Manufacturing method and device of lithium ion battery and battery pack

Abstract

The embodiment of the invention provides a lithium ion battery manufacturing method and device and a battery pack, and the method comprises the steps: obtaining a first network model and a preset formation process parameter set, and inputting each formation process parameter in the preset formation process parameter set into the first network model, representing a corresponding relation between the formation process parameters and the battery service life based on a first network model to obtain a first predicted service life corresponding to each formation process parameter, and then determining the formation process parameter corresponding to the first predicted service life which is not less than a preset first service life threshold as a target formation process parameter; and in the formation process of the lithium ion battery, the formation process parameters enabling the service life of the lithium ion battery to meet the first service life threshold value are selected to perform formation on the lithium ion battery, so that the lithium ion battery with longer service life is manufactured.

Description

Technical Field

[0001] The present application relates to the technical field of lithium-ion batteries, and in particular to a method and device for manufacturing a lithium-ion battery and a battery pack. Background Art

[0002] Due to its advantages such as high energy density, no memory effect and low self-discharge rate, lithium-ion batteries have been widely used in many fields such as new energy vehicles and energy storage grids. They are a solution to environmental pollution and greenhouse effect and help achieve "carbon peak" and "carbon neutrality".

[0003] At present, the life extension strategy of lithium-ion batteries is mainly achieved by adjusting the preset strategy of the battery management system after the lithium-ion batteries are produced, and has not yet been started during the production process of lithium-ion batteries. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, and battery pack for manufacturing lithium-ion batteries, so as to produce lithium-ion batteries with long lifespan during the lithium-ion manufacturing stage. The specific technical solutions are as follows:

[0005] A first aspect of the present application provides a method for manufacturing a lithium-ion battery, the method comprising:

[0006] A first network model is obtained, wherein the first network model characterizes a correspondence between a formation process parameter and a battery service life; a preset formation process parameter set is obtained, wherein the formation process parameter set includes: a plurality of formation process parameters; the formation process parameters are input into the first network model to obtain a first predicted service life corresponding to the formation process parameters; the formation process parameters corresponding to the first predicted service life that is not less than a preset first service life threshold are determined as target formation process parameters; and a formation operation is performed on a lithium-ion battery to be manufactured using the target formation process parameters to manufacture a lithium-ion battery.

[0007] During the lithium-ion battery formation process, the lithium-ion battery is formed using process parameters that ensure the lithium-ion service life meets a first service life threshold, thereby producing a lithium-ion battery with a longer life. This eliminates the need to implement complex battery life extension strategies within the battery management system or energy management system.

[0008] In one or more embodiments of the present application, a first formation process parameter set is selected, and the first predicted service life corresponding to all formation process parameters in the first formation process parameter set is not less than a preset first service life threshold, and the formation process parameter corresponding to the longest first predicted service life in the first formation process parameter set is determined as the target formation process parameter.

[0009] The target formation process parameters are the formation process parameters corresponding to the longest first predicted service life, which is equivalent to selecting an optimal formation process parameter from various formation process parameters, and then forming the lithium-ion battery based on the optimal formation process parameter to further manufacture a lithium-ion battery with a longer service life.

[0010] In one or more embodiments of the present application, a first formation process parameter set is selected, and the first predicted service life corresponding to all formation process parameters in the first formation process parameter set is not less than a preset first service life threshold value. The formation process parameters to be selected are determined from the first formation process parameter set, and the unformed battery to be tested is formed using the formation process parameters to be selected, and the performance parameters of the battery to be tested are obtained, and the performance parameters are input into a second network model to obtain a second predicted service life of the battery to be tested, and the formation process parameters to be selected corresponding to the second predicted service life that is not less than the preset first service life threshold value are determined as target formation process parameters. The second network model characterizes the correspondence between performance parameters and battery service life.

[0011] The two models are used to select formation process parameters corresponding to a service life that is not less than a preset first service life threshold as target formation process parameters. In this way, during the formation process of the lithium-ion battery, the formation process parameters that make the service life of the lithium ions meet the first service life threshold are selected to form the lithium-ion battery, so as to manufacture a long-life lithium-ion battery.

[0012] In one or more embodiments of the present application, the formation process parameters corresponding to the first predicted service life that is not less than a preset second service life threshold are used as the formation process parameters to be selected.

[0013] In one or more embodiments of the present application, in descending order of the first predicted service life, the formation process parameters with the first predicted service life in the first formation process parameter set being in the first preset number are selected as the formation process parameters to be selected.

[0014] Taking the formation process parameters corresponding to the first predicted service life of the preset number as the formation process parameters to be selected is equivalent to giving priority to selecting the formation process parameters with relatively long service life as the formation process parameters to be selected. This not only improves the possibility of determining the formation process parameters corresponding to the first predicted service life that meet the requirements, but also tries to select the formation process parameters with relatively long service life of the lithium-ion battery, and further manufactures lithium-ion batteries with longer service life.

[0015] In one or more embodiments of the present application, the to-be-selected chemical formation process parameter corresponding to the longest second predicted service life is determined as the target chemical formation process parameter.

[0016] The target formation process parameters are the formation process parameters corresponding to the longest first predicted service life, which is equivalent to selecting an optimal formation process parameter from various formation process parameters, and then forming the lithium-ion battery based on the optimal formation process parameter to further manufacture a lithium-ion battery with a longer service life.

[0017] In one or more embodiments of the present application, the selected forming process parameters corresponding to the second predicted service life having the longest service life and not less than the preset first service life threshold are used as target forming process parameters.

[0018] The target formation process parameters are the formation process parameters corresponding to the longest first predicted service life, which is equivalent to selecting an optimal formation process parameter from various formation process parameters, and then forming the lithium-ion battery based on the optimal formation process parameter to further manufacture a lithium-ion battery with a longer service life.

