Method and system for predicting electric quantity of vehicle battery and electronic equipment

Abstract

The invention relates to the technical field of vehicle battery capacity prediction, and discloses a vehicle battery capacity prediction method and system and electronic equipment. During prediction, training data are firstly obtained; training the initial battery power prediction model by adopting the training data set to obtain a target battery power prediction model; and obtaining the current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge-discharge rate, and inputting the values into the target battery electric quantity prediction model to obtain the target battery electric quantity. The charging and discharging rate of the battery is used as an influence factor of battery electric quantity prediction, and the prediction accuracy of the vehicle battery electric quantity is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle battery power prediction, and in particular to a vehicle battery power prediction method, system and electronic equipment. Background Art

[0002] Lithium batteries are widely used as power systems for new energy vehicles due to their various advantages such as high single-cell voltage, high density and high safety. During use, real-time control of the battery's state of charge (SOC), that is, the vehicle's battery power, is an important task of the battery management system and an important parameter reflecting the various battery performances. For example, the value of the charge and discharge power, the battery voltage threshold and the boundary threshold of the vehicle's use are all related to the vehicle's battery power. Therefore, real-time and accurate estimation of the vehicle's battery power will greatly promote the development of new energy vehicles.

[0003] It is crucial to accurately estimate the vehicle battery charge. The vehicle battery charge reflects the proportion of the battery's current remaining charge to the total capacity, and to a certain extent reflects the health of the battery, which directly affects the vehicle's endurance and performance, and also has a certain impact on the optimal configuration of the vehicle's energy management. Accurate vehicle battery charge estimation can ensure that the battery operates within a safe range, avoid overcharging and over-discharging, and extend battery life. In electric and hybrid vehicles, vehicle battery charge estimation is also the core of the energy management system, helping to optimize energy distribution and improve overall energy efficiency. Therefore, accurate vehicle battery charge estimation is of great significance to ensuring vehicle safety, improving performance and user experience. Summary of the invention

[0004] Based on the above problems, the present application proposes a vehicle battery power prediction method, system and electronic device, which can accurately predict the vehicle battery power.

[0005] The present application provides a method for predicting the battery power of a vehicle, including the following steps: Acquire a training data set; the training data set includes historical battery temperature, historical battery current, historical battery voltage, historical battery internal resistance, historical battery charge and discharge rate, and actual battery power; Using the training data set to train the initial battery power prediction model to obtain a target battery power prediction model; The current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate are obtained and input into the target battery power prediction model to obtain the target battery power.

[0006] On the other hand, the present application also provides a vehicle battery power prediction system, which executes the above-mentioned vehicle battery power prediction method, and the system includes a battery parameter acquisition module, a vehicle consumption acquisition module, and a prediction module; The battery parameter acquisition module acquires the current battery temperature, current battery current, current battery voltage, current battery internal resistance and current battery charge and discharge rate; The vehicle consumption acquisition module uses the vehicle controller to obtain the total power consumption of the vehicle and the mileage of the vehicle; The prediction module, in the battery control system, obtains the target battery power through the target battery power prediction model according to the current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate.

[0007] Another aspect of the present application further provides an electronic device, the electronic device comprising: a processor and a memory; The processor executes the steps of any of the above-mentioned vehicle battery power prediction methods by calling the program or instruction stored in the memory.

[0008] The embodiments of the present application have the following technical effects: When predicting the vehicle battery power in this application, first obtain training data; then use the training data set to train the initial battery power prediction model to obtain the target battery power prediction model; then obtain the current battery temperature, current battery current, current battery voltage, current battery internal resistance and current battery charge and discharge rate, and input them into the target battery power prediction model to obtain the target battery power. Using the battery charge and discharge rate as an influencing factor for battery power prediction improves the prediction accuracy of the vehicle battery power. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 is a flow chart of a vehicle battery power prediction method provided in an embodiment of the present application; Figure 2 is a structural schematic diagram of a vehicle battery power prediction system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application; Figure 4 is an annotated diagram of charging efficiency provided in an embodiment of the present application; Figure 5 It is a schematic diagram of the selection, crossover and mutation operations in the genetic algorithm provided in the embodiment of the present application. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work belong to the scope of protection of the present application.

