A method for determining the remaining charging time of a battery, an electronic device, and a medium.

Abstract

This application discloses a method, electronic device, and medium for determining the remaining charging time of a battery, relating to the field of battery charging technology. It acquires the battery's operating status and charging rate, and, combining the cloud and local communication status and charging rate, determines the target-dimensional electrothermal coupling model and target calculation level based on the computational level characteristics of different-dimensional electrothermal coupling models. The target-dimensional electrothermal coupling model is used to simulate the changes in thermal characteristics during the battery charging process in real time, estimating temperature changes and calculating the remaining charging time. This application fully utilizes the high computing power of the cloud and local resources, and combines communication status to achieve flexible model switching, avoiding the accuracy defects of fixed empirical values ​​or simplified compensation schemes. Real-time interactive parameter correction through the electrothermal coupling model reduces estimation errors and improves the accuracy of remaining charging time estimation throughout the entire battery lifespan, which is used for rationally planning charging and discharging strategies.

Description

Technical Field

[0001] This application relates to the field of battery charging technology, and in particular to a method for determining the remaining charging time of a battery, an electronic device, and a medium. Background Technology

[0002] The technology for estimating the remaining charging time of batteries in energy storage systems mainly adopts three types of solutions from the new energy vehicle field: step-by-step current calculation, simplified temperature rise compensation, and interval-triggered updates. However, energy storage systems have characteristics such as large capacity (MWh level), more complex operating conditions (long-term charging and discharging, outdoor environmental fluctuations), and high consistency requirements for multi-cell series and parallel connections. This results in poor accuracy and slow response when estimating the remaining charging time. Furthermore, the estimation process is all performed locally, consuming a lot of local computing resources, which in turn prolongs the estimation time.

[0003] Therefore, how to improve the accuracy of remaining charging time, provide real-time response, and reduce the consumption of computing resources to improve estimation efficiency is a problem that those skilled in the art urgently need to solve. Summary of the Invention

[0004] The purpose of this application is to provide a method, electronic device, and medium for determining the remaining charging time of a battery, in order to solve the problems of low estimation accuracy, slow response, high local computing resource consumption, and long estimation time of conventional solutions.

[0005] To address the aforementioned technical problems, this application provides a method for determining the remaining charging time of a battery, comprising: Obtain the current battery operating status information and the corresponding battery charging rate; The target dimension electrothermal coupling model and the corresponding target computing level are determined based on the communication status between the cloud and the local terminal and the battery charging rate; wherein, the target computing level is either the cloud or the local terminal. Within the target computational level, the operating status information is input into the target dimension electrothermal coupling model, and the temperature information corresponding to the current battery is output to determine the remaining charging time of the battery.

[0006] On the one hand, based on the communication status between the cloud and the local terminal and the battery charging rate, the target dimension electrothermal coupling model and the corresponding target calculation level are determined, including: Determine the current communication status between the cloud and the local terminal; Based on the current communication status, the relationship between the battery charging rate and the preset battery charging rate determines the target dimension electrothermal coupling model; The target computation level is determined based on the mapping relationship between the target dimension electrothermal coupling model and the computation level.

[0007] On the other hand, based on the current communication state, the target dimension electrothermal coupling model is determined by the relationship between the battery charging rate and the preset battery charging rate, including: If the current communication status is good and the battery charging rate is greater than or equal to the preset battery charging rate, then the first-dimensional electrothermal coupling model is determined to be used. When the current communication state is medium and the battery charging rate is greater than or equal to the preset battery charging rate, the student model corresponding to the first-dimensional electrothermal coupling model is adopted. If the current communication state is abnormal and the battery charging rate is greater than or equal to the preset battery charging rate, then the second-dimensional electrothermal coupling model is determined to be used; wherein, the dimension of the second-dimensional electrothermal coupling model is less than the dimension of the first-dimensional electrothermal coupling model. If the current communication status is good and the battery charging rate is less than the preset battery charging rate, then the second-dimensional electrothermal coupling model is used.

[0008] On the other hand, the construction process of the student model corresponding to the first-dimensional electrothermal coupling model also includes: After receiving the battery key feature data uploaded from the local terminal in the cloud, the battery key feature data is input into the first dimension electrothermal coupling model to output intermediate layer key feature data. The preset student model is invoked, the key feature data of the intermediate layer is input into the preset student model, and the model parameters of the preset student model are adjusted so that the output result is close to the output result of the first-dimensional electrothermal coupling model, thus completing the construction of the student model.

[0009] On the other hand, the process of determining the mapping relationship between the target dimension electrothermal coupling model and the computational level includes: Establish a first mapping relationship between the first-dimensional electrothermal coupling model and the cloud; Establish a second mapping relationship between the student model of the first-dimensional electrothermal coupling model and the local terminal; A third mapping relationship is established between the second-dimensional electrothermal coupling model and the local terminal to complete the process of determining the mapping relationship between the target-dimensional electrothermal coupling model and the computational level.

[0010] On the other hand, if the target-dimensional electrothermal coupling model is different from the previous target-dimensional electrothermal coupling model corresponding to the previous acquisition cycle, after outputting the temperature information corresponding to the current battery, the following is also included: Obtain the temperature information output in the previous acquisition cycle; If the difference between the previous temperature information and the temperature information corresponding to the current battery meets the first preset difference, and the difference between the computation time of the previous target dimension electrothermal coupling model and the computation time of the target dimension electrothermal coupling model meets the second preset difference, then the previous target dimension electrothermal coupling model is used.

[0011] On the other hand, the process of obtaining the battery charging rate includes: Obtain the current charging current and rated capacity of the battery; The battery charging rate is determined based on the charging current and the battery's rated capacity.

[0012] On the other hand, the process of obtaining the battery charging rate includes: A preset dimension electrothermal coupling model is invoked in advance, and the operating status information is input into the preset dimension electrothermal coupling model to output the temperature information corresponding to the current battery. The battery charging rate is determined by polynomial fitting based on the temperature information and SOC.

[0013] To address the aforementioned technical problems, this application also provides an electronic device, comprising: Memory, used to store computer programs; A processor, used to execute the computer program, implement the steps of the method for determining the remaining battery charging time as described.

