Battery temperature determination method and apparatus, computer device, readable storage medium, and program product
By acquiring the battery's operating parameters and status data, and using correlation coefficients to determine the battery temperature, the problem of poor safety and stability in existing battery temperature monitoring technologies is solved, achieving efficient battery temperature monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN POWER SUPPLY BUREAU
- Filing Date
- 2024-07-23
- Publication Date
- 2026-06-09
AI Technical Summary
In existing technologies, the method of monitoring the temperature of a power battery by placing sensors inside the battery has poor safety and stability, and is prone to battery short circuits and electrolyte leakage, resulting in low temperature monitoring efficiency.
By acquiring the battery's operating parameters, using correlation coefficients to determine state data, and inputting them into a pre-trained battery temperature determination model, the battery temperature can be directly measured without the need for internal sensors.
It improves battery safety and stability, and increases the efficiency of battery temperature monitoring.
Smart Images
Figure CN118962451B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of battery technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining battery temperature. Background Technology
[0002] New energy vehicles and various energy storage systems with power batteries as the core have been widely used. However, due to the difficulty in precisely controlling the chemical and physical reactions inside the power battery, side reactions are prone to occur, leading to thermal failures. Therefore, it is necessary to monitor the internal temperature of the power battery in real time.
[0003] In existing technologies, most methods involve placing a temperature transfer unit inside the battery to monitor the internal temperature of the power battery.
[0004] However, this method has poor safety and stability, and is prone to problems such as battery short circuits and electrolyte leakage, which in turn makes the temperature monitoring efficiency of power batteries low. Summary of the Invention
[0005] Therefore, it is necessary to provide a battery temperature determination method, device, computer equipment, computer-readable storage medium, and computer program product that can provide high safety and stability and improve the efficiency of power battery temperature monitoring, in response to the above-mentioned technical problems.
[0006] In a first aspect, this application provides a method for determining battery temperature, including:
[0007] The operating parameters of the target battery are obtained, and the state data of the target battery are determined based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery.
[0008] Target prediction data is determined from the working parameters and the state data based on the correlation coefficient between the working parameters and the state data.
[0009] The target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. This temperature information is used to characterize the internal temperature of the target battery.
[0010] In one embodiment, the process of acquiring the operating parameters of the target battery and determining the state data of the target battery based on the operating parameters includes: acquiring the operating parameters of the target battery, determining the state of charge information, health status information, and relaxation time distribution data of the target battery based on the operating parameters, and determining the state of charge information, health status information, and relaxation time distribution data as the state data of the target battery.
[0011] In one embodiment, determining the target prediction data from the operating parameters and the state data based on the correlation coefficient of the operating parameters and the state data includes: determining the correlation coefficient of the operating parameters and the state data based on the Spearman correlation algorithm; and determining the target prediction data from the operating parameters and the state data based on a correlation coefficient threshold and the correlation coefficient of the operating parameters and the state data.
[0012] In one embodiment, determining the target prediction data from the operating parameters and the state data based on a correlation coefficient threshold and the correlation coefficient between the operating parameters and the state data includes: determining the operating parameters and the state data whose correlation coefficient is greater than the correlation coefficient threshold as the target prediction data.
[0013] In one embodiment, the training method of the battery temperature determination model includes: obtaining a training dataset from a target database according to a preset ratio, and training an initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model, and determining the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions.
[0014] In one embodiment, before filtering the training dataset from the target database according to a preset ratio, the method further includes: acquiring temperature data and test operating parameters of the test battery, and determining the test state data of the test battery based on the test operating parameters, wherein the test battery is of the same type as the target battery; determining the correlation coefficient between the test operating parameters and the test state data, and constructing the target database based on the correlation coefficient between the test operating parameters and the test state data.
[0015] Secondly, this application also provides a battery temperature determination device, comprising:
[0016] The acquisition module is used to acquire the operating parameters of the target battery and determine the state data of the target battery based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery.
[0017] The determination module is used to determine the target prediction data from the working parameters and the state data based on the correlation coefficient between the working parameters and the state data;
[0018] The execution module is used to input the target prediction data into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. This temperature information is used to characterize the internal temperature of the target battery.