[0012] As the electric vehicle market grows, accurate management of remaining battery power becomes particularly important. Vehicle battery power prediction can monitor battery power in real time, helping car owners to arrange their trips reasonably and avoid running out of power, while extending battery life, improving performance, and reducing usage costs. When related technologies predict vehicle battery power, they only consider the vehicle's mileage when using the vehicle's electrical energy consumption, without considering the consumption of air conditioning, thermal management, and high-voltage accessories on the vehicle, resulting in a large prediction error for the vehicle's battery power.

[0013] Based on this problem, the vehicle battery power prediction method provided in this application takes the vehicle mileage and the consumption of air conditioning, thermal management and high-voltage accessories as the comprehensive consumption of the whole vehicle's electric energy; then, when estimating the current vehicle battery power through the target battery power prediction model, the input parameters are increased by the battery charge and discharge rate A on the basis of the battery temperature T, battery current I, battery voltage V, and battery internal resistance R, so as to further improve the accuracy of the prediction.

[0014] The battery charge and discharge rate refers to the current value required for the battery to discharge its rated capacity within a specified time. The battery charge and discharge rate determines how quickly a certain amount of energy can be stored in the battery, or how quickly the energy in the battery can be released. Therefore, how much capacity can be released at a high rate becomes an indicator of battery performance. The larger the capacity released at a high rate, the better the battery performance. Using the battery charge and discharge rate as an influencing factor for battery power prediction improves the accuracy of vehicle battery power prediction.

[0015] The vehicle battery power prediction method provided by this application is as follows: Figure 1 As shown, the following steps are included: Step S1: Acquire a training data set; the training data set includes historical battery temperature, historical battery current, historical battery voltage, historical battery internal resistance, historical battery charge and discharge rate, and actual battery power; Step S2: using the training data set to train the initial battery power prediction model to obtain a target battery power prediction model; The initial battery power prediction model refers to the model state before the training data set is used for training in the vehicle battery power prediction method. The model receives training data such as historical battery temperature, historical battery current, historical battery voltage, historical battery internal resistance, historical battery charge and discharge rate, and actual battery power, and learns and optimizes to obtain a target battery power prediction model that can more accurately predict the vehicle battery power. The initial battery power prediction model is the basis and starting point for building a high-precision prediction model.

[0016] Step S3: Obtain the current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate and input them into a target battery power prediction model to obtain a target battery power.

[0017] In some embodiments, the method for determining the actual battery power includes: Get the current battery temperature, current battery voltage and current charging efficiency of the battery; When the battery is in the charging stage, if the current battery temperature is not within the preset temperature range, or the current battery voltage is not within the preset voltage range, the actual battery capacity is determined according to the current charging efficiency.

[0018] In some embodiments, determining the actual battery power according to the current charging efficiency includes: Get the initial battery power and current battery rated capacity; The actual battery charge is determined based on the initial battery charge, the current battery rated capacity, and the current charging efficiency.

[0019] To ensure that the battery can work under the best and safest conditions, set the preset temperature range. By setting reasonable upper and lower temperature limits, the battery performance can be optimized, preventing damage to the battery from overheating or overcooling, while ensuring that the battery remains efficient and safe during the charging and discharging process. The preset temperature range can be flexibly set according to the actual needs of the user to ensure that the battery performance and safety match the user's specific application scenarios.

[0020] In some embodiments of the present application, 0°C ≤ preset temperature range ≤ 30°C, which can ensure the best balance between battery performance, safety and user needs.

[0021] When setting the upper and lower limits of the preset temperature range, the following factors should usually be considered: Battery material characteristics: Different types of batteries (such as lithium batteries, nickel-metal hydride batteries, etc.) have different sensitivities to temperature, and the temperature range needs to be set according to the thermal characteristics of the battery materials. If the thermal stability of the battery material is improved, the upper temperature limit may be allowed to be increased. If the performance of the battery material decreases at lower temperatures, the lower temperature limit may need to be increased.

[0022] Battery chemistry: The chemical reactions inside the battery have different activities at different temperatures. Too high or too low a temperature will affect the battery performance. If the chemical reaction remains active over a wider temperature range, the temperature range may need to be adjusted to accommodate this change. If the battery chemical reaction is more active at a specific temperature, a stricter upper temperature limit may be required to prevent overheating.

