Storage battery charging control method and related device

Abstract

The embodiment of the invention discloses a storage battery charging control method and a related device, and belongs to the field of vehicles. The method comprises the following steps: acquiring state information of a storage battery in a vehicle, wherein the state information at least comprises a current state of charge (SOC), current, voltage and temperature; based on the state information of the storage battery, target output voltage of a direct current-direct current converter DCDC of the vehicle is determined through a neural network model; and controlling the DCDC to charge the storage battery according to the target output voltage. Namely, the target output voltage of the DCDC is determined through the neural network model, so that charging control is performed on the storage battery, and the SOC of the storage battery is better maintained at a proper level.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a battery charging control method and related devices. Background Art

[0002] With the development of social economy, considering the increasing loss of petroleum energy and the pollution of vehicle exhaust emissions to the environment, the industry has begun to seek new energy as the power source of the whole vehicle. Among them, electric vehicles using batteries (such as lead-acid batteries, lithium batteries, etc.) as the main energy source are an important research direction at present. The battery is a storage container for electrical energy. The battery can be charged and discharged to provide the required electrical energy for the vehicle. Overcharging and over-discharging will affect the life of the battery. Therefore, it is necessary to maintain the SOC (state of charge) of the battery at an appropriate level, and the maintenance of SOC mainly depends on controlling the vehicle's DCDC (DC (Direct Current) -to-DC converter) output voltage. How to control the DCDC output voltage has become an important research direction in the industry. Summary of the invention

[0003] The present application provides a battery charging control method and related devices, which can better control the charging of the battery, thereby maintaining the SOC of the battery at an appropriate level. The technical solution is as follows:

[0004] In one aspect, a battery charging control method is provided, the method comprising:

[0005] Acquire status information of a battery in a vehicle, wherein the status information includes at least current SOC, current, voltage and temperature;

[0006] Based on the state information of the battery, determining a target output voltage of the DCDC of the vehicle through a neural network model;

[0007] The DCDC is controlled to charge the battery according to the target output voltage.

[0008] In a possible implementation, the neural network model includes a first neural network model;

[0009] The method of determining a target output voltage of a DCDC of the vehicle by a neural network model based on the state information of the battery includes:

[0010] Inputting the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model, wherein the reference SOC is the SOC to be achieved by the battery during this charging;

[0011] The target output voltage is determined based on the state information of the battery and the reference SOC.

[0012] In a possible implementation, the status information further includes start-up indication information, where the start-up indication information indicates whether the battery is turned on;

[0013] The step of inputting the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model comprises:

[0014] When the start-up indication information indicates that the battery is turned on, the state information of the battery is input into the first neural network model to obtain the reference SOC output by the first neural network model.

[0015] In a possible implementation, the neural network model includes a second neural network model;

[0016] The method of determining a target output voltage of a DC-DC converter DCDC of the vehicle by a neural network model based on the state information of the battery includes:

[0017] Determine a reference SOC based on the state information of the battery, where the reference SOC is the SOC to be achieved by the battery during this charging;

[0018] The state information of the battery and the reference SOC are input into the second neural network model to obtain the target output voltage output by the second neural network model.

[0019] In a possible implementation, the status information also includes at least one of the accuracy of the current SOC, fault information, SOH (State of Health) and start-up indication information, wherein the start-up indication information indicates whether the battery is turned on, and the fault information indicates whether the battery has a fault.

[0020] On the other hand, a battery charging control device is provided, the battery charging control device comprising an acquisition module, a determination module and a control module;

[0021] An acquisition module is used to acquire status information of a battery in a vehicle, wherein the status information at least includes current SOC, current, voltage and temperature;

[0022] A determination module, configured to determine a target output voltage of a DCDC of the vehicle through a neural network model based on the state information of the battery;

[0023] A control module is used to control the DCDC to charge the battery according to the target output voltage.

[0024] In a possible implementation, the neural network model includes a first neural network model;

[0025] The determining module comprises:

[0026] A first determination submodule is used to input the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model, where the reference SOC is the SOC to be achieved by the battery during this charging;

[0027] The second determination submodule is used to determine the target output voltage based on the state information of the battery and the reference SOC.

[0028] In a possible implementation, the status information further includes start-up indication information, where the start-up indication information indicates whether the battery is turned on;

[0029] The first determining submodule is specifically used for:

[0030] When the start-up indication information indicates that the battery is turned on, the state information of the battery is input into the first neural network model to obtain the reference SOC output by the first neural network model.

