Battery energy efficiency value prediction method

Abstract

The invention relates to the technical field of batteries, in particular to a battery energy efficiency value prediction method. In one aspect, the invention provides a battery energy efficiency value prediction method, and the method comprises the steps: obtaining a critical test frequency corresponding to a target battery under a preset working condition; obtaining to-be-predicted test times corresponding to the target battery; comparing the number of tests to be predicted with the number of critical tests; according to a comparison result, predicting predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of to-be-predicted test times; and inputting the number of to-be-predicted test times, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a target energy efficiency value preset model corresponding to the number of to-be-predicted test times, and outputting a predicted energy efficiency value corresponding to the number of to-be-predicted test times. The accuracy of the predicted energy efficiency value corresponding to the output predicted test times is ensured, so that the energy efficiency value of the target battery is predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of batteries, and in particular to a method for predicting battery energy efficiency values. Background Art

[0002] With the popularity of electric vehicles, the requirements for battery performance are getting higher and higher. Current research mainly focuses on capacity decay and impedance growth, and pays less attention to the energy efficiency of the battery cell throughout its life cycle.

[0003] However, energy efficiency is an important indicator for evaluating battery performance. A higher energy efficiency usually means that the battery has better performance, such as higher charging speed, lower self-discharge rate, etc.

[0004] Therefore, how to predict the energy efficiency value of batteries has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, the present invention provides a battery energy efficiency value prediction method to solve the problem of how to predict the energy efficiency value of a battery.

[0006] In a first aspect, the present invention provides a method for predicting battery energy efficiency value, the method comprising:

[0007] Obtaining a critical test number corresponding to a target battery under a preset working condition; wherein the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number;

[0008] Obtain the number of tests to be predicted corresponding to the target battery;

[0009] Compare the number of tests to be predicted with the critical number of tests;

[0010] According to the comparison results, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy corresponding to the number of tests to be predicted are predicted;

[0011] The number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy are input into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output.

[0012] The battery energy efficiency value prediction method provided in the embodiment of the present application obtains the critical test number corresponding to the target battery under the preset working conditions; obtains the number of tests to be predicted corresponding to the target battery; compares the number of tests to be predicted with the critical test number, thereby ensuring the accuracy of the comparison result obtained. According to the comparison result, the predicted charging capacity, predicted discharge capacity, predicted charging energy, and predicted discharge energy corresponding to the number of tests to be predicted are predicted, thereby ensuring the accuracy of the predicted charging capacity, predicted discharge capacity, predicted charging energy, and predicted discharge energy obtained by prediction. The number of tests to be predicted, the predicted charging capacity, the predicted discharge capacity, the predicted charging energy, and the predicted discharge energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, thereby ensuring the accuracy of the predicted energy efficiency value corresponding to the output predicted number of tests, thereby realizing the prediction of the energy efficiency value of the target battery.

[0013] In an optional implementation, obtaining a critical test number corresponding to a target battery under a preset working condition includes:

[0014] Obtaining each first test number and first test data corresponding to each first test number after performing a preset number of charge-discharge cycle tests on a test battery of the same batch as the target battery under a preset preload condition;

[0015] Based on the first test data corresponding to each first test number, predicting the test data corresponding to the second test number of the test battery after the preset number of times, to generate preset test data;

[0016] Acquire second test data obtained after the test battery is subjected to a second test number of charge and discharge cycle tests;

[0017] Determine, according to the preset test data and the second test data, that the second test number is a critical test number corresponding to the test battery;

[0018] The critical test number corresponding to the test battery is determined as the critical test number corresponding to the target battery.

[0019] The battery energy efficiency value prediction method provided in the embodiment of the present application obtains each first test number and the first test data corresponding to each first test number after the test battery of the same batch as the test battery is subjected to a preset number of charge-discharge cycle tests under a preset preload force condition. The accuracy of each first test number and each first test data corresponding to the test battery under the preset preload force condition obtained is ensured. Based on the first test data corresponding to each first test number, the test data corresponding to the second test number of the test battery after the preset number is predicted, and the preset test data is generated, thereby ensuring the accuracy of the generated preset test data. The second test data obtained after the test battery is subjected to a second number of charge-discharge cycle tests is obtained. Then, based on the preset test data and the second test data, the second test number is determined to be the critical test number corresponding to the test battery, and the critical test number corresponding to the test battery is determined to be the critical test number corresponding to the target battery, thereby ensuring the accuracy of the determined critical test number.

[0020] In an optional embodiment, the first test data includes first battery expansion force data; the preset test data includes a predicted battery expansion force ratio; based on the first test data corresponding to each first test number, predicting the test data corresponding to a second test number of the test battery after the preset number of times, generating the preset test data, including:

[0021] Based on the first battery expansion force data corresponding to each first test number, determining a first expansion force maximum value corresponding to the test battery within a first preset state of charge range and a second expansion force maximum value corresponding to the test battery within a second preset state of charge range; wherein the first preset state of charge range belongs to the second preset state of charge range;

[0022] The first battery expansion force ratio corresponding to each first test number is calculated by dividing the first expansion force maximum value by the second expansion force maximum value;

[0023] Based on the correspondence between each first test number and each first battery expansion force ratio, a first fitting function between each first test number and each first battery expansion force ratio is generated by fitting;

[0024] The second test number is input into the first fitting function to generate a predicted battery expansion force ratio.

[0025] The battery energy efficiency value prediction method provided in the embodiment of the present application determines the first expansion force maximum value corresponding to the test battery within the first preset state of charge range and the second expansion force maximum value corresponding to the test battery within the second preset state of charge range based on the first battery expansion force data corresponding to each first test number; the first expansion force maximum value is divided by the second expansion force maximum value to calculate the first battery expansion force ratio corresponding to each first test number, thereby ensuring the accuracy of the calculated first battery expansion force ratio corresponding to each first test number. Based on the corresponding relationship between each first test number and the first battery expansion force ratio, a first fitting function between each first test number and each first battery expansion force ratio is fitted to ensure the accuracy of the generated first fitting function. The second test number is input into the first fitting function to generate a predicted battery expansion force ratio, thereby ensuring the accuracy of the generated predicted battery expansion force ratio.

[0026] In an optional implementation, the first test data further includes first battery capacity retention rate data, and the second test data includes second battery expansion force data and second battery capacity retention rate data; and determining the second test number as a critical test number corresponding to the test battery according to the preset test data and the second test data includes:

[0027] Calculating a second battery expansion force ratio corresponding to a second number of tests according to the second battery expansion force data;

[0028] Subtracting the second battery expansion force ratio from the predicted battery expansion force ratio to obtain an expansion force ratio deviation;

[0029] If the expansion force ratio deviation is greater than the preset deviation threshold, based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, the second test number is determined to be the critical test number corresponding to the test battery.