[0023] Safety threshold: When the battery is overheated, thermal runaway may occur, and when the temperature is too low, the battery structure may be damaged, so it is necessary to set a safe upper and lower temperature limit. If the battery technology advances so that the battery can work safely at higher or lower temperatures, the upper and lower temperature limits can be adjusted accordingly.

[0024] Ambient temperature: Temperature changes in the battery's environment, such as extreme weather conditions, need to be taken into account. When using the battery in extremely high or low temperatures, it may be necessary to lower the upper temperature limit or raise the lower temperature limit to protect the battery.

[0025] Battery cooling capability: The design and efficiency of the battery cooling system will affect the maximum temperature that the battery can reach. If the efficiency of the battery cooling system is improved, it may allow the upper temperature limit to be increased. If the cooling capability is reduced, the upper temperature limit may need to be lowered to prevent overheating.

[0026] Battery usage patterns: Different usage patterns, such as continuous charge and discharge, intermittent use, etc., have different effects on temperature. If the battery usage pattern becomes more intense (such as frequent rapid charge and discharge), the upper temperature limit may need to be lowered to prevent overheating.

[0027] Battery aging: As batteries age, their tolerance to temperature may decrease. As batteries age, their tolerance to temperature may decrease, so the upper temperature limit may need to be lowered and the lower temperature limit raised.

[0028] In general, the setting of upper and lower temperature limits needs to be considered comprehensively based on factors such as battery performance, safety, environmental conditions, and usage patterns. As these factors change, it may be necessary to periodically re-evaluate and adjust the temperature range to ensure that the battery operates at the optimal and safest temperature.

[0029] The preset voltage range is to ensure that the battery or electrical system can operate stably, safely and efficiently, meet the specific needs of different users and application scenarios, and optimize the performance of the battery. The preset voltage range can be flexibly adjusted according to the actual needs of the user to ensure that the performance of the electrical system or battery matches the user's specific application scenario. By accurately controlling the voltage range, the battery life can be extended, the system efficiency can be improved, the normal operation of the equipment can be guaranteed, and the user's high requirements for power quality and stability can be met.

[0030] In some embodiments of the present application, 3.2V≤preset voltage range≤3.4V, which can avoid damage caused by overvoltage or overcurrent, while ensuring stable and reliable power output under various conditions.

[0031] The voltage upper limit and voltage lower limit of the preset voltage range usually need to consider the following factors when setting: Battery chemistry: Batteries of different chemistry systems have different operating voltage ranges, and the voltage range needs to be set according to the battery type. If the new battery chemistry allows higher voltages, the upper voltage limit may need to be increased. If the new chemistry works more stably at lower voltages, the lower voltage limit may need to be lowered.

[0032] Battery performance: The voltage range should ensure that the battery can provide the required power and energy during the charge and discharge process. If the battery performance improves, the voltage range may need to be adjusted to accommodate higher energy output requirements. If the battery performance decreases, the voltage limit may need to be lowered to prevent over-discharge.

[0033] Safety voltage limit: To avoid overcharging and over-discharging of the battery, it is necessary to set safe upper and lower voltage limits. If the safety test of the battery shows that it can work safely at a higher voltage, it may be necessary to increase the upper voltage limit. If the safety test shows that a lower voltage limit can reduce safety risks, it may be necessary to lower the upper voltage limit.

[0034] Battery Life: Long-term operation at extreme voltages may shorten battery life. To extend battery life, the upper voltage limit may need to be lowered to reduce the risk of overcharging. Similarly, the lower voltage limit may need to be raised to avoid deep discharge.

[0035] Battery Management System (BMS): The design and control strategy of the BMS needs to be able to handle the set voltage range. If the monitoring and control capabilities of the BMS are improved, the voltage can be controlled more accurately, which may allow a wider voltage range. If the BMS can better handle voltage fluctuations, the voltage range may need to be adjusted to optimize performance.

[0036] The estimation of the vehicle battery power requires accurate voltage information, so the setting of the voltage range needs to take into account the estimation accuracy requirements of the vehicle battery power. If the vehicle battery power estimation becomes more accurate, the voltage range may need to be adjusted to better reflect the actual state of the battery.

