Charging remaining time prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a charging remaining time prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an initial temperature, an initial state of charge and an initial charging rate of a target battery at an initial moment; the initial temperature, the initial charging rate and the sum value of the initial charge state and the preset charge state step length are used as input, and the temperature of the target battery at the end point of each prediction interval is predicted through a temperature rise prediction network; the preset state-of-charge step length is used for indicating the state-of-charge variation of the adjacent prediction intervals; determining the charging rate of the target battery in each prediction interval from the mapping relation between the temperature and the charge state of the target battery and the charging rate; the preset charge state step length is compared with the charging rate of the target battery in the prediction interval, and the charging time of the target battery in each prediction interval is determined; and determining the sum value of the charging durations of all the prediction intervals as the charging remaining time of the target battery.

Description

Technical Field

[0001] This disclosure relates to the field of battery management technology, and in particular to a method, apparatus, electronic device, and storage medium for predicting remaining charging time. Background Technology

[0002] The remaining charging time of a target battery refers to the time required for the battery to complete charging from the current moment. Relevant charging time prediction schemes typically employ real-time prediction methods such as machine learning and physical modeling. However, when using machine learning to predict the remaining charging time, inaccurate predictions are not possible if the historical charging data for the target battery does not cover all operating conditions. Similarly, physical modeling methods often use average current for calculations, but in actual charging processes, the target battery's current is affected by its temperature, thus also preventing accurate predictions of the remaining charging time. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for predicting remaining charging time.

[0004] According to a first aspect of this disclosure, a method for predicting remaining charging time is provided, comprising:

[0005] Obtain the initial temperature, initial state of charge, and initial charge rate of the target battery at the initial moment;

[0006] Using the initial temperature, initial charging rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval; the preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals.

[0007] The charging rate of the target battery in each prediction interval is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0008] The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval.

[0009] The sum of the charging times for all predicted intervals is determined as the remaining charging time for the target battery.

[0010] In some embodiments of this disclosure, obtaining the initial temperature, initial state of charge, and initial charge rate of the target battery at an initial time includes:

[0011] Obtain the initial temperature and initial state of charge of the target battery at the initial moment;

[0012] The initial charging rate of the target battery at the initial moment is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0013] In some embodiments of this disclosure, the step of using the initial temperature, initial charge rate, and the sum of the initial state of charge and a preset state of charge step size as inputs to predict the temperature of the target battery at the end of each prediction interval using a temperature rise prediction network includes:

[0014] The difference between the rated capacity of the target battery and the initial state of charge is compared with a preset state of charge step size to determine the number of prediction intervals.

[0015] Using the initial temperature, initial charge rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval.

[0016] In some embodiments of this disclosure, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval, including:

[0017] Using the sum of the initial temperature, initial state of charge and preset state of charge step size, and initial charge rate as input, a temperature rise prediction network is used to predict the temperature rise of the target battery at the end of the first prediction interval.

[0018] The sum of the temperature rise of the target battery at the end of the first prediction interval and the initial temperature is determined to be the temperature of the target battery at the end of the first prediction interval.

[0019] The initial temperature is updated using the temperature of the target battery at the end of the first prediction interval. The sum of the initial state of charge and the preset state of charge step size is updated using the state of charge of the target battery at the end of the corresponding prediction interval. The initial charging rate is updated using the charging rate of the target battery in the corresponding prediction interval. Each prediction interval of the target battery is traversed to obtain the temperature of the target battery at the end of each prediction interval.

[0020] In some embodiments of this disclosure, updating the sum of the initial state of charge and the preset state of charge step size using the state of charge of the target battery at the end of the corresponding prediction interval includes:

[0021] The sum of the initial state of charge and the first integer multiple of the preset state of charge step size is determined to be the sum of the updated initial state of charge and the preset state of charge step size; the first integer multiple refers to an integer multiple that is the same as the index of the prediction interval.

[0022] In some embodiments of this disclosure, determining the charging rate of the target battery in each prediction interval from the mapping relationship between the target battery's temperature and state of charge and the charging rate includes:

[0023] Obtain the charging rate MAP table, which is used to indicate the mapping relationship between the target battery's temperature and state of charge and the charging rate.

[0024] The temperature and state of charge of the target battery at the end of each prediction interval are compared with the charge rate MAP table, and the charge rate of the target battery in each prediction interval is determined from the charge rate MAP table.

[0025] In some embodiments of this disclosure, the charging time of the target battery in each prediction interval is determined by comparing a preset state of charge step size with the charging rate of the target battery in the prediction interval, including:

[0026] The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in other prediction intervals except the last prediction interval.