[0014] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for determining the remaining battery charging time as described above.

[0015] This application provides a method for determining the remaining charging time of a battery. First, it acquires the current battery operating status information and the battery charging rate. The operating status information mainly includes the current and voltage of the battery, while the battery charging rate is used as a reference to provide a basis for selecting the appropriate target dimension electrothermal coupling model. Second, based on the communication status between the cloud and the local end, and the battery charging rate, it determines the number of dimensions of the electrothermal coupling model to select and whether to process it in the cloud or locally. This is because three-dimensional electrothermal coupling models have high accuracy, but the local computing power is insufficient; one-dimensional electrothermal coupling models can be implemented locally, but the accuracy is low. Traditionally, the local end cannot utilize the results output by multi-dimensional electrothermal coupling models from the cloud when network communication is poor. By fully considering the application characteristics of different-dimensional electrothermal coupling models at different computational levels, the entire determination process can save local computing resources, fully utilize the high computing power of the cloud, and also consider the switching between different-dimensional electrothermal coupling models under different communication states between the local end and the cloud, improving the flexibility and diversity of application scenarios and shortening the computation time. Furthermore, regardless of the dimension, the electrothermal coupling model simulates the changes in battery thermal characteristics during charging to estimate temperature changes in real time during subsequent charging. This allows for real-time estimation of remaining charging time, improving accuracy and responding to changes in real time. Compared to conventional step-by-step current calculations, this application no longer uses fixed empirical values ​​for temperature rise. Instead, it calculates battery heat generation in real time and indirectly compensates for battery aging effects through real-time corrections. Compared to simplified temperature rise compensation schemes in conventional approaches, in addition to real-time calculation of battery heat generation, it can accurately calculate the increased heat generation and temperature rise even with battery aging, ensuring accuracy throughout the battery's lifespan. Simultaneously, the model performs bias correction to reduce estimation errors. Unlike conventional interval-triggered update schemes, the electrothermal coupling model is not interval-based but calculates current heat generation and temperature rise in real time based on time steps. The heat generation calculated by the electrical model is transferred to the thermal model, and the real-time temperature calculated by the thermal model is immediately fed back to the electrical model to correct internal resistance and voltage parameters. Finally, within the target calculation level, the specific application of the target dimension electrothermal coupling model is used to output the corresponding temperature information, thereby determining the remaining charging time of the battery, improving the accuracy of the remaining charging time estimation, and enabling reasonable planning of charging and discharging strategies.

[0016] In addition, this application also provides an electronic device and a medium that have the same beneficial effects as the method for determining the remaining charging time of a battery described above. Attached Figure Description

[0017] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for determining the remaining charging time of a battery, provided in an embodiment of this application; Figure 2 A schematic diagram of a second-order RC equivalent circuit model structure provided in the process of building a three-dimensional electrothermal coupling model according to an embodiment of this application; Figure 3 A schematic diagram of a three-dimensional electrothermal coupling model provided in an embodiment of this application; Figure 4 This is a schematic diagram of the equivalent circuit model structure during the construction of a one-dimensional electrothermal coupling model, as provided in an embodiment of this application. Figure 5 A flowchart illustrating another method for determining the remaining charging time of a battery, provided as an embodiment of this application; Figure 6 A structural diagram of a device for determining the remaining charging time of a battery provided in an embodiment of this application; Figure 7 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0020] The core of this application is to provide a method, electronic device, and medium for determining the remaining charging time of a battery, in order to solve the problems of low estimation accuracy, slow response, high local computing resource consumption, and long estimation time of conventional solutions.

[0021] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] As the new energy industry develops towards large-scale and high-reliability, energy storage systems (such as grid-side peak-shaving energy storage, renewable energy-supporting energy storage, and microgrid energy storage) have become core infrastructure for ensuring the stable operation of the power system. As the energy core of the energy storage system, the accuracy of the remaining charging time estimation of batteries directly affects the energy storage dispatch efficiency. Accurate estimation of remaining charging time helps the dispatch center to rationally plan charging and discharging strategies (such as coordinating with photovoltaic / wind power output periods and avoiding peak-valley electricity prices). However, excessive deviation can easily lead to delayed response of the energy storage system, reduced capacity utilization, and even affect the stability of the power grid.

[0023] Currently, the technology for estimating the remaining charging time of batteries in energy storage systems mainly adopts three types of solutions from the field of new energy vehicles: step-by-step current calculation, simplified temperature rise compensation, and interval triggering update. However, energy storage systems have characteristics such as large capacity (MWh level), more complex operating conditions (long-term charging and discharging, outdoor environmental fluctuations), and high consistency requirements for multi-cell series and parallel connection. Existing technologies are difficult to adapt to these characteristics and generally suffer from defects such as insufficient accuracy, lag in dynamic response, and failure to consider the special needs of energy storage scenarios.

[0024] Decomposition of current calculation: a basic estimation method based on fixed-order current; This method divides the battery charging process into multiple stages. First, it acquires charging information for different stages, voltage-charge state curves of the battery at different temperatures, and initial charging state information. Then, it acquires the temperature rise and charging amount for each charging stage. Finally, it calculates the charging time for each stage and sums them up to obtain the total charging time.

[0025] Although this method calculates the temperature rise at the start of charging, it does not consider the difference between the theoretically calculated temperature rise and the actual battery temperature rise, and there is no real-time correction mechanism during charging, resulting in inherent errors in the time calculation. At the same time, it does not take into account the impact of capacity reduction after battery aging, which further amplifies the error and cannot meet the estimation accuracy requirements of energy storage systems.

[0026] Interval-triggered update: A method for estimating the remaining time based on temperature variation and charging interval; The method first determines the charging request current and the corresponding battery temperature change rate, then estimates the first estimated time for the battery to charge from the current state of charge to the upper limit of the target range, and the second estimated time for the battery to change from the current temperature to the upper limit of the target range. The method then updates the estimated ranges for charge and temperature until the upper limit of the charge range reaches the target value. Finally, the method accumulates the smaller estimated time each time to obtain the total remaining time.

