Battery residual charging time compensation method and system and electronic equipment

Abstract

The invention discloses a battery residual charging time compensation method and system and electronic equipment, and belongs to the technical field of secondary batteries. According to the battery residual charging time compensation method provided by the embodiment of the invention, the current parameters of the battery are firstly determined for compensation value prediction; the method comprises the following steps: acquiring an activation function of a forgetting gate in a long-short-term memory network model, acquiring a gradient adjustment coefficient for adjusting the gradient of the activation function, and adjusting the gradient of the activation function through the gradient adjustment coefficient to obtain an improved long-short-term memory network model, thereby solving the problem that the gradient of the long-short-term memory network model disappears. The long-term memory ability of the long-short-term memory network model is improved; the current parameters of the battery are substituted into the improved long short-term memory network model, the compensation value of the residual charging time is obtained through the improved long short-term memory network model, the prediction value of the residual charging time is corrected through the compensation value, and the prediction accuracy of the residual charging time is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of secondary batteries, and specifically relates to a method, system and electronic device for compensating remaining charging time of a battery. Background Art

[0002] Power batteries are batteries used to provide electricity to drive electric vehicles, hybrid vehicles and other electric vehicles. In actual use, the charging efficiency of power batteries will change due to the influence of various external environments such as temperature, humidity, altitude, etc., which will cause deviations in the prediction of the remaining charging time. Summary of the invention

[0003] Purpose of the invention: This application develops a battery remaining charging time compensation method, system and electronic device, aiming to solve the technical problem of the prediction deviation of the remaining charging time of secondary batteries in the prior art.

[0004] Technical solution: In a first aspect, an embodiment of the present application provides a method for compensating a battery's remaining charging time, comprising:

[0005] Determine the current parameters of the battery;

[0006] Obtaining an improved long short-term memory network model, wherein the improved long short-term memory network model is obtained by replacing a first activation function in the long short-term memory network model with a second activation function, wherein the long short-term memory network model includes a forget gate, and the first activation function is an activation function of the forget gate;

[0007] The current parameters of the battery are input into the improved long short-term memory network model to obtain a compensation value of the remaining charging time.

[0008] In some embodiments, the step of obtaining an improved long short-term memory network model comprises:

[0009] Obtaining the first activation function of the long short-term memory network model;

[0010] Determine the gradient adjustment factor;

[0011] Adjust the first activation function based on the gradient adjustment coefficient to obtain the second activation function;

[0012] The second activation function is used to replace the first activation function in the long short-term memory network model to obtain the improved long short-term memory network model.

[0013] In some embodiments, the characterization formula of the second activation function includes:

[0014]

[0015] Among them, Zigmoid is the second activation function; Sigmmoid is the first activation function; x is the input feature vector; β is the gradient adjustment coefficient.

[0016] In some embodiments, before the step of inputting the current battery parameters into the improved long short-term memory network model, the battery remaining charging time compensation method further includes:

[0017] Abnormal data in the current parameters of the battery are removed, and the current parameters of the battery are normalized.

[0018] In some embodiments, the step of removing abnormal data in the current parameters of the battery includes:

[0019] Determine the 99% quantile of the current parameter of the battery as an upper bound;

[0020] Determine the 1% quantile of the current parameter of the battery as a lower bound;

[0021] The current battery parameters above the upper limit and the current battery parameters below the lower limit are determined as the abnormal data, and the abnormal data are removed.

[0022] In some embodiments, the characterization formula for normalizing the current parameters of the battery includes:

[0023]

[0024] Among them, x norm is the current parameter of the battery after normalization; x is the current parameter of the battery before normalization; x min is the minimum value of the current battery parameter; x max is the maximum value of the current parameter of the battery.

[0025] In some embodiments, the step of determining the current parameters of the battery includes:

[0026] Determining the parameters to be determined, and determining the weights of the parameters to be determined;

[0027] Determine the weight range;

[0028] In response to the weight of the undetermined parameter being within a weight range, the undetermined parameter is determined to be the current parameter of the battery.

[0029] In some embodiments, the current parameters of the battery include rated capacity, rated voltage, maximum allowable charging current, initial maximum single cell voltage, initial minimum single cell voltage, initial charging state, maximum temperature, minimum temperature, charging station altitude, compensation time for a single completed charge, and the deviation between the calculated time and the actual time for a single completed charge.