[0031] In a possible implementation, the neural network model includes a second neural network model;

[0032] The determining module comprises:

[0033] A third determination submodule is used to determine a reference SOC based on the state information of the battery, where the reference SOC is the SOC to be achieved by the battery during this charging;

[0034] The fourth determination submodule is used to input the state information of the battery and the reference SOC into the second neural network model to obtain the target output voltage output by the second neural network model.

[0035] In one possible implementation, the status information also includes at least one of the accuracy of the current SOC, fault information, battery health status (SOH), and start-up indication information, wherein the start-up indication information indicates whether the battery is turned on, and the fault information indicates whether the battery has a fault.

[0036] In another aspect, a battery charging control device is provided, the device comprising:

[0037] processor;

[0038] a memory for storing processor-executable instructions;

[0039] The processor is configured to execute part or all of the steps in the above-mentioned battery charging control method.

[0040] On the other hand, a vehicle is provided, comprising a memory and a controller, wherein the memory is used to store a computer program, and the controller is used to execute the computer program stored in the memory to implement the battery charging control method described above.

[0041] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the above-mentioned battery charging control method is implemented.

[0042] On the other hand, a computer program product is provided, wherein computer instructions are stored in the computer program product, and when the computer instructions are executed by a processor, the above-mentioned battery charging control method is implemented.

[0043] The technical solution provided by this application can at least bring the following beneficial effects:

[0044] After obtaining information about the current SOC, current, voltage, temperature, etc. of the battery, the target output voltage of the DCDC is determined through a neural network model. Since the neural network model must be trained, and the trained neural network model must be recognized for its accuracy and prediction efficiency in analyzing and predicting the target output voltage of the DCDC, the target output voltage determined by the neural network model is more in line with the actual current power supply situation of the battery. Controlling the battery charging according to the target output voltage can better maintain the battery SOC at an appropriate level. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0047] Figure 2 is a flow chart of a battery charging control method provided in an embodiment of the present application;

[0048] Figure 3is a flow chart of another battery charging control method provided in an embodiment of the present application;

[0049] Figure 4 It is a structural schematic diagram of a battery charging control device provided in an embodiment of the present application;

[0050] Figure 5 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0052] Before explaining in detail the battery charging control method provided in the embodiment of the present application, the application scenarios involved in the embodiment of the present application are first introduced.

[0053] With the rapid development of energy technology, lithium batteries, lead-acid batteries and other batteries have been widely used in vehicles. Since the use conditions of batteries are relatively complex, and the charging effect of lithium batteries is greatly affected by the battery's own power, temperature and other charging parameters, and the change of charging parameters may cause the required charging voltage of the battery to change. If the charging voltage changes greatly, it may accelerate the loss of battery life and reduce the structural stability of the battery, which will lead to safety hazards in the process of vehicle power use. Therefore, the current charging stability of batteries is poor.

[0054] Based on this, an embodiment of the present application provides a battery charging control method, which can improve the charging stability of the battery and slow down the battery loss rate.

[0055] Before explaining in detail the charging control method provided in the embodiment of the present application, the implementation environment involved in the embodiment of the present application is first introduced.

[0056] Please refer to Figure 1 , Figure 1 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. The implementation environment includes a battery 101 , a battery sensor 102 , a DCDC controller 103 and a DCDC 104 .

[0057] The storage battery 101 is used to provide electric energy for the vehicle. For example, the storage battery 101 can be connected to one or more electric loads to provide electric energy for the connected electric loads.

[0058] The vehicle generally further includes a power battery (not shown in the figure). The power battery is used to charge the storage battery 101. Generally, in electric vehicles and hybrid vehicles, the power battery is also used to provide power energy for the vehicle.

[0059] In some embodiments, the current output by the power battery is a high voltage current, while the current required for charging the storage battery 101 is a low voltage current. Based on this, a DCDC 104 may be connected between the power battery and the storage battery 101, and the DCDC 104 is used to adjust the voltage output by the power battery to replenish the storage battery 101 with electric energy based on the current of the charging voltage required by the storage battery 101.

[0060] The battery sensor 102 is connected to the battery 101 and is used to obtain status information of the battery 101 and send the status information to the DCDC controller 103 .