[0027] This method only recalculates the remaining time after the battery temperature reaches the estimated upper limit temperature, and does not achieve real-time updates of temperature and time estimates. As a result, when the operating conditions fluctuate during charging (such as changes in ambient temperature), the deviation between the estimated results and the actual time gradually increases, making it difficult to adapt to the dynamic scheduling requirements of energy storage systems.

[0028] Simplified temperature rise compensation: A method for estimating the remaining time based on temperature change and the charging interval; This method obtains the remaining battery power through the Battery Management System (BMS), divides the charging into several stages, obtains the initial charging temperature of the first stage and the temperature rise of each stage to determine the initial temperature of the subsequent stages, obtains the maximum allowable charging current based on the initial temperature, calculates the time of each stage and accumulates them to obtain the total charging time.

[0029] The temperature rise was calculated using a fixed value, but no temperature rise model adapted to actual operating conditions was built. After the battery aged, the fixed value and the actual temperature rise differed significantly, and there was no real-time update mechanism, resulting in a high error in the estimation of charging time, which could not meet the accuracy requirements of energy storage batteries for the remaining charging time.

[0030] In addition, considering that the computation is performed only on the local machine regardless of the method, local computing resources are limited.

[0031] The method for determining the remaining charging time of a battery provided in this application can solve the above-mentioned technical problems.

[0032] Figure 1 A flowchart illustrating a method for determining the remaining charging time of a battery, as provided in this application embodiment, is shown below. Figure 1 As shown, the method includes: S11: Obtain the current battery operating status information and the corresponding battery charging rate; S12: Determine the target dimension electrothermal coupling model and the corresponding target computing level based on the communication status between the cloud and the local terminal and the battery charging rate; wherein, the target computing level is either the cloud or the local terminal; S13: Within the target computational level, input the running status information into the target dimension electrothermal coupling model, and output the temperature information corresponding to the current battery to determine the remaining charging time of the battery.

[0033] Specifically, the current operating status of the battery is collected in real time by sensors in the Battery Management System (BMS), and can include electrical parameters, thermal parameters, and battery identification information. Electrical parameters can include current voltage, current, and state of charge. Thermal parameters can include battery surface temperature and ambient temperature. Battery identification information can include rated capacity and health status.

[0034] There are two methods to obtain the battery charging rate: one is direct calculation based on physical parameters, and the other is a strategy lookup table based on battery state. Direct calculation of physical parameters determines the ratio of the current charging current to the battery capacity. For the second method, strategy lookup table based on battery state, in practical applications, especially for complex scenarios such as electric vehicles and energy storage systems, the charging rate is not a fixed value, but is dynamically determined by the BMS based on the battery's real-time state. The BMS monitors multiple key battery parameters in real time and then looks them up in a pre-calibrated charging map (MAP) to determine the maximum permissible safe charging rate. Influencing factors include state of charge (SOC) and battery temperature. SOC allows for higher fast charging rates when the battery is low, but when the battery is close to full charge (e.g., above 80%), the rate is significantly reduced to protect the battery. Battery temperature limits the charging rate when it is too high or too low. High-current charging at low temperatures can easily cause lithium plating, while high temperatures exacerbate battery aging and the risk of thermal runaway.

[0035] The communication status between the cloud and the local terminal is determined by the system periodically monitoring the network connection quality between the local terminal and the cloud server, including signal strength, network latency, and bandwidth. A threshold is set, for example, latency below 100ms and stable bandwidth, which is considered good communication. This communication status establishes the foundation for subsequent use of cloud computing resources. When communication is good, and the battery charging rate is high, the powerful computing capabilities of the cloud are utilized to employ a high-dimensional electrothermal coupling model. High-rate charging generates significant heat, and the internal temperature distribution of the battery is extremely uneven. The three-dimensional electrothermal coupling model can accurately simulate the potential and temperature field distribution inside the battery, capturing local hot spots and thus providing the most accurate temperature prediction.

[0036] In the event of communication interruption or poor performance, regardless of the charging rate, the system prioritizes ensuring the availability of functions. In this case, the target computation level will be selected as the local end, and the target dimension electrothermal coupling model will adopt a low-dimensional electrothermal coupling model. This model has a smaller computational load and is suitable for real-time operation on the local end.

[0037] When communication is good and charging at a low rate, the battery generates less heat and the temperature distribution is relatively uniform. Therefore, there is no need to use a high-dimensional electrothermal coupling model with a large computational load. In order to save cloud resources and communication bandwidth, a one-dimensional electrothermal coupling model on the local end is adopted, which has a moderate computational load.

[0038] Within the target computational level, the running status information is input into the target dimension electrothermal coupling model, and the current battery temperature information is output to determine the remaining charging time of the battery.

[0039] Taking a three-dimensional electrothermal coupling model as an example, firstly, based on the current battery operating state, the BMS transmits operational information such as current battery temperature, ambient battery temperature, current, voltage, state of charge (SOC), and charging map to the cloud via methods including but not limited to telematics terminal boxes (T-boxes) and 4G technology for cloud model calculations. Secondly, cloud data cleaning involves cleaning the latest uploaded data from the local device on the cloud server based on historical data. Methods include, but are not limited to, missing value imputation, outlier removal, and data filtering to remove noise. The cleaned data is then used for cloud model calculations. Thirdly, the cloud electrothermal coupling model is established, starting with the construction of an electrical characteristic model. A second-order RC equivalent circuit model is used as the electrical characteristic model. External characteristic parameters such as battery current, terminal voltage, and temperature are used to describe the working state of the lithium-ion battery. Electronic components such as resistors, capacitors, and voltage sources are used to quantify the physical problem. The changes in battery state are briefly described by the volt-ampere characteristics exhibited by the electrical components. The equivalent circuit diagram and state equation of the electrical characteristic model are shown below.

[0040] Figure 2 A schematic diagram of a second-order RC equivalent circuit model structure provided in the process of building a three-dimensional electrothermal coupling model according to an embodiment of this application is shown below. Figure 2 As shown, its corresponding state equation is: ; in, As a voltage source, For internal resistance, The polarization resistance of the first group of polarization units. The capacitance of the first group of polarization units; This is the polarization resistance of the second group of polarization units. The capacitance of the second polarization unit; This is the terminal voltage.