[0019] Thirdly, this application also provides a computer device, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the method described in any of the embodiments of the first aspect above.
[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the embodiments of the first aspect above.
[0021] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the embodiments of the first aspect above.
[0022] The aforementioned battery temperature determination method, apparatus, computer equipment, computer-readable storage medium, and computer program product first acquire the operating parameters of the target battery and determine the state data of the target battery based on these operating parameters. These operating parameters refer to parameters directly obtained by measuring the target battery. Then, target prediction data is determined from the operating parameters and state data based on the correlation coefficient between them. Finally, the target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the model. This temperature information characterizes the internal temperature of the target battery. The battery temperature determination method provided in this application determines the battery's state data through directly measurable operating parameters. Based on the state data and operating parameters, the battery temperature of the target battery can be determined without the need for sensors inside the battery to monitor its temperature, thus improving battery safety and stability, and consequently increasing the efficiency of battery temperature monitoring. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 This is a flowchart illustrating a battery temperature determination method in one embodiment;
[0025] Figure 2 This is a flowchart illustrating a method for obtaining operating parameters of a target battery and determining the state data of the target battery based on the operating parameters in one embodiment.
[0026] Figure 3This is a schematic diagram of a process for determining target prediction data from the operating parameters and the state data based on the correlation coefficient between the operating parameters and the state data in one embodiment.
[0027] Figure 4 This is a flowchart illustrating the training method for a battery temperature determination model in one embodiment.
[0028] Figure 5 This is a flowchart illustrating a method in one embodiment before selecting a training dataset from a target database according to a preset ratio;
[0029] Figure 6 This is a flowchart illustrating the battery temperature determination method in another embodiment;
[0030] Figure 7 This is a structural block diagram of a battery temperature determination device in one embodiment;
[0031] Figure 8 This is a structural block diagram of the battery temperature determination device in another embodiment;
[0032] Figure 9 This is an internal structural diagram of a computer device in one embodiment;
[0033] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation
[0034] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0035] New energy vehicles and various energy storage systems with power batteries as the core have been widely used. However, due to the difficulty in precisely controlling the chemical and physical reactions inside the power battery, side reactions are prone to occur, leading to thermal failures. Therefore, it is necessary to monitor the internal temperature of the power battery in real time.
[0036] In existing technologies, most methods involve placing a temperature transfer unit inside the battery to monitor the internal temperature of the power battery.
[0037] However, this method has poor safety and stability, and is prone to problems such as battery short circuits and electrolyte leakage, which in turn makes the temperature monitoring efficiency of power batteries low.
[0038] In view of this, this application provides a battery temperature determination method with high safety and stability, which can effectively improve the efficiency of power battery temperature monitoring.
[0039] The battery temperature determination method provided in this application can be executed by a computer device, which can be a terminal or a server.
[0040] In one exemplary embodiment, such as Figure 1 As shown, a method for determining battery temperature is provided, which includes the following steps:
[0041] Step 101: Obtain the operating parameters of the target battery and determine the state data of the target battery based on the operating parameters.
[0042] The operating parameters refer to those obtained directly from measuring the target battery.
[0043] Optionally, the operating parameters may include the internal resistance and electrochemical impedance of the target battery.
[0044] The internal resistance of a battery refers to the resistance encountered when current flows through the inside of the target battery during operation. It includes ohmic internal resistance and polarization internal resistance, which in turn includes electrochemical polarization internal resistance and concentration polarization internal resistance.
[0045] In one possible approach, the internal resistance of the target battery can be obtained through AC measurement, also known as AC injection.
[0046] In another possible approach, the internal resistance of the target battery can be obtained through a DC measurement method, also known as a DC discharge method.
[0047] In another possible approach, the internal resistance of the target battery can be determined using the MCCF method. Specifically, a pulsed charge-discharge current with a duration of 5 seconds is used, and the voltage drop is recorded to calculate the internal resistance of the target battery.
[0048] In another possible approach, the internal resistance of the target battery can be determined using the DCR method. Specifically, different charging and discharging rates are applied for 10 seconds, and the voltage and current are recorded to form a target straight line. The slope of this target straight line is the internal resistance of the target battery.
