Battery remaining capacity prediction method and device, computer equipment and storage medium
By obtaining battery operating parameters, calling performance models and power models to predict the performance parameters and real discharge of the battery, the problem of low accuracy of battery residual power prediction in the prior art is solved, and higher prediction accuracy is achieved.
Patent Information
- Application Number
- CN202411294938.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2025-03-04
AI Technical Summary
The existing battery residual battery prediction method has low accuracy and fails to fully consider the impact of the battery itself, environmental conditions and working conditions.
By obtaining the operating parameters of the battery to be predicted, calling the pre-trained performance model to predict the performance parameters, combining the power model to predict the real discharge based on the operating parameters and performance parameters, and finally determining the remaining power.
This method can more accurately consider the impact of multiple factors on the battery SOC, significantly improving the accuracy of battery residual battery prediction.
Smart Images
Figure CN119556162A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of energy storage technology, and in particular to a method, device, computer equipment and storage medium for predicting remaining battery power. Background Art
[0002] In the field of electric vehicles, the prediction of the remaining capacity (SOC) of the battery is a crucial technical issue. The SOC of the battery is affected by many factors, such as the battery state, environmental conditions, and working conditions. However, the existing SOC prediction methods often do not fully consider the influence of these factors, resulting in low prediction accuracy. Summary of the invention
[0003] In view of this, the present disclosure proposes a battery remaining power prediction method, device, computer equipment and storage medium to solve the problem of low accuracy of battery remaining power prediction in the related art.
[0004] The first embodiment of the present disclosure provides a method for predicting the remaining battery power, the method comprising:
[0005] Obtaining operating parameters of the battery to be predicted;
[0006] Calling a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters; the performance parameters are used to characterize the impact of internal changes of the battery to be predicted on the battery charging and discharging capacity;
[0007] Calling a power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; the power model is obtained by training based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge capacities, and performance parameters and operating parameters corresponding to each discharge capacity;
[0008] The remaining power of the battery to be predicted is determined according to the current power of the battery to be predicted and the actual discharge power.
[0009] The disclosed embodiment calls a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters, and calls a power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters, and determines the remaining power of the battery to be predicted according to the current power of the battery to be predicted and the actual discharge capacity. This can fully consider the impact of various factors such as the battery's own state, environmental conditions, and working conditions on the battery SOC prediction, thereby greatly improving the accuracy of the battery remaining power prediction.
[0010] In the embodiment of the present disclosure, after calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters, the method further includes:
[0011] Determine the change rate of the discharge amount according to the actual discharge amount and the corresponding working time;
[0012] The target total power in the performance parameter is corrected according to the change rate; the target total power refers to the maximum power that the battery to be predicted can store under the current working state.
[0013] In an embodiment of the present disclosure, calling a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters includes:
[0014] Determining a current operating state of the battery to be predicted according to the operating parameters;
[0015] If the current working state of the battery to be predicted is a discharge state, a first performance model is used to predict a first performance parameter of the battery to be predicted; the first performance parameter includes a target total power, an internal resistance value, and a discharge dynamic response; wherein the first performance model is obtained by training based on operating parameters in the discharge state and corresponding performance parameters;
[0016] If the current working state of the battery to be predicted is a charging state, a second performance model is used to predict the second performance parameters of the battery to be predicted; the second performance parameters include a target total power, an internal resistance value, and a charging dynamic response; wherein the second performance model is based on the operating parameters under the charging state and the corresponding performance parameters trained.
[0017] In the embodiment of the present disclosure, the operating parameter includes at least one of voltage, current, power consumption, and temperature.
[0018] In the embodiment of the present disclosure, calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters includes:
[0019] Determining a voltage change rate and a temperature change rate of the battery to be predicted in a current working state;
[0020] The operating parameters, performance parameters, voltage change rate and temperature change rate of the battery to be predicted are input into the power model, and the actual discharge capacity of the battery to be predicted in the current working state is output.
[0021] In an embodiment of the present disclosure, the method further includes:
[0022] The performance model is obtained by training using a first battery training sample set, wherein the number of cycles between two first battery training samples in the first battery training sample set is different;
[0023] The power model is obtained by training using a second battery training sample set, wherein the discharge rates of the second battery training samples in the second battery training sample set are different from each other.