[0037] Battery aging and health: Battery aging may change its voltage characteristics, requiring the voltage range to be adjusted to accommodate aging batteries. As batteries age, their voltage characteristics may change, and the upper voltage limit may need to be lowered and the lower voltage limit raised to accommodate the performance changes of aging batteries.

[0038] Charge and discharge curves: The charge and discharge curve of a battery can help determine the optimal voltage range. If the charge and discharge curve shows that the battery performs best at a specific voltage, the voltage range may need to be adjusted to optimize performance.

[0039] In general, the setting of the upper and lower voltage limits needs to be considered comprehensively based on factors such as battery performance, safety, environmental conditions, usage patterns, and the capabilities of the battery management system. As these factors change, it may be necessary to periodically re-evaluate and adjust the voltage range to ensure that the battery operates in the best and safest working condition.

[0040] Based on the problem of large prediction errors of vehicle battery power, in order to make the prediction model obtain more accurate reference variables, the two algorithms, the ampere-hour integration method and the ampere-hour integration method using charging efficiency, are integrated for calculation. This is because when the temperature is high, the battery voltage will change significantly, which is easy to trigger voltage correction of the vehicle battery power, while when the temperature is low, the battery activity is low. Even if the same amount of energy is replenished, the vehicle battery power cannot be restored to the initial value. When the temperature is low, the BMS will correct it when estimating the vehicle battery power. Therefore, the charging efficiency estimation method can be used when the temperature is low or high, and the ampere-hour integration method can be used to estimate the vehicle battery power when the battery performance is stable.

[0041] For example, taking lithium iron phosphate as an example, the voltage fluctuation in the range of 2.8V~3.2V is large, and the charging current will be affected accordingly. Therefore, it is recommended to use charging efficiency estimation. 3.4V~3.65V also belongs to the range with large fluctuations. It is also recommended to use the charging efficiency estimation method. Only in the platform area of ​​3.2V~3.4V can the ampere-hour integration be used. Based on the above, a piecewise function can be established to represent the actual vehicle battery power.

[0042] In some embodiments of the present application, the actual battery power is determined according to the initial battery power, the current battery rated capacity and the current charging efficiency, and can be calculated by the ampere-hour integration method, and the formula is as follows: - ; In the formula, SOC efficent Indicates the actual battery capacity when the current battery temperature is not within the preset temperature range or the current battery voltage is not within the preset voltage range in the charging state. SOC0 indicates the initial battery capacity. η charge represents the current charging efficiency, i(t) is the battery current at time t, t0 represents the initial time of the test, and C is the current rated capacity of the battery.

[0043] In some embodiments, the vehicle battery power prediction method further includes: Obtain the battery charging power per unit time and the average power consumption of the vehicle per unit time; The current charging efficiency is obtained based on the ratio of the battery charging power per unit time to the average power consumption of the vehicle per unit time.

[0044] How to define the current charging efficiency? We can understand it as dividing the charging time into multiple time periods. The definition of the interval length of each time period is calibrated according to multiple sets of experimental data. For a simple example, the total charging time is 1 minute, and 1 minute can be divided into 12 parts, each part is 5 seconds, that is, the ratio of the battery charging power in 5 seconds to the average power consumption of the vehicle is defined as the battery charging efficiency. In fact, the definition of unit time needs to be obtained based on test calibration. The ratio of the battery charging power per unit time to the average power consumption of the vehicle per unit time is used as the current charging efficiency, which can be expressed as: ; Where W charge Indicates the battery charging power per unit time, W 平均功耗 Indicates the average power consumption of the vehicle per unit time.

[0045] For example, the concept of charging efficiency can also be represented by a graph, such as Figure 4 As shown, that is, the ratio of power consumption per unit time to charging power per unit time, the relationship between multiple sets of data charging efficiency and battery capacity can be established. For example: if the battery power drops by 0.1% in 10 seconds during the discharge process, we can observe whether 0.1% of the capacity is replenished in 10 seconds during charging, which means that the charging efficiency is 1, and the vehicle battery power increases by 0.1%.

[0046] In some embodiments, the method for determining the average power consumption of the vehicle per unit time is: Obtain the total power consumption of the vehicle per unit time and the mileage of the vehicle per unit time; According to the ratio of the total power consumption of the vehicle in a unit time to the mileage of the vehicle in a unit time, the average power consumption of the vehicle in the unit time is obtained.