[0049] Electrochemical impedance refers to the resistance encountered when current passes through the target cell.
[0050] Furthermore, after determining the operating parameters of the target battery, the state data of the target battery can also be determined based on the operating parameters.
[0051] In one possible implementation, the operating parameters can be input into a pre-trained state data determination model to obtain the state data of the target battery output by the state data determination model.
[0052] In another possible implementation, the state data of the target battery can be determined based on the operating parameters and a preset mapping list, which stores the mapping relationship between the operating parameters of the target battery and the state data of the target battery.
[0053] Step 102: Determine the target prediction data from the working parameters and the state data based on the correlation coefficient between the working parameters and the state data.
[0054] Optionally, the correlation coefficient may include a first correlation coefficient and a second correlation coefficient, wherein the first correlation coefficient is a correlation coefficient determined based on the working parameters, and the second correlation coefficient is a correlation coefficient determined based on the state data.
[0055] In one possible implementation, the first correlation coefficient and the second correlation coefficient can be determined based on statistical algorithms.
[0056] Furthermore, the target prediction data can be determined based on a preset correlation coefficient threshold and the first and second correlation coefficients. Specifically, operating parameters with a first correlation coefficient greater than the preset correlation coefficient threshold can be determined as the target prediction data, and state data with a second correlation coefficient greater than the preset correlation coefficient threshold can be determined as the target prediction data.
[0057] The target prediction data can also be determined based on a preset correlation coefficient range and the first correlation coefficient and the second correlation coefficient. Specifically, the working parameters whose first correlation coefficient is within the preset correlation coefficient range can be determined as the target prediction data, and the state data whose second correlation coefficient is within the preset correlation coefficient range can be determined as the target prediction data.
[0058] Step 103: Input the target prediction data into the pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model.
[0059] This temperature information is used to characterize the internal temperature of the target battery.
[0060] In one possible implementation, the target prediction data can be directly input into the pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. Based on the temperature information of the target battery, the internal temperature of the target battery can be determined, thereby predicting the thermal failure event of the target battery based on the internal temperature of the target battery.
[0061] In another possible implementation, as described above, the target prediction data includes operating parameters and state data. Optionally, the battery temperature determination model includes a first battery temperature determination sub-model and a second battery temperature determination sub-model. The operating parameters in the target prediction data can be input into the first battery temperature determination sub-model to obtain the first temperature information of the target battery. Then, the state data in the target prediction data can be input into the second battery temperature determination sub-model to obtain the second temperature information of the target battery. Finally, the temperature information of the target battery is determined based on the first battery temperature information and the second battery temperature information.
[0062] The aforementioned battery temperature determination method first acquires the operating parameters of the target battery and determines the state data of the target battery based on these operating parameters. These operating parameters refer to those directly obtained through measurement of the target battery. Then, based on the correlation coefficient between the operating parameters and the state data, target prediction data is determined from the operating parameters and the state data. Finally, the target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the model. This temperature information characterizes the internal temperature of the target battery. The battery temperature determination method provided in this application determines the battery's state data through directly measurable operating parameters. Based on the state data and operating parameters, the battery temperature of the target battery can be determined without the need for sensors inside the battery to monitor its temperature, thus improving battery safety and stability, and consequently increasing the efficiency of battery temperature monitoring.
[0063] In one exemplary embodiment, such as Figure 2 As shown, the process of acquiring the operating parameters of the target battery and determining the state data of the target battery based on these operating parameters includes the following steps:
[0064] Step 201: Obtain the operating parameters of the target battery, and determine the state of charge information, health information and relaxation time distribution data of the target battery based on the operating parameters;
[0065] Step 202: Determine the state of charge information, the health status information, and the relaxation time distribution data as the state data of the target battery.
[0066] Optionally, the state of charge information refers to the ratio of the remaining capacity of the target battery after a period of use or long-term storage to its capacity in a fully charged state. The health status information is used to quantitatively describe the performance state of the target battery. The relaxation time distribution data refers to the data obtained after efficiently and rapidly decomposing the electrochemical impedance of the target battery using digital methods.
[0067] For example, taking the process of determining the state of charge information as an example, in one possible implementation, after obtaining the operating parameters of the target battery, the operating parameters can be input into a pre-trained state of charge information determination model to obtain the state of charge information of the target battery output by the state of charge information determination model.