[0027] Determine whether the actual charge step size of the last predicted interval of the target battery is equal to the preset state of charge step size;

[0028] If the judgment result is negative, the actual charging step size is compared with the charging rate of the target battery in the last prediction interval to determine the charging time of the target battery in the last prediction interval.

[0029] The sum of the charging times for all predicted intervals is determined as the remaining charging time for the target battery, including:

[0030] The sum of the charging times of the target battery in all prediction intervals except the last prediction interval, and the sum of the charging times of the target battery in the last prediction interval, are determined as the remaining charging time of the target battery.

[0031] According to a second aspect of this disclosure, a charging remaining time prediction device is provided, comprising:

[0032] The acquisition unit is used to acquire the initial temperature, initial state of charge, and initial charging rate of the target battery at the initial moment.

[0033] The prediction unit is used to predict the temperature of the target battery at the end of each prediction interval using the initial temperature, initial charge rate, and the sum of the initial state of charge and a preset state of charge step size as inputs, and employing a temperature rise prediction network; the preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals.

[0034] A prediction interval charging rate determination unit is used to determine the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0035] A prediction interval charging time determination unit is used to compare the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval.

[0036] A charging remaining time determination unit is used to determine the sum of the charging times of all the predicted intervals as the remaining charging time of the target battery.

[0037] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0038] At least one processor; and

[0039] A memory that is communicatively connected to at least one processor; wherein,

[0040] The memory stores instructions that can be executed by at least one processor, such that the at least one processor is able to perform the method described in the first aspect above.

[0041] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method of the first aspect described above.

[0042] This disclosure provides a method, apparatus, electronic device, and storage medium for predicting remaining charging time. The method includes: acquiring the initial temperature, initial state of charge (SOC), and initial charging rate of a target battery at an initial moment; using the initial temperature, initial charging rate, and the sum of the initial SOC and a preset SOC step size as input, predicting the temperature of the target battery at the end of each prediction interval using a temperature rise prediction network; the preset SOC step size indicating the change in SOC between adjacent prediction intervals; determining the charging rate of the target battery in each prediction interval from the mapping relationship between the target battery's temperature and SOC and charging rate; comparing the preset SOC step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval; and determining the sum of the charging times of all prediction intervals as the remaining charging time of the target battery.

[0043] According to the scheme disclosed herein, after predicting the temperature of the target battery at the end of each prediction interval through a temperature rise prediction network, the charging rate of the target battery in each prediction interval is determined from the mapping relationship between the temperature of the target battery and the state of charge and the charging rate. The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval. Finally, the sum of the charging times of all prediction intervals is determined as the remaining charging time of the target battery, which can more accurately predict the remaining charging time of the target battery.

[0044] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0045] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0046] Figure 1 A flowchart illustrating the remaining charging time prediction method provided in this embodiment of the present disclosure;

[0047] Figure 2 A flowchart illustrating the remaining charging time prediction method provided as an application example of this disclosure;

[0048] Figure 3 This is a schematic diagram of the structure of the charging remaining time prediction device provided in the embodiments of this disclosure;

[0049] Figure 4 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0050] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0051] The present disclosure provides a method for predicting remaining charging time, which can be applied to electric vehicles or other battery-powered terminals. The executing entity of the method can be the vehicle's Battery Management System (BMS).

[0052] like Figure 1 As shown, the charging remaining time prediction method provided in this embodiment includes the following steps:

[0053] Step 101: Obtain the initial temperature, initial state of charge, and initial charging rate of the target battery at the initial moment;

[0054] In one embodiment, the initial temperature refers to the battery temperature at the start of charging.

[0055] In one embodiment, the initial state of charge refers to the state of charge at the start of charging.

[0056] In one embodiment, the initial temperature of the target battery at the initial moment can be obtained by a temperature sensor.

[0057] In one embodiment, the initial state of charge of the target battery at the initial moment can be obtained by a state of charge (SOC) sensor.

[0058] In one embodiment, the initial temperature and initial state of charge of the target battery at the initial moment can be obtained from the BMS.

[0059] In one embodiment, step 101 includes:

[0060] Obtain the initial temperature and initial state of charge of the target battery at the initial moment;

[0061] The initial charging rate of the target battery at the initial moment is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0062] In one embodiment, the battery charging rate is used to measure the charging speed of the battery; the higher the charging rate, the faster the battery charges.