[0030] The battery energy efficiency value prediction method provided in the embodiment of the present application calculates the second battery expansion force ratio corresponding to the second test number according to the second battery expansion force data; subtracts the second battery expansion force ratio from the predicted battery expansion force ratio to obtain the expansion force ratio deviation; if the expansion force ratio deviation is greater than the preset deviation threshold, the electronic device determines that the second battery expansion force ratio corresponding to the second test number is reduced, and then determines that the second test number is the critical test number corresponding to the test battery based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, thereby ensuring the accuracy of the critical test number corresponding to the determined test battery.

[0031] In an optional implementation, based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, determining the second test number as the critical test number corresponding to the test battery includes:

[0032] Based on the corresponding relationship between each first test number and each first battery capacity retention rate data, a first capacity decay curve function is obtained by fitting based on the Arrhenius model;

[0033] Based on the correspondence between at least two second test times and the second battery capacity retention rate data, a second capacity decay curve function is obtained by fitting based on the Arrhenius model;

[0034] Based on the first capacity decay curve function and the second capacity decay curve function, the second test number is determined to be a critical test number corresponding to the test battery.

[0035] The battery energy efficiency value prediction method provided in the embodiment of the present application is based on the correspondence between each first test number and each first battery capacity retention rate data, and the first capacity decay curve function is obtained by fitting based on the Arrhenius model, thereby ensuring the accuracy of the first capacity decay curve function obtained by fitting. Based on the correspondence between at least two second test numbers and the second battery capacity retention rate data, the second capacity decay curve function is obtained by fitting based on the Arrhenius model, thereby ensuring the accuracy of the second capacity decay curve function obtained by fitting. Based on the first capacity decay curve function and the second capacity decay curve function, the second test number is determined to be the critical test number corresponding to the test battery, thereby ensuring the accuracy of the determined critical test number.

[0036] In an optional implementation, based on the first capacity decay curve function and the second capacity decay curve function, determining the second test number as the critical test number corresponding to the test battery includes:

[0037] Obtaining a first exponential factor in a first capacity decay curve function;

[0038] Obtaining a second exponential factor in a second capacity decay curve function;

[0039] Calculate the growth rate of the second exponential factor relative to the first exponential factor;

[0040] If the growth rate is greater than the preset growth rate threshold, the second test number is determined to be a critical test number corresponding to the test battery.

[0041] The battery energy efficiency value prediction method provided in the embodiment of the present application obtains the first exponential factor in the first capacity decay curve function; obtains the second exponential factor in the second capacity decay curve function; calculates the growth rate of the second exponential factor relative to the first exponential factor, thereby ensuring the accuracy of the calculated growth rate. If the growth rate is greater than the preset growth rate threshold, the second test number is determined to be the critical test number corresponding to the test battery, thereby ensuring the accuracy of the determined critical test number.

[0042] In an optional implementation, predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison result includes:

[0043] If the number of tests to be predicted is less than or equal to the critical number of tests, then obtain a fitting relationship between the first number of tests and the charging capacity, a fitting relationship between the first number of tests and the discharging capacity, a fitting relationship between the first number of tests and the charging energy, and a fitting relationship between the first number of tests and the discharging energy; wherein the fitting relationship between the first number of tests and the charging capacity, the fitting relationship between the first number of tests and the discharging capacity, the fitting relationship between the first number of tests and the charging energy, and the fitting relationship between the first number of tests and the discharging energy are all obtained by fitting the first training test numbers of the test batteries of the same batch as the target battery before the critical number of tests under the preset preload condition, and the first training charging capacity, the first training discharging capacity, the first training charging energy, and the first training discharging energy corresponding to each first training test number;

[0044] Based on the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy, the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted are predicted respectively.

[0045] The battery energy efficiency value prediction method provided in the embodiment of the present application, if the number of tests to be predicted is less than or equal to the critical number of tests, then obtain the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy; based on the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy, respectively predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted, taking into account the battery capacity attenuation, thereby ensuring the accuracy of the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy.

[0046] In an optional implementation, predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison result also includes:

[0047] If the number of tests to be predicted is greater than the critical number of tests, a fitting relationship between the second number of tests and the charging capacity, a fitting relationship between the second number of tests and the discharging capacity, a fitting relationship between the second number of tests and the charging energy, and a fitting relationship between the second number of tests and the discharging energy are obtained; wherein the fitting relationship between the second number of tests and the charging capacity, the fitting relationship between the second number of tests and the discharging capacity, the fitting relationship between the second number of tests and the charging energy, and the fitting relationship between the second number of tests and the discharging energy are all obtained by fitting the second training test numbers of the test batteries of the same batch as the target battery under the preset preload condition after the critical number of tests, and the second training charging capacity, the second training discharging capacity, the second training charging energy, and the second training discharging energy corresponding to each second training test number;

[0048] Based on the fitting relationship between the second test number and the charging capacity, the fitting relationship between the second test number and the discharging capacity, the fitting relationship between the second test number and the charging energy, and the fitting relationship between the second test number and the discharging energy, the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted are predicted respectively.

[0049] The battery energy efficiency value prediction method provided by the embodiment of the present application, if the number of tests to be predicted is greater than the critical number of tests, then obtain the fitting relationship between the second number of tests and the charging capacity, the second number of tests and the discharging capacity, the second number of tests and the charging energy, and the second number of tests and the discharging energy; based on the fitting relationship between the second number of tests and the charging capacity, the second number of tests and the discharging capacity, the second number of tests and the charging energy, and the second number of tests and the discharging energy, respectively predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted. The battery capacity attenuation is taken into account, thereby ensuring the accuracy of the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy obtained by prediction.

[0050] In an optional implementation, the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy are input into a preset model of a target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, including:

[0051] Compare the number of tests to be predicted with the critical number of tests to determine the preset model of the target energy efficiency value;

[0052] Input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted;

[0053] The battery energy efficiency value prediction method provided in the embodiment of the present application compares the number of tests to be predicted with the critical number of tests, determines the preset model of the target energy efficiency value, and ensures the accuracy of the preset model of the determined standard energy efficiency value. The number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, which ensures the accuracy of the output predicted energy efficiency value corresponding to the number of tests to be predicted.