[0068] In another possible implementation, after obtaining the operating parameters of the target battery, the state of charge (SOC) information of the target battery can be determined based on the operating parameters and a preset SOC mapping relationship list, as shown in Table 1.
[0069] Table 1
[0070]
[0071] For example, taking the process of determining the health status information as an example, in one possible implementation, after obtaining the operating parameters of the target battery, the operating parameters can be input into a pre-trained health status information determination model to obtain the health status information of the target battery output by the health status information determination model.
[0072] In another possible implementation, after obtaining the operating parameters of the target battery, the health status information of the target battery can also be determined according to the operating parameters and a preset health status information mapping relationship list, as shown in Table 2.
[0073] Table 2
[0074]
[0075] For example, taking the process of determining the relaxation time distribution data as an example, in one possible implementation, after obtaining the operating parameters of the target battery, the operating parameters can be input into a pre-trained relaxation time distribution data determination model to obtain the relaxation time distribution data of the target battery output by the relaxation time distribution data determination model.
[0076] In another possible implementation, after obtaining the operating parameters of the target battery, the relaxation time distribution data of the target battery can also be determined according to the operating parameters and a preset relaxation time distribution data mapping relationship list, which can be shown in Table 3.
[0077] Table 3
[0078]
[0079] In one exemplary embodiment, such as Figure 3As shown, the method for determining target prediction data from the operating parameters and the state data based on the correlation coefficient between the operating parameters and the state data includes:
[0080] Step 301: Determine the correlation coefficient between the working parameter and the state data based on the Spearman correlation algorithm.
[0081] In one possible implementation, the Spearman correlation algorithm is calculated as follows:
[0082] ;
[0083] in, and They are and The position, and These represent the average rank, and i represents the working parameter or status data.
[0084] Furthermore, the following formula for calculating Spearman correlation can also be used:
[0085] ;
[0086] in, This represents the position difference of the i-th data pair, and n represents the total number of data.
[0087] Step 302: Determine the target prediction data from the working parameter and the state data based on the correlation coefficient threshold and the correlation coefficient between the working parameter and the state data.
[0088] Optionally, the correlation coefficient threshold can be preset by technicians according to actual needs. For example, the correlation coefficient threshold can be 0.7.
[0089] In an exemplary embodiment, determining the target prediction data from the working parameters and the state data based on a correlation coefficient threshold and the correlation coefficient between the working parameters and the state data includes: determining the working parameters and the state data whose correlation coefficient is greater than the correlation coefficient threshold as the target prediction data.
[0090] In one possible implementation, after determining the correlation coefficient between the working parameter and the state data based on the Spearman correlation algorithm, the working parameter and the state data with a correlation coefficient greater than the correlation coefficient threshold can be identified as the target prediction data.
[0091] In one exemplary embodiment, such as Figure 4 As shown, the training method for this battery temperature determination model includes the following steps:
[0092] Step 401: Obtain the training dataset from the target database according to the preset ratio, and train the initial battery temperature determination model based on the training dataset to obtain the candidate battery temperature determination model.
[0093] Optionally, this preset ratio can be pre-set by the technician according to actual needs. The target database is a database pre-built by the technician according to actual needs.
[0094] Optionally, the initial battery temperature determination model can be a neural network model, which can be one or more of the following: feedforward neural network, convolutional neural network, recurrent neural network, long short-term memory neural network, etc.
[0095] In one possible implementation, there are multiple training datasets, each including a test dataset and a corresponding validation dataset. The test dataset can be used as input to the initial battery temperature determination model, and the validation dataset can be used as output to train the initial battery temperature determination model to obtain the candidate battery temperature determination model.
[0096] Step 402: Obtain the determination coefficient and mean absolute error of the candidate battery temperature determination model. If the determination coefficient and mean absolute error meet the preset conditions, determine the candidate battery temperature determination model as the battery temperature determination model.
[0097] Optionally, the coefficient of determination is the goodness of fit of the candidate battery temperature determination model. This preset condition can be set by technicians according to actual needs.