[0063] In one embodiment, the mapping relationship between the temperature and state of charge of the target battery and the charging rate can be obtained by the cell manufacturer based on cell characteristic test data.

[0064] In one embodiment, the mapping relationship between the temperature and state of charge of the target battery and the charging rate can be represented in the form of a graph, such as a three-dimensional graph or a two-dimensional table.

[0065] In one embodiment, the mapping relationship between the temperature and state of charge of the target battery and the charging rate can also be expressed in the form of a functional expression.

[0066] In one embodiment, target batteries of the same model have the same mapping relationship between temperature, state of charge, and charging rate.

[0067] Step 102: Using the initial temperature, initial charging rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, the temperature of the target battery at the end of each prediction interval is predicted using a temperature rise prediction network.

[0068] In one embodiment, the preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals.

[0069] In one embodiment, the sum of the initial state of charge of the current prediction interval and the preset state of charge step size is used to represent the state of charge of the current prediction interval.

[0070] In one embodiment, the temperature rise prediction network refers to a trained temperature rise prediction network.

[0071] In one embodiment, a temperature rise prediction network is used to predict the temperature rise value of the target battery at the end of each prediction interval.

[0072] In one embodiment, the initial temperature, the sum of the initial state of charge and the preset state of charge step size, and the initial charging rate are used as feature inputs to the temperature rise prediction network. The temperature rise of the target battery after increasing the initial state of charge by the preset state of charge step size is used as the label input to the temperature rise prediction network. The temperature rise prediction network is used to predict the temperature rise value of the target battery at the end of each prediction interval.

[0073] In one embodiment, increasing the number of input samples can improve the accuracy of the temperature rise prediction network to some extent. For example, 30,000 historical data samples of the target battery can be selected as feature inputs of the temperature rise prediction network. This disclosure does not limit this.

[0074] In one embodiment, the initial temperature of the current prediction interval is the temperature at the end of the previous prediction interval.

[0075] In one embodiment, the sum of the initial temperature of each prediction interval and the temperature rise at the end of each prediction interval is determined as the temperature at the end of each prediction interval.

[0076] In one embodiment, step 102 includes:

[0077] The difference between the rated capacity of the target battery and the initial state of charge is compared with a preset state of charge step size to determine the number of prediction intervals.

[0078] In one embodiment, the rated capacity of the target battery refers to the total amount of electrical energy that the target battery can store or release under specific conditions, typically 100% of the rated capacity of the target battery.

[0079] In one embodiment, the preset state of charge step size is a certain percentage of the rated capacity of the target battery, such as a preset state of charge step size of 5% of the rated capacity. This is not limited in this disclosure.

[0080] In one embodiment, since the battery has a large specific heat capacity, if the data is divided too densely, the temperature change of the target battery will not be obvious. Therefore, the preset state of charge step size cannot be too small.

[0081] In one embodiment, the number of prediction intervals is the ratio of the difference between the rated capacity and the initial state of charge of the target battery to a preset state of charge step size. For example, the number of prediction intervals can be N, where N is a positive integer.

[0082] Using the initial temperature, initial charge rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval.

[0083] Step 103: Determine the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0084] In one embodiment, the target battery may have the same or different charging rates in each prediction interval.

[0085] In one embodiment, the charging rate of the target battery is related to the temperature and state of charge of the target battery. By determining the charging rate for each prediction interval, it is helpful to assess the safety of the target battery in each prediction interval.

[0086] Step 104: Compare the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval.

[0087] In one embodiment, if the target battery has a different charging rate in each prediction interval, the charging time required for the target battery in each prediction interval will also be different.

[0088] Step 105: Determine the sum of the charging times for all predicted intervals as the remaining charging time for the target battery.

[0089] In one embodiment, the remaining charging time of the target battery can be obtained with high accuracy by determining the sum of the charging times of all predicted intervals as the remaining charging time of the target battery.

[0090] This disclosure provides a method, apparatus, electronic device, and storage medium for predicting remaining charging time. The method includes: acquiring the initial temperature, initial state of charge (SOC), and initial charging rate of a target battery at an initial moment; using the initial temperature, initial charging rate, and the sum of the initial SOC and a preset SOC step size as input, predicting the temperature of the target battery at the end of each prediction interval using a temperature rise prediction network; the preset SOC step size indicating the change in SOC between adjacent prediction intervals; determining the charging rate of the target battery in each prediction interval from the mapping relationship between the target battery's temperature and SOC and charging rate; comparing the preset SOC step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval; and determining the sum of the charging times of all prediction intervals as the remaining charging time of the target battery.