[0024] In the disclosed embodiment, the current power level is calculated based on the battery voltage measured at a previous moment when the battery to be predicted was operating.
[0025] The embodiment of the second aspect of the present disclosure provides a battery remaining power prediction device, including:
[0026] A parameter acquisition module, used to obtain the operating parameters of the battery to be predicted;
[0027] A performance parameter prediction module, used to call a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters; the performance parameters are used to characterize the impact of the internal changes of the battery to be predicted on the battery charging and discharging capacity;
[0028] A real discharge capacity prediction module, used for calling a power model to predict the real discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; the power model is obtained by training based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge capacities, and performance parameters and operating parameters corresponding to each discharge capacity;
[0029] The remaining power determination module is used to determine the remaining power of the battery to be predicted and obtain the operating parameters of the battery to be predicted according to the current power of the battery to be predicted and the actual discharge capacity.
[0030] An embodiment of the third aspect of the present disclosure provides an electronic device, which includes a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery remaining power prediction method described in the first aspect by executing the computer instructions.
[0031] An embodiment of the fourth aspect of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the battery remaining power prediction method described in the first aspect above.
[0032] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will become apparent from the following description or be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present disclosure. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.
[0034] In the attached picture:
[0035] Figure 1 A schematic diagram showing a flow chart of a method for predicting remaining battery power provided by an embodiment of the present disclosure;
[0036] Figure 2 A schematic diagram showing a flow chart of another method for predicting remaining battery power provided by an embodiment of the present disclosure;
[0037] Figure 3 A schematic diagram showing the structure of a battery remaining power prediction device provided by an embodiment of the present disclosure is shown;
[0038] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;
[0039] Figure 5 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0040] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0041] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.
[0042] The following describes the technical scenarios involved in the embodiments of the present disclosure.
[0043] Since the capacity that a battery can release is affected by many factors such as discharge rate, battery temperature, and number of charge and discharge cycles, the battery SOC calculation should fully consider the influence of these factors. For the battery SOC prediction of electric vehicles, the main influencing factors are as follows:
[0044] (1) Impact of the battery itself
[0045] The life of the battery actually determines the actual power of the battery. This parameter is affected by factors such as the number of battery cycles, working environment, and depth of discharge. These similar state variables will determine the total amount of power that the battery can discharge. Only by determining the total power of the battery can the remaining power of the battery be accurately calculated. In addition, for the same model of battery, there will be consistency issues within different battery packs and between battery groups, that is, the equivalent parameters for a certain battery may not be applicable to another group of batteries, so for each specific battery, its state parameters need to be corrected when predicting.
[0046] (2) Impact of battery usage
[0047] The change in discharge capacity caused by the way the battery is used is not only determined by the different discharge rates of the battery, but also because the existence of regenerative braking technology means that the battery in the use of electric vehicles does not only include the discharge process. The battery's charge and discharge chemical reactions are inverse processes, and the products generated by the side reactions in this process are not the same, which determines that the battery exhibits different characteristics in the circuit under different charge and discharge states. This conclusion is also proved by the calculation based on the test data of the actual battery in the following text. Therefore, it is necessary to consider the battery on the electric vehicle under the charge and discharge states separately in order to accurately simulate the actual situation of the battery.
[0048] In actual practice, the sources of error in the SOC prediction result can usually be divided into errors caused by aging, errors caused by usage, and errors caused by measurement. The measurement error is caused by the measurement accuracy of sensors and other equipment and is an unavoidable error; while the error in the battery itself and the error in usage are the key points that need to be considered and corrected during the prediction process. Based on the above analysis, the battery remaining power prediction method proposed in the embodiment of the present disclosure can correct the main causes of the error and improve the prediction accuracy.
[0049] According to an embodiment of the present disclosure, an embodiment of a method for predicting remaining battery power is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0050] In this embodiment, a method for predicting the remaining battery power is provided. Figure 1 is a flowchart of a method for predicting remaining battery power according to an embodiment of the present disclosure. Figure 1 As shown, the process includes the following steps:
[0051] Step S101, obtaining the operating parameters of the battery to be predicted.
