Method for designing non-combustible phosphate electrolyte compatible with graphite cathode by utilizing machine learning

Abstract

The invention belongs to the technical field of lithium battery safety, and particularly discloses a method for designing a non-combustible phosphate electrolyte compatible with a graphite cathode by utilizing machine learning, and the method comprises the following steps: inputting a fixed component contained in a target phosphate electrolyte into a machine learning model, and obtaining a first molar ratio critical value of a main solvent and a phosphate solvent, the critical number of phosphate molecules compatible with the graphite negative electrode is represented; setting constraint conditions and an optimization target: setting a first constraint condition based on the first molar ratio critical value, setting a second constraint condition based on the flame retardance of the electrolyte, and setting a third constraint condition based on the ionic conductivity of the electrolyte; maximization of graphite cathode compatibility is taken as a first optimization target, maximization of flame retardance is taken as a second optimization target, and maximization of ion transmission capability is taken as a third optimization target; and based on the set constraint condition and the optimization target, constructing a phosphate ester electrolyte proportioning optimization model and carrying out solving to determine the optimal proportioning of the target phosphate ester electrolyte.

Description

Technical Field

[0001] The present application belongs to the field of lithium battery safety technology, and more specifically, to a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning. Background Art

[0002] Lithium-ion batteries are widely used in 3C electronic products, electric vehicles, energy storage and other fields. However, the electrolyte inside the battery is highly flammable and volatile. In recent years, lithium battery safety accidents caused by electrolytes have occurred frequently. The development of non-flammable electrolytes can not only improve the intrinsic safety of batteries, but also prevent batteries from detonating adjacent batteries after a fire, reduce the risk of secondary disasters, and thus improve the safety of batteries and energy storage systems.

[0003] Phosphate flame retardant solvents have the advantages of low cost, excellent flame retardancy and easy miscibility with existing commercial carbonate electrolytes. They are considered to be an ideal flame retardant solvent for the development of non-flammable electrolytes. However, phosphate flame retardants have strong interactions with lithium ions, are easily present in the main solvation structure shell and participate in the formation of the solid electrolyte interface (SEI) film. Since their products have poor ability to shield electrons, the formed SEI film is difficult to effectively prevent the continuous decomposition of the solvent, which in turn causes the failure of the graphite negative electrode. This limits the development of phosphate-based non-flammable electrolytes. Summary of the invention

[0004] In view of the defects existing in the related art, the embodiment of the present application provides a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning, aiming to solve the problem in the related art that the phosphate electrolyte is prone to cause failure of the graphite negative electrode.

[0005] In a first aspect, an embodiment of the present application provides a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning, comprising:

[0006] Inputting fixed components contained in the target phosphate ester electrolyte into the machine learning model to obtain a first molar ratio critical value of the main solvent and the phosphate ester solvent in the target phosphate ester electrolyte, wherein the first molar ratio critical value is used to characterize the critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when it is compatible with the graphite negative electrode;

[0007] Setting constraints and optimization goals, including: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on the first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte; maximizing the compatibility of the target phosphate electrolyte with the graphite negative electrode as the first optimization goal, maximizing the flame retardancy of the target phosphate electrolyte as the second optimization goal, and maximizing the ion transmission capacity of the target phosphate electrolyte as the third optimization goal;

[0008] Construct a phosphate electrolyte ratio optimization model based on the set constraints and optimization objectives;

[0009] The phosphate ester electrolyte formulation optimization model is solved to determine the optimal ratio of the target phosphate ester electrolyte.

[0010] In some embodiments, whether the phosphate electrolyte is compatible with the graphite negative electrode is characterized by the performance parameters of the graphite negative electrode, and the performance parameters include the first cycle charge and discharge efficiency of the graphite, the reversible capacity and capacity retention rate of the graphite negative electrode during the cycle.

[0011] In some embodiments, the machine learning model is trained based on the following steps:

[0012] Obtaining the molar ratio of the main solvent to the phosphate ester solvent in non-flammable phosphate ester electrolyte samples containing different components and different ratios, and the corresponding performance parameters of the graphite negative electrode;

[0013] Based on the performance parameters of the graphite negative electrode, the critical value of the first molar ratio of the main solvent and the phosphate ester solvent in the non-flammable phosphate ester electrolyte samples containing different components is determined to construct a training sample;

[0014] The machine learning model is trained based on the training samples to learn the mapping relationship between the components contained in the non-flammable phosphate electrolyte sample and the first molar ratio critical value.