[0061] The DCDC controller 103 can be connected to the battery sensor 102 and the DCDC 104, and can control the charging voltage of the battery 101 by adjusting the voltage output by the DCDC 104. For example, the DCDC controller 103 can obtain the status information of the battery 101 collected by the battery sensor 102, and determine the voltage required for charging the battery 101 based on the status information of the battery 101, and then adjust the output voltage of the DCDC 104 so that the voltage output by the DCDC 104 can meet the charging requirements of the battery 101.

[0062] In the embodiment of the present application, the implementation environment also includes a battery management system (referred to as management system, Figure 1 (not shown), the battery management system can be connected to the battery sensor 102 and the DCDC controller 103. The battery management system is used to obtain the status information of the battery 101 collected by the battery sensor 102 and send the status information to the DCDC controller 103.

[0063] The battery management system may be a LBMS (Low Voltage Battery Management System) of the vehicle, which is used to detect and monitor parameters such as voltage, current, temperature, SOC, and SOH of the battery 101 .

[0064] It should be noted that the application scenarios and implementation environments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. That is, those skilled in the art should understand that the above-mentioned battery 101, battery sensor 102, DCDC controller 103, DCDC104, power battery, and battery management system are only examples, and other existing or future power batteries, controllers, batteries, battery management systems, etc., if applicable to the embodiments of the present application, should also be included in the protection scope of the embodiments of the present application, and are included here by reference. In other words, those of ordinary skill in the art will know that with the evolution of application scenarios and vehicle system architectures, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0065] Next, the battery charging control method provided in the embodiment of the present application is explained in detail.

[0066] The execution subject of the battery charging control method provided in the embodiment of the present application is a controller (also referred to as a processor), such as the DCDC controller introduced above, or other controllers in the vehicle, such as ZCU (Zone Control Unit), VCU (Vehicle Control Unit), etc. The controller can be a general-purpose CPU (Central Processing Unit), NP (Network Processor), microprocessor, or one or more integrated circuits for implementing the scheme of the present application, for example, ASIC (Application-Specific Integrated Circuit), PLD (Programmable Logic Device) or a combination thereof. The above-mentioned PLD can be CPLD (Complex Programmable Logic Device), FPGA (Field-Programmable Gate Array), GAL (Generic Array Logic) or any combination thereof.

[0067] Figure 2 This is a flow chart of a battery charging control method provided in an embodiment of the present application. The method is applied to a controller, which may be a controller in a vehicle or a controller in other devices or equipment. This embodiment of the present application does not limit this. Please refer to Figure 2 , the method comprises the following steps.

[0068] Step 201: Acquire status information of a battery in a vehicle, where the status information at least includes the current state of charge SOC, current, voltage and temperature.

[0069] Among them, SOC is the state of charge of the battery, which is used to indicate the percentage of the remaining power of the battery to the rated capacity of the battery, that is, the current remaining capacity of the battery.

[0070] In some embodiments, the acquired state information also includes at least one of the accuracy of the current SOC, fault information, SOH, and start-up indication information, wherein the start-up indication information indicates whether the battery is turned on, that is, whether it is supplying power, and the fault information indicates whether the battery has a fault.

[0071] Since the embodiment of the present application is mainly used to realize the charging control of the battery, therefore, in a possible implementation, when the battery needs to be charged, step 201 is executed again. Based on this, in some scenarios, the current SOC and / or discharge voltage of the battery can be periodically obtained. When the current SOC of the battery is less than the SOC threshold and / or the discharge voltage of the battery is less than the voltage threshold, it is considered that the battery is currently insufficient and needs to be charged.

[0072] In the embodiment of the present application, the battery status information can be acquired by the battery management system and sent to the controller. The battery management system acquires the battery status information through the battery sensor, that is, the battery sensor acquires the battery status information and sends it to the battery management system.

[0073] In some embodiments, the controller also obtains the upper current limit, lower current limit, upper voltage limit and lower voltage limit of the battery to constrain the output voltage and output current of the DCDC. The upper current limit, lower current limit, upper voltage limit and lower voltage limit of the battery can also be used as information included in the battery status information.

[0074] Table 1 is an example of information that can be obtained by the controller in the embodiment of the present application. Referring to Table 1, the controller can obtain the current SOC of the battery, the accuracy of the current SOC, the current, the temperature, the voltage, the upper current limit, the lower current limit, the upper voltage limit and the lower voltage limit. Among them, the sender represents the party that collects information, and the receiver represents the party that receives information. In the embodiment of the present application, the sender can be an LBMS or a battery sensor, etc., and the receiver can be a controller, such as a ZCU.