[0052] In some specific embodiments, the operating parameters of the battery to be predicted in the current working state include but are not limited to voltage U, current I, power consumption (integral of current over time) Q and temperature T; wherein the current working state includes the battery discharge state and the battery charge state.
[0053] In some specific embodiments, the method further includes: calculating the current power of the battery to be predicted based on the open circuit voltage measured at the last moment before the battery to be predicted works. The open circuit voltage (OCV) refers to the voltage measured when the battery is not loaded, which is directly related to the chemical state of the battery and changes with the change of SOC; the specific calculation method of the current power of the battery to be predicted is not specifically limited here, for example: a relationship table between SOC and OCV can be established through experiments, and after measuring the current OCV, the corresponding SOC value can be directly obtained by looking up the table.
[0054] Step S102, calling a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters.
[0055] In the disclosed embodiment, the performance parameter is used to characterize the influence of the internal changes of the battery to be predicted on the charging and discharging ability of the battery; the size of the performance parameter is determined by the state of the battery itself. In order to ensure that the performance of the battery can be accurately described, four parameters Qeff, Rin, τ1, and τ2 are used as parameters to represent the battery performance. Among them, Qeff represents the target total power, which is used to characterize the maximum power that the battery can store under the current working state (charging or discharging). The target total power can be corrected according to the attenuation curve of the battery and the total amount of cyclic discharge during actual use; the ohmic internal resistance Rin is used to reflect the influence of steady-state changes and aging during the use of the battery. According to the fitting results, it can be divided into Rinc in the charging state and Rind in the discharging state, and applied in different use cases; τ1 and τ2 represent the dynamic response of the battery, which can also be considered separately under different charging and discharging states.
[0056] In some specific embodiments, the above step S102 includes steps S1021 to S1023:
[0057] Step S1021, determining the current working state of the battery to be predicted according to the operating parameters.
[0058] In the embodiment of the present disclosure, the current working state of the battery to be predicted can be determined in the following manner:
[0059] Judge based on the direction of the battery current, for example: if the battery current is flowing in, then the battery is in a charging state; if the current is flowing out, then the battery is in a discharging state;
[0060] The judgment is made based on the change in battery voltage. For example, if the battery is being charged, the voltage will usually increase gradually until it approaches the maximum charging voltage of the battery. Conversely, if the battery is being discharged, the battery voltage will gradually decrease as the power decreases.
[0061] The judgment is based on the temperature change of the battery. For example, when charging, the battery temperature may rise, while when discharging, the temperature change may not be so obvious, especially at low discharge rates.
[0062] Step S1022: If the current working state of the battery to be predicted is a discharging state, a first performance model is used to predict a first performance parameter of the battery to be predicted.
[0063] In the embodiments of the present disclosure, Figure 2 As shown, when it is determined according to the operating parameters that the current working state of the battery to be predicted is discharging, the first performance model is used to predict the first performance parameter of the battery to be predicted; and the obtained first performance parameter is used as the input of the power model.
[0064] In the disclosed embodiment, the first performance parameter includes but is not limited to the target total power, internal resistance value and discharge dynamic response; wherein, the first performance model is trained based on the operating parameters in the discharge state (such as the above-mentioned voltage U, current I, consumed power (integral of current over time) Q and temperature T), and the measured corresponding performance parameters (such as the above-mentioned four parameters of Qeff, Rin, τ1, τ2), and the first performance model is the structure with the smallest error selected after training with a large number of data samples. The choice of structure is not unique and is selected according to the specific training situation.
[0065] In some specific embodiments, a first battery training sample set in a discharge state may be used to train a first performance model, wherein the number of cycles between two first battery training samples in the first battery training sample set is different; the number of cycles refers to the number of charge and discharge cycles of the battery.
[0066] Step S1023: If the current working state of the battery to be predicted is a charging state, a second performance model is used to predict a second performance parameter of the battery to be predicted.
[0067] In the embodiments of the present disclosure, Figure 2 As shown, when it is determined according to the operating parameters that the current working state of the battery to be predicted is charging, the second performance model is used to predict the second performance parameter of the battery to be predicted; and the obtained second performance parameter is used as the input of the power model.