[0091] According to the scheme disclosed herein, after predicting the temperature of the target battery at the end of each prediction interval through a temperature rise prediction network, the charging rate of the target battery in each prediction interval is determined from the mapping relationship between the temperature of the target battery and the state of charge and the charging rate. The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval. Finally, the sum of the charging times of all prediction intervals is determined as the remaining charging time of the target battery, which can more accurately predict the remaining charging time of the target battery.

[0092] In one embodiment, the temperature rise prediction network employs the XGBOOST (Extreme Gradient Boosting) model.

[0093] In one embodiment, the temperature rise prediction network may also employ a neural network model.

[0094] In one embodiment, the temperature rise prediction network may also employ a support vector machine model.

[0095] Correspondingly,

[0096] The temperature of the target battery at the end of each prediction interval is predicted using a temperature rise prediction network, including:

[0097] The temperature of the target battery at the end of each prediction interval is predicted using a first temperature rise prediction network, which refers to a pre-trained second temperature rise prediction network.

[0098] In one embodiment, the second temperature rise prediction network refers to the temperature rise prediction network before training.

[0099] In one embodiment, the temperature of the target battery at the end of each prediction interval is predicted using a trained second temperature rise prediction network, which can reduce the error in the predicted temperature at the end of each prediction interval.

[0100] In one embodiment, before predicting the temperature of the target battery at the end of each prediction interval using a first temperature rise prediction network, the remaining charging time prediction method further includes:

[0101] Obtain at least one training sample of at least one training battery of the same model as the target battery. The training sample includes at least the sum of the initial state of charge and the preset state of charge step size of the training battery, the initial temperature of the training battery, the charging rate during the process of increasing the initial state of charge of the training battery by the preset state of charge step size, and the training label is the temperature rise of the training battery after increasing the initial state of charge of the training battery by the preset state of charge step size.

[0102] In one embodiment, at least one training sample can be obtained from historical data of a training battery of the same model as the target battery.

[0103] In one embodiment, at least one training sample of a training battery of the same model as the target battery should cover charging data samples of the training battery throughout the four seasons.

[0104] In one embodiment, at least one training sample may come from multiple batteries of the same model as the target battery, such as 100 batteries of the same model as the target battery.

[0105] The second temperature rise prediction network is trained using at least one training sample to obtain the first temperature rise prediction network.

[0106] In one embodiment, the prediction accuracy of the first temperature rise prediction network is related to the number of training samples.

[0107] In one embodiment, the temperature of the target battery at the end of each prediction interval is predicted using a temperature rise prediction network, including:

[0108] Using the sum of the initial temperature, initial state of charge and preset state of charge step size, and initial charge rate as input, a temperature rise prediction network is used to predict the temperature rise of the target battery at the end of the first prediction interval.

[0109] In one embodiment, the initial temperature of each prediction interval is different. For example, the initial temperature of the first prediction interval is the battery temperature at the start of charging, the initial temperature of the second prediction interval is the temperature at the end of the first prediction interval, and the initial temperature of the last prediction interval is the temperature at the end of the penultimate prediction interval.

[0110] In one embodiment, the initial charging rate is different for each prediction interval, and the initial charging rate for each prediction interval can be determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0111] In one embodiment, the state of charge of each prediction interval is different. For example, the state of charge of the first prediction interval is the sum of the initial state of charge and the preset state of charge step size, and the state of charge of the second prediction interval is the sum of the state of charge of the first prediction interval and the preset state of charge step size. The state of charge of two adjacent prediction intervals differs by the preset state of charge step size.

[0112] In one embodiment, the temperature rise of the target battery at the end of the first prediction interval refers to the temperature rise of the target battery as it increases by a preset state of charge step.

[0113] The sum of the temperature rise of the target battery at the end of the first prediction interval and the initial temperature is determined to be the temperature of the target battery at the end of the first prediction interval.

[0114] In one embodiment, the temperature of the target battery at the end of the first prediction interval refers to the temperature of the target battery after it has increased by a preset state of charge step.

[0115] The initial temperature is updated using the temperature of the target battery at the end of the first prediction interval. The sum of the initial state of charge and the preset state of charge step size is updated using the state of charge of the target battery at the end of the corresponding prediction interval. The initial charging rate is updated using the charging rate of the target battery in the corresponding prediction interval. Each prediction interval of the target battery is traversed to obtain the temperature of the target battery at the end of each prediction interval.