[0019] In one or more embodiments of the present application, a formation process parameter that has not been selected in the first formation process parameter set and corresponds to the longest first predicted service life is used as the current formation process parameter, the unformed battery to be tested is formed using the to-be-selected formation process parameter, and the performance parameters of the battery to be tested are obtained, and the performance parameters are input into a second network model to obtain a second predicted service life of the battery to be tested, and it is determined whether the second predicted service life is not less than the preset first service life threshold value. If so, the current formation process parameter is determined as the target formation process parameter; if not, the step is returned to use the formation process parameter that has not been selected in the first formation process parameter set and corresponds to the longest first predicted service life as the current formation process parameter, and the execution is continued until the second predicted service life is not less than the preset first service life threshold value; or the first formation process parameter set is traversed.

[0020] In one or more embodiments of the present application, an unformed battery to be tested is formed using each of the formation process parameters, and performance parameters of the battery to be tested are obtained, and the performance parameters are input into a second network model to obtain a second predicted service life of the battery to be tested; the second network model characterizes the correspondence between the performance parameters and the battery service life, and for each formation process parameter, the difference between the second predicted service life corresponding to the formation process parameter and the first predicted service life corresponding to the formation process parameter is calculated; if the difference is not greater than a preset difference threshold, the formation process parameter is determined as the target formation process parameter.

[0021] If the difference is not greater than the preset difference threshold, it indicates that the error in the first predicted service life predicted based on the first network model is not large. Because the formation process parameters to be selected are the formation process parameters corresponding to the first predicted service life that are not less than the preset first service life threshold, the service life corresponding to the formation process parameters to be selected meets the preset first service life threshold requirement. In the formation process of the lithium-ion battery, the formation process parameters that make the service life of the lithium ions meet the first service life threshold are selected to form the lithium-ion battery to produce a lithium-ion battery with a longer life.

[0022] A second aspect of the present application provides a lithium-ion battery manufacturing device for implementing any of the lithium-ion battery manufacturing methods of the first aspect.

[0023] A third aspect of the present application provides a battery pack, which includes the lithium-ion battery manufacturing device provided in the second aspect.

[0024] In yet another aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory is configured to store a computer program; and the processor is configured to implement any of the aforementioned methods for manufacturing a lithium-ion battery when executing the program stored in the memory.

[0025] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned methods for manufacturing a lithium-ion battery is implemented.

[0026] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned methods for manufacturing lithium-ion batteries.

[0027] Beneficial effects of the embodiments of the present application:

[0028] The embodiments of the present application provide a method, device, and battery pack for manufacturing a lithium-ion battery. The method obtains a first network model and a preset set of formation process parameters, inputs each formation process parameter in the preset set of formation process parameters into the first network model, obtains a first predicted service life corresponding to each formation process parameter based on the correspondence between the formation process parameters learned by the first network model and the battery service life, and then determines the formation process parameter corresponding to the first predicted service life that is not less than the preset first service life threshold as the target formation process parameter. Then, during the formation process of the lithium-ion battery, the formation process parameter that makes the service life of the lithium ions meet the first service life threshold is selected to form the lithium-ion battery, so as to produce a lithium-ion battery with a longer life. There is no need to set up a complex battery life extension strategy in the battery management system or energy management system.

[0029] Of course, it is not necessary to achieve all the advantages described above at the same time when implementing any product or method of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0031] Figure 1 A schematic diagram of a first process flow of a method for manufacturing a lithium-ion battery provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a typical three-stage formation strategy and recording parameters provided in an embodiment of the present application;

[0033] Figure 3 A second schematic flow chart of the method for manufacturing a lithium-ion battery provided in an embodiment of the present application;

[0034] Figure 4 A third schematic flow chart of the method for manufacturing a lithium-ion battery provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and in detail describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0037] In order to produce a long-life lithium-ion battery during the lithium-ion manufacturing stage, the embodiments of the present application provide a method, an apparatus, and a battery pack for manufacturing a lithium-ion battery.

[0038] The following first introduces the manufacturing method of the lithium-ion battery provided in the embodiment of the present application.

[0039] Lithium-ion batteries are classified into several types based on the cathode material, including lithium cobalt oxide batteries, lithium manganese oxide batteries, lithium nickel oxide batteries, ternary materials batteries, lithium iron phosphate batteries, lithium iron manganese phosphate batteries, or batteries that combine these materials (ternary mixed lithium iron phosphate batteries, ternary mixed lithium iron manganese phosphate batteries). Lithium-ion batteries are also classified by their appearance into various structures, including rectangular parallelepiped (prismatic cells), prismatic, cylindrical (cylindrical cells), and pouch (soft-pack cells).

[0040] After battery assembly is complete, the first specific charge and discharge cycle of the battery is called formation. Battery formation is a key step in transforming a battery from a "semi-finished product" to a "usable state." It affects the battery's initial performance and long-term reliability and is an indispensable part of the battery manufacturing process.

[0041] During the battery formation process, the present application proposes monitoring at least one of the following parameters: charging current, charge cut-off state of charge, ambient temperature, ambient humidity, and cell pressure.

[0042] During their research and development, the inventors discovered that using different formation process parameters for lithium-ion batteries of the same specifications resulted in different service lives. Based on this, the inventors developed a method for producing lithium-ion batteries with longer lifespans by determining the formation process parameters based on the corresponding relationship between the battery's formation process parameters and its service life.

[0043] To facilitate subsequent explanations, let's first introduce a few common terms in this field:

[0044] The battery in this application generally refers to a lithium-ion battery unless otherwise specified.