[0068] In the disclosed embodiment, the second performance parameter includes the target total power, the internal resistance value, and the charging dynamic response; wherein the second performance model is obtained by training based on the operating parameters under the charging state and the corresponding performance parameters. The second performance model is a structure with the smallest error selected after training based on a large number of data samples. The choice of structure is not unique and is selected based on the specific training situation.
[0069] In some specific embodiments, a first battery training sample set in a charging state may be used to train a second performance model, wherein the number of cycles between two first battery training samples in the first battery training sample set is different.
[0070] In the process of training the network model, the determination of the number of hidden layers and nodes of the network model directly affects the prediction effect of the network model. Taking the network model training in this paper as an example, due to the limited training data samples, it is necessary to train different numbers of hidden layer nodes, and judge the optimal solution by comparing the calculation result errors. At the same time, it is also necessary to judge whether the parameters calculated by the network model meet the corresponding change rules through the prediction results in the program. Taking the training of the first performance model in the discharge stage as an example, the network model structure contains 4 input parameters and 4 output parameters. After comparing the calculation errors of single hidden layer and double hidden layer respectively, this paper finally chooses to use the double hidden layer method; in order to determine the number of hidden layer nodes, by comparing the network calculation errors of different numbers of nodes, the number of nodes with the smallest error is finally selected as the structure of the network model used by the program. The first performance model in the discharge stage of this paper adopts a two-layer structure with 20 nodes each, and the number of nodes in the second performance model in the charging stage is 11 and 16 respectively; the performance module nodes are 10 and 20 respectively.
[0071] Step S103, calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters.
[0072] In some specific embodiments, the power model is trained based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge amounts, and performance parameters and operating parameters corresponding to each discharge amount, for example: mapping relationship 1 includes 30% discharge amount-battery performance parameter 1-operating parameter 1, mapping relationship 2 includes 50% discharge amount-battery performance parameter 2-operating parameter 2, and mapping relationship 3 includes 70% discharge amount-battery performance parameter 3-operating parameter 3.
[0073] In some specific embodiments, the above step S103 includes step S1031-step S1032:
[0074] Step S1031, determining the voltage change rate and temperature change rate of the battery to be predicted in the current working state.
[0075] Specifically, the voltage change rate and temperature change rate can be obtained according to the maintenance time of the current working state (such as charging or discharging) of the battery and the changes of the voltage and current during the corresponding maintenance time.
[0076] Step S1032, inputting the operating parameters, performance parameters, voltage change rate and temperature change rate of the battery to be predicted into the power model, and outputting the actual discharge capacity of the battery to be predicted in the current working state.
[0077] In the above steps S1031-S1032, the disclosed embodiment also takes into account that the amount of electricity discharged by the battery during the actual driving of the electric vehicle is not only related to the state of the battery itself, but also closely related to environmental conditions such as temperature, working conditions such as discharge rate, voltage change rate and other parameters. The use of the battery during the driving of the car directly determines the amount of electricity actually discharged by the battery. Therefore, the voltage change rate and temperature change rate of the battery to be predicted in the current working state are used as inputs of the electricity model to predict the actual discharge amount of the battery in the current working state.
[0078] The disclosed embodiment can fully consider that the battery SOC is affected by multiple factors such as the battery state, environmental conditions, working conditions, etc. through the above-mentioned method, thereby greatly improving the accuracy of battery remaining power prediction.
[0079] In some specific embodiments, after the above step S103, the method further includes:
[0080] Step a1, determining the change rate of the discharge amount according to the actual discharge amount and the corresponding working time.
[0081] In the embodiments of the present disclosure, the corresponding working time can be understood as the working time of battery charging or discharging, and the rate of change of discharge amount can be understood as the change of discharge amount per unit time. For example, when the actual discharge amount is 5Ah and the discharge time is 2h, the rate of change of discharge amount is 5 / 2=2.5Ah / h.
[0082] Step a2: correcting the target total power in the performance parameter according to the change rate.
[0083] In the disclosed embodiment, the target total power refers to the maximum power that the battery to be predicted can store under the current working state. If the rate of change of the battery discharge capacity gradually decreases, it can be indicated that the health of the battery is deteriorating, and the target total power of the battery will decrease accordingly; the proportion of the decrease depends on the change in the rate of change of the battery discharge capacity. In the process of correcting the target total power, the corresponding weighting coefficient can be selected according to the change in the rate of change of the discharge capacity, and the final target total power can be calculated by the weighting coefficient and the target total power, for example: a1*B=B1; wherein a1 represents the weighting coefficient, B represents the target total power, and B1 represents the final target total power obtained after correction.