[0116] In one embodiment, a temperature rise prediction network is used to predict the temperature rise of the target battery at the end of each prediction interval, and the sum of the temperature rise of the target battery at the end of each prediction interval and the initial temperature of the target battery in each prediction interval is determined to be the temperature of the target battery at the end of each prediction interval.

[0117] In one embodiment, updating the sum of the initial state of charge and the preset state of charge step size using the state of charge of the target battery at the end of the corresponding prediction interval includes:

[0118] The sum of the initial state of charge and the first integer multiple of the preset state of charge step size is determined to be the sum of the updated initial state of charge and the preset state of charge step size.

[0119] In one embodiment, the first integer multiple refers to an integer multiple that is the same as the index of the prediction interval.

[0120] In one embodiment, the sum of the initial state of charge and the preset state of charge step size in the first prediction interval refers to the sum of one times the initial state of charge and the preset state of charge step size; the sum of the initial state of charge and the preset state of charge step size in the second prediction interval refers to the sum of twice the initial state of charge and the preset state of charge step size; and the sum of the initial state of charge and the preset state of charge step size in the Nth prediction interval refers to the sum of N times the initial state of charge and the preset state of charge step size.

[0121] In one embodiment, determining the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate includes:

[0122] Obtain the charging rate MAP table;

[0123] In one embodiment, a charge rate MAP table is used to indicate the mapping relationship between the temperature and state of charge of the target battery and the charge rate.

[0124] In one embodiment, the charge rate MAP table is typically a two-dimensional table, where rows and columns represent temperature and state of charge, respectively, and the value at the intersection of a row and a column represents the charge rate corresponding to the current temperature and the current state of charge.

[0125] In one embodiment, the charge rate MAP meter can be provided by the cell manufacturer.

[0126] The temperature and state of charge of the target battery at the end of each prediction interval are compared with the charge rate MAP table, and the charge rate of the target battery in each prediction interval is determined from the charge rate MAP table.

[0127] In one embodiment, step 104 includes:

[0128] The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in other prediction intervals except the last prediction interval.

[0129] In one embodiment, the other prediction intervals besides the last prediction interval refer to the first N-1 prediction intervals among the aforementioned N prediction intervals.

[0130] In one embodiment, the charging time for the first N-1 prediction intervals can be obtained by comparing the preset state of charge step size with the charging rate of the target battery in the corresponding prediction interval.

[0131] Determine whether the actual charge step size of the last predicted interval of the target battery is equal to the preset state of charge step size;

[0132] In one embodiment, the last prediction interval refers to the Nth prediction interval among the aforementioned N prediction intervals.

[0133] In one embodiment, if the actual charge step size of the Nth prediction interval of the target battery is equal to the preset state of charge step size, the preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the Nth prediction interval of the target battery.

[0134] If the judgment result is negative, the actual charging step size is compared with the charging rate of the target battery in the last prediction interval to determine the charging time of the target battery excluding the last prediction interval.

[0135] Correspondingly,

[0136] In one embodiment, determining the sum of the charging times for all predicted intervals as the remaining charging time of the target battery includes:

[0137] The sum of the charging times of the target battery in all prediction intervals except the last prediction interval, and the sum of the charging times of the target battery in the last prediction interval, are determined as the remaining charging time of the target battery.

[0138] In one embodiment, the accuracy of the remaining charging time prediction for the target battery can be improved by determining the sum of the charging times for all predicted intervals of the target battery.

[0139] According to the scheme disclosed herein:

[0140] First, by acquiring the initial temperature and initial state of charge (SBC) of the target battery at the initial moment, the initial charging rate of the target battery at the initial moment is determined from the mapping relationship between the target battery's temperature and SBC and the charging rate. This allows for the acquisition of the initial charging rate of the target battery at different initial moments. By comparing the difference between the target battery's rated capacity and the initial SBC with a preset SBC step size, the ratio is determined as the number of prediction intervals. Using the initial temperature, the sum of the initial SBC and the preset SBC step size, and the initial charging rate as inputs, a temperature rise prediction network predicts the temperature of the target battery at the end of each prediction interval. Based on the temperature at the end of each prediction interval, the charging rate for each prediction interval is determined. By determining the charging rate of the target battery in each prediction interval from the mapping relationship between the target battery's temperature and SBC and the charging rate, and comparing the preset SBC step size with the charging rate of the target battery in the prediction interval, the charging time of the target battery in each prediction interval is determined. Finally, the sum of the charging times of all prediction intervals is determined as the remaining charging time of the target battery, enabling a more accurate prediction of the remaining charging time of the target battery.