[0015] In some embodiments, the target phosphate electrolyte comprises a lithium salt, an organic non-flammable phosphate solvent, an organic carbonate solvent, a low-viscosity organic carbonate solvent, and an additive, wherein the organic carbonate solvent is a main solvent.

[0016] In some embodiments, the flame retardancy of the target phosphate ester electrolyte is characterized by a second molar ratio critical value of the low viscosity organic carbonate solvent and the organic non-flammable phosphate ester solvent, and the ionic conductivity of the target phosphate ester electrolyte is characterized by a third molar ratio critical value of the lithium salt and the organic non-flammable phosphate ester solvent.

[0017] In some embodiments, the first constraint is:

[0018] The molar ratio of the organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is greater than or equal to a first molar ratio critical value;

[0019] The second constraint is:

[0020] The molar ratio of the low-viscosity organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is less than or equal to a second molar ratio critical value;

[0021] The third constraint is:

[0022] The molar ratio of the lithium salt to the organic non-flammable phosphate ester solvent in the target phosphate ester electrolyte is less than or equal to a third molar ratio critical value.

[0023] In some embodiments, the organic non-flammable phosphate ester solvent has the general structural formula:

[0024]

[0025] Here, R1 and R2 are each independently one of an alkyl group having 1 to 10 carbon atoms and a halogenated alkyl group having 1 to 10 carbon atoms, and R3 is an alkyl group having 1 to 10 carbon atoms or an alkoxy group having 1 to 10 carbon atoms.

[0026] In some embodiments, the phosphate electrolyte meets the following requirements when compatible with the graphite negative electrode: the first cycle charge and discharge efficiency of the graphite is ≥85%, the reversible capacity of the graphite negative electrode during the cycle is ≥360 mAh / g, and the capacity retention rate of the graphite negative electrode after 100 cycles is ≥90%.

[0027] In some embodiments, solving a phosphate electrolyte formulation optimization model includes:

[0028] The phosphate electrolyte formulation optimization model was solved using the NSGA-II algorithm.

[0029] In a second aspect, an embodiment of the present application further provides a device for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning, comprising:

[0030] An acquisition module is used to input a fixed component contained in a target phosphate ester electrolyte into a machine learning model to obtain a first molar ratio critical value of a main solvent and a phosphate ester solvent in the target phosphate ester electrolyte, wherein the first molar ratio critical value is used to characterize a critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when it is compatible with a graphite negative electrode;

[0031] A setting module, used to set constraints and optimization targets, including: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on a first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte; maximizing the compatibility of the target phosphate electrolyte with the graphite negative electrode as the first optimization target, maximizing the flame retardancy of the target phosphate electrolyte as the second optimization target, and maximizing the ion transmission capacity of the target phosphate electrolyte as the third optimization target;

[0032] A construction module is used to construct a phosphate electrolyte ratio optimization model based on set constraints and optimization objectives;

[0033] The determination module is used to solve the phosphate ester electrolyte formula optimization model and determine the optimal ratio of the target phosphate ester electrolyte.

[0034] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0035] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0036] In a fifth aspect, an embodiment of the present application further provides a computer program product, which, when executed on a processor, enables the processor to execute the method described in the first aspect or any possible implementation of the first aspect.

[0037] The embodiment of the present application provides a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning. The first molar ratio critical value of the main solvent and the phosphate solvent in a target phosphate electrolyte containing fixed components is obtained by a machine learning model to characterize the critical number of phosphate molecules allowed to exist in the target phosphate electrolyte under the condition of compatibility with the graphite negative electrode; while considering the graphite negative electrode compatibility, flame retardancy and ion transmission capacity of the target phosphate electrolyte, constraints and optimization objectives are set, and a phosphate electrolyte ratio optimization model with multiple constraints and multiple optimization objectives is constructed. The model is solved to obtain the optimal ratio of the target phosphate electrolyte that takes into account the graphite negative electrode compatibility, flame retardancy and ion transmission capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 It is a flow chart of a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning provided in an embodiment of the present application;

[0040] Figure 2 It is a schematic structural diagram of a device for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning provided in an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] Figure 1 is a flow chart of a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning provided in an embodiment of the present application, such as Figure 1 As shown, the method at least includes the following steps:

[0044] S101. Inputting fixed components contained in the target phosphate ester electrolyte into a machine learning model to obtain a first molar ratio critical value of the main solvent and the phosphate ester solvent in the target phosphate ester electrolyte.