[0098] In one possible implementation, after obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model, the candidate battery temperature determination model with the determination coefficient closest to 1 and the smallest mean absolute error is determined as the battery temperature determination model.
[0099] In one exemplary embodiment, such as Figure 5 As shown, before selecting the training dataset from the target database according to a preset ratio, the method further includes the following steps:
[0100] Step 501: Obtain the temperature data and test operating parameters of the test battery, and determine the test status data of the test battery based on the test operating parameters.
[0101] The test battery is of the same type as the target battery.
[0102] Optionally, the temperature data refers to the internal temperature information of the test battery.
[0103] In one possible implementation, an embedded thermocouple or temperature sensor can be used to acquire the temperature data of the test, that is, the internal temperature information of the test battery. Specifically, in an inert gas environment, the thermocouple or temperature sensor is embedded at the geometric center of the battery to obtain the true internal temperature information of the battery.
[0104] Another possible approach is to use thermal imaging equipment to analyze and obtain the internal temperature of the battery. Specifically, an infrared imager is used to directly act on the test battery during operation, converting the invisible infrared energy into a visible thermal image, and then analyzing the internal temperature information of the battery through the thermal image.
[0105] Optionally, the test parameters include the battery internal resistance and electrochemical impedance of the test battery.
[0106] In one possible implementation, the battery internal resistance and electrochemical impedance of the test battery can be collected by measuring the current using a Hall effect current sensor and by integrating chips such as the LTC6804-1 chip and the AD5941 chip onto a development board.
[0107] Furthermore, after obtaining the test operating parameters of the test battery, the test status data of the test battery can be determined based on the test operating parameters.
[0108] Step 502: Determine the correlation coefficient between the test working parameters and the test status data, and construct the target database based on the correlation coefficient between the test working parameters and the test status data.
[0109] In one possible implementation, the correlation coefficient between the test operating parameter and the test state data can be determined first based on the Spearman correlation algorithm, and the test operating parameter and the test state data with a correlation coefficient greater than the correlation coefficient threshold can be retained.
[0110] Furthermore, for the relaxation time distribution data in the test state data of the retained test battery, select... The target database was constructed using relaxation time distribution data in the range of 3.97s–66.2s.
[0111] Based on the electrochemical impedance of the test cells in the retained test parameters, the target database was constructed by selecting electrochemical impedances in the frequency range of 7943.28Hz-3981.07Hz.
[0112] Furthermore, the target database is constructed based on the correlation coefficient between the test working parameters after the above screening process and the test status data.
[0113] In one exemplary embodiment, such as Figure 6 As shown, another method for determining battery temperature is provided, which includes the following steps:
[0114] Step 601: Obtain the operating parameters of the target battery, and determine the state of charge information, health information and relaxation time distribution data of the target battery based on the operating parameters; determine the state of charge information, health information and relaxation time distribution data as the state data of the target battery, and the operating parameters refer to the parameters directly obtained by measuring the target battery.
[0115] Step 602: Determine the correlation coefficient between the working parameter and the state data based on the Spearman correlation algorithm; determine the working parameter and the state data with a correlation coefficient greater than the correlation coefficient threshold as the target prediction data;
[0116] Step 603: Input the target prediction data into the pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery.
[0117] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0118] Based on the same inventive concept, this application also provides a battery temperature determining device for implementing the battery temperature determining method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more battery temperature determining device embodiments provided below can be found in the limitations of the battery temperature determining method described above, and will not be repeated here.
[0119] In one exemplary embodiment, such as Figure 7 As shown, a battery temperature determination device 700 is provided, including: an acquisition module 701, a determination module 702, and an execution module 703, wherein:
[0120] The acquisition module 701 is used to acquire the operating parameters of the target battery and determine the state data of the target battery based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery.
[0121] The determination module 702 is used to determine the target prediction data from the working parameters and the state data based on the correlation coefficient between the working parameters and the state data;
[0122] The execution module 703 is used to input the target prediction data into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery.
[0123] In one embodiment, the acquisition module 701 is specifically used to acquire the operating parameters of the target battery, determine the state of charge information, health status information, and relaxation time distribution data of the target battery based on the operating parameters, and determine the state of charge information, health status information, and relaxation time distribution data as the state data of the target battery.