[0045] Battery life includes calendar life and cycle life. Calendar life refers to the time from when a battery leaves the factory until it expires. Cycle life refers to the number of cycles after repeated charge and discharge before the battery's capacity drops to the point where it can no longer meet usage requirements.

[0046] Unless otherwise specified, battery life in this application generally refers to cycle life. Specifically, a battery is tested for a certain number of charge and discharge cycles. When the ratio of the current capacity to the initial capacity reaches a preset threshold, such as 80% or 75%, the number of cycles is recorded as the battery's service life.

[0047] like Figure 1 As shown, Figure 1 A schematic flow chart of a method for manufacturing a lithium-ion battery according to some embodiments of the present application. The method comprises:

[0048] S10, obtaining a first network model, the first network model representing the corresponding relationship between the formation process parameters and the battery life;

[0049] S20, obtaining a preset chemical formation process parameter set, where the chemical formation process parameter set includes a plurality of chemical formation process parameters;

[0050] S30, inputting the chemical formation process parameters into the first network model respectively to obtain a first predicted service life corresponding to the chemical formation process parameters;

[0051] S40, determining a formation process parameter corresponding to a first predicted service life that is not less than a preset first service life threshold as a target formation process parameter, and performing a formation operation on the lithium ion battery to be manufactured using the target formation process parameter to manufacture a lithium ion battery.

[0052] The first network model is a pre-trained network model. The first network model learns the corresponding relationship between the formation process parameters and the battery life. The first network model can characterize the corresponding relationship between the formation process parameters and the battery life. The present application obtains the first network model and a preset formation process parameter set, and then inputs each formation process parameter in the preset formation process parameter set into the first network model respectively. Because the first network model has learned the corresponding relationship between the formation process parameters and the battery life, a first predicted service life corresponding to each formation process parameter is obtained based on the first network model, and then the formation process parameter corresponding to the first predicted service life that is not less than the preset first service life threshold is determined as the target formation process parameter. In the formation process of the lithium-ion battery, the formation process parameter that makes the service life of the lithium ion meet the first service life threshold is selected to form the lithium-ion battery to produce a lithium-ion battery with a longer life. There is no need to set a complex battery life extension strategy in the battery management system and the energy management system.

[0053] In one example, after obtaining the first predicted service life corresponding to each formation process parameter based on the first network model, the first predicted service life that is not less than the preset first service life threshold is used as the target predicted service life, and the formation process parameter corresponding to the target predicted service life is determined as the target formation process parameter.

[0054] In some embodiments of the present application, in order to manufacture a lithium-ion battery with a longer life, it is necessary to pre-construct a network model, the pre-constructed network model is a preset first network model, and the preset first network model is trained.

[0055] In some embodiments of the present application, the preset first network model includes one or more of a convolutional neural network, a fully connected neural network, a recurrent neural network, a long short-term memory neural network, an attention mechanism, and a Transformer (a deep learning model based on a self-attention mechanism). In one example, the preset first network model is a fully connected neural network.

[0056] The following introduces the formation process parameter method of lithium-ion batteries.

[0057] First, obtain a sample battery set.

[0058] The sample battery set includes a plurality of sample batteries, and the sample batteries in the sample battery set are grouped according to a preset division rule to obtain a plurality of sample battery groups, wherein the preset division rule is determined based on battery information, and the battery information includes battery specification information.

[0059] In some embodiments of the present application, the battery specifications include at least one of the specification information such as the type of battery, the capacity of the battery, etc. In some embodiments of the present application, the type of battery is divided into multiple battery types according to different battery electrolyte components, different positive and negative electrode compositions, and different isolation membranes, and the capacity of the battery is divided into multiple battery capacities according to the capacity size. In one example, the battery specifications include the type of battery, and when the sample batteries in the sample battery set are grouped based on the battery specifications, the sample batteries of the same battery type are divided into the same group. In another example, the battery specifications include the capacity of the battery, and when the sample batteries in the sample battery set are grouped based on the battery specifications, the sample batteries of the same battery capacity are divided into the same group. In another example, the battery specifications include the type of battery and the capacity of the battery, and when the sample batteries in the sample battery set are grouped based on the battery specifications, the sample batteries of the same battery type and / or the same battery capacity are divided into the same group.

[0060] Next, a sample data set is determined based on the sample battery set.

[0061] The sample data set includes multiple pieces of sample data, each piece of sample data includes battery information of a sample battery, formation process parameters of the sample battery, and the service life of the sample battery.

[0062] The battery information of the sample battery is preset, and the battery information of the sample battery is obtained after the sample battery is obtained.

[0063] After the sample batteries in the sample battery set are grouped according to a preset division rule, a plurality of sample battery groups are obtained, wherein each sample battery group includes a plurality of sample batteries.

[0064] For each sample battery pack, different formation process parameters are used to perform formation operations on the sample batteries in the group. The formation process parameters include at least one of the following parameters: charging current, charge end state of charge, ambient temperature, ambient humidity, and battery cell pressure. The formation process parameters include parameters under each formation cycle. Figure 2 As shown, Figure 2 A typical three-stage formation strategy and a schematic diagram of the recording parameters are shown. In the figure, I is the charging current.

[0065] Each sample battery is then cycled until the battery capacity decays to a preset threshold value of the initial capacity, for example, 80%, at which point the cycle is terminated and the number of cycles at this point is recorded as the battery's service life.

[0066] In some embodiments of the present application, the conditions under which the sample battery is subjected to the formation operation are not limited to temperature, charge / discharge rate, ambient humidity, and the like. The formation process of the lithium-ion battery is not limited to single cycle, double cycle, or multi-cycle, and is not limited to charging schemes such as constant current charging, constant current constant voltage charging, multi-stage constant current charging, and pulse charging. The positive and negative electrode materials of the lithium-ion battery can be any positive and negative electrode materials of a lithium-ion battery.