[0030] In a second aspect, an embodiment of the present application further provides a battery remaining charging time compensation system, comprising:

[0031] A parameter determination module, the parameter determination module is used to determine the current parameters of the battery;

[0032] A model acquisition module, the model acquisition module is used to acquire an improved long short-term memory network model, the improved long short-term memory network model is obtained by replacing the first activation function in the long short-term memory network model with a second activation function, the long short-term memory network model includes a forget gate, and the first activation function is the activation function of the forget gate;

[0033] A compensation calculation module is used to input the current parameters of the battery into the improved long short-term memory network model to obtain a compensation value of the remaining charging time.

[0034] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0035] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery remaining charging time compensation method as described in any one of the first aspects by executing the computer instructions.

[0036] Beneficial effect: Compared with the prior art, a battery remaining charging time compensation method provided in an embodiment of the present application is applied in the field of secondary batteries and is used to compensate for the predicted difference of the remaining charging time when the secondary battery is charged. The battery remaining charging time compensation method provided in an embodiment of the present application first determines the current parameters of the battery for prediction of the compensation value; obtains the activation function of the forget gate in the long short-term memory network model, updates the activation function of the forget gate, obtains the improved long short-term memory network model, and improves the long-term memory capacity of the long short-term memory network model; brings the current parameters of the battery into the improved long short-term memory network model, and obtains the compensation value of the remaining charging time through the improved long short-term memory network model, so as to correct the predicted value of the remaining charging time through the compensation value, and improve the accuracy of the remaining charging time prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1A flowchart of the steps of the method for compensating the remaining charging time of a battery provided in an embodiment of the present application;

[0039] Figure 2 A specific flow chart for obtaining an improved long short-term memory network model provided in an embodiment of the present application;

[0040] Figure 3 A specific flow chart of removing abnormal data in the current parameters of the battery in the method for compensating the remaining charging time of the battery provided in the embodiment of the present application;

[0041] Figure 4 A flowchart of the steps of determining the current parameters of the battery in the method for compensating the remaining charging time of the battery provided in an embodiment of the present application;

[0042] Figure 5 A simplified diagram of the module connections of the battery remaining charging time compensation system provided in an embodiment of the present application;

[0043] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0044] Figure 7 A network structure diagram of an improved long short-term memory network model in a battery remaining charging time compensation method provided in an embodiment of the present application;

[0045] Figure 8 A flowchart of an optimized and improved long short-term memory network model in a battery remaining charging time compensation method provided in an embodiment of the present application.

[0046] Reference numerals: 10, parameter determination module; 20, model acquisition module; 30, compensation calculation module; 100, memory; 200, processor. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0048] Since the charging efficiency of power batteries is limited by factors such as temperature, battery parameters, and charging pile output capacity, how to accurately estimate the remaining charging time has become one of the difficulties in the current battery management system design. In addition to avoiding unsafe behaviors such as overcharging of lithium batteries, relatively accurate remaining charging time can also bring users a better user experience, allowing them to reasonably plan their overall itinerary.

[0049] The defects of the current remaining charging time compensation algorithm are as follows:

[0050] 1. Model accuracy limitation: The existing temperature compensation model cannot fully and accurately reflect the actual behavior of all types of batteries under various extreme temperatures, resulting in large estimation deviations.

[0051] 2. Insufficient dynamics: The ambient temperature and the internal temperature of the battery may change rapidly. The frequency and response speed of the current algorithm to update the compensation coefficient are not fast enough, which in turn affects the accuracy of the estimation.

[0052] 3. Lack of personalized compensation: Batteries of the same model have performance differences in different usage cycles and different manufacturing batches. The general compensation strategy cannot adapt well to the optimal charging state of each individual battery.

[0053] 4. The balance between safety and efficiency: Although an overly aggressive temperature compensation strategy can improve charging efficiency, it will reduce safety. An overly conservative temperature compensation strategy can ensure safety but reduce charging efficiency.

[0054] 5. Influence of complex environment: In actual use, in addition to temperature and humidity, factors such as altitude will also affect the charging efficiency. The existing temperature compensation algorithm does not take into account its impact on charging efficiency.