[0124] In one embodiment, the determination module 702 is specifically used to determine the correlation coefficient between the operating parameter and the state data based on the Spearman correlation algorithm; and to determine the target prediction data from the operating parameter and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameter and the state data.
[0125] In one embodiment, the determination module 702 is specifically used to determine the working parameter and the state data whose correlation coefficient is greater than the correlation coefficient threshold as the target prediction data.
[0126] In one embodiment, such as Figure 8 As shown, another battery temperature determination device 800 is provided. In addition to the various modules included in the battery temperature determination device 700, the battery temperature determination device 800 also includes a training module 704.
[0127] In one embodiment, the training module 704 is configured to obtain a training dataset from the target database according to a preset ratio, and train the initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtain the determination coefficient and mean absolute error of the candidate battery temperature determination model, and determine the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions.
[0128] In one embodiment, the training module 704 is further configured to acquire temperature data and test operating parameters of the test battery, and determine the test state data of the test battery based on the test operating parameters, wherein the test battery is of the same type as the target battery; determine the correlation coefficient between the test operating parameters and the test state data, and construct the target database based on the correlation coefficient between the test operating parameters and the test state data.
[0129] Each module in the aforementioned battery temperature determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0130] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a method for determining battery temperature.
[0131] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for determining battery temperature.
[0132] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0133] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0134] The operating parameters of the target battery are obtained, and the state data of the target battery are determined based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery. The target prediction data is determined from the operating parameters and the state data based on the correlation coefficient between the operating parameters and the state data. The target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery.
[0135] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining the operating parameters of the target battery, determining the state of charge information, health status information, and relaxation time distribution data of the target battery based on the operating parameters, and determining the state of charge information, health status information, and relaxation time distribution data as the state data of the target battery.
[0136] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the correlation coefficient between the operating parameter and the state data based on the Spearman correlation algorithm; and determining the target prediction data from the operating parameter and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameter and the state data.
[0137] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the operating parameter with a correlation coefficient greater than the correlation coefficient threshold and the state data as the target prediction data.
[0138] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining a training dataset from the target database according to a preset ratio, and training the initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model, and determining the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions.
[0139] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring temperature data and test operating parameters of the test battery, and determining test state data of the test battery based on the test operating parameters, wherein the test battery is of the same type as the target battery; determining the correlation coefficient between the test operating parameters and the test state data, and constructing the target database based on the correlation coefficient between the test operating parameters and the test state data.
[0140] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0141] The operating parameters of the target battery are obtained, and the state data of the target battery are determined based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery. The target prediction data is determined from the operating parameters and the state data based on the correlation coefficient between the operating parameters and the state data. The target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery.
[0142] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the operating parameters of the target battery, determining the state of charge information, health status information, and relaxation time distribution data of the target battery based on the operating parameters, and determining the state of charge information, health status information, and relaxation time distribution data as the state data of the target battery.
[0143] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the correlation coefficient between the operating parameter and the state data based on the Spearman correlation algorithm; and determining the target prediction data from the operating parameter and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameter and the state data.
[0144] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the operating parameter with a correlation coefficient greater than the correlation coefficient threshold and the state data as the target prediction data.
[0145] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a training dataset from the target database according to a preset ratio, and training the initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model, and determining the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions.
[0146] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring temperature data and test operating parameters of the test battery, and determining test state data of the test battery based on the test operating parameters, wherein the test battery is of the same type as the target battery; determining the correlation coefficient between the test operating parameters and the test state data, and constructing the target database based on the correlation coefficient between the test operating parameters and the test state data.
[0147] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0148] The operating parameters of the target battery are obtained, and the state data of the target battery are determined based on the operating parameters. The operating parameters refer to the parameters directly obtained by measuring the target battery. The target prediction data is determined from the operating parameters and the state data based on the correlation coefficient between the operating parameters and the state data. The target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery.
[0149] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the operating parameters of the target battery, determining the state of charge information, health status information, and relaxation time distribution data of the target battery based on the operating parameters, and determining the state of charge information, health status information, and relaxation time distribution data as the state data of the target battery.