[0041] When building a thermal property model, first build a heat generation model: The Bernardi heat generation rate formula is used to obtain the heat generated by the battery cell itself. The formula is as follows: ; in, I The charging / discharging current is in A. The battery open-circuit voltage is V; The terminal voltage is V; For the battery volume, m3 ; It is the entropy heat coefficient.

[0042] Next, build the heat dissipation model: Based on Newton's law of cooling, Fourier's law of thermal conductivity, and the three-dimensional unsteady-state heat transfer theory, a heat dissipation model is established to simulate the time-series temperature changes of the battery. The specific formulas are as follows: 1) Newton's Law of Cooling: ; in, h The convective heat transfer coefficient is W / (m 2 ·K); A To generate the area for convective heat transfer, m 2 ; The temperature of the fluid medium, in K; Let K be the surface temperature of the solid.

[0043] 2) Fourier's law of heat conduction: ; Where - indicates the direction of heat transfer; is the thermal conductivity of the battery, W / (m·K); For temperature gradient.

[0044] 3) Three-dimensional unsteady-state heat conduction law: ; The boundary conditions are as follows: ; in, The density of the battery, kg / m³ 3 ; The specific heat capacity of the battery is J / (kg·K); , , For the battery along x, y, z Thermal conductivity in three directions, W / (m·K); For temperature along the battery x, y, z Rates of change in three directions; is the convective heat transfer coefficient of the battery surface, W / (m·K); A , B , C For the battery along , , The length in three directions, in meters (m); The ambient temperature is in K.

[0045] Finally, the electrothermal coupling model was built: Figure 3A schematic diagram of a three-dimensional electrothermal coupling model provided in this application embodiment is shown below. Figure 3 As shown, the charging / discharging current, initial battery temperature, and battery temperature output from the thermal characteristic model are considered. T Input electrical characteristic model, output voltage E A thermal characteristic model is provided, and the input parameters of the thermal characteristic model also include the ambient temperature. T0 (The temperature of the fluid on the battery surface, i.e., the ambient temperature) The battery temperature is output by considering the external temperature field and the external temperature field. T .

[0046] Combining the above electrical and thermal characteristic models, an electrothermal coupling model is established to simulate the changes in battery thermal characteristics during charging and to estimate temperature changes in real time during subsequent charging.

[0047] Taking a one-dimensional electrothermal coupling model as an example, Figure 4 This application provides an example of an equivalent circuit model structure diagram illustrating the construction process of a one-dimensional electrothermal coupling model. Figure 4 As shown, this model uses the thermoelectric similarity principle to convert thermal parameters into electrical parameters. That is, the entire temperature field of the lithium-ion battery is converted into the voltage field of the battery, the specific heat capacity of the battery and the specific heat capacity distribution of the battery shell are converted into internal heat capacity and external heat capacity, the heating power is converted into a current source, and the internal and external heat conduction rates are converted into thermal resistance. Based on Kirchhoff's laws, the corresponding mathematical model is derived. Q For the heating power, the solution method refers to the calculation method of the three-dimensional model. T 1 represents the internal temperature of the battery cell. T 2 represents the battery pack casing temperature. For ambient temperature, C 1 represents the internal heat capacity of the battery. C 2 represents the external heat capacity of the battery. Ri The internal thermal conductivity of the battery. R o represents the external convective heat transfer coefficient of the battery. According to Kirchhoff's laws, the following formula can be obtained: ; At this time, let: ; Performing the Laplace transform, we obtain the following transfer function: ; The purpose of building a one-dimensional model is to obtain the difference between the temperature at the battery center and the ambient temperature, in order to evaluate the average temperature of the battery.

[0048] Therefore, by simplifying the above formula, we can obtain the difference between the battery's internal temperature and the battery's ambient temperature, calculated as follows: ; By iteratively solving the problem, the battery temperature state for a future period of time can be obtained.

[0049] It should be noted that this embodiment determines the target dimension electrothermal coupling model based on the battery operating status information in real time during the current acquisition cycle, and then determines the remaining charging time of the battery. Regarding the target dimension electrothermal coupling model of the previous acquisition cycle, if it is the same, it will continue to be used; if it is different, a switch needs to be performed.

[0050] In practical applications, if the battery charging rate is around a certain threshold, it may fluctuate. Therefore, the above model selection mechanism should introduce a filtering time, that is, calculate the enable calculation every 5 minutes. When switching between the electrothermal coupling model calculation in the current acquisition cycle and the previous acquisition cycle, to take into account user perception, a remaining charging time tracking strategy should be followed. That is, when the difference between the two calculation results is greater than 1 minute, it should track for 0.5 minutes every 1 minute of running time (the actual tracking rate should be weighed according to the different perceptions of different customer groups) until it is completely tracked.

[0051] Regardless of the temperature information calculated by the electrothermal coupling model of any dimension, the real-time SOC is calculated by the ampere-hour integration method. The current charging current is then obtained by inputting the MAP and the SOC is calculated in real time. The calculated SOC and temperature are then injected back into the model for iterative solution until SOC = 100%. The above calculation time is then added to the model as the remaining charging time of the battery.

[0052] The formula for calculating ampere-hours using the integral method is as follows: ; in, For the initial SOC, For the current SOC, For charging and discharging efficiency, For battery capacity, This is the integral of the current.