[0047] The average power consumption per unit time of the vehicle proposed in this application is calculated based on the energy consumption. The ratio of the total power consumption per unit time of the vehicle to the mileage of the vehicle per unit time is taken as the average power consumption per unit time of the vehicle. The average power consumption per unit time of the vehicle is calculated by the following formula W 平均功耗 : W 平均功耗= W 总 / H; Where W 总is the total power consumption of the vehicle per unit time, and H is the mileage of the vehicle per unit time.

[0048] The total power consumption of the vehicle per unit time includes the current consumed by the vehicle's mileage, as well as the power consumed by the air conditioner, thermal management, and high-voltage accessories during driving. This can be read from the vehicle controller (VCU). The mileage of the vehicle per unit time can also be read directly.

[0049] In the process of predicting the target battery power in this application, the average power consumption of the vehicle is added to the process of predicting the target battery power, and the total power consumption of the vehicle during vehicle use is comprehensively considered, rather than just considering the power consumption of the vehicle's mileage. This is more in line with the actual usage scenario of the vehicle, making the prediction result of the target battery power more accurate.

[0050] If the battery is in charging state, the temperature is within the preset temperature range and the voltage is within the preset voltage range, the vehicle battery capacity is calculated by the ampere-hour integration method based on the battery initial SOC and the battery rated capacity; In some embodiments, the method for determining the actual battery power further includes: Get the current battery temperature, current battery current and current battery voltage of the battery; When the battery is in a charging stage, the current battery temperature is within a preset temperature range and the current battery voltage is within a preset voltage range, or when the battery is in a discharging stage, the actual battery capacity is determined according to the current battery current.

[0051] In some embodiments, determining the actual battery power according to the current battery current includes: Get the initial battery power and current battery rated capacity; The actual battery capacity is determined based on the initial battery capacity, the current battery rated capacity and the current battery current. It is calculated using the ampere-hour integration method, and the formula is as follows: - ; Wherein, SOC represents the actual battery capacity when the battery is in the charging stage, the current battery temperature is within the preset temperature range and the current battery voltage is within the preset voltage range, or when the battery is in the discharging stage, SOC0 represents the initial battery capacity, i(t) is the battery current at time t, t0 represents the initial time of the test, and C is the current rated capacity of the battery.

[0052] Since the amount of electricity consumed by a vehicle during non-driving mileage varies under different temperatures and voltages, this application only takes into account the influencing factors of the vehicle's average power consumption when calculating the target battery power under charging and only when the temperature is not within the preset temperature range and the voltage is not within the preset voltage range, so as to improve the prediction efficiency while taking into account the prediction accuracy.

[0053] When the training data set is used to train the initial battery capacity prediction model, the above two calculation scenarios of the actual battery capacity are included in the training data set. Therefore, the target battery capacity prediction model obtained after training can be applied to the prediction of the vehicle battery capacity under charging and discharging states.

[0054] In the training data set used to train the target battery power prediction model in this application, the calculation process of the vehicle battery power adds the vehicle's average power consumption, comprehensively considering the total power consumption of the vehicle during vehicle use, rather than just considering the power consumption of the vehicle's mileage, which is more in line with the vehicle's actual usage scenarios and makes the prediction results of the vehicle's battery power more accurate.

[0055] There are many models for predicting vehicle battery power, such as deep learning models, support vector machines, random forests, etc. However, genetic algorithms can explore multiple areas of the solution space through operations such as crossover and mutation, avoiding falling into local optimal solutions. This robustness enables genetic algorithms to maintain high prediction accuracy when faced with complex and changeable battery characteristics. Therefore, this application chooses genetic algorithms to predict vehicle battery power.

[0056] In some embodiments, a genetic algorithm is used to iteratively update the target battery power prediction model through fitness scores. The calculation formula of the target battery power prediction model is: ; In the formula, SOC 预测 represents the predicted vehicle battery capacity, f represents the function used by the genetic algorithm, T is the battery temperature, I is the battery current, V is the battery voltage, R is the battery internal resistance, and A is the battery charge and discharge rate.