[0075] Table 1

[0076]

[0077]

[0078] It should be understood that Table 1 is an example and is not used to limit the embodiments of the present application. In the specific implementation, the senders of various information may be the same or different, and the accuracy and scope of various information may also be selected according to actual needs. The embodiments of the present application do not limit these.

[0079] Step 202: Based on the battery status information, determine the target output voltage of the DC-DC converter DCDC of the vehicle through a neural network model.

[0080] That is, the controller determines the target output voltage of the DCDC through the neural network model.

[0081] In an embodiment of the present application, the neural network model includes a first neural network model; based on the status information of the battery, the target output voltage of the vehicle's DC-DC converter DCDC is determined by the neural network model, including: inputting the status information of the battery into the first neural network model to obtain a reference SOC output by the first neural network model, the reference SOC is the SOC to be achieved by the battery during this charging; based on the battery status information and the reference SOC, the target output voltage is determined.

[0082] In a possible implementation, when the state information also includes start-up indication information, if the start-up indication information indicates that the battery is turned on, the state information of the battery is input into the first neural network model to obtain the reference SOC output by the first neural network model. That is, when the vehicle is running (when the battery is turned on), the reference SOC is dynamically determined by the first neural network model.

[0083] In a possible implementation, if the start-up indication information indicates that the battery is not turned on, a preset static reference SOC is determined as the reference SOC. That is, when the vehicle is parked (the battery is not turned on), the static reference SOC is determined as the reference SOC. The static reference SOC is, for example, 100% or other larger values.

[0084] Exemplarily, "OFF" or "Comfortable" indicates that the battery is not turned on, and "ON" indicates that the battery is turned on. When the battery's on-state information is "OFF" or "Comfortable", the reference SOC is a static reference SOC. When the battery's on-state information changes from "OFF" or "Comfortable" to "ON", the reference SOC is dynamically determined by the first neural network model.

[0085] In some other embodiments, the controller determines the reference SOC based on the temperature of the battery and the current SOC of the power battery. In one possible implementation, the controller determines the reference SOC based on the temperature of the battery and the current SOC of the power battery according to a first mapping relationship. The first mapping relationship represents a mapping relationship function or a mapping relationship table between the temperature of the battery, the SOC of the power battery, and the reference SOC, which can be flexibly selected based on actual use requirements, and the embodiments of the present application do not limit this.

[0086] In a possible implementation manner, the first mapping relationship may be determined based on experimental statistical data and expert experience.

[0087] After determining the reference SOC, the controller determines a target output voltage of the DCDC based on the state information of the battery and the reference SOC.

[0088] In some embodiments, the neural network model includes a second neural network model, and the controller inputs the battery state information and the reference SOC into the second neural network model to obtain the target output voltage output by the second neural network model. That is, the controller determines the target output voltage through the second neural network model.

[0089] In some other embodiments, the controller determines the target output voltage according to the second mapping relationship based on the battery status information and the reference SOC. The second mapping relationship represents a mapping relationship function or a mapping relationship table between the battery status, the reference SOC, and the output voltage of the DCDC, which can be flexibly selected based on actual use requirements, and the embodiments of the present application are not limited to this.

[0090] As an example, the second mapping relationship represents a mapping relationship table between the battery temperature, the reference SOC, and the output voltage of the DCDC, and the controller determines the target output voltage according to the second mapping relationship based on the battery temperature and the reference SOC.

[0091] Table 2 is a mapping table of the battery temperature, reference SOC and output voltage of the DCDC provided in an embodiment of the present application. In Table 2, the first row represents the battery temperature, the first column represents the reference SOC, and the remaining data represents the output voltage of the DCDC.

[0092] Table 2

[0093]

[0094] It should be understood that Table 2 is an example and is not intended to limit the embodiments of the present application. In a specific implementation, the output voltage of the DCDC corresponding to different temperatures and reference SOCs can be determined according to actual needs, and the embodiments of the present application are not limited to this. In a possible implementation, the second mapping relationship can be determined based on experimental statistical data and expert experience.

[0095] Taking Table 2 as an example, after obtaining the battery temperature and reference SOC, the controller can determine the output voltage of the DCDC corresponding to the battery temperature and reference SOC by interpolation based on Table 2 to obtain the target output voltage.