[0053] This application provides a method for determining the remaining charging time of a battery. First, it acquires the current battery operating status information and the battery charging rate. The operating status information mainly includes the current and voltage of the battery, while the battery charging rate is used as a reference to provide a basis for selecting the appropriate target dimension electrothermal coupling model. Second, based on the communication status between the cloud and the local end, and the battery charging rate, it determines the number of dimensions of the electrothermal coupling model to select and whether to process it in the cloud or locally. This is because three-dimensional electrothermal coupling models have high accuracy, but the local computing power is insufficient; one-dimensional electrothermal coupling models can be implemented locally, but the accuracy is low. Traditionally, the local end cannot utilize the results output by multi-dimensional electrothermal coupling models from the cloud when network communication is poor. By fully considering the application characteristics of different-dimensional electrothermal coupling models at different computational levels, the entire determination process can save local computing resources, fully utilize the high computing power of the cloud, and also consider the switching between different-dimensional electrothermal coupling models under different communication states between the local end and the cloud, improving the flexibility and diversity of application scenarios and shortening computation time. Furthermore, regardless of the dimension, the electrothermal coupling model simulates the changes in battery thermal characteristics during charging to estimate temperature changes in real time during subsequent charging. This allows for real-time estimation of remaining charging time, improving accuracy and responding to changes in real time. Compared to conventional step-by-step current calculations, this application no longer uses fixed empirical values ​​for temperature rise. Instead, it calculates battery heat generation in real time and indirectly compensates for battery aging effects through real-time corrections. Compared to simplified temperature rise compensation schemes in conventional approaches, in addition to real-time calculation of battery heat generation, it can accurately calculate the increased heat generation and temperature rise even with battery aging, ensuring accuracy throughout the battery's lifespan. Simultaneously, the model performs bias correction to reduce estimation errors. Unlike conventional interval-triggered update schemes, the electrothermal coupling model is not interval-based but calculates current heat generation and temperature rise in real time based on time steps. The heat generation calculated by the electrical model is transferred to the thermal model, and the real-time temperature calculated by the thermal model is immediately fed back to the electrical model to correct internal resistance and voltage parameters. Finally, within the target calculation level, the specific application of the target dimension electrothermal coupling model is used to output the corresponding temperature information, thereby determining the remaining charging time of the battery, improving the accuracy of the remaining charging time estimation, and enabling reasonable planning of charging and discharging strategies.

[0054] In some embodiments, the process of obtaining the battery charging rate includes: Obtain the current charging current and rated capacity of the battery; The battery charging rate is determined based on the charging current and the battery's rated capacity.

[0055] Specifically, the current charging current value is acquired in real time by a current sensor (such as a Hall sensor or a shunt) installed in the battery circuit. The battery's rated capacity (C) is usually stored in the non-volatile memory of the BMS. This value is written at the factory and represents the battery's nominal capacity (Ah) under standard conditions (such as 25°C, 0.2C charge / discharge).

[0056] The system calculates the charging rate based on a preset mathematical relationship, using the acquired charging current and the battery's rated capacity. The formula is as follows: Charging current ÷ Battery rated capacity = Battery charging rate.

[0057] The method provided in this embodiment for determining the battery charging rate using physical parameters involves minimal computation and does not consume excessive processor resources, thus enabling the determination of the target dimension electrothermal coupling model based on the battery charging rate.

[0058] In some embodiments, the process of obtaining the battery charging rate includes: A preset dimension electrothermal coupling model is invoked in advance, and the operating status information is input into the preset dimension electrothermal coupling model to output the temperature information corresponding to the current battery. The battery charging rate is determined by polynomial fitting based on temperature information and SOC.

[0059] Specifically, after adding the cell charging MAP, it can be seen that when the SOC is too low or too high, and the temperature is too low or too high, the charging rate of the battery is relatively small. The low battery rate has little impact on the estimation of the remaining charging time, so a one-dimensional model can be used for calculation, while a three-dimensional model is used for calculation in the range of high charging rate.

[0060] The process of determining the battery charging rate can be achieved using polynomial fitting. The following formula is obtained by fitting the MAP (Magnitude Mapping) using a polynomial: ; Where T represents the current battery temperature and C represents the battery charging rate.

[0061] This embodiment indirectly derives the current charging rate by analyzing the relationship between the battery's temperature response characteristics and SOC changes under specific operating conditions. This directly reflects the actual thermal effect of the charging rate on the battery. Since battery life and safety are primarily affected by temperature, this charging rate determined based on thermal characteristics more accurately characterizes the battery's stress state and aging level. The coefficients obtained through polynomial fitting directly reflect the nonlinearity of the battery's temperature rise. These coefficients can serve as input features for machine learning algorithms to more intelligently determine whether the battery is in an overheating risk zone, or to dynamically adjust subsequent charging current to avoid temperature overshoot.

[0062] In some embodiments, the target dimension electrothermal coupling model and the corresponding target computation level are determined based on the communication status between the cloud and the local terminal and the battery charging rate, including: Determine the current communication status between the cloud and the local device; Based on the current communication status, the relationship between the battery charging rate and the preset battery charging rate determines the target dimension electrothermal coupling model; The target computation level is determined based on the mapping relationship between the target dimension electrothermal coupling model and the computation level.

[0063] Specifically, the current communication status is detected via heartbeat, which can be determined based on whether a response is received from the cloud within a preset time, including whether the communication is good, abnormal, or interrupted. Then, the target dimension electrothermal coupling model is selected based on the relationship between the battery charging rate and the preset battery charging rate.

[0064] It should be noted that in this embodiment, communication is the primary condition. If communication is normal, the choice of which dimension of electrothermal coupling model to select is based on the magnitude of the multiplier.

[0065] The target computational level is then determined based on the mapping relationship between the target-dimensional electrothermal coupling model and the computational level. A one-dimensional model is simple, requires low computational power, and can be deployed locally, but its computational accuracy is poor because it simplifies the battery system to a single point. A three-dimensional model is complex, requires solving partial differential equations, requires high computational power, and cannot be deployed locally, but its computational accuracy is high due to the three-dimensional computation. Depending on the current cloud communication status, if there is no cloud communication, the one-dimensional model is selected for computation. If communication is normal, the final target-dimensional electrothermal coupling model is further determined based on the relationship between the battery charging rate and the preset battery charging rate.

[0066] This embodiment uses a step-by-step judgment logic to determine the target dimension electrothermal coupling model and its execution end, considering both communication status and charging rate to avoid wasting computational resources. Introducing communication status as the primary judgment condition enables the system to adapt to network fluctuations. When communication is abnormal, the system can automatically degrade to running the local model, preventing situations where the remaining charging time cannot be calculated or the calculation results are severely deviated due to network interruption, thus ensuring a continuous user experience.

