries under the actual battery parameters; performs a usage simulation test on the experimental battery according to the actual battery parameters to obtain the experimental battery parameters and the actual health information of the battery under the experimental battery parameters, thereby reducing the acquisition cost and acquisition cycle of the actual battery parameters and the actual health information of the battery under the actual battery parameters; trains a neural network model based on the actual battery parameters, the experimental battery parameters and their corresponding actual health information to obtain a battery health prediction model, thereby realizing the training of the battery health prediction model and helping to improve the accuracy of the prediction of the battery health prediction model.

[0087] Example 3

[0088] Figure 5 This is a schematic diagram of the structure of a vehicle battery health prediction device provided by the third embodiment of the present invention. Figure 5 As shown, the device includes: a battery parameter acquisition module 310, a battery health prediction module 320, and a prompt information generation module 330. The battery parameter acquisition module 310 is used to obtain a first battery parameter of the battery based on a first sensor deployed on the battery of the target vehicle, and determine a second battery parameter of the target vehicle battery based on the first battery parameter; the predicted health information determination module 320 is used to determine the predicted health information of the battery based on the first battery parameter, the second battery parameter, and the battery health prediction model; the prompt information generation module 330 is used to generate a prompt information when the predicted health information is less than or equal to a first preset threshold, and send the prompt information to the target terminal; wherein the prompt information is used to remind the user to replace the battery.

[0089] The technical solution of this embodiment is to obtain the first battery parameter of the battery through the first sensor deployed on the battery of the target vehicle through the battery parameter acquisition module 310, and determine the second battery parameter of the target vehicle battery based on the first battery parameter, thereby providing comprehensive battery data support for subsequent analysis and processing; the battery health prediction module 320 determines the predicted health information of the battery according to the first battery parameter, the second battery parameter and the battery health prediction model, thereby realizing the prediction of the battery health; the prompt information generation module 330 generates a prompt information for reminding the user to replace the battery when the predicted health information is less than or equal to the first preset threshold, and sends the prompt information to the target terminal, thereby reducing the possibility of vehicle failure due to battery failure, solving the problem of low accuracy of battery health prediction in the prior art, and improving the accuracy of battery health prediction.

[0090] Based on the above embodiment, the device optionally further includes a model training module, which is used to: obtain actual battery parameters of batteries of multiple reference vehicles and actual health information of the batteries under the actual battery parameters; perform a usage simulation test on the experimental battery according to the actual battery parameters to obtain the experimental battery parameters and the actual health information of the battery under the experimental battery parameters; and train a neural network model based on the actual battery parameters, the experimental battery parameters and their corresponding actual health information to obtain a battery health prediction model.

[0091] Optionally, the actual battery parameters include a third battery parameter and a fourth battery parameter.

[0092] Optionally, the model training module is also used to: for each reference vehicle, obtain the third battery parameter of the battery based on the second sensor deployed on the battery of the reference vehicle, determine the fourth battery parameter of the battery based on the third battery parameter of the battery, and determine the actual battery parameter of the battery based on the third battery parameter and the fourth battery parameter.

[0093] Optionally, the model training module is also used to: determine the remaining battery capacity information of the battery based on actual battery parameters, and map the remaining battery capacity information to the actual health information of the battery based on the remaining battery capacity information and a preset mapping relationship.

[0094] Optionally, the model training module is also used to: determine the charge and discharge curve and ambient temperature curve of the battery based on actual battery parameters; charge and discharge the experimental battery according to the charge and discharge curve, and control the ambient temperature of the experimental battery according to the ambient temperature curve, so that the experimental battery is in a simulated usage state; when the experimental battery is in a simulated usage state, obtain the experimental battery parameters of the experimental battery and the actual health information of the battery under the experimental battery parameters.

[0095] Optionally, the model training module is also used to: use each group of actual battery parameters and experimental battery parameters as sample input data; input the sample input data into a pre-established neural network model for processing to obtain predicted health information corresponding to the sample input data; adjust the model parameters of the neural network model based on the actual health information and the predicted health information to obtain a battery health prediction model.

[0096] Optionally, the model training module is further used to: normalize the sample input data, and input the normalized sample input data into a pre-established neural network model for processing.

[0097] Optionally, the first battery parameter includes at least one of voltage information, current information, resistance information, and temperature information of the battery.

[0098] Optionally, the second battery parameter includes at least one of the number of deep discharge times, number of times the battery is not fully charged, state of charge information, and current power gain information.

[0099] Optionally, the vehicle battery health prediction device further includes a battery parameter preprocessing module. The battery parameter preprocessing module is configured to, after obtaining first battery parameters of the battery based on a first sensor deployed on the target vehicle's battery, preprocess the first battery parameters and update the first battery parameters based on the preprocessing results; the preprocessing includes data screening and / or erroneous data deletion.