[0054] In an optional implementation, the number of tests to be predicted is compared with the critical number of tests to determine a preset model of a target energy efficiency value, including:

[0055] If the number of tests to be predicted is less than or equal to the critical number of tests, the target energy efficiency value preset model is determined to be the first energy efficiency value preset model; the first energy efficiency value preset model is obtained by training the test batteries of the same batch as the target battery under the preset preload condition before the critical number of tests and the first training charging capacity, first training discharging capacity, first training charging energy, first training discharging energy and first training energy efficiency value corresponding to each first training test number; wherein the first training energy efficiency value is label data;

[0056] If the number of tests to be predicted is greater than the critical number of tests, the target energy efficiency value preset model is determined to be the second energy efficiency value preset model; the second energy efficiency value preset model is obtained by training the test batteries of the same batch as the target battery under the preset preload conditions after the critical number of tests, and the second training charging capacity, second training discharging capacity, second training charging energy, second training discharging energy and second training energy efficiency value corresponding to each second training test number; wherein the second training energy efficiency value is label data.

[0057] The battery energy efficiency value prediction method provided in the embodiment of the present application determines that the target energy efficiency value preset model is the first energy efficiency value preset model if the number of tests to be predicted is less than or equal to the critical number of tests; if the number of tests to be predicted is less than or equal to the critical number of tests, the target energy efficiency value preset model is determined to be the first energy efficiency value preset model, which takes into account the battery capacity attenuation, thereby ensuring the accuracy of the determined target energy efficiency value preset model.

[0058] In a second aspect, the present invention provides a battery energy efficiency value prediction device, the device comprising:

[0059] A first acquisition module is used to acquire the critical test number corresponding to the target battery under the preset working conditions; wherein the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number;

[0060] The second acquisition module is used to obtain the number of tests to be predicted corresponding to the target battery;

[0061] A comparison module, used for comparing the number of tests to be predicted with the critical number of tests;

[0062] A prediction module, used to predict the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison results;

[0063] The output module is used to input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0064] In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the battery energy efficiency value prediction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0065] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the battery energy efficiency value prediction method of the first aspect or any corresponding embodiment thereof.

[0066] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the battery energy efficiency value prediction method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 is a flow chart of a method for predicting battery energy efficiency value according to an embodiment of the present invention;

[0069] Figure 2 is a flow chart of another battery energy efficiency value prediction method according to an embodiment of the present invention;

[0070] Figure 3 is a schematic diagram of a curve of F30 / F100 corresponding to different first test times according to an embodiment of the present invention;

[0071] Figure 4 2 is a schematic diagram of a first capacity decay curve function, a second capacity decay curve function and test data corresponding to a 45° C. cycle according to an embodiment of the present invention;

[0072] Figure 5 is a flow chart of another battery energy efficiency value prediction method according to an embodiment of the present invention;

[0073] Figure 6 is a structural block diagram of a battery energy efficiency value prediction device according to an embodiment of the present invention;

[0074] Figure 7 It is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0076] With the popularity of electric vehicles, the requirements for battery performance are getting higher and higher. Current research mainly focuses on capacity decay and impedance growth, and pays less attention to the energy efficiency of the battery cell throughout its life cycle.

[0077] However, energy efficiency is an important indicator for evaluating battery performance. A higher energy efficiency usually means that the battery has better performance, such as higher charging speed, lower self-discharge rate, etc.

[0078] Therefore, how to predict the energy efficiency value of batteries has become an urgent problem to be solved.

[0079] Based on the above problems, an embodiment of the present application provides a method for predicting the energy efficiency value of a battery, which obtains the critical test number corresponding to the target battery under the preset working conditions; obtains the number of tests to be predicted corresponding to the target battery; compares the number of tests to be predicted with the critical test number, and ensures the accuracy of the comparison result obtained. According to the comparison result, the predicted charging capacity, predicted discharge capacity, predicted charging energy and predicted discharge energy corresponding to the number of tests to be predicted are predicted, and the accuracy of the predicted charging capacity, predicted discharge capacity, predicted charging energy and predicted discharge energy obtained by prediction is ensured. The number of tests to be predicted, the predicted charging capacity, the predicted discharge capacity, the predicted charging energy and the predicted discharge energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, and the accuracy of the predicted energy efficiency value corresponding to the output predicted number of tests is ensured, thereby realizing the prediction of the energy efficiency value of the target battery.

[0080] It should be noted that the method for predicting the battery energy efficiency value provided in the embodiment of the present application, its execution subject may be a device for predicting the battery energy efficiency value, and the device for predicting the battery energy efficiency value may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device may be a server or a terminal, wherein the server in the embodiment of the present application may be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, and other intelligent hardware devices such as an intelligent robot. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0081] According to an embodiment of the present invention, an embodiment of a battery energy efficiency value prediction method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0082] In this embodiment, a battery energy efficiency value prediction method is provided, which can be used for the above-mentioned electronic device. Figure 1 is a flow chart of a method for predicting battery energy efficiency value according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0083] Step S101, obtaining the critical test times corresponding to the target battery under the preset working conditions.

[0084] Among them, the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number.

[0085] Specifically, the electronic device may receive the critical test number of the target battery under the preset working condition input by the user, and may also receive the critical test number of the target battery under the preset working condition sent by other devices.

[0086] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the critical test number corresponding to the target battery under preset operating conditions.

[0087] This step will be described in detail below.

[0088] Step S102, obtaining the number of tests to be predicted corresponding to the target battery.

[0089] Specifically, the electronic device may receive the number of tests to be predicted corresponding to the target battery input by the user, or may receive the number of tests to be predicted corresponding to the target battery based on the current number of charging tests corresponding to the target battery, and determine the number of tests to be predicted corresponding to the target battery.

[0090] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the number of tests to be predicted corresponding to the target battery.

[0091] Step S103, comparing the number of tests to be predicted with the critical number of tests.

[0092] Specifically, the electronic device may compare the number of tests to be predicted with the critical number of tests.

[0093] Step S104, predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison result.

[0094] Specifically, the electronic device can determine a preset fitting relationship or a preset prediction model according to the comparison result, and then predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted based on the preset fitting relationship or the preset prediction model.

[0095] Step S105, input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0096] Specifically, after predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted, the electronic device can input the number of tests to be predicted, the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0097] This step will be described in detail below.

[0098] The battery energy efficiency value prediction method provided in the embodiment of the present application obtains the critical test number corresponding to the target battery under the preset working conditions; obtains the number of tests to be predicted corresponding to the target battery; compares the number of tests to be predicted with the critical test number, thereby ensuring the accuracy of the comparison result obtained. According to the comparison result, the predicted charging capacity, predicted discharge capacity, predicted charging energy, and predicted discharge energy corresponding to the number of tests to be predicted are predicted, thereby ensuring the accuracy of the predicted charging capacity, predicted discharge capacity, predicted charging energy, and predicted discharge energy obtained by prediction. The number of tests to be predicted, the predicted charging capacity, the predicted discharge capacity, the predicted charging energy, and the predicted discharge energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, thereby ensuring the accuracy of the predicted energy efficiency value corresponding to the output predicted number of tests, thereby realizing the prediction of the energy efficiency value of the target battery.