[0096] In other embodiments, the controller may determine the SOC difference between the current SOC of the battery and the reference SOC, determine the target charging current corresponding to the SOC difference, obtain the current of the battery, determine the current difference between the current of the battery and the target charging current, determine the target charging voltage corresponding to the current difference, and determine the target charging voltage as the target output voltage of the DCDC. This implementation method may be referred to as a closed-loop compensation algorithm.

[0097] Among them, the controller can determine the target charging current corresponding to the SOC difference based on the third mapping relationship, and the third mapping relationship represents the mapping relationship between the SOC difference and the charging current. The controller can determine the target charging voltage corresponding to the current difference based on the fourth mapping relationship, and the fourth mapping relationship represents the mapping relationship between the current difference and the target charging voltage. In a possible implementation, the third mapping relationship and the fourth mapping relationship can be determined based on experimental statistical data and expert experience.

[0098] In some other embodiments, the controller may also determine the target charging current corresponding to the SOC difference based on the current SOC and reference SOC of the battery through a proportional, integral and differential control algorithm; and determine the target output voltage through a proportional, integral and differential control algorithm based on the current difference between the battery current and the target charging current.

[0099] Among them, the proportional, integral and differential control algorithm is referred to as the PID control algorithm, P refers to proportional control, I refers to integral control, and D refers to differential control.

[0100] In some other embodiments, the controller further obtains an output configuration word of the DCDC, the output configuration word is a first value or a second value, and different output configuration words represent different configurations of the DCDC, which is related to the model and specification of the DCDC. Wherein, when the output configuration word is a first value, the controller determines the output voltage of the DCDC according to the second mapping relationship. When the output configuration word is a second value, the controller determines the output voltage of the DCDC according to the above-mentioned closed-loop compensation algorithm.

[0101] The first value and the second value may be 0 and 1 respectively, or may be other values.

[0102] In some other embodiments, the controller determines whether the battery is faulty based on the fault information, and if the battery is faulty, the backup voltage is used to determine the output voltage of the DCDC. If the battery is not faulty, the output voltage of the DCDC is determined based on the output configuration word of the DCDC.

[0103] Figure 3 is a flow chart of another battery charging control method provided in an embodiment of the present application. Figure 3 First, the vehicle state is determined (it can be determined based on the battery start-up indication information). When the vehicle state indicates that the vehicle is stationary, the static reference SOC is determined as the reference SOC. When the vehicle state indicates that the vehicle is moving, the reference SOC is dynamically determined (for example, determined by the first neural network model). Then, it is determined whether the battery has a fault. In the case of a fault, the backup voltage is used to determine the output voltage of the DCDC. In the case of no fault, the output configuration word of the DCDC is determined. If the output configuration word is a first value (for example, 1), the output voltage of the DCDC is determined according to the MAP table (i.e., the second mapping relationship). If the output configuration word is a second value, the output voltage of the DCDC is determined according to the above-mentioned closed-loop compensation algorithm.

[0104] Combined with the above introduction, the controller first determines the reference SOC, and then determines the target output voltage based on the reference SOC. The reference SOC can be determined by the first neural network model or not, and after obtaining the reference SOC, the target output voltage can be determined by the second neural network model or not.

[0105] Based on this, another implementation method of the controller determining the target output voltage of the vehicle's DC-DC converter DCDC based on the battery status information through a neural network model is: based on the battery status information, determine the reference SOC, input the battery status information and the reference SOC into the second neural network model, and obtain the target output voltage output by the second neural network model.

[0106] The first neural network model and the second neural network model in the embodiment of the present application can be models of different architectures or models of the same architecture, which is not limited in the embodiment of the present application. The structures of the first neural network model and the second neural network model can also be the same or different, which is not limited in the embodiment of the present application. In one possible implementation, the first neural network model is a convolutional neural network model, a cyclic convolutional neural network model or other deep learning model, and the second neural network model is a convolutional neural network model, a cyclic convolutional neural network model or other deep learning model.

[0107] In addition, the embodiments of the present application do not limit the training method, model parameter quantity, number of layers, etc. of the first neural network model and the second neural network model. Among them, the first neural network model can be obtained by training with a first sample set, and the first sample set includes multiple state information samples and a reference SOC corresponding to each state information sample. The second neural network model can be obtained by training with a second sample set, and the second sample set includes multiple state information samples, a reference SOC corresponding to each state information sample, and the output voltage of the DCDC.