[0055] In view of this, a battery remaining charging time compensation method provided in an embodiment of the present application is applied in the field of secondary batteries and is used to compensate for the predicted difference of the remaining charging time when the secondary battery is charged. The battery remaining charging time compensation method provided in an embodiment of the present application first determines the current parameters of the battery for prediction of the compensation value; obtains the activation function of the forget gate in the long short-term memory network model, updates the activation function of the forget gate, obtains the improved long short-term memory network model, and improves the long-term memory capacity of the long short-term memory network model; brings the current parameters of the battery into the improved long short-term memory network model, and obtains the compensation value of the remaining charging time through the improved long short-term memory network model, so as to correct the predicted value of the remaining charging time through the compensation value, and improve the accuracy of the remaining charging time prediction.

[0056] In some embodiments, see Figure 1 , Figure 1 This is a flowchart of the method for compensating the remaining battery charging time provided in an embodiment of the present application. The method for compensating the remaining battery charging time provided in an embodiment of the present application is specifically implemented through steps 100 to 300:

[0057] Step 100: Determine current battery parameters.

[0058] In some embodiments, see Figure 4 , Figure 4This is a flowchart of the steps of determining the current parameters of the battery in the method for compensating the remaining charging time of the battery provided in an embodiment of the present application. The method for determining the current parameters of the battery is specifically implemented through steps 110 to 130:

[0059] Step 110: Determine the parameters to be determined, and determine the weights of the parameters to be determined.

[0060] Step 120: Determine the weight range.

[0061] Step 130: In response to the weight of the undetermined parameter being within the weight range, determining that the undetermined parameter is a current parameter of the battery.

[0062] In some embodiments, the current parameters of the battery include rated capacity, rated voltage, maximum allowable charging current, initial maximum single cell voltage, initial minimum single cell voltage, initial charging state, maximum temperature, minimum temperature, charging station altitude, compensation time for a single completed charge, and the deviation between the calculated time for a single completed charge and the actual time.

[0063] It can be understood that when selecting the current parameters of the battery, the parameters that need to be considered can be determined according to the external environment and the battery's own state. At the same time, there is no limit on the number of parameters to be considered, and any number of parameters can be determined according to the external environment and the battery's own state. For example, when in extreme temperature conditions, such as severe cold or heat, the weight of the temperature parameter will increase. At this time, the temperature parameter needs to be considered, and other parameters can be increased or decreased as appropriate according to the calculation efficiency requirements and the result accuracy requirements; for example, when in extreme altitude conditions, when the altitude is extremely high or extremely low, the weight of the altitude parameter will increase. At this time, the altitude parameter needs to be considered, and other parameters can be increased or decreased as appropriate according to the calculation efficiency requirements and the result accuracy requirements. In the embodiment of the present application, in order to improve the calculation accuracy of the compensation value, the rated capacity, rated voltage, maximum allowable charging current, initial maximum single cell voltage, initial minimum single cell voltage, initial charging state, maximum temperature, minimum temperature, charging station altitude, compensation time for a single completed charge, and deviation data between the calculated time and the actual time for a single completed charge are considered.

[0064] Step 200: Obtain an improved long short-term memory network model, where the improved long short-term memory network model is obtained by replacing the first activation function in the long short-term memory network model with the second activation function, where the long short-term memory network model includes a forget gate, and the first activation function is the activation function of the forget gate.

[0065] In some embodiments, see Figure 2 , Figure 2The specific flow chart of obtaining an improved long short-term memory network model provided in the embodiment of the present application, the method of obtaining the improved long short-term memory network model is specifically implemented through steps 210 to 240:

[0066] Step 210: Obtain a first activation function of the long short-term memory network model.

[0067] Step 220: Determine the gradient adjustment coefficient.

[0068] Specifically, the method for determining the gradient adjustment coefficient β may include:

[0069] According to the data length and the memory length of the LSTM network forget gate, the following inequality is obtained:

[0070]

[0071] From the above inequality, we can know that:

[0072]

[0073] From the calculation, we know that the upper bound of β is 2.7 and the lower bound is 1.0, so the final value of β is as follows:

[0074]

[0075] in:

[0076]

[0077] In the above formulas, L is the data length, which is consistent with the memory length of the forget gate of the LSTM network, and g min To maintain the lower bound of the gradient for continuous training.

[0078] Step 230: Adjust the first activation function based on the gradient adjustment coefficient to obtain a second activation function.