[0067] In some embodiments, the target-dimensional electrothermal coupling model is determined based on the relationship between the current communication state and the battery charging rate and a preset battery charging rate, including: If the current communication status is good and the battery charging rate is greater than or equal to the preset battery charging rate, the first-dimensional electrothermal coupling model is determined to be used. When the current communication state is medium and the battery charging rate is greater than or equal to the preset battery charging rate, the student model corresponding to the first-dimensional electrothermal coupling model is adopted. If the current communication state is abnormal and the battery charging rate is greater than or equal to the preset battery charging rate, the second-dimensional electrothermal coupling model is determined to be used; wherein, the dimension of the second-dimensional electrothermal coupling model is smaller than the dimension of the first-dimensional electrothermal coupling model. If the current communication status is good and the battery charging rate is less than the preset battery charging rate, the second-dimensional electrothermal coupling model is selected.

[0068] Specifically, the first-dimensional electrothermal coupling model refers to a high-precision, computationally intensive model (such as a three-dimensional or higher-order electrothermal coupling model). Deployed in the cloud, this model accurately simulates the complex heat distribution inside a battery. The student model is a lightweight neural network model trained using simulation data from the first-dimensional electrothermal coupling model through knowledge distillation. It retains the main characteristics of the high-dimensional model but is small in size, has fast inference speed, and can be deployed locally or on edge nodes. The second-dimensional electrothermal coupling model refers to a traditional low-dimensional physical model (such as a one-dimensional electrothermal coupling model). This model is based on simplified physical formulas, has low computational load, and requires very little computing power; it is typically pre-installed locally.

[0069] Under fast charging and network conditions permitting, the highest accuracy is prioritized. The system uploads data to the cloud and uses a high-dimensional model for calculation to obtain the most accurate internal temperature field distribution of the battery. This is implemented when the current communication status is good (e.g., sufficient bandwidth, extremely low latency, stable connection) and the current battery charging rate is greater than or equal to the preset battery charging rate.

[0070] When network quality degrades and cannot support the large amount of data transmission required by high-dimensional models, the system activates a locally deployed student model to avoid prediction lag caused by transmission delays. This model can simulate thermal behavior at high charging rates with extremely low latency, ensuring real-time prediction during the fast charging phase. Specifically, the system is invoked when the current communication state is moderate (e.g., bandwidth is limited, there is some latency or fluctuation, but the connection is not interrupted) and the current battery charging rate is greater than or equal to the preset battery charging rate.

[0071] In the extreme case of complete communication interruption, both the cloud model and the student model (if not pre-configured locally) become unavailable. To ensure degraded system operation, the system activates the local electrothermal coupling model. Although this sacrifices some accuracy, it guarantees real-time temperature monitoring. Specifically, the system is invoked when the current communication state is abnormal (e.g., network outage, prolonged timeout, severe packet loss) and the current battery charging rate is greater than or equal to the preset battery charging rate.

[0072] Under slow charging conditions, battery thermal changes are relatively gradual, and the accuracy requirements for the model are not high. Even with good communication, there is no need to call upon high-performance cloud computing resources; the local model can be used directly to meet the needs, thus saving cloud computing resources and communication costs. In other words, the model is invoked only when the current communication status is good and the current battery charging rate is less than the preset battery charging rate.

[0073] This embodiment not only considers communication connectivity but also introduces a classification of communication status (good, medium, abnormal). It combines the comparison results of battery charging rate and preset charging rate to determine the target dimension electrothermal coupling model from four specific preset models. This enables the system to utilize network resources more intelligently, improve the flexibility of model invocation, save computing resources, and improve computing efficiency.

[0074] In some embodiments, the process of constructing the student model corresponding to the first-dimensional electrothermal coupling model further includes: After receiving the battery key feature data uploaded from the local end in the cloud, the battery key feature data is input into the first-dimensional electrothermal coupling model to output the intermediate layer key feature data. Call the preset student model, input the key feature data of the intermediate layer into the preset student model, adjust the model parameters of the preset student model so that the output result is close to the output result of the first dimension electrothermal coupling model, and complete the construction of the student model.

[0075] Specifically, the local device (such as the BMS) collects real-time battery operating data under various conditions (different temperatures, SOC, charge / discharge rates) and defines it as key battery characteristic data. This data is compressed or filtered before being uploaded to the cloud. Upon receiving the data, the cloud uses it as input excitation to apply to the first-dimensional electrothermal coupling model (teacher model), which performs high-precision simulation calculations. In addition to outputting the final temperature prediction result, the system captures the output data of the teacher model's intermediate layers, i.e., the intermediate layer key feature data. This intermediate layer data contains deep, high-dimensional electrothermal coupling feature representations (such as feature maps or high-dimensional tensors) extracted by the teacher model during the calculation process, which contain richer information about the physical processes than the final single prediction value.

[0076] The cloud invokes a pre-designed student model. This model typically employs a lightweight neural network architecture (such as MobileNet, a lightweight multi-layer perceptron (MLP), or a simplified version of a physical information neural network), with a much smaller number of parameters than the teacher model. The acquired intermediate layer key feature data is used as a supervision signal and input into the pre-designed student model. The student model performs forward propagation computation to generate its own prediction output. The difference loss between the student model output and the teacher model output (including the final result and / or intermediate layer features) is calculated. This loss function includes not only the error of the prediction value (such as mean squared error (MSE)) but also the difference at the feature level (such as Kullback-Leibler (KL) divergence or feature matching loss). Based on this loss function, the model parameters (weights and biases) of the pre-designed student model are adjusted using the backpropagation algorithm. This process is repeated until the output of the student model statistically approximates (converges to) the output of the first-dimensional electrothermal coupling model. At this point, the student model is considered to have learned the architectural logic of the teacher model, and the construction process is complete. The trained student model can then be deployed and used locally.

[0077] The student model provided in this embodiment uses knowledge distillation technology to transfer features from the teacher model to the structurally simple student model, achieving prediction accuracy close to that of a high-dimensional model. This resolves the contradiction between insufficient local computing power and the need for high-precision prediction, and reduces the difficulty of local model development and data dependence.