[0057] The change in battery power is affected by many factors, including charge and discharge current, temperature, aging, etc. The relationship between these factors is often nonlinear. Genetic Algorithm (GA) can handle complex nonlinear problems and find the global optimal solution instead of the local optimal solution by simulating natural selection and genetic mechanisms. The characteristics of the battery will change over time and with usage. The genetic algorithm can adapt to these changes through continuous learning and evolution, maintaining the accuracy and effectiveness of the prediction model. This adaptive ability is particularly important for long-term vehicle batteries.

[0058] In some embodiments of the present application, the vehicle battery power prediction method further includes: Obtain the error between the target battery power and the actual battery power; wherein the error may be a root mean square error or an absolute error, etc., and the present application uses the method shown in the following formula to calculate the error between the target battery power and the actual battery power: ; Where, fitness i represents the fitness score of the i-th training data set, N is the number of training data sets, represents the predicted vehicle battery capacity of the target battery capacity prediction model corresponding to the i-th training data set, Represents the labeled vehicle battery power corresponding to the i-th training data set.

[0059] The target battery power prediction model is then updated using error back propagation.

[0060] Fitness function evaluation plays a very critical role in optimizing model parameters, solving the difference between the initial battery power value and the actual battery power value, and improving the coupling performance of the target battery power prediction model. In the process of building the target battery power prediction model, it needs to be optimized. The genetic algorithm obtains battery power individuals that are closer to the actual value, and each individual represents the measurement model under the parameters at that time.

[0061] The fitness function evaluation is realized by using methods such as root mean square deviation or absolute error. When evaluating the fitness, the above individual parameters are substituted into the model to obtain the individual fitness of the predicted value and the actual value. The higher the fitness score, the more optimal the individual solution. As the genetic algorithm proceeds, the quality of the solution will improve and the fitness will increase. When the fitness score meets the preset fitness score, the iteration is terminated and the training of the prediction model is completed. Exemplarily, the fitness score can be preset to 1, that is, the closer to 1, the more suitable.

[0062] Selection, crossover, and mutation operations: Specific individuals are selected for reproduction and production of offspring based on fitness values. Individuals with higher values ​​are selected and their genetic material is passed on to the next generation. Crossover is to create a pair of new individuals. Usually, some chromosomes from the current parent generation are exchanged to create two new chromosomes representing the offspring. This operation is called crossover or recombination. Figure 5 shown.

[0063] In the mutation operation, a parameter of an individual can be randomly selected, and a certain random value can be increased or decreased to increase the diversity of the population. For example, the temperature parameter or voltage parameter in an individual can be mutated to obtain a new individual.

[0064] Finally, through continuous reproduction and iteration, the individual with the highest fitness is selected as the final optimization result, and the optimization parameters of the target battery power prediction model are obtained, thereby fitting a target battery power prediction model that is closer to the actual battery power value. The target battery power prediction model of this application has input parameters such as temperature, current, voltage, and internal resistance, as well as charge and discharge rate, which combines the battery's charge and discharge capabilities per unit time with the vehicle's average power consumption to further improve the prediction accuracy of the vehicle's battery power. This prevents battery abuse, which can cause overcharging or over-discharging, and protects the health of the battery; it helps the entire vehicle understand the power of the current battery system more clearly, and avoids complaints from customers when using it.

[0065] Some embodiments of the present application further provide a vehicle battery power prediction system, which executes any of the above vehicle battery power prediction methods, such as Figure 2 As shown, the system includes a battery parameter acquisition module, a vehicle consumption acquisition module, and a prediction module; Battery parameter acquisition module, which obtains the current battery temperature, current battery current, current battery voltage, current battery internal resistance and current battery charge and discharge rate; The vehicle consumption acquisition module uses the vehicle controller to obtain the total power consumption and mileage of the vehicle; The prediction module, in the battery control system, obtains the target battery power through the target battery power prediction model according to the current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate.

[0066] Some embodiments of the present application further provide an electronic device, the electronic device comprising: Processor and memory; The processor is used to execute the steps of any of the above-mentioned vehicle battery power prediction methods by calling the program or instructions stored in the memory.

[0067] Figure 3 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 , the electronic device 500 includes one or more processors 501 and a memory 502.

[0068] The processor 501 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.