[0084] Step S104, determining the remaining power of the battery to be predicted according to the current power of the battery to be predicted and the actual discharge power.
[0085] In the embodiment of the present disclosure, the current power level can be calculated based on the battery voltage measured at a moment before the battery to be predicted works. The calculation method can refer to the specific embodiment of the above step S101.
[0086] In the disclosed embodiment, the remaining power of the battery can be predicted by subtracting the actual discharge capacity from the current power. The accuracy of the remaining power calculated in this way will be much greater than the accuracy of the traditional rated capacity ampere-hour method.
[0087] Corresponding to the implementation of the above battery remaining power prediction method, the present disclosure also provides a battery remaining power prediction device for executing the above Figure 1 to Figure 2 The method for predicting the remaining battery power of any of the embodiments shown in the figure. Figure 3 As shown, the battery remaining power prediction device includes:
[0088] A parameter acquisition module, used to obtain the operating parameters of the battery to be predicted;
[0089] A performance parameter prediction module, used to call a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters; the performance parameters are used to characterize the impact of the internal changes of the battery to be predicted on the battery charging and discharging capacity;
[0090] A real discharge capacity prediction module, used for calling a power model to predict the real discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; the power model is obtained by training based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge capacities, and performance parameters and operating parameters corresponding to each discharge capacity;
[0091] The remaining power determination module is used to determine the remaining power of the battery to be predicted and obtain the operating parameters of the battery to be predicted according to the current power of the battery to be predicted and the actual discharge capacity.
[0092] Optionally, the device also includes: a correction module, which is used to determine the rate of change of the discharge capacity through the actual discharge capacity and the corresponding working time after calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; and correct the target total power in the performance parameters according to the change rate; the target total power refers to the maximum power that the battery to be predicted can store under the current working state.
[0093] Optionally, the performance parameter prediction module is also used to: determine the current working state of the battery to be predicted based on the operating parameters; if the current working state of the battery to be predicted is a discharge state, use a first performance model to predict the first performance parameter of the battery to be predicted; the first performance parameter includes a target total power, an internal resistance value, and a discharge dynamic response; wherein the first performance model is based on the operating parameters in the discharge state, and the corresponding performance parameters are trained; if the current working state of the battery to be predicted is a charging state, use a second performance model to predict the second performance parameter of the battery to be predicted; the second performance parameters include a target total power, an internal resistance value, and a charging dynamic response; wherein the second performance model is based on the operating parameters in the charging state, and the corresponding performance parameters are trained.
[0094] Optionally, the actual discharge capacity prediction module is also used to: determine the voltage change rate and temperature change rate of the battery to be predicted in the current working state; input the operating parameters, performance parameters, voltage change rate and temperature change rate of the battery to be predicted into the power model, and output the actual discharge capacity of the battery to be predicted in the current working state.
[0095] Optionally, the device also includes: a model training module, used to use a first battery training sample set to train and obtain the performance model, and the number of cycles between the first battery training samples in the first battery training sample set is different; and use a second battery training sample set to train and obtain the power model, and the discharge rates between the second battery training samples in the second battery training sample set are different.
[0096] The battery remaining power prediction device provided in the above-mentioned embodiment of the present disclosure and the battery remaining power prediction method provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0097] The present disclosure also provides an electronic device to perform the above-mentioned battery remaining power prediction method. Figure 4 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 4 As shown, the electronic device 4 includes: a processor 400, a memory 401, a bus 402 and a communication interface 403, wherein the processor 400, the communication interface 403 and the memory 401 are connected via the bus 402; the memory 401 stores a computer program that can be run on the processor 400, and the processor 400 executes the aforementioned Figure 1 to Figure 2 A method for predicting the remaining battery power provided by any of the illustrated embodiments.
[0098] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.