[0079] In some embodiments, in the steps of the battery remaining charging time compensation method provided in embodiment s of the present application, determining the characterization formula of the second activation function includes:

[0080]

[0081] Among them, Zigmoid is the second activation function; Sigmmoid is the first activation function; x is the input feature vector; β is the gradient adjustment coefficient.

[0082] Step 240: Use the second activation function to replace the first activation function in the long short-term memory network model to obtain an improved long short-term memory network model.

[0083] In some embodiments, see Figure 7 , Figure 7 This is a network structure diagram of the improved long short-term memory network model in the battery remaining charging time compensation method provided in the embodiment of the present application. In the battery remaining charging time compensation method provided in the embodiment of the present application, the characterization formula of the improved long short-term memory network model is as follows:

[0084] f t =zigmoid(W fx x t +W fh h t-1 +b f );

[0085] o t =sigmoid(W ox x t +W oh h t-1 +b o );

[0086] q′ t =tanh(W cx x t +W ch h t-1 +b c );

[0087] q t =f t ⊙q t-1 +(1-f t )⊙q′ t ;

[0088] h t =o t ⊙tanh(q t );

[0089] Among them, W fx , W fn 、b f , W ox , W oh 、b o , W cx , W ch 、b c is the trainable parameter of Z-LSTM; ⊙ is the element-by-element penalty symbol. t is the output of the forget gate, and its value is compressed in the interval [0, 1]; W fx , W ox , W cx For x t The weight of x t is the current input; h t-1 is the output of the upper hidden unit; Wfh , W oh , W ch h t-1 The weight of f 、b o 、b c is the offset; o t For the previous step h t-1 and x t The value after processing by the activation function, q′ t is h in the previous step t-1 and x t The output value after processing by the tanh function; based on the update calculation process of the forget gate and input gate of the above LSTM model, the updated value q is obtained t ;h t is the final output result.

[0090] In some embodiments, see Figure 8 , Figure 8 The flowchart of optimizing the improved long short-term memory network model in the battery remaining charging time compensation method provided in the embodiment of the present application, after obtaining the improved long short-term memory network model, the theoretical output is obtained based on the historical parameters of the battery, and the historical parameters of the battery are input into the improved long short-term memory network model to obtain the model output, and the loss function is calculated based on the model output and the theoretical output. The improved long short-term memory network model is optimized by Adam adaptive moment estimation based on the calculation result of the loss function to further optimize the hyperparameters of the improved long short-term memory network model to improve the accuracy of the improved long short-term memory network model in predicting the compensation value of the remaining charging time. It can be understood that the improved long short-term memory network model can also be optimized in real time by using the theoretical output and model output of the current parameters of the battery to optimize the improved long short-term memory network model using the current real-time data while predicting to adapt to different real-time environmental requirements.

[0091] In some embodiments, before the step of inputting the current battery parameters into the improved long short-term memory network model, the battery remaining charging time compensation method also includes: removing abnormal data in the calculated data and normalizing the calculated data.

[0092] In some embodiments, see Figure 3 , Figure 3 This is a specific flow chart of removing abnormal data in the current parameters of the battery in the method for compensating the remaining charging time of the battery provided in an embodiment of the present application. The method for removing abnormal data in the current parameters of the battery is specifically implemented through steps a to c:

[0093] Step a: Determine the 99% quantile of the current parameters of the battery as the upper bound.

[0094] Step b: Determine the 1% quantile of the current parameters of the battery as the lower bound.

[0095] Step c: Determine that the current battery parameters above the upper limit and the current battery parameters below the lower limit are abnormal data, and remove the abnormal data.

[0096] In some embodiments, in the method for supplementing the remaining charging time of a battery provided in an embodiment of the present application, the characterization formula for normalizing the current parameters of the battery includes:

[0097]

[0098] Among them, x norm is the current battery parameter after normalization; x is the current battery parameter before normalization; x min is the minimum value of the current battery parameter; x max It is the maximum value of the current battery parameters.

[0099] Step 300: Input the current parameters of the battery into the improved long short-term memory network model to obtain a compensation value of the remaining charging time.