[0108] In some other embodiments, the controller inputs the battery status information into the neural network model to obtain the target output voltage of the DCDC output by the neural network model. That is, the target output voltage is directly obtained after analyzing the battery status information through a neural network model. The embodiments of the present application do not limit the architecture, structure, training method, model parameter quantity, number of layers, etc. of the neural network model. In one possible implementation, the neural network model is a convolutional neural network model, a recurrent convolutional neural network model, or other deep learning models. The neural network model can be obtained by training a third sample set, and the third sample set includes multiple status information samples and the output voltage of the DCDC corresponding to each status information sample.

[0109] Step 203: Control the DCDC to charge the battery according to the target output voltage.

[0110] After determining the target output voltage of the DCDC, the controller controls the DCDC to charge the battery according to the target output voltage, that is, controls the output voltage of the DCDC to be the target output voltage.

[0111] To summarize, in the embodiment of the present application, after obtaining various information such as the current SOC, current, voltage and temperature of the battery, the target output voltage of the DCDC is determined by a neural network model. Since the neural network model must be trained, and the trained neural network model must be recognized for its accuracy and prediction efficiency in analyzing and predicting the target output voltage of the DCDC, the target output voltage determined by the neural network model is more in line with the actual current power supply situation of the battery. The battery is charged and controlled according to the target output voltage, which can better maintain the SOC of the battery at an appropriate level.

[0112] All the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and the embodiments of the present application will not be described in detail one by one.

[0113] Figure 4 This is a schematic diagram of the structure of a battery charging control device provided in an embodiment of the present application. The battery charging control device 400 can be implemented by software, hardware or a combination of both to become part or all of a controller, which can be a controller of a vehicle or other equipment. Please refer to Figure 4 The battery charging control device 400 includes: an acquisition module 401, a determination module 402 and a control module 403.

[0114] An acquisition module 401 is used to acquire status information of a battery in a vehicle, where the status information at least includes current SOC, current, voltage and temperature;

[0115] A determination module 402, configured to determine a target output voltage of a DCDC of a vehicle through a neural network model based on the state information of the battery;

[0116] The control module 403 is used to control the DCDC to charge the battery according to the target output voltage.

[0117] In one possible implementation, the neural network model includes a first neural network model;

[0118] The determination module 402 includes:

[0119] A first determination submodule is used to input the state information of the battery into the first neural network model to obtain a reference SOC output by the first neural network model, where the reference SOC is the SOC to be achieved by the battery during this charging;

[0120] The second determination submodule is used to determine the target output voltage based on the state information of the battery and the reference SOC.

[0121] In a possible implementation, the status information further includes start-up indication information, where the start-up indication information indicates whether the battery is turned on;

[0122] The first determination submodule is specifically used for:

[0123] When the start-up indication information indicates that the battery is turned on, the state information of the battery is input into the first neural network model to obtain a reference SOC output by the first neural network model.

[0124] In one possible implementation, the neural network model includes a second neural network model;

[0125] The determination module 402 includes:

[0126] A third determination submodule is used to determine a reference SOC based on the state information of the battery, where the reference SOC is the SOC to be achieved by the battery during this charging;

[0127] The fourth determination submodule is used to input the battery status information and the reference SOC into the second neural network model to obtain the target output voltage output by the second neural network model.

[0128] In a possible implementation, the status information also includes at least one of the accuracy of the current SOC, fault information, battery health status (SOH), and start-up indication information, the start-up indication information indicates whether the battery is turned on, and the fault information indicates whether the battery has a fault.

[0129] In the embodiment of the present application, after obtaining various information such as the current SOC, current, voltage and temperature of the battery, the target output voltage of the DCDC is determined by a neural network model. Since the neural network model must be trained, and the performance of the trained neural network model for analyzing and predicting the accuracy and prediction efficiency of the target output voltage of the DCDC must also be recognized, therefore, the target output voltage determined by the neural network model is more in line with the actual current power supply situation of the battery. The battery is charged and controlled according to the target output voltage, which can better maintain the SOC of the battery at an appropriate level.