[0099] In this embodiment, a battery energy efficiency value prediction method is provided, which can be used for the above-mentioned electronic device. Figure 2 is a flow chart of a method for predicting battery energy efficiency value according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0100] Step S201, obtaining the critical test times corresponding to the target battery under the preset working conditions.

[0101] Among them, the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number.

[0102] Specifically, the above step S201 may include the following steps:

[0103] Step S2011, obtaining each first test number and first test data corresponding to each first test number after performing a preset number of charge and discharge cycle tests on a test battery of the same batch as the target battery under a preset preload condition.

[0104] Optionally, the electronic device can receive the test battery input by the user, after performing a preset number of charge and discharge cycle tests under preset preload conditions, and the obtained first test times and first test data corresponding to each first test times; the electronic device can also receive the test battery sent by other devices, after performing a preset number of charge and discharge cycle tests under preset preload conditions, and the obtained first test times and first test data corresponding to each first test times.

[0105] The electronic device can also perform a preset number of charge-discharge cycle tests on the test battery under a preset preload condition based on the charge-discharge test cabinet. Then, the charge-discharge test cabinet generates each first test number corresponding to the test battery and first test data corresponding to each first test number. The charge-discharge test cabinet adopts step charging during the charging process of the test battery.

[0106] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains each first test number and first test data corresponding to each first test number after the test battery is subjected to a preset number of charge and discharge cycle tests under a preset preload force condition.

[0107] The preset number of times may be 500 times, 550 times, or other times. The embodiment of the present application does not specifically limit the preset number of times.

[0108] Exemplarily, assuming the preset number of times is 500 times, the electronic device can obtain the first test data corresponding to each charge and discharge cycle test after the test battery is subjected to 500 charge and discharge cycle tests under the preset preload force condition, that is, the first test data corresponding to the first charge and discharge cycle test, the first test data corresponding to the second charge and discharge cycle test, and ..., the first test data corresponding to the 500th charge and discharge cycle test.

[0109] Step S2012, based on the first test data corresponding to each first test number, predict the test data corresponding to the second test number of the test battery after the preset number of times, and generate preset test data.

[0110] Specifically, the electronic device can train a test data prediction model based on the corresponding relationship between each first test number and each first test data. Then, the electronic device inputs the second test number into the test data prediction model, and the test data prediction model outputs the preset test data.

[0111] Specifically, the first test data includes first battery expansion force data; the preset test data includes a predicted battery expansion force ratio; the above step S2012 may include the following steps:

[0112] Step a1, based on the first battery expansion force data corresponding to each first test number, determining a first expansion force maximum value corresponding to the test battery within a first preset state of charge range and a second expansion force maximum value corresponding to the test battery within a second preset state of charge range.

[0113] The first preset state of charge range belongs to the second preset state of charge range.

[0114] Specifically, the electronic device can identify the first battery expansion force data corresponding to each first test number, and determine the first expansion force maximum value corresponding to the test battery within the first preset state of charge range and the second expansion force maximum value corresponding to the test battery within the second preset state of charge range.

[0115] Exemplarily, the first preset state of charge range can be 0%-30%, or 0%-33%, or 5%-30%, and the second preset state of charge range can be 0%-100%, or 5%-90%, or 0%-95%. The embodiments of the present application do not specifically limit the first preset state of charge range and the second preset state of charge range.

[0116] Step a2: dividing the first expansion force maximum value by the second expansion force maximum value to calculate the first battery expansion force ratio corresponding to each first test number.

[0117] Specifically, the electronic device may calculate the first battery expansion force ratio corresponding to each first test number by dividing the first expansion force maximum value by the second expansion force maximum value.

[0118] In an optional embodiment of the present application, the electronic device can identify the first battery expansion force data corresponding to each first test number, determine the maximum expansion force F100 in the entire charging process, the minimum expansion force F0 in the entire charging process, the maximum expansion force F30 in 0% to 30% SOC, and the minimum expansion force F60 in 30% to 60% SOC, and analyze the ratio α (F0 / F100, F30 / F100, F60 / F100, F60 / F30) between the above extreme values. As shown in Table 1 below, the expansion force extreme value data corresponding to different test times are shown.

[0119] Table 1 Expansion force extreme value data corresponding to different test times

[0120] Number of tests 1 100 200 300 400 500 600 700 800 F0 1383 3718 4272 4838 5215 5735 6429 7910 10339 F30 3624 7322 7989 8631 8980 9514 10197 11475 13757 F60 3043 5726 6351 6957 7327 7818 8507 9886 12284 F100 4790 7897 8395 8868 9136 9553 10197 11475 13757 F0 / F100 28.9％ 47.1％ 50.9％ 54.6％ 57.1％ 60.0％ 63.0％ 68.9％ 75.2％ F30 / F100 75.7％ 92.7％ 95.2％ 97.3％ 98.3％ 99.6％ 100.0％ 100.0％ 100.0％ F60 / F100 63.5％ 72.5％ 75.7％ 78.5％ 80.2％ 81.8％ 83.4％ 86.2％ 89.3％

[0121] For example, Figure 3 As shown in FIG. , it is a schematic diagram of the curve of F30 / F100 corresponding to different first test times. Figure 3 It can be seen that the linear relationship between F30 / F100 and the number of tests has a fitting degree of >96%. After 600 tests, the linear fitting degree is <95%. This change also corresponds to the inflection point of the cycle capacity attenuation. The linear fitting degree of F0 / F100 and F60 / F100 in the first 500 tests and the first 600 tests is slightly different.

[0122] Therefore, in the embodiment of the present application, the maximum value of the first expansion force may be F30, and the maximum value of the second expansion force may be F100.

[0123] Step a3: based on the corresponding relationship between each first test number and each first battery expansion force ratio, generate a first fitting function between each first test number and each first battery expansion force ratio by fitting.

[0124] Specifically, the electronic device may generate a first fitting function between each first test number and each first battery expansion force ratio based on the corresponding relationship between each first test number and each first battery expansion force ratio by using a preset fitting method.

[0125] Among them, the preset fitting method can be a linear fitting method, a polynomial fitting method, or other fitting methods. The embodiment of the present application does not specifically limit the preset fitting method.

[0126] Exemplarily, the first fitting function may be as follows:

[0127] y=ax+b(1)

[0128] Wherein, x is the first test number, y is the first battery expansion force ratio corresponding to each first test number, and a and b are both non-zero constants.