[0078] In some embodiments, the process of determining the mapping relationship between the target dimension electrothermal coupling model and the computational hierarchy includes: Establish the first mapping relationship between the first-dimensional electrothermal coupling model and the cloud; Establish a second mapping relationship between the student model of the first-dimensional electrothermal coupling model and the local terminal; A third mapping relationship is established between the second-dimensional electrothermal coupling model and the local terminal to complete the process of determining the mapping relationship between the target-dimensional electrothermal coupling model and the computational level.

[0079] Specifically, the characteristics of the first-dimensional electrothermal coupling model are analyzed. This model typically involves solving complex partial differential equations, requiring significant CPU / GPU computing power and memory resources. Due to limited local computing power, it cannot handle the computation of such high-dimensional models; therefore, a first mapping relationship is established. This relationship is defined as automatically routing the computation task to the cloud computing cluster when the system needs to invoke the first-dimensional electrothermal coupling model. In the cloud service registry or edge computing management platform, the model's unique identifier (ID) or service name is bound to the address of the cloud computing node.

[0080] Identify the characteristics of the student model (e.g., a lightweight neural network model). This model undergoes knowledge distillation and compression, resulting in a small size, fast inference speed, and optimization for operation on resource-constrained devices. Establish a second mapping relationship. This relationship is defined as follows: when the system decision requires invoking the student model of the first-dimensional electrothermal coupling model, the computational task is routed to the local end. This mapping utilizes the idle computing power of the local end, avoids network latency in data upload, and achieves millisecond-level real-time response.

[0081] Confirm the location of the second-dimensional electrothermal coupling model. This model is based on simplified physical formulas, has simple computational logic, and is the fundamental algorithm of the battery management system. Establish a third mapping relationship. This relationship is defined as follows: when the system decision requires calling the second-dimensional electrothermal coupling model, the computation task is also executed locally.

[0082] This embodiment provides a mapping method that allows the system to quickly locate the physical execution environment of the target-dimensional electrothermal coupling model after determining the model, ensuring that the computational task is accurately distributed to the cloud or local machine for execution. This avoids wasting computing resources (such as using cloud computing power to calculate simple formulas) or being insufficient (such as crashing due to running high-dimensional models locally), maximizing the resource utilization of the entire system.

[0083] In some embodiments, if the target dimension electrothermal coupling model is different from the previous target dimension electrothermal coupling model corresponding to the previous acquisition cycle, after outputting the temperature information corresponding to the current battery, the method further includes: Obtain the temperature information output in the previous acquisition cycle; If the difference between the previous temperature information and the current temperature information of the battery meets the first preset difference, and the difference between the computation time of the previous target dimension electrothermal coupling model and the computation time of the target dimension electrothermal coupling model meets the second preset difference, then the previous target dimension electrothermal coupling model will be used.

[0084] Specifically, when the system detects an inconsistency between the target dimension electrothermal coupling model in the current acquisition cycle and the model used in the previous acquisition cycle, it first outputs the battery temperature information calculated based on the new model to ensure the real-time nature of the monitoring data. Subsequently, the system does not immediately lock onto the new model. Instead, it retrieves the temperature information output from the previous acquisition cycle and calculates the difference between it and the current temperature information. Simultaneously, the system records the historical computation time of the previous target dimension electrothermal coupling model and compares it with the computation time of the current target dimension electrothermal coupling model to calculate the time difference. If the temperature difference is less than a first preset difference (e.g., 1℃) and the computation time difference is less than a second preset difference (e.g., 5ms), it is determined that the environmental conditions are changing gradually and the computational efficiency of the old and new models is similar. In this case, the system will execute a model reuse strategy, i.e., revert to and continue using the target dimension electrothermal coupling model from the previous acquisition cycle for subsequent temperature monitoring and calculation. This mechanism avoids unnecessary model switching during minor changes in operating conditions or redundant model updates, reducing computational jitter caused by the initialization of new model parameters.

[0085] In this embodiment, when switching between the target dimension electrothermal coupling models corresponding to the current and previous acquisition cycles, if the temperature change is gradual and the model computational load is similar, the converged old model is used. This avoids parameter resets and iterative calculations caused by frequent model switching, significantly improving the system's computational efficiency and response speed. Furthermore, it reduces potential numerical oscillations during model switching, enhancing the stability of battery temperature prediction and providing more reliable data support for the safe operation of the battery and the formulation of thermal management strategies.

[0086] In some embodiments, Figure 5 A flowchart illustrating another method for determining the remaining battery charging time provided in an embodiment of this application is shown below. Figure 5 As shown, it includes: S21: Local terminal collects battery temperature, current, voltage, SOC, and charging MAP information and uploads it to the cloud; S22: Cloud-based data cleaning; S23: Determine if the current SOC is less than 100%. If yes, proceed to step S24; otherwise, proceed to step S25. S24: Calculation of temperature rise using an electro-thermal coupling model; S26: Look up the table to obtain the current charging current using SOC and T; S27: Cumulative charging time; S28: Calculate SOC and return to step S23; S25: Outputs the cumulative charging time and transmits it to the local terminal; S26: Determine if the cloud communication is abnormal; if yes, proceed to step S29; otherwise, proceed to step S30. S29: Local human-computer interaction page display; S30: Calculate the remaining charging time using the local one-dimensional model and proceed to step S29.

[0087] The foregoing has described in detail various embodiments of the method for determining the remaining battery charging time. Based on this, this application also discloses a device for determining the remaining battery charging time corresponding to the above method. Figure 6 This is a structural diagram of a device for determining the remaining charging time of a battery, provided in an embodiment of this application. Figure 6 As shown, the device includes: The acquisition module 11 is used to acquire the current operating status information of the battery and the corresponding battery charging rate; The first determining module 12 is used to determine the target dimension electrothermal coupling model and the corresponding target computing level based on the communication status between the cloud and the local terminal and the battery charging rate; wherein, the target computing level is either the cloud or the local terminal; The second determining module 13 is used to input the running status information into the target dimension electrothermal coupling model within the target calculation level, and output the temperature information corresponding to the current battery to determine the remaining charging time of the battery.

[0088] Since the embodiments of the device part correspond to the embodiments described above, please refer to the embodiments described in the method part for the embodiments of the device part, and will not be repeated here.