[0150] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the correlation coefficient between the operating parameter and the state data based on the Spearman correlation algorithm; and determining the target prediction data from the operating parameter and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameter and the state data.
[0151] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the operating parameter with a correlation coefficient greater than the correlation coefficient threshold and the state data as the target prediction data.
[0152] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a training dataset from the target database according to a preset ratio, and training the initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model, and determining the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions.
[0153] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring temperature data and test operating parameters of the test battery, and determining test state data of the test battery based on the test operating parameters, wherein the test battery is of the same type as the target battery; determining the correlation coefficient between the test operating parameters and the test state data, and constructing the target database based on the correlation coefficient between the test operating parameters and the test state data.
[0154] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for determining battery temperature, characterized in that, The method includes: The operating parameters of the target battery are obtained, and the state of charge information, health information, and relaxation time distribution data of the target battery are determined based on the operating parameters. The state of charge information, health information, and relaxation time distribution data are determined as the state data of the target battery. The operating parameters refer to the parameters directly obtained by measuring the target battery. The correlation coefficient between the operating parameters and the state data is determined based on the Spearman correlation algorithm; target prediction data is determined from the operating parameters and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameters and the state data. The target prediction data is input into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model. The temperature information is used to characterize the internal temperature of the target battery. The training method for the battery temperature determination model includes: obtaining a training dataset from a target database according to a preset ratio, and training an initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; obtaining the determination coefficient and mean absolute error of the candidate battery temperature determination model; and determining the candidate battery temperature determination model as the battery temperature determination model when the determination coefficient and the mean absolute error meet preset conditions, wherein the determination coefficient is the goodness of fit of the candidate battery temperature determination model.
2. The method according to claim 1, characterized in that, The process of determining the target prediction data from the operating parameters and the state data based on a correlation coefficient threshold and the correlation coefficient between the operating parameters and the state data includes: The working parameters and the state data whose correlation coefficients are greater than the correlation coefficient threshold are determined as the target prediction data.
3. The method according to claim 1, characterized in that, Before selecting the training dataset from the target database according to a preset ratio, the method further includes: The temperature data and test operating parameters of the test battery are acquired, and the test status data of the test battery are determined based on the test operating parameters. The test battery is of the same type as the target battery. Determine the correlation coefficient between the test operating parameters and the test status data, and construct the target database based on the correlation coefficient between the test operating parameters and the test status data.
4. The method according to claim 1, characterized in that, The operating parameters of the target battery include its internal resistance and electrochemical impedance.
5. The method according to claim 1, characterized in that, The correlation coefficient includes a first correlation coefficient and a second correlation coefficient; the first correlation coefficient is determined based on the working parameters, and the second correlation coefficient is determined based on the status data.
6. The method according to claim 1, characterized in that, Determining the state of charge information of the target battery based on the operating parameters includes: The state of charge (SOC) information of the target battery is determined based on the operating parameters and the preset SOC mapping list.
7. A battery temperature determination device, characterized in that, The device includes: The acquisition module is used to acquire the operating parameters of the target battery, and determine the state of charge information, health information, and relaxation time distribution data of the target battery based on the operating parameters; the state of charge information, the health information, and the relaxation time distribution data are determined as the state data of the target battery, and the operating parameters refer to the parameters directly obtained by measuring the target battery; The determination module is used to determine the correlation coefficient between the operating parameters and the state data based on the Spearman correlation algorithm; and to determine the target prediction data from the operating parameters and the state data based on the correlation coefficient threshold and the correlation coefficient between the operating parameters and the state data. An execution module is used to input the target prediction data into a pre-trained battery temperature determination model to obtain the temperature information of the target battery output by the battery temperature determination model, wherein the temperature information is used to characterize the internal temperature of the target battery. The training module is used to obtain a training dataset from the target database according to a preset ratio, and to train the initial battery temperature determination model based on the training dataset to obtain a candidate battery temperature determination model; to obtain the determination coefficient and mean absolute error of the candidate battery temperature determination model, and to determine the candidate battery temperature determination model as the battery temperature determination model if the determination coefficient and the mean absolute error meet preset conditions, wherein the determination coefficient is the goodness of fit of the candidate battery temperature determination model.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.