[0129] Step a4, inputting the second test number into the first fitting function to generate a predicted battery expansion force ratio.

[0130] Specifically, the electronic device may input the second test number into the first fitting function to generate a predicted battery expansion force ratio.

[0131] Step S2013, obtaining second test data obtained after the test battery is subjected to a second test number of charge and discharge cycle tests.

[0132] Optionally, the electronic device may receive the second test data input by the user after the test battery is subjected to the second test number of charge-discharge cycle tests. The electronic device may also receive the second test data sent by other devices after the test battery is subjected to the second test number of charge-discharge cycle tests.

[0133] Optionally, the electronic device may also perform a second test number of charge and discharge cycle tests on the test battery based on the charge and discharge test cabinet to obtain second test data transmitted by the charge and discharge test cabinet.

[0134] The embodiment of the present application does not specifically limit the manner in which the second test data is obtained after the electronic device obtains the test battery and performs the charge and discharge cycle test for the second test number of times.

[0135] Step S2014, determining the second test number as a critical test number corresponding to the test battery according to the preset test data and the second test data.

[0136] Specifically, the first test data further includes first battery capacity retention rate data, and the second test data includes second battery expansion force data and second battery capacity retention rate data; the above step S2014 may include the following steps:

[0137] Step b1, calculating the second battery expansion force ratio corresponding to the second test number according to the second battery expansion force data.

[0138] Specifically, the electronic device can identify the second battery expansion force data corresponding to the second test number, and determine the third expansion force maximum value corresponding to the test battery within the first preset state of charge range and the fourth expansion force maximum value corresponding to the test battery within the second preset state of charge range.

[0139] Exemplarily, the first preset state of charge range can be 0%-30%, or 0%-33%, or 5%-30%, and the second preset state of charge range can be 0%-100%, or 5%-90%, or 0%-95%. The embodiments of the present application do not specifically limit the first preset state of charge range and the second preset state of charge range.

[0140] Then, the electronic device may calculate a second battery expansion force ratio corresponding to the second test number by dividing the third expansion force maximum value by the fourth expansion force maximum value.

[0141] Step b2, subtracting the second battery expansion force ratio from the predicted battery expansion force ratio to obtain an expansion force ratio deviation.

[0142] Specifically, the electronic device may subtract the second battery expansion force ratio from the predicted battery expansion force ratio to obtain an expansion force ratio deviation.

[0143] Step b3: if the expansion force ratio deviation is greater than the preset deviation threshold, based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, determine the second test number as the critical test number corresponding to the test battery.

[0144] In an optional embodiment, if the expansion force ratio deviation is greater than a preset deviation threshold, the electronic device may compare the first battery capacity retention rate data with the second battery capacity retention rate data. If the second battery capacity retention rate data is less than the first battery capacity retention rate data, the second test number is determined to be the critical test number corresponding to the test battery.

[0145] Specifically, in the above step b3, "determining the second test number as the critical test number corresponding to the test battery based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data" includes the following steps:

[0146] Step b31, based on the corresponding relationship between each first test number and each first battery capacity retention rate data, a first capacity decay curve function is obtained by fitting based on the Arrhenius model.

[0147] Specifically, the electronic device may obtain the first capacity decay curve function based on the Arrhenius model fitting based on the corresponding relationship between each first test number and each first battery capacity retention rate data.

[0148] Exemplarily, the first capacity decay curve function may be as follows:

[0149] Y=1-B*t^z(2)

[0150] Among them, t is the number of tests, z is the exponential factor, and B is the attenuation coefficient.

[0151] Step b32, based on the correspondence between at least two second test times and the second battery capacity retention rate data, obtain a second capacity decay curve function based on Arrhenius model fitting.

[0152] Specifically, the electronic device may obtain the second capacity decay curve function based on the Arrhenius model fitting based on the correspondence between at least two second test times and the second battery capacity retention rate data.

[0153] Step b33: Based on the first capacity decay curve function and the second capacity decay curve function, determine the second test number as the critical test number corresponding to the test battery.

[0154] Specifically, the above step b33 may include the following steps:

[0155] Step b331, obtaining a first exponential factor in the first capacity decay curve function.

[0156] Specifically, the electronic device may identify the first capacity decay curve function and determine a first exponential factor in the first capacity decay curve function.

[0157] Step b332, obtaining a second exponential factor in the second capacity decay curve function.

[0158] Specifically, the electronic device may identify the second capacity decay curve function and determine a second exponential factor in the second capacity decay curve function.

[0159] Step b333, calculating the growth rate of the second exponential factor relative to the first exponential factor.

[0160] Specifically, the electronic device may calculate a growth rate of the second exponential factor relative to the first exponential factor based on the first exponential factor and the second exponential factor.

[0161] Step b334, if the growth rate is greater than the preset growth rate threshold, the second test number is determined to be the critical test number corresponding to the test battery.

[0162] Specifically, the electronic device can receive a preset growth rate threshold value input by a user, or can receive a preset growth rate threshold value sent by other devices, and can also set the preset growth rate threshold value according to actual conditions. The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the preset growth rate threshold value.

[0163] Exemplarily, the preset growth rate threshold may be 30% or 29%. The embodiment of the present application does not specifically limit the preset growth rate threshold.

[0164] Then, the electronic device compares the growth rate with a preset growth rate threshold, and if the growth rate is greater than the preset growth rate threshold, determines that the second test number is a critical test number corresponding to the test battery.

[0165] For example, Figure 4 As shown, it is a schematic diagram of the first capacity decay curve function, the second capacity decay curve function and the test data corresponding to the 45°C cycle. Among them, the preset number of times is 500 times, and the electronic device can obtain the first capacity decay curve function by fitting the relationship: Y = 1-B*t^z according to the first battery capacity retention rate data corresponding to the first 500 test times. Confirm that the exponential factor corresponding to the first capacity decay curve function is z = 0.52. Then, the electronic device obtains the second capacity decay curve function according to the second battery capacity retention rate data corresponding to the 500-600 test times by fitting the relationship: Y = 1-B*t^z. Confirm that the exponential factor corresponding to the first capacity decay curve function is z = 0.71. It can be seen from the curve that the capacity retention rate drops rapidly after 600 cycles (the second capacity decay curve function (z = 0.71) represents the exponential factor under the decay trend of the 500-600 test times; the second capacity decay curve function (z = 0.52) represents the exponential factor under the decay trend of the first 500 test times). By observing the cycle capacity decay curve alone, it can be seen that the decay trend around 500-600 cycles accelerates to a certain extent (exponential factor from 0.52→0.71, growth rate H>30%). Therefore, the electronic device determines the 660th test number as the critical test number corresponding to the performance critical value of the test battery.