[0067] When cycling each sample battery, the cycling test conditions are not limited to temperature, charge / discharge rate, ambient humidity, and other conditions. The charge / discharge scheme includes a charging scheme and a discharging scheme. The charging scheme includes at least one of the following charging methods: constant current charging, constant current constant voltage charging, multi-stage constant current charging, or pulse charging. The discharging scheme includes at least one of the following discharging methods: constant current discharge, pulse discharge, or dynamic current discharge.

[0068] In some embodiments of the present application, each charging method further includes at least one charging rate.

[0069] In some embodiments of the present application, each discharge mode further includes at least one discharge rate.

[0070] For each sample battery, the battery information, formation process parameters, and service life of the sample battery are used as a piece of sample data, and a sample data set is established based on each sample data. Then, a preset first network model is trained based on the sample data set.

[0071] The preset first network model is trained using the formation process parameters of the sample battery in each sample data of the sample data set and the service life of the sample battery, so that the preset first network model learns the corresponding relationship between the formation process parameters of the sample battery and the service life of the sample battery, so as to establish a mapping relationship between the formation process parameters of the battery and the service life of the battery, and obtain a trained first network model.

[0072] In some embodiments of the present application, a formation process parameter set is pre-acquired. The formation process parameter set includes multiple formation process parameters. For example, the formation process parameters include four parameters: charging current, charge-cutoff state of charge, ambient temperature, and cell pressure. Using charging current, charge-cutoff state of charge, ambient temperature, and cell pressure as combination conditions, all possible parameter combinations of the four parameters are listed, with each parameter combination corresponding to a formation process parameter.

[0073] Each formation process parameter is input into a first network model to obtain a first predicted service life corresponding to each formation process parameter. The formation process parameter corresponding to the first predicted service life that is not less than a preset first service life threshold is determined as a target formation process parameter. The preset first service life threshold is determined based on actual conditions and is not limited in this application.

[0074] A first network model and a preset formation process parameter set are obtained, and each formation process parameter in the preset formation process parameter set is respectively input into the first network model. Based on the correspondence between the formation process parameters and the battery service life learned by the first network model, a first predicted service life corresponding to each formation process parameter is obtained. The formation process parameter corresponding to the first predicted service life that is not less than a preset first service life threshold is determined as a target formation process parameter. In this way, during the formation process of the lithium-ion battery, the formation process parameter that makes the service life of the lithium ions meet the first service life threshold is selected to form the lithium-ion battery, and in the lithium-ion manufacturing stage, a lithium-ion battery with a longer service life is manufactured.

[0075] In some embodiments of the present application, after obtaining the first predicted service life corresponding to each formation process parameter, the formation process parameter corresponding to the longest first predicted service life is determined as the target formation process parameter.

[0076] The target formation process parameters are the formation process parameters corresponding to the longest first predicted service life, which is equivalent to selecting an optimal formation process parameter from various formation process parameters, and then forming the lithium-ion battery based on the optimal formation process parameter to further manufacture a lithium-ion battery with a longer service life.

[0077] Furthermore, during the research and development process, the inventors discovered that the capacity decay of lithium-ion batteries can lead to changes in the battery's performance parameters, which include at least one of the following: voltage, current, temperature, magnetic field, and electrochemical impedance. Based on this, the inventors further developed a method for manufacturing long-life lithium-ion batteries by determining formation process parameters based on the corresponding relationship between battery performance parameters and battery life, as well as the corresponding relationship between battery formation process parameters and battery life.

[0078] To this end, it is necessary to construct another network model in advance, that is, a preset second network model, and train the preset second network model.

[0079] In some embodiments of the present application, the preset second network model includes one or more of a convolutional neural network, a fully connected neural network, a recurrent neural network, a long short-term memory neural network, an attention mechanism, and a Transformer (a deep learning model based on a self-attention mechanism). In one example, the second network model is a long short-term memory neural network model with an attention mechanism.

[0080] In the above embodiment, when forming operations are performed on each group of sample batteries using different forming process parameters, performance parameters of the sample batteries during the forming process are obtained.

[0081] The performance parameters of the sample battery include at least one of the following performance parameters: voltage, current, temperature, magnetic field data, and electrochemical impedance data.

[0082] The magnetic field data is recorded by a magnetic field device, and the magnetic field data includes at least one of the following data: magnetic induction intensity, magnetic field distribution, and magnetic field line direction.

[0083] During the formation process, the voltage, current, temperature, and magnetic field data of the sample battery are collected randomly according to the collection conditions or according to a preset time period, or data is collected within a certain time period according to a preset time period. The preset time period is determined based on actual conditions and is not limited here.

[0084] The electrochemical impedance spectroscopy data include the electrochemical impedance spectroscopy data at the start of charging, the electrochemical impedance spectroscopy data at the end of charging, and the electrochemical impedance spectroscopy data at the charge rate turning point.

[0085] For each sample battery, the battery information of the sample battery, the performance parameters of the sample battery, and the service life of the sample battery are taken as a piece of sample data, and a sample data set is established based on each piece of sample data.

[0086] The performance parameters of the sample battery in each piece of sample data and the service life of the sample battery are used to train a preset second network model, so that the preset second network model learns the corresponding relationship between the performance parameters of the sample battery and the service life of the sample battery, so as to establish a mapping relationship between the performance parameters of the battery and the service life of the battery, and obtain a trained second network model.