[0100] A vehicle battery health prediction device provided in an embodiment of the present invention can execute a vehicle battery health prediction method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0101] Example 4

[0102] Figure 6 1 is a structural diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 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 may 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 required herein.

[0103] like Figure 6As 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.

[0104] Various components in the electronic device 10 are connected to an input / output (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.

[0105] 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 dedicated 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 a method for predicting vehicle battery health.

[0106] In some embodiments, a method for predicting the health of a vehicle battery may be implemented as a computer program tangibly embodied 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 predicting the health of a vehicle battery described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for predicting the health of a vehicle battery in any other appropriate manner (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex 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.

[0108] Computer programs for implementing the vehicle battery health prediction method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can 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.

[0109] Example 5

[0110] The fifth embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute a method for predicting the health of a vehicle battery, the method comprising:

[0111] Based on a first sensor deployed on the battery of a target vehicle, a first battery parameter of the battery is obtained, and a second battery parameter of the battery of the target vehicle is determined based on the first battery parameter; predicted health information of the battery is determined according to the first battery parameter, the second battery parameter and a battery health prediction model; when the predicted health information is less than or equal to a first preset threshold, a prompt message is generated and sent to the target terminal; wherein the prompt message is used to remind the user to replace the battery.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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 predicting vehicle battery health, characterized in that: include: Acquiring a first battery parameter of the battery of the target vehicle based on a first sensor disposed on the battery, and determining a second battery parameter of the battery of the target vehicle based on the first battery parameter; Determining predicted health information of the battery according to the first battery parameter, the second battery parameter, and a battery health prediction model; When the predicted health information is less than or equal to a first preset threshold, a prompt message is generated and sent to a target terminal; wherein the prompt message is used to remind the user to replace the battery.

2. The method according to claim 1, characterized in that The battery health prediction model is obtained through the following training method: Acquiring actual battery parameters of batteries of a plurality of reference vehicles and actual health information of the batteries under the actual battery parameters; Performing a usage simulation test on the experimental battery according to the actual battery parameters to obtain experimental battery parameters and actual health information of the battery under the experimental battery parameters; A neural network model is trained based on the actual battery parameters, the experimental battery parameters and the corresponding actual health information to obtain a battery health prediction model.

3. The method according to claim 2, characterized in that The actual battery parameters include a third battery parameter and a fourth battery parameter; The obtaining of actual battery parameters of batteries of multiple reference vehicles includes: For each reference vehicle, a third battery parameter of the battery is obtained based on a second sensor deployed on the battery of the reference vehicle, and a fourth battery parameter of the battery is determined based on the third battery parameter of the battery. The actual battery parameter of the battery is determined based on the third battery parameter and the fourth battery parameter.

4. The method according to claim 2, characterized in that The obtaining of actual health information of batteries of multiple reference vehicles under the actual battery parameters includes: The remaining battery capacity information of the battery is determined based on the actual battery parameters, and the remaining battery capacity information is mapped to the actual health information of the battery based on the remaining battery capacity information and a preset mapping relationship.

5. The method according to claim 2, characterized in that The performing a usage simulation test on the experimental battery according to the actual battery parameters to obtain the experimental battery parameters and actual health information of the battery under the experimental battery parameters includes: determining a charge and discharge curve and an ambient temperature curve of the battery based on the actual battery parameters; charging and discharging the experimental battery according to the charge-discharge curve, and controlling the ambient temperature of the experimental battery according to the ambient temperature curve, so that the experimental battery is in a simulated use state; When the experimental battery is in the simulated use state, experimental battery parameters of the experimental battery and actual health information of the battery under the experimental battery parameters are obtained.

6. The method according to claim 2, characterized in that The training of the neural network model based on the actual battery parameters, the experimental battery parameters and the corresponding health information includes: Taking each group of the actual battery parameters and the experimental battery parameters as sample input data respectively; Inputting the sample input data into a pre-established neural network model for processing to obtain predicted health information corresponding to the sample input data; The model parameters of the neural network model are adjusted based on the actual health information and the predicted health information to obtain the battery health prediction model.

7. The method according to claim 6, characterized in that The step of inputting the sample input data into a pre-established neural network model for processing includes: The sample input data is normalized, and the normalized sample input data is input into a pre-established neural network model for processing.

8. The method according to claim 1, characterized in that The first battery parameter includes at least one of the voltage information, current information, resistance information and temperature information of the battery; the second battery parameter includes at least one of the number of deep discharge times, the number of times the battery is not fully charged, the state of charge information and the current power gain information.

9. The method according to claim 1, characterized in that After obtaining a first battery parameter of the battery based on a first sensor deployed on the battery of the target vehicle, the method further includes: Preprocessing is performed on the first battery parameter, and the first battery parameter is updated according to the preprocessing result; wherein the preprocessing includes data screening processing and / or erroneous data deletion processing.

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 vehicle battery health prediction method according to any one of claims 1 to 9 when executed.

Images