[0166] Step S2015, determining the critical test number corresponding to the test battery as the critical test number corresponding to the target battery.

[0167] Specifically, the electronic device determines the critical test number corresponding to the test battery as the critical test number corresponding to the target battery.

[0168] Step S202, obtaining the number of tests to be predicted corresponding to the target battery.

[0169] For details about this step, please refer to the above description of step S102, which will not be elaborated here.

[0170] Step S203, comparing the test number to be predicted with the critical test number.

[0171] For details about this step, please refer to the above description of step S103, which will not be elaborated here.

[0172] Step S204, predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison result.

[0173] For details about this step, please refer to the above description of step S104, which will not be elaborated here.

[0174] Step S205, input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0175] For details about this step, please refer to the above description of step S105, which will not be elaborated here.

[0176] The battery energy efficiency value prediction method provided in the embodiment of the present application obtains each first test number and the first test data corresponding to each first test number after the test battery of the same batch as the test battery is subjected to a preset number of charge and discharge cycle tests under a preset preload condition. The accuracy of each first test number and each first test data corresponding to the test battery under the preset preload condition obtained is ensured. Based on the first battery expansion force data corresponding to each first test number, the maximum first expansion force corresponding to the test battery within the first preset state of charge range and the maximum second expansion force corresponding to the test battery within the second preset state of charge range are determined; the first expansion force maximum value is divided by the second expansion force maximum value to calculate the first battery expansion force ratio corresponding to each first test number, thereby ensuring the accuracy of the calculated first battery expansion force ratio corresponding to each first test number. Based on the corresponding relationship between each first test number and the first battery expansion force ratio, a first fitting function between each first test number and each first battery expansion force ratio is fitted to ensure the accuracy of the generated first fitting function. The second test number is input into the first fitting function to generate a predicted battery expansion force ratio, thereby ensuring the accuracy of the generated predicted battery expansion force ratio. The second test data obtained after the test battery is subjected to the charge and discharge cycle test for the second test number is obtained. Then, according to the second battery expansion force data, the second battery expansion force ratio corresponding to the second test number is calculated; the expansion force ratio deviation is obtained by subtracting the second battery expansion force ratio from the predicted battery expansion force ratio; if the expansion force ratio deviation is greater than the preset deviation threshold, the electronic device determines that the second battery expansion force ratio corresponding to the second test number is reduced, and then based on the corresponding relationship between each first test number and each first battery capacity retention rate data, the first capacity decay curve function is fitted based on the Arrhenius model, thereby ensuring the accuracy of the fitted first capacity decay curve function. Based on the corresponding relationship between at least two second test numbers and the second battery capacity retention rate data, the second capacity decay curve function is fitted based on the Arrhenius model, thereby ensuring the accuracy of the fitted second capacity decay curve function. The first exponential factor in the first capacity decay curve function is obtained; the second exponential factor in the second capacity decay curve function is obtained; the growth rate of the second exponential factor relative to the first exponential factor is calculated, thereby ensuring the accuracy of the calculated growth rate. If the growth rate is greater than the preset growth rate threshold, the second test number is determined to be the critical test number corresponding to the test battery, thereby ensuring the accuracy of the determined critical test number.

[0177] In this embodiment, a battery energy efficiency value prediction method is provided, which can be used for the above-mentioned electronic device. Figure 5 is a flow chart of a method for predicting battery energy efficiency value according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0178] Step S301, obtaining the critical test times corresponding to the target battery under the preset working conditions.

[0179] Among them, the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number.

[0180] For details about this step, please refer to the above description of step S201, which will not be elaborated here.

[0181] Step S302, obtaining the number of tests to be predicted corresponding to the target battery.

[0182] For details about this step, please refer to the above description of step S202, which will not be elaborated here.

[0183] Step S303, comparing the test number to be predicted with the critical test number.

[0184] For details about this step, please refer to the above description of step S203, which will not be elaborated here.

[0185] Step S304, predicting the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison result.

[0186] Specifically, the above step S304 may include the following steps:

[0187] Step S3041, if the number of tests to be predicted is less than or equal to the critical number of tests, then obtain the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy.

[0188] Among them, the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy are all obtained by fitting the first training test numbers of the test batteries in the same batch as the target battery under the preset preload condition before the critical test number, and the first training charging capacity, first training discharging capacity, first training charging energy, and first training discharging energy corresponding to each first training test number.

[0189] Specifically, if the number of tests to be predicted is less than or equal to the critical number of tests, the electronic device obtains the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy.

[0190] Step S3042, based on the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy, respectively predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted.

[0191] Specifically, the electronic device inputs the number of tests to be predicted into the fitting relationship between the first test number and the charging capacity, and predicts the predicted charging capacity corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the first test number and the discharge capacity, and predicts the predicted discharge capacity corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the first test number and the charging energy, and predicts the predicted charging energy corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the first test number and the discharge energy, and predicts the predicted discharge energy corresponding to the number of tests to be predicted.

[0192] Step S3043, if the number of tests to be predicted is greater than the critical number of tests, then obtain the fitting relationship between the second test number and the charging capacity, the fitting relationship between the second test number and the discharging capacity, the fitting relationship between the second test number and the charging energy, and the fitting relationship between the second test number and the discharging energy.

[0193] Among them, the fitting relationship between the second test number and the charging capacity, the fitting relationship between the second test number and the discharging capacity, the fitting relationship between the second test number and the charging energy, and the fitting relationship between the second test number and the discharging energy are all obtained by fitting the second training test numbers of the test batteries in the same batch as the target battery under the preset preload conditions after the critical test number, and the second training charging capacity, second training discharging capacity, second training charging energy, and second training discharging energy corresponding to each second training test number.

[0194] Specifically, if the number of tests to be predicted is greater than the critical number of tests, the electronic device obtains the fitting relationship between the second test number and the charging capacity, the fitting relationship between the second test number and the discharging capacity, the fitting relationship between the second test number and the charging energy, and the fitting relationship between the second test number and the discharging energy.

[0195] Step S3044, based on the fitting relationship between the second test number and the charging capacity, the fitting relationship between the second test number and the discharging capacity, the fitting relationship between the second test number and the charging energy, and the fitting relationship between the second test number and the discharging energy, respectively predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted.

[0196] Specifically, the electronic device inputs the number of tests to be predicted into the fitting relationship between the second number of tests and the charging capacity, and predicts the predicted charging capacity corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the second number of tests and the discharge capacity, and predicts the predicted discharge capacity corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the second number of tests and the charging energy, and predicts the predicted charging energy corresponding to the number of tests to be predicted; inputs the number of tests to be predicted into the fitting relationship between the second number of tests and the discharge energy, and predicts the predicted discharge energy corresponding to the number of tests to be predicted.