[0087] like Figure 3 As shown, in some embodiments of the present application, the method further includes:

[0088] S50, obtaining a second network model,

[0089] Step S40 includes the following steps:

[0090] Step S401, selecting a first formation process parameter set, wherein the first predicted service life corresponding to all formation process parameters in the first formation process parameter set is not less than a preset first service life threshold, and determining a formation process parameter to be selected from the first formation process parameter set;

[0091] Step S402, forming the unformed battery to be tested using the formation process parameters to be selected, and obtaining performance parameters of the battery to be tested;

[0092] Step S403: Inputting the performance parameters of the battery to be tested into the second network model to obtain a second predicted service life of the battery to be tested. The second network model learns the corresponding relationship between the battery performance parameters and the battery service life. The second network model characterizes the corresponding relationship between the performance parameters and the battery service life.

[0093] Step S404 , taking the second predicted service life that is not less than the preset first service life threshold as the target predicted service life, and determining the chemical formation process parameters corresponding to the target predicted service life as the target chemical formation process parameters.

[0094] After obtaining the first predicted service life corresponding to each formation process parameter based on the first network model, the present application selects some formation process parameters from each formation process parameter as the formation process parameters to be selected based on the size of each first predicted service life.

[0095] In some embodiments of the present application, the formation process parameters corresponding to the first predicted service life that meets the preset service life requirement are used as the formation process parameters to be selected. Exemplary, a preset second service life threshold value is set, each first predicted service life is compared with the preset second service life threshold value, and the formation process parameters corresponding to the first predicted service life that is not less than the preset second service life threshold value are used as the formation process parameters to be selected. For example, a total of 100 formation process parameters are included, the preset second service life threshold value is 10000 cycles, and the formation process parameters corresponding to the first predicted service life that is not less than 10000 cycles are used as the formation process parameters to be selected.

[0096] In some other embodiments of the present application, from each formation process parameter, select the formation process parameter of preset number as formation process parameter to be selected. Exemplary, each first predicted service life is sorted in the order from long to short, and the formation process parameter corresponding to the first predicted service life positioned at the front preset number is used as formation process parameter to be selected. For example, the preset number is 10, which includes 100 formation process parameters in total, obtains the first predicted service life corresponding to 100 formation process parameters, and each first predicted service life is sorted in the order from long to short, and the formation process parameter corresponding to the first predicted service life positioned at the front 10 is used as formation process parameter to be selected.

[0097] A method of selecting some of the formation process parameters from various formation process parameters as the formation process parameters to be selected is specifically set based on actual conditions.

[0098] After selecting the formation process parameters to be selected based on the first predicted service life, the unformed battery to be tested is formed using the formation process parameters to be selected, and performance parameters of the battery to be tested are obtained. The service life of the battery to be tested is predicted by the second network model. The above-mentioned battery to be tested is an unformed battery, and the battery to be formed based on the formation process parameters to be selected in the next step. In this way, the formation process parameters corresponding to a service life not less than a preset first service life threshold are selected as target formation process parameters through the two models. In this way, during the formation process of the lithium-ion battery, the formation process parameters that make the service life of the lithium ions meet the first service life threshold are selected to form the lithium-ion battery, so as to manufacture a lithium-ion battery with a long service life.

[0099] In some embodiments of the present application, a formation process parameter corresponding to a first predicted service life that is not less than a preset second service life threshold is used as a formation process parameter to be selected. In one example, the preset first service life threshold is the same as the preset second service life threshold, and in another example, the preset first service life threshold is different from the preset second service life threshold.

[0100] In one example, the preset second service life threshold is equal to the preset first service life threshold. For the target formation process parameters, the first network model and the second network model predict that the service life corresponding to the target formation process parameters is greater than the preset first service life threshold, thereby improving the accuracy of ensuring that the service life corresponding to the selected target formation process parameters is not less than the preset first service life threshold. In this way, during the formation process of the lithium-ion battery, the formation process parameters that make the service life of the lithium ions meet the first service life threshold are selected to form the lithium-ion battery, so as to manufacture a lithium-ion battery with a long life.

[0101] In one example, the preset second service life threshold is greater than the preset first service life threshold. For example, the preset first service life threshold is 10,000 cycles, and the preset second service life threshold is 11,000 cycles. First, the formation process parameters with a number of cycles of not less than 11,000 are used as the formation process parameters to be selected, and the unformed battery to be tested is formed using the to-be-selected formation process parameters, and the performance parameters of the battery to be tested are obtained. The performance parameters of the battery to be tested are input into the second network model, and the probability that the second predicted service life of the battery to be tested is greater than the preset first service life threshold based on the second network model is increased, thereby increasing the possibility of determining that the target formation process parameters meet the service life requirements while reducing the amount of calculation.

[0102] In one example, the second service life threshold is preset to be no greater than the first service life threshold, for example, the first service life threshold is preset to be 10,000 cycles, and the second service life threshold is preset to be 9,000 cycles, and the formation process parameters that are no less than the preset second service life threshold (9,000 cycles) are used as the formation process parameters to be selected. Specifically, the formation process parameters corresponding to the first predicted service life of 9,000-10,000 cycles are selected as the formation process parameters to be selected, and then the formation process parameters corresponding to the second predicted service life that is no less than the preset first service life threshold are selected by the second network model to be determined as the target formation process parameters, so as to avoid the formation process parameters that meet the requirements from being determined as the target formation process parameters due to inaccurate first network model algorithm.

[0103] In some embodiments of the present application, the first predicted service lives are sorted from longest to shortest, and the first predicted service lives of the first formation process parameter set are ranked before a preset number of formation process parameters as the formation process parameters to be selected.

[0104] Taking the formation process parameters corresponding to the first predicted service life of the preset number as the formation process parameters to be selected is equivalent to giving priority to selecting the formation process parameters with relatively long service life as the formation process parameters to be selected. This not only improves the possibility of determining the formation process parameters corresponding to the first predicted service life that meet the requirements, but also tries to select the formation process parameters with relatively long service life of the lithium-ion battery, and further manufactures lithium-ion batteries with longer service life.