[0099] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 401 is used to store programs. After receiving the execution instruction, the processor 400 executes the program. Figure 1 to Figure 2 The remaining battery power prediction method disclosed in any of the illustrated embodiments may be applied to the processor 400 or implemented by the processor 400 .
[0100] The processor 400 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 400 or the instruction in the form of software. The above processor 400 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.
[0101] The electronic device provided by the embodiment of the present disclosure and the battery remaining power prediction method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.
[0102] The present disclosure also provides a computer-readable storage medium corresponding to the battery remaining power prediction method provided in the above embodiment. Figure 5 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is executed by a processor, the remaining battery power prediction method provided in any of the aforementioned embodiments will be executed.
[0103] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.
[0104] The computer-readable storage medium provided in the above-mentioned embodiments of the present disclosure and the battery remaining power prediction method provided in the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0105] It should be noted that:
[0106] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.
[0107] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed disclosure requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present disclosure.
[0108] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of this disclosure and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.
[0109] The above is only a preferred specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.
Claims
1. A method for predicting remaining battery power, characterized in that: The method comprises: Obtaining operating parameters of the battery to be predicted; Calling a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters; the performance parameters are used to characterize the impact of internal changes of the battery to be predicted on the battery charging and discharging capacity; Calling a power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; the power model is obtained by training based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge capacities, and performance parameters and operating parameters corresponding to each discharge capacity; The remaining power of the battery to be predicted is determined according to the current power of the battery to be predicted and the actual discharge power.
2. The method according to claim 1, characterized in that After calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters, the method further includes: Determine the change rate of the discharge amount according to the actual discharge amount and the corresponding working time; The target total power in the performance parameter is corrected according to the change rate; the target total power refers to the maximum power that the battery to be predicted can store under the current working state.
3. The method according to claim 2, characterized in that Calling a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters includes: Determining a current operating state of the battery to be predicted according to the operating parameters; If the current working state of the battery to be predicted is a discharge state, a first performance model is used to predict a first performance parameter of the battery to be predicted; the first performance parameter includes a target total power, an internal resistance value, and a discharge dynamic response; wherein the first performance model is obtained by training based on operating parameters in the discharge state and corresponding performance parameters; If the current working state of the battery to be predicted is a charging state, a second performance model is used to predict the second performance parameters of the battery to be predicted; the second performance parameters include a target total power, an internal resistance value, and a charging dynamic response; wherein the second performance model is based on the operating parameters under the charging state and the corresponding performance parameters trained.
4. The method according to claim 1 or 2, characterized in that: The operating parameter includes at least one of voltage, current, power consumption, and temperature.
5. The method according to claim 1 or 2, characterized in that: Calling the power model to predict the actual discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters includes: Determining a voltage change rate and a temperature change rate of the battery to be predicted in a current working state; The operating parameters, performance parameters, voltage change rate and temperature change rate of the battery to be predicted are input into the power model, and the actual discharge capacity of the battery to be predicted in the current working state is output.
6. The method according to claim 1 or 2, characterized in that: The method further comprises: The performance model is obtained by training using a first battery training sample set, wherein the number of cycles between two first battery training samples in the first battery training sample set is different; The power model is obtained by training using a second battery training sample set, wherein the discharge rates of the second battery training samples in the second battery training sample set are different from each other.
7. The method according to claim 1 or 2, characterized in that: The current power level is calculated based on the battery voltage measured at a moment before the battery to be predicted operates.
8. A battery remaining power prediction device, characterized in that: The device comprises: A parameter acquisition module, used to obtain the operating parameters of the battery to be predicted; A performance parameter prediction module, used to call a pre-trained performance model to predict the performance parameters of the battery to be predicted according to the operating parameters; the performance parameters are used to characterize the impact of the internal changes of the battery to be predicted on the battery charging and discharging capacity; A real discharge capacity prediction module, used for calling a power model to predict the real discharge capacity of the battery to be predicted according to the operating parameters and the performance parameters; the power model is obtained by training based on multiple mapping relationships, and the multiple mapping relationships include multiple discharge capacities, and performance parameters and operating parameters corresponding to each discharge capacity; The remaining power determination module is used to determine the remaining power of the battery to be predicted and obtain the operating parameters of the battery to be predicted according to the current power of the battery to be predicted and the actual discharge capacity.
9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.