[0089] For a description of the device for determining the remaining charging time of a battery provided in this application, please refer to the above method embodiments. This application will not repeat the description here, as it has the same beneficial effects as the above method for determining the remaining charging time of a battery.

[0090] Figure 7 A structural diagram of an electronic device provided in an embodiment of this application, such as... Figure 7 As shown, the device includes: Memory 21 is used to store computer programs; Processor 22 is configured to execute a computer program to implement a method for determining the remaining charging time of a battery.

[0091] The electronic devices provided in this embodiment may include, but are not limited to, smartphones, tablets, laptops, or desktop computers.

[0092] The processor 22 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 22 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor, also known as the CPU, is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 22 may integrate a GPU, which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 22 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0093] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 21 is used to store at least the following computer program 211, which, after being loaded and executed by the processor 22, is capable of implementing the relevant steps of the method for determining the remaining battery charging time disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may also include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. The operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, the data involved in the method for determining the remaining battery charging time.

[0094] In some embodiments, the electronic device may further include a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27.

[0095] Those skilled in the field can understand, Figure 7 The structures shown do not constitute a limitation on electronic devices and may include more or fewer components than those shown.

[0096] The processor 22 implements the method for determining the remaining battery charging time provided in any of the above embodiments by calling instructions stored in the memory 21.

[0097] For an introduction to the electronic device provided in this application, please refer to the above method embodiments. This application will not repeat the details here, but it has the same beneficial effects as the above method for determining the remaining charging time of the battery.

[0098] Furthermore, this application also provides a computer-readable storage medium storing a computer program, which, when executed by processor 22, implements the steps of the method for determining the remaining charging time of the battery as described above.

[0099] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments. This application will not repeat the description here, but it has the same beneficial effects as the above method for determining the remaining charging time of the battery.

[0101] The foregoing has provided a detailed description of a method for determining the remaining charging time of a battery, an electronic device, and a medium provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

[0102] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

Claims

1. A method for determining the remaining charging time of a battery, characterized in that, include: Obtain the current battery operating status information and the corresponding battery charging rate; The target dimension electrothermal coupling model and the corresponding target computing level are determined based on the communication status between the cloud and the local terminal and the battery charging rate; wherein, the target computing level is either the cloud or the local terminal. Within the target computational level, the operating status information is input into the target dimension electrothermal coupling model, and the temperature information corresponding to the current battery is output to determine the remaining charging time of the battery.

2. The method for determining the remaining charging time of a battery according to claim 1, characterized in that, Based on the communication status between the cloud and the local terminal, and the battery charging rate, the target dimension electrothermal coupling model and the corresponding target computation level are determined, including: Determine the current communication status between the cloud and the local terminal; Based on the current communication status, the relationship between the battery charging rate and the preset battery charging rate determines the target dimension electrothermal coupling model; The target computation level is determined based on the mapping relationship between the target dimension electrothermal coupling model and the computation level.

3. The method for determining the remaining charging time of a battery according to claim 2, characterized in that, Based on the current communication state, the relationship between the battery charging rate and the preset battery charging rate determines the target dimension electrothermal coupling model, including: If the current communication status is good and the battery charging rate is greater than or equal to the preset battery charging rate, then the first-dimensional electrothermal coupling model is determined to be used. When the current communication state is medium and the battery charging rate is greater than or equal to the preset battery charging rate, the student model corresponding to the first-dimensional electrothermal coupling model is adopted. If the current communication state is abnormal and the battery charging rate is greater than or equal to the preset battery charging rate, then the second-dimensional electrothermal coupling model is determined to be used; wherein, the dimension of the second-dimensional electrothermal coupling model is less than the dimension of the first-dimensional electrothermal coupling model. If the current communication status is good and the battery charging rate is less than the preset battery charging rate, then the second-dimensional electrothermal coupling model is used.

4. The method for determining the remaining charging time of a battery according to claim 3, characterized in that, The construction process of the student model corresponding to the first-dimensional electrothermal coupling model also includes: After receiving the battery key feature data uploaded from the local terminal in the cloud, the battery key feature data is input into the first dimension electrothermal coupling model to output intermediate layer key feature data. The preset student model is invoked, the key feature data of the intermediate layer is input into the preset student model, and the model parameters of the preset student model are adjusted so that the output result is close to the output result of the first-dimensional electrothermal coupling model, thus completing the construction of the student model.

5. The method for determining the remaining charging time of a battery according to claim 3 or 4, characterized in that, The process of determining the mapping relationship between the target dimension electrothermal coupling model and the computational level includes: Establish a first mapping relationship between the first-dimensional electrothermal coupling model and the cloud; Establish a second mapping relationship between the student model of the first-dimensional electrothermal coupling model and the local terminal; A third mapping relationship is established between the second-dimensional electrothermal coupling model and the local terminal to complete the process of determining the mapping relationship between the target-dimensional electrothermal coupling model and the computational level.

6. The method for determining the remaining charging time of a battery according to claim 1, characterized in that, If the target dimension electrothermal coupling model is different from the previous target dimension electrothermal coupling model corresponding to the previous acquisition cycle, after outputting the temperature information corresponding to the current battery, the following is also included: Obtain the temperature information output in the previous acquisition cycle; If the difference between the previous temperature information and the temperature information corresponding to the current battery meets the first preset difference, and the difference between the computation time of the previous target dimension electrothermal coupling model and the computation time of the target dimension electrothermal coupling model meets the second preset difference, then the previous target dimension electrothermal coupling model is used.

7. The method for determining the remaining charging time of a battery according to claim 1, characterized in that, The process of obtaining the battery charging rate includes: Obtain the current charging current and rated capacity of the battery; The battery charging rate is determined based on the charging current and the battery's rated capacity.

8. The method for determining the remaining charging time of a battery according to claim 1, characterized in that, The process of obtaining the battery charging rate includes: A preset dimension electrothermal coupling model is invoked in advance, and the operating status information is input into the preset dimension electrothermal coupling model to output the temperature information corresponding to the current battery. The battery charging rate is determined by polynomial fitting based on the temperature information and SOC.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the method for determining the remaining charging time of a battery as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for determining the remaining charging time of a battery as described in any one of claims 1 to 8.

Images