[0105] like Figure 4 As shown, in some embodiments of the present application, the above step S402 is implemented by the following steps:

[0106] Step S4021, selecting an unselected formation process parameter from the to-be-selected formation process parameters as the current formation process parameter, forming an unformed battery to be tested using the current formation process parameter, and obtaining performance parameters of the battery to be tested;

[0107] The above step S404 is implemented by the following steps:

[0108] Step S4041, determining whether the second predicted service life is not less than a preset first service life threshold, if so, executing step S4042, if not, executing step S4043;

[0109] Step S4042: determining the current forming process parameters as target forming process parameters.

[0110] Step S4043, return to step S4021, continue to execute S4021, step S403, step S4041 until the preset end condition is met.

[0111] In some embodiments of the present application, if the second predicted service life is not less than the preset first service life threshold, the current formation process parameters are determined as target formation process parameters, and it is determined that the preset end conditions are met, or after traversing all the formation process parameters to be selected, one or more target formation process parameters are obtained, and it is determined that the preset end conditions are met.

[0112] The process ends when a target forming process parameter is determined, or ends when all the forming process parameters in the forming process parameter set are traversed and all the target forming process parameters are found.

[0113] In some embodiments of the present application, the current chemical formation process parameters corresponding to the longest second predicted service life are determined as target chemical formation process parameters.

[0114] In some embodiments of the present application, a formation process parameter that has not been selected in the first formation process parameter set and corresponds to the longest first predicted service life is used as the current formation process parameter; and the unformed battery to be tested is formed using the current formation process parameter, and performance parameters of the battery to be tested are obtained;

[0115] Inputting the performance parameters of the battery to be tested into the second network model, and obtaining a second predicted service life of the battery to be tested based on the second network model;

[0116] Determining whether the second predicted service life is not less than a preset first service life threshold;

[0117] If so, the current formation process parameters are determined as the target formation process parameters. If not, return to the step and use the formation process parameters that have not been selected in the first formation process parameter set and correspond to the longest first predicted service life as the current formation process parameters, and continue to execute until the preset end condition is met.

[0118] The chemical formation process parameters with the longest second predicted service life are preferentially selected as the current chemical formation process parameters, thereby shortening the time for determining the target chemical formation process parameters and improving efficiency.

[0119] In some embodiments of the present application, when multiple target formation process parameters are obtained, the formation process parameter to be tested corresponding to the second predicted service life with the longest service life and not less than the preset first service life threshold requirement is used as the target formation process parameter.

[0120] If multiple target formation process parameters are obtained, the formation process parameters to be tested corresponding to the second predicted service life that has the longest service life and is not less than the preset first service life threshold requirement are the optimized formation process parameters, and the lithium-ion battery is formed based on the optimal formation process parameters to improve the service life of the manufactured lithium-ion battery.

[0121] In some embodiments of the present application, step S40 includes the following steps:

[0122] Forming the unformed battery to be tested using various formation process parameters, and obtaining performance parameters of the battery to be tested;

[0123] The performance parameters are input into the second network model to obtain a second predicted service life of the battery to be tested; the second network model characterizes the corresponding relationship between the performance parameters and the battery service life,

[0124] For each formation process parameter, calculating the difference between a second predicted service life corresponding to the formation process parameter and a first predicted service life corresponding to the formation process parameter;

[0125] If the difference is not greater than a preset difference threshold, the chemical formation process parameter is determined as the target chemical formation process parameter.

[0126] The preset difference threshold is determined based on actual conditions. If the difference is not greater than the preset difference threshold, it indicates that the error of the first predicted service life obtained based on the prediction of the first network model is not large. Because the formation process parameter to be selected is the formation process parameter corresponding to the first predicted service life that is not less than the preset first service life threshold, the service life corresponding to the formation process parameter to be selected meets the preset first service life threshold requirement. In the formation process of the lithium ion battery, the formation process parameter that makes the service life of the lithium ions meet the first service life threshold is selected to form the lithium ion battery to produce a lithium ion battery with a longer life.

[0127] In some embodiments of the present application, the method further includes:

[0128] Obtain a sample data set, the sample data set includes multiple sample data, each sample data includes a formation process parameter of a sample battery and a service life of the sample battery,

[0129] The preset first network model is trained using the formation process parameters of the sample battery in each sample data and the service life of the sample battery, so that the preset first network model learns the corresponding relationship between the formation process parameters of the sample battery and the service life of the sample battery, thereby obtaining a trained first network model.

[0130] The preset first network model is trained by the following steps:

[0131] Step 001: Obtain an unused sample data, input the formation process parameters of the sample battery of the unused sample data and the service life of the sample battery into a preset first network model for training, and obtain the predicted service life of the sample data;

[0132] Step 002, calculating a loss function of a first network model based on the predicted service life of the sample data and the service life of a sample battery corresponding to the sample;

[0133] Step 003, adjust the parameters of the first network model according to the loss function; determine whether the training end condition is met. If not, then determine another unused sample data from the sample data set and continue training the preset first network model until it is not less than the preset first training end condition, thereby obtaining a trained first network model.

[0134] In some embodiments of the present application, the preset first training end condition is set according to actual conditions, such as reaching a preset number of training times, the loss of the network model converging, or the prediction accuracy of the network model being greater than a preset accuracy threshold.