[0100] Understandably, see Figure 8 , Figure 8 The flowchart of the improved long short-term memory network model in the battery remaining charging time compensation method provided in the embodiment of the present application is used to input the current battery parameters into the improved long short-term memory network model to obtain the compensation value of the remaining charging time. At the same time, the theoretical output can be obtained based on the current battery parameters, and then the loss function is calculated based on the theoretical output and the model output to obtain the loss function. The improved long short-term memory network model is subjected to real-time Adam adaptive moment estimation optimization processing based on the loss function to further optimize the hyperparameters of the improved long short-term memory network model, so as to realize the real-time optimization of the improved long short-term memory network model using the current data while predicting, so as to adapt to different real-time environmental requirements.

[0101] It can be understood that, compared with the prior art, the battery remaining charging time compensation method provided by the embodiment of the present application is applied in the field of secondary batteries, and is used to compensate for the predicted difference of the remaining charging time when the secondary battery is charged. The method for confirming the remaining charging time compensation value of the secondary battery provided by the embodiment of the present application first confirms the current parameters of the battery for prediction of the compensation value; obtains the activation function of the forget gate in the long short-term memory network model, and obtains the gradient adjustment coefficient for adjusting the gradient of the activation function, and adjusts the gradient of the activation function by the gradient adjustment coefficient to obtain the improved long short-term memory network model, solves the problem of the gradient disappearance of the long short-term memory network model, and improves the long-term memory capacity of the long short-term memory network model; brings the current parameters of the battery into the improved long short-term memory network model, and obtains the compensation value of the remaining charging time by the improved long short-term memory network model, so as to correct the predicted value of the remaining charging time by the compensation value, and improve the accuracy of the remaining charging time prediction.

[0102] Accordingly, the embodiment of the present application also provides a battery remaining charging time compensation system, please refer to Figure 5 , Figure 5 This is a schematic diagram of the module connection of the battery remaining charging time compensation system provided in an embodiment of the present application. The battery remaining charging time compensation system provided in an embodiment of the present application includes:

[0103] A parameter determination module 10, the parameter determination module 10 is used to determine the current parameters of the battery;

[0104] A model acquisition module 20, the model acquisition module 20 is used to obtain an improved long short-term memory network model, the improved long short-term memory network model is obtained by replacing the first activation function in the long short-term memory network model with the second activation function, the long short-term memory network model includes a forget gate, and the first activation function is the activation function of the forget gate;

[0105] The compensation calculation module 30 is used to input the current parameters of the battery into the improved long short-term memory network model to obtain the compensation value of the remaining charging time.

[0106] In some embodiments, the model acquisition module 20 is specifically used to:

[0107] Get the first activation function of the long short-term memory network model;

[0108] Determine the gradient adjustment factor;

[0109] Adjust the first activation function based on the gradient adjustment coefficient to obtain a second activation function;

[0110] The second activation function is used to replace the first activation function in the long short-term memory network model to obtain an improved long short-term memory network model.

[0111] In some embodiments, the battery remaining charging time compensation system is specifically used to:

[0112] Remove abnormal data from the current battery parameters and normalize the current battery parameters.

[0113] In some embodiments, the battery remaining charging time compensation system is specifically used to:

[0114] Determine the 99% quantile of the current battery parameter as the upper bound;

[0115] Determine the 1% quantile of the current battery parameters as the lower bound;

[0116] The current battery parameters above the upper limit and the current battery parameters below the lower limit are determined to be abnormal data, and the abnormal data are removed.

[0117] In some embodiments, the parameter determination module 10 is specifically used to:

[0118] Determine the parameters to be determined, and determine the weights of the parameters to be determined;

[0119] Determine the weight range;

[0120] In response to the weight of the undetermined parameter being within the weight range, the undetermined parameter is determined to be a current parameter of the battery.

[0121] Accordingly, an embodiment of the present application further provides an electronic device, see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device provided in an embodiment of the present application includes:

[0122] The memory 100 and the processor 200 are connected to each other in communication, the memory 100 stores computer instructions, and the processor 200 executes the remaining battery charging time compensation method provided in the embodiment of the present application by executing the computer instructions. Specifically, the memory 100 and the processor 200 are connected via a communication bus.

[0123] In some embodiments, the processor 200 may be a central processing unit (CPU). The processor 200 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0124] In some embodiments, the memory 100 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the methods in the method embodiments of the present application. The processor 200 executes various functional applications and data processing of the processor 200 by running the non-transitory software programs, instructions and modules stored in the memory 100, that is, implementing the methods in the above method embodiments.