[0197] Step S305, input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0198] Specifically, the above step S305 may include the following steps:

[0199] Step S3051, comparing the number of tests to be predicted with the critical number of tests to determine a preset model for a target energy efficiency value.

[0200] Specifically, the above step S3051 may include the following steps:

[0201] Step c1: if the number of tests to be predicted is less than or equal to the critical number of tests, determining the target energy efficiency value preset model as the first energy efficiency value preset model.

[0202] Among them, the first energy efficiency value preset model is obtained by training the test batteries of the same batch as the target battery under the preset preload conditions before the critical test times, and the first training charging capacity, first training discharging capacity, first training charging energy, first training discharging energy and first training energy efficiency value corresponding to each first training test times; wherein the first training energy efficiency value is label data.

[0203] Step c2: if the number of tests to be predicted is greater than the critical number of tests, the target energy efficiency value preset model is determined to be the second energy efficiency value preset model.

[0204] Among them, the second energy efficiency value preset model is obtained by training the test batteries of the same batch as the target battery under the preset preload conditions after the critical test times, and the second training charging capacity, second training discharging capacity, second training charging energy, second training discharging energy and second training energy efficiency value corresponding to each second training test time; wherein the second training energy efficiency value is label data.

[0205] The first energy efficiency value preset model and the second energy efficiency value preset model can be a BP neural network, a CNN neural network, or other neural network models. When the first energy efficiency value preset model and the second energy efficiency value preset model are BP neural networks, the training process can include the following steps:

[0206] 1) Data preprocessing: standardize and de-standardize the input features and target variables; divide the data into training set and test set: the first 80% of the data is used as the training set, and the last 20% of the data is used as the test set.

[0207] 2) Create and train a BP neural network, set training parameters, including the number of hidden neurons, number of iterations, error threshold, and learning rate, train the network, and make predictions on the test set.

[0208] 3) Obtain error values, including: determination coefficient, residual sum of squares, total sum of squares, mean absolute error, and mean relative error.

[0209] 4) Update model parameters: Update model parameters based on the obtained error value.

[0210] Step S3052, input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0211] Specifically, the electronic device inputs the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted. The preset model of the target energy efficiency value extracts features from the input data, and outputs the predicted energy efficiency value corresponding to the number of tests to be predicted based on the extracted features.

[0212] The battery energy efficiency value prediction method provided in the embodiment of the present application, if the number of tests to be predicted is less than or equal to the critical number of tests, then obtain the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy; based on the fitting relationship between the first test number and the charging capacity, the fitting relationship between the first test number and the discharging capacity, the fitting relationship between the first test number and the charging energy, and the fitting relationship between the first test number and the discharging energy, respectively predict the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy corresponding to the number of tests to be predicted, taking into account the battery capacity attenuation, thereby ensuring the accuracy of the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy.

[0213] If the number of tests to be predicted is greater than the critical number of tests, the fitting relationship between the second number of tests and the charging capacity, the fitting relationship between the second number of tests and the discharging capacity, the fitting relationship between the second number of tests and the charging energy, and the fitting relationship between the second number of tests and the discharging energy are obtained; based on the fitting relationship between the second number of tests and the charging capacity, the fitting relationship between the second number of tests and the discharging capacity, the fitting relationship between the second number of tests and the charging energy, and the fitting relationship between the second number of tests and the discharging energy, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy corresponding to the number of tests to be predicted are predicted respectively. The battery capacity attenuation is taken into account, thereby ensuring the accuracy of the predicted charging capacity, predicted discharging capacity, predicted charging energy, and predicted discharging energy.

[0214] The number of tests to be predicted is compared with the critical number of tests. If the number of tests to be predicted is less than or equal to the critical number of tests, the preset model of the target energy efficiency value is determined to be the first preset model of energy efficiency value; if the number of tests to be predicted is less than or equal to the critical number of tests, the preset model of the target energy efficiency value is determined to be the first preset model of energy efficiency value, taking into account the battery capacity attenuation, thereby ensuring the accuracy of the determined preset model of the target energy efficiency value. Then, the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output, thereby ensuring the accuracy of the output predicted energy efficiency value corresponding to the number of tests to be predicted.

[0215] In this embodiment, a battery energy efficiency value prediction device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0216] This embodiment provides a battery energy efficiency value prediction device, such as Figure 6 As shown, including:

[0217] The first acquisition module 401 is used to acquire the critical test number corresponding to the target battery under the preset working condition; wherein the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number;

[0218] The second acquisition module 402 is used to acquire the number of tests to be predicted corresponding to the target battery;

[0219] A comparison module 403 is used to compare the number of tests to be predicted with the critical number of tests;

[0220] A prediction module 404, used to predict the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted according to the comparison results;

[0221] The output module 405 is used to input the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy into a preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and output the predicted energy efficiency value corresponding to the number of tests to be predicted.

[0222] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0223] The battery energy efficiency value prediction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0224] The embodiment of the present invention also provides an electronic device having the above Figure 6 The battery energy efficiency value prediction device shown.

[0225] See also Figure 7 , Figure 7 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the electronic device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0226] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0227] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0228] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device 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.

[0229] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0230] The electronic device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0231] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0232] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0233] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0234] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for predicting battery energy efficiency value, characterized in that: The method comprises: Obtaining a critical test number corresponding to a target battery under a preset working condition; wherein the capacity decay rate of the target battery after the critical test number is greater than the capacity decay rate of the target battery before the critical test number; Obtaining the number of tests to be predicted corresponding to the target battery; Comparing the number of tests to be predicted with the critical number of tests; According to the comparison results, predict the predicted charging capacity, predicted discharging capacity, predicted charging energy and predicted discharging energy corresponding to the number of tests to be predicted; The number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy are input into a preset model of a target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output.

2. The method according to claim 1, characterized in that The obtaining of the critical test number corresponding to the target battery under the preset working condition includes: Obtaining each first test number and first test data corresponding to each first test number after performing a preset number of charge-discharge cycle tests on a test battery of the same batch as the target battery under a preset preload force condition; Based on the first test data corresponding to each of the first test times, predicting the test data corresponding to the second test times of the test battery after the preset times, to generate preset test data; Acquiring second test data obtained after the test battery is subjected to a second test number of charge and discharge cycle tests; Determining, according to the preset test data and the second test data, that the second test number is a critical test number corresponding to the test battery; The critical test number corresponding to the test battery is determined as the critical test number corresponding to the target battery.