[0135] The preset second network model is trained by the following steps:

[0136] Step 01: Obtain an unused sample data, input the performance parameters of the sample battery of the unused sample data and the service life of the sample battery into a preset second network model for training, and obtain the predicted service life of the sample data;

[0137] Step 02, calculating the loss function of the second network model according to the predicted service life of the sample data and the service life of the sample battery corresponding to the sample;

[0138] Step 03, adjust the parameters of the second network model according to the loss function; determine whether the training end condition is met. If not, then determine another unused sample data from the sample data set and continue training the preset second network model until it is not less than the preset second training end condition, thereby obtaining a trained second network model.

[0139] In some embodiments of the present application, the preset second training end condition is set according to actual conditions, such as reaching a preset number of training times, the loss of the network model converging, or the prediction accuracy of the network model being greater than a preset accuracy threshold.

[0140] The present application provides a model training device, which is used to implement any of the above-mentioned methods for manufacturing lithium-ion batteries.

[0141] In some embodiments of the present application, the device includes:

[0142] A first acquisition module is configured to acquire a first network model; the first network model represents the correspondence between the formation process parameters and the battery life;

[0143] A second acquisition module is configured to acquire a preset chemical formation process parameter set, wherein the chemical formation process parameter set includes: a plurality of chemical formation process parameters;

[0144] a processing module configured to input a formation process parameter into a first network model to obtain a first predicted service life corresponding to the formation process parameter;

[0145] The determination module is configured to determine the formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold as the target formation process parameters, and perform a formation operation on the lithium ion battery to be manufactured using the target formation process parameters to manufacture the lithium ion battery.

[0146] In some embodiments of the present application, the determination module is specifically configured to:

[0147] Selecting a first formation process parameter set, wherein first predicted service lives corresponding to all formation process parameters in the first formation process parameter set are not less than a preset first service life threshold;

[0148] The chemical formation process parameter corresponding to the longest first predicted service life in the first chemical formation process parameter set is determined as the target chemical formation process parameter.

[0149] In some embodiments of the present application, the determination module is specifically configured to:

[0150] Selecting a first formation process parameter set, wherein first predicted service lives corresponding to all formation process parameters in the first formation process parameter set are not less than a preset first service life threshold;

[0151] Determining a to-be-selected chemical formation process parameter from a first chemical formation process parameter set;

[0152] Forming the unformed battery to be tested using the selected formation process parameters, and obtaining performance parameters of the battery to be tested;

[0153] Inputting the performance parameters into the second network model to obtain a second predicted service life of the battery to be tested;

[0154] The to-be-selected formation process parameters corresponding to the second predicted service life that is not less than the preset first service life threshold are determined as target formation process parameters; wherein the second network model characterizes the corresponding relationship between the performance parameters and the battery service life.

[0155] In some embodiments of the present application, the determination module is specifically configured to:

[0156] using the chemical formation process parameters corresponding to the first predicted service life that is not less than the preset second service life threshold as the chemical formation process parameters to be selected; or

[0157] In descending order of the first predicted service life, the formation process parameters with the first predicted service life being in the first preset number in the first formation process parameter set are selected as the formation process parameters to be selected.

[0158] In some embodiments of the present application, the determination module is specifically configured to:

[0159] The to-be-selected chemical formation process parameters corresponding to the longest second predicted service life are determined as target chemical formation process parameters.

[0160] In some embodiments of the present application, the determination module is specifically configured to:

[0161] The to-be-selected chemical formation process parameters corresponding to the second predicted service life having the longest service life and not less than the preset first service life threshold are used as target chemical formation process parameters.

[0162] In some embodiments of the present application, the determination module is specifically configured to:

[0163] Using a formation process parameter in the first formation process parameter set that has not been selected and corresponds to the longest first predicted service life as a current formation process parameter;

[0164] Determining the selected chemical formation process parameters corresponding to the second predicted service life that is not less than the preset first service life threshold as target chemical formation process parameters includes:

[0165] Determine whether the second predicted service life is not less than the preset first service life threshold. If so, determine the current formation process parameter as the target formation process parameter; if not, return to the step and use the formation process parameter that has not been selected in the first formation process parameter set and corresponds to the longest first predicted service life as the current formation process parameter, and continue to execute until the second predicted service life is not less than the preset first service life threshold; or the first formation process parameter set is traversed.

[0166] In some embodiments of the present application, the determination module is specifically configured to:

[0167] Forming the unformed battery to be tested using various formation process parameters, and obtaining performance parameters of the battery to be tested;

[0168] The performance parameters are input into the second network model to obtain a second predicted service life of the battery to be tested; the second network model characterizes the corresponding relationship between the performance parameters and the battery service life,

[0169] For each formation process parameter, calculating the difference between a second predicted service life corresponding to the formation process parameter and a first predicted service life corresponding to the formation process parameter;

[0170] If the difference is not greater than a preset difference threshold, the chemical formation process parameter is determined as the target chemical formation process parameter.

[0171] In some embodiments of the present application, the apparatus further comprises:

[0172] The sample acquisition module is configured to: acquire a sample data set, wherein the sample data set includes a plurality of sample data, each sample data including a formation process parameter of a sample battery and a service life of the sample battery;

[0173] The training module is configured to: use the formation process parameters of the sample battery in each sample data of the sample data set and the service life of the sample battery to train a preset first network model, so that the preset first network model learns the correspondence between the formation process parameters of the sample battery and the service life of the sample battery, and obtains a trained first network model.

[0174] The present application also provides a battery pack, which includes any of the above-mentioned lithium-ion battery manufacturing devices.

[0175] The present application also provides an electronic device, such as Figure 5 As shown, it includes a processor 601 , a communication interface 602 , a memory 603 and a communication bus 604 , wherein the processor 601 , the communication interface 602 , and the memory 603 communicate with each other via the communication bus 604 .