[0069] The memory 502 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 501 may run the program instructions to implement the vehicle battery power prediction method of any embodiment of the present application described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0070] In one example, the electronic device 500 may further include: an input device 503 and an output device 504, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 503 may include, for example, a keyboard, a mouse, etc. The output device 504 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 504 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0071] Of course, to simplify, Figure 3 Only some of the components related to the present application in the electronic device 500 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 500 may also include any other appropriate components.

[0072] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the vehicle battery power prediction method provided by any embodiment of the present application.

[0073] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0074] In addition, another aspect of the present application provides a storage medium, which stores a computer executable program, and the computer executable program is called by a processor to execute the steps of any of the above-mentioned vehicle battery power prediction methods.

[0075] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0076] It should be noted that the terms used in this application are only for describing specific embodiments, rather than limiting the scope of this application. As in the specification of this application, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0077] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present application.

Claims

1. A vehicle battery power prediction method, characterized in that: The following steps are involved: Acquire a training data set; the training data set includes historical battery temperature, historical battery current, historical battery voltage, historical battery internal resistance, historical battery charge and discharge rate, and actual battery power; Using the training data set to train an initial battery power prediction model to obtain a target battery power prediction model; The current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate are obtained, and input into the target battery power prediction model to obtain the target battery power.

2. The vehicle battery power prediction method according to claim 1, characterized in that: The method further comprises: Get the current battery temperature, current battery voltage and current charging efficiency of the battery; When the battery is in the charging stage, if the current battery temperature is not within the preset temperature range, or the current battery voltage is not within the preset voltage range, the actual battery power is determined according to the current charging efficiency.

3. The vehicle battery power prediction method according to claim 2, characterized in that: Determining the actual battery power according to the current charging efficiency includes: Get the initial battery power and current battery rated capacity; The actual battery capacity is determined according to the initial battery capacity, the current battery rated capacity and the current charging efficiency.

4. The vehicle battery power prediction method according to claim 1, characterized in that: The method further comprises: Get the current battery temperature, current battery current and current battery voltage of the battery; When the battery is in a charging stage, the current battery temperature is within a preset temperature range and the current battery voltage is within a preset voltage range, or when the battery is in a discharging stage, the actual battery power is determined according to the current battery current.

5. The vehicle battery power prediction method according to claim 4, characterized in that: Determining the actual battery power according to the current battery current includes: Get the initial battery power and current battery rated capacity; The actual battery capacity is determined according to the initial battery capacity, the current battery rated capacity and the current battery current.

6. The vehicle battery power prediction method according to claim 1, characterized in that: The method further comprises: Obtaining an error between the target battery power and the actual battery power; The target battery power prediction model is updated using the error back propagation.

7. The vehicle battery power prediction method according to claim 2, characterized in that: The method further comprises: Obtain the battery charging power per unit time and the average power consumption of the vehicle per unit time; The current charging efficiency is obtained according to the ratio of the battery charging power per unit time to the average power consumption of the vehicle per unit time.

8. The vehicle battery power prediction method according to claim 7, characterized in that: The method further comprises: Obtain the total power consumption of the vehicle per unit time and the mileage of the vehicle per unit time; According to the ratio of the total power consumption of the vehicle in a unit time to the mileage of the vehicle in a unit time, the average power consumption of the vehicle in the unit time is obtained.

9. A vehicle battery power prediction system, executing the vehicle battery power prediction method according to any one of claims 1 to 8, characterized in that: The system includes a battery parameter acquisition module, a vehicle consumption acquisition module, and a prediction module; The battery parameter acquisition module acquires the current battery temperature, current battery current, current battery voltage, current battery internal resistance and current battery charge and discharge rate; The vehicle consumption acquisition module uses the vehicle controller to obtain the total power consumption of the vehicle and the mileage of the vehicle; The prediction module, in the battery control system, obtains the target battery power through the target battery power prediction model according to the current battery temperature, the current battery current, the current battery voltage, the current battery internal resistance and the current battery charge and discharge rate.

10. An electronic device, characterized in that: The electronic device comprises: a processor and a memory; The processor executes the steps of the vehicle battery power prediction method according to any one of claims 1 to 8 by calling the program or instruction stored in the memory.

Images