[0141] Secondly, by acquiring at least one training sample from at least one training battery of the same model as the target battery, and using at least one training sample to train the second temperature rise prediction network to obtain the first temperature rise prediction network, the accuracy of the temperature rise prediction network in predicting the remaining charging time of the target battery can be improved.

[0142] The following specific application examples further illustrate the remaining charging time prediction method provided in this disclosure.

[0143] Figure 2 A flowchart illustrating a method for predicting remaining charging time, provided as an application example of this disclosure, is shown below. Figure 2 As shown in the example, the method for predicting remaining charging time provided in this disclosure includes the following steps:

[0144] Step 201: Obtain the initial temperature and initial state of charge of the target battery at the initial moment;

[0145] Step 202: Obtain the charging rate MAP table. The charging rate MAP table is used to indicate the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0146] Step 203: Determine the initial charging rate of the target battery at the initial moment from the charging rate MAP table;

[0147] Step 204: Compare the difference between the rated capacity of the target battery and the initial state of charge with the preset state of charge step size, and determine the number of prediction intervals by the ratio.

[0148] Step 205: Obtain at least one training sample of at least one training battery of the same model as the target battery. The training sample includes at least the sum of the initial state of charge of the training battery and the preset state of charge step, the initial temperature of the training battery, the charging rate during the process of increasing the initial state of charge of the training battery by the preset state of charge step, and the training label is the temperature rise of the training battery after increasing the initial state of charge of the training battery by the preset state of charge step.

[0149] Step 206: Train the second temperature rise prediction network using at least one training sample to obtain the first temperature rise prediction network.

[0150] Step 207: Using the initial temperature, the sum of the initial state of charge and the preset state of charge step size, and the initial charge rate as inputs, the temperature rise prediction network is used to predict the temperature rise of the target battery at the end of the first prediction interval.

[0151] In one embodiment, the temperature rise prediction network employs the XGBOOST model.

[0152] Step 208: Determine the sum of the temperature rise of the target battery at the end of the first prediction interval and the initial temperature as the temperature of the target battery at the end of the first prediction interval.

[0153] Step 209: Update the initial temperature using the temperature of the target battery at the end of the first prediction interval, determine the sum of the initial state of charge and the first integer multiple of the preset state of charge step size as the sum of the updated initial state of charge and the preset state of charge step size, update the initial charging rate using the charging rate of the target battery in the corresponding prediction interval, traverse each prediction interval of the target battery, and obtain the temperature of the target battery at the end of each prediction interval.

[0154] In one embodiment, the first integer multiple refers to an integer multiple that is the same as the index of the prediction interval.

[0155] Step 210: Compare the temperature and state of charge of the target battery at the end of each prediction interval with the charge rate MAP table, and determine the charge rate of the target battery in each prediction interval from the charge rate MAP table.

[0156] Step 211: Compare the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in other prediction intervals except the last prediction interval.

[0157] Step 212: Determine whether the actual charge step size of the last predicted interval of the target battery is equal to the preset charge state step size;

[0158] If the judgment result is yes, proceed to step 213;

[0159] If the result is negative, proceed to step 214;

[0160] Step 213: Compare the preset state of charge step size with the charging rate corresponding to the target battery in the last prediction interval to determine the charging time of the target battery in the last prediction interval.

[0161] Step 214: Compare the actual charge step size with the charging rate of the target battery in the last prediction interval to determine the charging time of the target battery in the last prediction interval.

[0162] Step 215: Determine the remaining charging time of the target battery as the sum of the charging times of the target battery in the last prediction interval and the sum of the charging times of the target battery in the last prediction interval.

[0163] Corresponding to the above-described method for predicting remaining charging time, this invention also proposes a device for predicting remaining charging time. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments, and will not be repeated here.

[0164] Figure 3This is a schematic diagram of the structure of a charging remaining time prediction device provided in an embodiment of this disclosure, as shown below. Figure 3 As shown, the charging remaining time prediction device 300 includes:

[0165] The acquisition unit 301 is used to acquire the initial temperature, initial state of charge, and initial charging rate of the target battery at the initial moment.

[0166] The prediction unit 302 is used to predict the temperature of the target battery at the end of each prediction interval using the initial temperature, initial charging rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, and the temperature rise prediction network. The preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals.

[0167] The prediction interval charging rate determination unit 303 is used to determine the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0168] The prediction interval charging time determination unit 304 is used to compare the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval.

[0169] The remaining charging time determination unit 305 is used to determine the sum of the charging times of all the predicted intervals as the remaining charging time of the target battery.