[0130] It should be noted that: the battery charging control device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when controlling the charging of the battery. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the battery charging control device provided in the above embodiment and the battery charging control method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0131] Figure 55 is a structural block diagram of a vehicle 500 provided in an embodiment of the present application. Generally, the vehicle 500 includes: a controller 501 and a memory 502 .

[0132] The controller 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The controller 501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA, and PLA (Programmable Logic Array). The controller 501 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU; the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the controller 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the controller 501 may also include an AI (Artificial Intelligence) processor, such as an NPU (Neural Network Processing Unit), which is used to process computing operations related to machine learning.

[0133] The memory 502 may include one or more non-temporary computer-readable storage media. The memory 502 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-temporary computer-readable storage medium in the memory 502 is used to store at least one instruction, which is used to be executed by the controller 501 to implement the battery charging control method provided in the method embodiment of the present application.

[0134] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by the controller, the steps of the battery charging control method in the above embodiment are implemented. For example, the computer-readable storage medium can be a ROM (read-only memory), a RAM (random access memory), a CD-ROM (compact disc read-only memory), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0135] It is worth noting that the computer-readable storage medium mentioned in the embodiments of the present application may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0136] It should be understood that all or part of the steps to implement the above embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-mentioned computer readable storage medium.

[0137] That is, in some embodiments, a computer program product is further provided, wherein computer instructions are stored in the computer program product, and when the computer instructions are executed by the controller, the steps of the battery charging control method are implemented. In other words, a computer program is provided, and when the computer program is executed by the controller, the battery charging control method is implemented.

[0138] It should be understood that the "at least one" mentioned herein refers to one or more, and "multiple" refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not limit them to be necessarily different.

[0139] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the status information involved in the embodiments of this application is obtained with full authorization.

[0140] The above-mentioned embodiments are provided for the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A battery charging control method, characterized in that: The method comprises: Acquire status information of a battery in a vehicle, wherein the status information includes at least current state of charge (SOC), current, voltage and temperature; Based on the state information of the battery, determining a target output voltage of a DC-DC converter DCDC of the vehicle through a neural network model; The DCDC is controlled to charge the battery according to the target output voltage.

2. The method according to claim 1, characterized in that The neural network model includes a first neural network model; The method of determining a target output voltage of a DC-DC converter DCDC of the vehicle by a neural network model based on the state information of the battery includes: Inputting the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model, wherein the reference SOC is the SOC to be achieved by the battery during this charging; The target output voltage is determined based on the state information of the battery and the reference SOC.

3. The method according to claim 2, characterized in that The state information further includes start-up indication information, wherein the start-up indication information indicates whether the battery is turned on; The step of inputting the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model comprises: When the start-up indication information indicates that the battery is turned on, the state information of the battery is input into the first neural network model to obtain the reference SOC output by the first neural network model.

4. The method according to claim 1, characterized in that The neural network model includes a second neural network model; The method of determining a target output voltage of a DC-DC converter DCDC of the vehicle by a neural network model based on the state information of the battery includes: Determine a reference SOC based on the state information of the battery, where the reference SOC is the SOC to be achieved by the battery during this charging; The state information of the battery and the reference SOC are input into the second neural network model to obtain the target output voltage output by the second neural network model.

5. The method according to any one of claims 1 to 4, characterized in that: The status information also includes at least one of the accuracy of the current SOC, fault information, battery health status SOH and start-up indication information, the start-up indication information indicates whether the battery is turned on, and the fault information indicates whether the battery has a fault.

6. A battery charging control device, characterized in that: The device comprises: An acquisition module is used to acquire status information of a battery in a vehicle, wherein the status information at least includes a current state of charge SOC, current, voltage and temperature; A determination module, configured to determine a target output voltage of a DC-DC converter DCDC of the vehicle through a neural network model based on the state information of the battery; A charging module is used to control the DCDC to charge the battery according to the target output voltage.

7. The device according to claim 6, characterized in that The determining module comprises: A first determination submodule is used to input the state information of the battery into the first neural network model to obtain the reference SOC output by the first neural network model, where the reference SOC is the SOC to be achieved by the battery during this charging; The second determination submodule is used to determine the target output voltage based on the state information of the battery and the reference SOC.

8. A vehicle, characterized in that: The vehicle comprises a memory and a controller, wherein the memory is used to store a computer program, and the controller is used to run the computer program to execute the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the controller, the method according to any one of claims 1 to 5 is implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed on the controller, the method according to any one of claims 1 to 5 is implemented.

Images