3. The method according to claim 2, characterized in that The first test data includes first battery expansion force data; the preset test data includes a predicted battery expansion force ratio; the test data corresponding to a second test number of the test battery after the preset number of times is predicted based on the first test data corresponding to each of the first test times to generate the preset test data, including: Based on the first battery expansion force data corresponding to each of the first test times, determining a first expansion force maximum value corresponding to a first preset state of charge range of the test battery and a second expansion force maximum value corresponding to a second preset state of charge range of the test battery; wherein the first preset state of charge range belongs to the second preset state of charge range; Dividing the first expansion force maximum value by the second expansion force maximum value to calculate a first battery expansion force ratio corresponding to each of the first test times; Based on the correspondence between each of the first test times and the first battery expansion force ratio, a first fitting function between each of the first test times and the first battery expansion force ratio is generated by fitting; The second test number is input into the first fitting function to generate the predicted battery expansion force ratio.

4. The method according to claim 3, characterized in that The first test data further includes first battery capacity retention rate data, and the second test data includes second battery expansion force data and second battery capacity retention rate data; and determining, based on the preset test data and the second test data, that the second test number is a critical test number corresponding to the test battery, includes: Calculating a second battery expansion force ratio corresponding to the second test number according to the second battery expansion force data; subtracting the second battery expansion force ratio from the predicted battery expansion force ratio to obtain an expansion force ratio deviation; If the expansion force ratio deviation is greater than a preset deviation threshold, based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, the second test number is determined to be the critical test number corresponding to the test battery.

5. The method according to claim 4, characterized in that The determining, based on the relationship between the first battery capacity retention rate data and the second battery capacity retention rate data, that the second test number is a critical test number corresponding to the test battery includes: Based on the corresponding relationship between each of the first test times and each of the first battery capacity retention rate data, a first capacity decay curve function is obtained by fitting based on the Arrhenius model; Based on the correspondence between at least two of the second test times and the second battery capacity retention rate data, a second capacity decay curve function is obtained by fitting based on the Arrhenius model; Based on the first capacity decay curve function and the second capacity decay curve function, the second test number is determined to be the critical test number corresponding to the test battery.

6. The method according to claim 5, characterized in that The determining, based on the first capacity decay curve function and the second capacity decay curve function, that the second test number is a critical test number corresponding to the test battery includes: Obtaining a first exponential factor in the first capacity decay curve function; Obtaining a second exponential factor in the second capacity decay curve function; calculating the growth rate of the second exponential factor relative to the first exponential factor; If the growth rate is greater than a preset growth rate threshold, the second test number is determined to be the critical test number corresponding to the test battery.

7. The method according to claim 1, characterized in that The predicting, based on the comparison result, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy corresponding to the number of tests to be predicted includes: If the number of tests to be predicted is less than or equal to the critical number of tests, then obtain a fitting relationship between the first number of tests and the charging capacity, a fitting relationship between the first number of tests and the discharging capacity, a fitting relationship between the first number of tests and the charging energy, and a fitting relationship between the first number of tests and the discharging energy; wherein the fitting relationship between the first number of tests and the charging capacity, the fitting relationship between the first number of tests and the discharging capacity, the fitting relationship between the first number of tests and the charging energy, and the fitting relationship between the first number of tests and the discharging energy are all obtained by fitting the first training test numbers before the critical number of tests of the test battery in the same batch as the target battery under the preset preload condition, and the first training charging capacity, the first training discharging capacity, the first training charging energy, and the first training discharging energy corresponding to each of the first training test numbers; Based on the fitting relationship between the first number of tests and the charging capacity, the fitting relationship between the first number of tests and the discharging capacity, the fitting relationship between the first number of tests and the charging energy, and the fitting relationship between the first number of tests and the discharging energy, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy corresponding to the number of tests to be predicted are predicted respectively.

8. The method according to claim 1, characterized in that The predicting, according to the comparison result, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy corresponding to the number of tests to be predicted further includes: If the number of tests to be predicted is greater than the critical number of tests, a fitting relationship between the second number of tests and the charging capacity, a fitting relationship between the second number of tests and the discharging capacity, a fitting relationship between the second number of tests and the charging energy, and a fitting relationship between the second number of tests and the discharging energy are obtained; wherein the fitting relationship between the second number of tests and the charging capacity, the fitting relationship between the second number of tests and the discharging capacity, the fitting relationship between the second number of tests and the charging energy, and the fitting relationship between the second number of tests and the discharging energy are all obtained by fitting the second training test numbers after the critical number of tests of the test battery in the same batch as the target battery under the preset preload condition, and the second training charging capacity, the second training discharging capacity, the second training charging energy, and the second training discharging energy corresponding to each second training test number; Based on the fitting relationship between the second number of tests and the charging capacity, the fitting relationship between the second number of tests and the discharging capacity, the fitting relationship between the second number of tests and the charging energy, and the fitting relationship between the second number of tests and the discharging energy, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy corresponding to the number of tests to be predicted are predicted respectively.

9. The method according to claim 1, characterized in that: The step of inputting the number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy, and the predicted discharging energy into a preset model of a target energy efficiency value corresponding to the number of tests to be predicted, and outputting a predicted energy efficiency value corresponding to the number of tests to be predicted includes: Comparing the number of tests to be predicted with the critical number of tests to determine the preset model of the target energy efficiency value; The number of tests to be predicted, the predicted charging capacity, the predicted discharging capacity, the predicted charging energy and the predicted discharging energy are input into the preset model of the target energy efficiency value corresponding to the number of tests to be predicted, and the predicted energy efficiency value corresponding to the number of tests to be predicted is output.

10. The method according to claim 1, characterized in that The step of comparing the number of tests to be predicted with the critical number of tests to determine the preset model of the target energy efficiency value includes: If the number of tests to be predicted is less than or equal to the critical number of tests, the target energy efficiency value preset model is determined to be a first energy efficiency value preset model; the first energy efficiency value preset model is obtained by training the test battery of the same batch as the target battery under the preset preload condition before the critical number of tests and the first training charging capacity, first training discharging capacity, first training charging energy, first training discharging energy and first training energy efficiency value corresponding to each of the first training test times; wherein the first training energy efficiency value is label data; If the number of tests to be predicted is greater than the critical number of tests, the target energy efficiency value preset model is determined to be a second energy efficiency value preset model; the second energy efficiency value preset model is obtained by training the test batteries of the same batch as the target battery under the preset preload conditions for each second training test number after the critical number of tests and the second training charging capacity, second training discharging capacity, second training charging energy, second training discharging energy and second training energy efficiency value corresponding to each second training test number; wherein the second training energy efficiency value is label data.

Images