[0170] In one embodiment, the acquisition unit 301 is specifically used for:

[0171] Obtain the initial temperature and initial state of charge of the target battery at the initial moment;

[0172] The initial charging rate of the target battery at the initial moment is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

[0173] In one embodiment, the prediction unit 302 is specifically used for:

[0174] The difference between the rated capacity of the target battery and the initial state of charge is compared with a preset state of charge step size to determine the number of prediction intervals.

[0175] Using the initial temperature, initial charge rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval.

[0176] In one embodiment, the temperature rise prediction network employs the XGBOOST model;

[0177] Correspondingly,

[0178] In one embodiment, the prediction unit 302 is specifically used for:

[0179] The temperature of the target battery at the end of each prediction interval is predicted using a first temperature rise prediction network, which refers to a pre-trained second temperature rise prediction network.

[0180] In one embodiment, the remaining charging time prediction device 300 further includes a training unit, which is used for:

[0181] Obtain at least one training sample of at least one training battery of the same model as the target battery. The training sample includes at least the sum of the initial state of charge and the preset state of charge step size of the training battery, the initial temperature of the training battery, the charging rate during the process of increasing the initial state of charge of the training battery by the preset state of charge step size, and the training label is the temperature rise of the training battery after increasing the initial state of charge of the training battery by the preset state of charge step size.

[0182] The second temperature rise prediction network is trained using at least one training sample to obtain the first temperature rise prediction network.

[0183] In one embodiment, the prediction unit 302 is specifically used for:

[0184] Using the sum of the initial temperature, initial state of charge and preset state of charge step size, and initial charge rate as input, a temperature rise prediction network is used to predict the temperature rise of the target battery at the end of the first prediction interval.

[0185] The sum of the temperature rise of the target battery at the end of the first prediction interval and the initial temperature is determined to be the temperature of the target battery at the end of the first prediction interval.

[0186] The initial temperature is updated using the temperature of the target battery at the end of the first prediction interval. The sum of the initial state of charge and the preset state of charge step size is updated using the state of charge of the target battery at the end of the corresponding prediction interval. The initial charging rate is updated using the charging rate of the target battery in the corresponding prediction interval. Each prediction interval of the target battery is traversed to obtain the temperature of the target battery at the end of each prediction interval.

[0187] In one embodiment, the prediction unit 302 is specifically used for:

[0188] The sum of the initial state of charge and the first integer multiple of the preset state of charge step size is determined to be the sum of the updated initial state of charge and the preset state of charge step size; the first integer multiple refers to an integer multiple that is the same as the index of the prediction interval.

[0189] In one embodiment, the predicted interval charging rate determination unit 305 is specifically used for:

[0190] Obtain the charging rate MAP table, which is used to indicate the mapping relationship between the target battery's temperature and state of charge and the charging rate.

[0191] The temperature and state of charge of the target battery at the end of each prediction interval are compared with the charge rate MAP table, and the charge rate of the target battery in each prediction interval is determined from the charge rate MAP table.

[0192] In one embodiment, the predicted interval charging time determination unit 304 is specifically used for:

[0193] The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in other prediction intervals except the last prediction interval.

[0194] Determine whether the actual charge step size of the last predicted interval of the target battery is equal to the preset state of charge step size;

[0195] If the judgment result is negative, the actual charging step size is compared with the charging rate of the target battery in the last prediction interval to determine the charging time of the target battery in the last prediction interval.

[0196] Correspondingly,

[0197] In one embodiment, the remaining charging time determination unit 305 is specifically used for:

[0198] The sum of the charging times of the target battery in all prediction intervals except the last prediction interval, and the sum of the charging times of the target battery in the last prediction interval, are determined as the remaining charging time of the target battery.

[0199] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0200] According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium storing computer instructions.

[0201] Specifically, this disclosure provides an electronic device, including:

[0202] At least one processor; and

[0203] A memory that is communicatively connected to at least one processor; wherein,

[0204] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the steps of the aforementioned charging remaining time prediction method.

[0205] This disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the steps of the aforementioned charging remaining time prediction method.

[0206] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, in-vehicle devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0207] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. The RAM 403 may also store various programs and data required for the operation of the device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0208] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0209] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the charging remaining time prediction method. For example, in some embodiments, the charging remaining time prediction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned charging remaining time prediction method by any other suitable means (e.g., by means of firmware).