[0176] Memory 603, used for storing computer programs;

[0177] The processor 601 is configured to execute the program stored in the memory 603 by performing the following steps:

[0178] Obtaining a first network model, where the first network model represents a corresponding relationship between formation process parameters and battery life;

[0179] Obtaining a preset chemical formation process parameter set, where the chemical formation process parameter set includes: multiple chemical formation process parameters;

[0180] Inputting the chemical formation process parameters into the first network model to obtain a first predicted service life corresponding to the chemical formation process parameters;

[0181] The formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold are determined as target formation process parameters, and the target formation process parameters are used to perform a formation operation on the lithium ion battery to be manufactured to obtain the lithium ion battery.

[0182] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0183] The communication interface is used for communication between the above electronic device and other devices.

[0184] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0185] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0186] In another embodiment provided in the present application, a computer-readable storage medium is further provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, any of the above-mentioned methods for manufacturing a lithium-ion battery is implemented.

[0187] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any of the methods for manufacturing a lithium-ion battery in the above embodiments.

[0188] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0189] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0190] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, the embodiments of the device, battery pack, electronic device, computer-readable storage medium, and computer program product containing instructions are generally similar to the method embodiments, so their description is relatively simple. For related portions, refer to the description of the method embodiments.

[0191] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the scope of protection of the present application.

Claims

1. A method for manufacturing a lithium-ion battery, characterized in that: The method comprises: Obtaining a first network model, wherein the first network model represents a corresponding relationship between a formation process parameter and a battery service life; Obtaining a preset chemical formation process parameter set, wherein the chemical formation process parameter set includes: a plurality of chemical formation process parameters; Inputting the chemical formation process parameters into the first network model to obtain a first predicted service life corresponding to the chemical formation process parameters; The formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold are determined as target formation process parameters, and the target formation process parameters are used to perform a formation operation on the lithium ion battery to be manufactured to obtain the lithium ion battery.

2. The method according to claim 1, characterized in that The step of determining the chemical formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold as target chemical formation process parameters includes: Selecting a first formation process parameter set, wherein first predicted service lives corresponding to all formation process parameters in the first formation process parameter set are not less than a preset first service life threshold; The chemical formation process parameter corresponding to the longest first predicted service life in the first chemical formation process parameter set is determined as the target chemical formation process parameter.

3. The method according to claim 1, characterized in that The step of determining the chemical formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold as target chemical formation process parameters includes: Selecting a first formation process parameter set, wherein first predicted service lives corresponding to all formation process parameters in the first formation process parameter set are not less than a preset first service life threshold; Determining a to-be-selected chemical formation process parameter from the first chemical formation process parameter set; Forming an unformed battery to be tested using the formation process parameters to be selected, and obtaining performance parameters of the battery to be tested; Inputting the performance parameter into a second network model to obtain a second predicted service life of the battery to be tested; The selected formation process parameters corresponding to the second predicted service life that is not less than the preset first service life threshold are determined as target formation process parameters; wherein the second network model characterizes the corresponding relationship between the performance parameters and the battery service life.

4. The method according to claim 3, characterized in that The determining of the to-be-selected chemical formation process parameters from the first chemical formation process parameter set includes: using the chemical formation process parameters corresponding to the first predicted service life that is not less than the preset second service life threshold as the chemical formation process parameters to be selected; or According to the first predicted service life from longest to shortest, the formation process parameters whose first predicted service life is located in the first set of formation process parameters are selected as the formation process parameters to be selected.

5. The method according to claim 3, characterized in that The step of determining the selected chemical formation process parameter corresponding to the second predicted service life that is not less than the preset first service life threshold as the target chemical formation process parameter includes: The to-be-selected chemical formation process parameters corresponding to the longest second predicted service life are determined as target chemical formation process parameters.

6. The method according to claim 5, characterized in that The step of determining the selected chemical formation process parameters corresponding to the longest second predicted service life as target chemical formation process parameters includes: The to-be-selected chemical formation process parameters corresponding to the second predicted service life having the longest service life and not less than the preset first service life threshold are used as target chemical formation process parameters.

7. The method according to claim 3, characterized in that The determining of the to-be-selected chemical formation process parameters from the first chemical formation process parameter set includes: Using a formation process parameter in the first formation process parameter set that has not been selected and corresponds to the longest first predicted service life as a current formation process parameter; The step of determining the selected chemical formation process parameter corresponding to the second predicted service life that is not less than the preset first service life threshold as the target chemical formation process parameter includes: Determine whether the second predicted service life is not less than the preset first service life threshold. If so, determine the current formation process parameter as the target formation process parameter; if not, return to the step and use the formation process parameter that has not been selected in the first formation process parameter set and corresponds to the longest first predicted service life as the current formation process parameter, and continue to execute until the second predicted service life is not less than the preset first service life threshold; or the first formation process parameter set is traversed.

8. The method according to claim 1, characterized in that The step of determining the chemical formation process parameters corresponding to the first predicted service life that is not less than the preset first service life threshold as target chemical formation process parameters includes: Using the formation process parameters to form an unformed battery to be tested, and obtaining performance parameters of the battery to be tested; The performance parameters are input into a second network model to obtain a second predicted service life of the battery to be tested; the second network model represents the corresponding relationship between the performance parameters and the battery service life, For each formation process parameter, calculating the difference between a second predicted service life corresponding to the formation process parameter and a first predicted service life corresponding to the formation process parameter; If the difference is not greater than a preset difference threshold, the chemical formation process parameter is determined as the target chemical formation process parameter.

9. A lithium ion battery manufacturing device, characterized in that: The device is used to implement the method for manufacturing a lithium-ion battery according to any one of claims 1 to 8.

10. A battery pack, characterized in that: A lithium-ion battery manufacturing device comprising the device as claimed in claim 9.

Images