[0125] In some embodiments, the memory 100 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created by the processor 200, etc. In addition, the memory 100 may include a high-speed random access memory 100, and may also include a non-volatile memory 100, such as at least one disk memory 100, a flash memory device, or other non-volatile solid-state memory 100. In some embodiments, the memory 100 may optionally include a memory 100 remotely arranged relative to the processor 200, and these remote memories 100 may be connected to the processor 200 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0126] In some embodiments, one or more modules are stored in the memory 100 and when executed by the processor 200, the methods in the above method embodiments are performed.

[0127] In some embodiments, the specific details of the above-mentioned electronic device can be understood by referring to the corresponding related descriptions and effects in the above-mentioned method embodiments, and will not be repeated here.

[0128] The present application has introduced in detail a battery remaining charging time compensation method, system and electronic device provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for compensating the remaining charging time of a battery, characterized in that: include: Determine the current parameters of the battery; Obtaining an improved long short-term memory network model, wherein the improved long short-term memory network model is obtained by replacing a first activation function in the long short-term memory network model with a second activation function, wherein the long short-term memory network model includes a forget gate, and the first activation function is an activation function of the forget gate; The current parameters of the battery are input into the improved long short-term memory network model to obtain a compensation value of the remaining charging time.

2. The method for compensating the remaining battery charging time according to claim 1, characterized in that: The step of obtaining the improved long short-term memory network model comprises: Obtaining the first activation function of the long short-term memory network model; Determine the gradient adjustment factor; Adjust the first activation function based on the gradient adjustment coefficient to obtain the second activation function; The second activation function is used to replace the first activation function in the long short-term memory network model to obtain the improved long short-term memory network model.

3. The method for compensating the remaining battery charging time according to claim 2, characterized in that: The characterization formula of the second activation function includes: Among them, Zigmoid is the second activation function; Sigmmoid is the first activation function; x is the input feature vector; β is the gradient adjustment coefficient.

4. The method for compensating the remaining battery charging time according to claim 1, characterized in that: Before the step of inputting the current battery parameters into the improved long short-term memory network model, the battery remaining charging time compensation method further includes: Abnormal data in the current parameters of the battery are removed, and the current parameters of the battery are normalized.

5. The method for compensating the remaining battery charging time according to claim 4, characterized in that: The step of removing abnormal data in the current parameters of the battery comprises: Determine the 99% quantile of the current parameter of the battery as an upper bound; Determine the 1% quantile of the current parameter of the battery as a lower bound; The current battery parameters above the upper limit and the current battery parameters below the lower limit are determined as the abnormal data, and the abnormal data are removed.

6. The method for compensating the remaining battery charging time according to claim 4, characterized in that: The characterization formula for normalizing the current parameters of the battery includes: Among them, x morm is the current parameter of the battery after normalization; x is the current parameter of the battery before normalization; x min is the minimum value of the current battery parameter; x max is the maximum value of the current parameter of the battery.

7. The method for compensating the remaining battery charging time according to claim 1, characterized in that: The step of determining the current parameters of the battery comprises: Determining the parameters to be determined, and determining the weights of the parameters to be determined; Determine the weight range; In response to the weight of the undetermined parameter being within a weight range, the undetermined parameter is determined to be the current parameter of the battery.

8. The method for compensating the remaining battery charging time according to claim 1, characterized in that: The current battery parameters include rated capacity, rated voltage, maximum allowable charging current, initial maximum single cell voltage, initial minimum single cell voltage, initial charging state, maximum temperature, minimum temperature, charging station altitude, compensation time for a single completed charge, and deviation between the calculated time and actual time for a single completed charge.

9. A battery remaining charging time compensation system, characterized in that: include: A parameter determination module, the parameter determination module is used to determine the current parameters of the battery; A model acquisition module, the model acquisition module is used to acquire an improved long short-term memory network model, the improved long short-term memory network model is obtained by replacing the first activation function in the long short-term memory network model with a second activation function, the long short-term memory network model includes a forget gate, and the first activation function is the activation function of the forget gate; A compensation calculation module is used to input the current parameters of the battery into the improved long short-term memory network model to obtain a compensation value of the remaining charging time.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the battery remaining charging time compensation method as described in any one of claims 1 to 8 by executing the computer instructions.

Images