[0210] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0211] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0212] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0213] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0214] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for predicting remaining charging time, characterized in that, include: Obtain the initial temperature, initial state of charge, and initial charge rate of the target battery at the initial moment; Using the initial temperature, initial charging rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval; the preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals. The charging rate of the target battery in each prediction interval is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate. The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval. The sum of the charging times for all predicted intervals is determined as the remaining charging time for the target battery.

2. The method according to claim 1, characterized in that, The acquisition of the initial temperature, initial state of charge, and initial charge rate of the target battery at the initial moment includes: Obtain the initial temperature and initial state of charge of the target battery at the initial moment; The initial charging rate of the target battery at the initial moment is determined from the mapping relationship between the temperature and state of charge of the target battery and the charging rate.

3. The method according to claim 1, characterized in that, The step of using the initial temperature, initial charge rate, and the sum of the initial state of charge and a preset state of charge step size as inputs, and employing a temperature rise prediction network to predict the temperature of the target battery at the end of each prediction interval, includes: The difference between the rated capacity of the target battery and the initial state of charge is compared with a preset state of charge step size to determine the number of prediction intervals. Using the initial temperature, initial charge rate, and the sum of the initial state of charge and the preset state of charge step size as inputs, a temperature rise prediction network is used to predict the temperature of the target battery at the end of each prediction interval.

4. The method according to claim 1, characterized in that, The method of using a temperature rise prediction network to predict the temperature of the target battery at the end of each prediction interval includes: Using the sum of the initial temperature, initial state of charge, and preset state of charge step size, and the initial charge rate as input, a temperature rise prediction network is used to predict the temperature rise of the target battery at the end of the first prediction interval. The sum of the temperature rise of the target battery at the end of the first prediction interval and the initial temperature is determined to be the temperature of the target battery at the end of the first prediction interval; The initial temperature is updated using the temperature of the target battery at the end of the first prediction interval. The sum of the initial state of charge and the preset state of charge step size is updated using the state of charge of the target battery at the end of the corresponding prediction interval. The initial charging rate is updated using the charging rate of the target battery in the corresponding prediction interval. Each prediction interval of the target battery is traversed to obtain the temperature of the target battery at the end of each prediction interval.

5. The method according to claim 4, characterized in that, The step of updating the sum of the initial state of charge and the preset state of charge step size using the state of charge of the target battery at the end of the corresponding prediction interval includes: The sum of the initial state of charge and a first integer multiple of the preset state of charge step size is determined to be the updated sum of the initial state of charge and the preset state of charge step size; the first integer multiple refers to an integer multiple that is the same as the index of the prediction interval.

6. The method according to claim 1, characterized in that, Determining the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate includes: Obtain a charging rate MAP table, which is used to indicate the mapping relationship between the temperature and state of charge of the target battery and the charging rate; The temperature and state of charge of the target battery at the end of each prediction interval are compared with the charge rate MAP table, and the charge rate of the target battery in each prediction interval is determined from the charge rate MAP table.

7. The method according to claim 1, characterized in that, The step of comparing the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval includes: The preset state of charge step size is compared with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in other prediction intervals except the last prediction interval. Determine whether the actual charge step size of the last predicted interval of the target battery is equal to the preset charge state step size; If the judgment result is negative, the actual charging step size is compared with the charging rate of the target battery in the last prediction interval to determine the charging time of the target battery in the last prediction interval. Determining the sum of the charging times for all predicted intervals as the remaining charging time of the target battery includes: The sum of the charging times of the target battery in all prediction intervals except the last prediction interval and the sum of the charging times of the target battery in the last prediction interval are determined as the remaining charging time of the target battery.

8. A device for predicting remaining charging time, characterized in that, include: The acquisition unit is used to acquire the initial temperature, initial state of charge, and initial charging rate of the target battery at the initial moment. The prediction unit is used to predict the temperature of the target battery at the end of each prediction interval using the initial temperature, initial charge rate, and the sum of the initial state of charge and a preset state of charge step size as inputs, and employing a temperature rise prediction network; the preset state of charge step size is used to indicate the amount of change in state of charge between adjacent prediction intervals. A prediction interval charging rate determination unit is used to determine the charging rate of the target battery in each prediction interval from the mapping relationship between the temperature and state of charge of the target battery and the charging rate. A prediction interval charging time determination unit is used to compare the preset state of charge step size with the charging rate of the target battery in the prediction interval to determine the charging time of the target battery in each prediction interval. A charging remaining time determination unit is used to determine the sum of the charging times of all the predicted intervals as the remaining charging time of the target battery.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

Images