[0045] The first molar ratio critical value is used to characterize the critical number of phosphate molecules allowed to exist in the target phosphate electrolyte while being compatible with the graphite negative electrode.

[0046] Specifically, phosphate electrolyte is an electrolyte with phosphate compounds as the main solvent or additive. Phosphate compounds usually have good flame retardant properties; phosphate electrolyte can show good electrochemical stability under a specific salt and solvent molar ratio; phosphate compounds can form a SEI film on the surface of the battery electrode, which helps to inhibit the decomposition of the electrolyte and the corrosion of the electrode.

[0047] However, phosphate flame retardants have strong interactions with lithium ions and are likely to appear in the main solvation structure shell and participate in the formation of the SEI film. However, since their products have poor ability to shield electrons, the SEI film formed is difficult to effectively prevent the continuous decomposition of the solvent, thereby causing failure of the graphite negative electrode.

[0048] Optionally, whether the phosphate electrolyte is compatible with the graphite negative electrode is characterized by the performance parameters of the graphite negative electrode, including the first cycle charge and discharge efficiency of the graphite (ie, coulombic efficiency), the reversible capacity of the graphite negative electrode during the cycle, and the capacity retention rate after a preset number of cycles.

[0049] The compatibility of phosphate ester electrolyte with graphite negative electrode is related to the number of phosphate ester molecules in the electrolyte. At present, the critical number of phosphate ester molecules of phosphate ester electrolyte with fixed components when compatible with graphite negative electrode is generally obtained in the following way: evaluate the compatibility of multiple groups of phosphate ester electrolytes with the same components but different ratios with graphite negative electrode, observe the initial coulombic efficiency, reversible capacity and capacity retention rate of graphite negative electrode during the cycle; then use Raman spectroscopy to analyze the number of phosphate ester molecules in phosphate ester electrolytes with different ratios, construct binary data (performance parameters of graphite negative electrode, number of phosphate ester molecules), and select the critical number of phosphate ester molecules of phosphate ester electrolyte containing the current components.

[0050] However, the cycle of manual screening is long, the process is cumbersome, and the result error is large. Therefore, in the embodiment of the present application, it is considered to use machine learning to clarify the physicochemical properties of the solvent and the interaction between the solvent and lithium ions. At the same time, since the statistics of the critical number of phosphate molecules require strict variable control of phosphate electrolytes with different ratios, it is considered in the embodiment of the present application to characterize the critical number of phosphate molecules by the critical value of the molar ratio between the main solvent and the phosphate solvent in the phosphate electrolyte (referred to as the first molar ratio critical value), thereby reducing statistical requirements and complexity.

[0051] When the molar ratio between the main solvent and the phosphate solvent in the target phosphate electrolyte is greater than or equal to the first molar ratio critical value, it indicates that the target phosphate electrolyte is compatible with the graphite negative electrode. Therefore, constraints can be set based on the first molar ratio critical value to participate in solving the optimal ratio of the phosphate electrolyte compatible with the graphite negative electrode.

[0052] The machine learning model learns the mapping relationship between the components contained in the phosphate ester electrolytes of different components and the first molar ratio critical value of the main solvent and the phosphate ester solvent when compatible with the graphite negative electrode through pre-training. The fixed components contained in the target phosphate ester electrolyte are input into the trained machine learning model, and the first molar ratio critical value of the main solvent and the phosphate ester solvent in the target phosphate ester electrolyte output by the machine learning model is obtained to characterize the critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when compatible with the graphite negative electrode.

[0053] Optionally, when the target phosphate electrolyte is compatible with the graphite negative electrode, it satisfies: the first cycle charge and discharge efficiency of the graphite is ≥85%, the reversible capacity of the graphite negative electrode during the cycle is ≥360mAh / g, and the capacity retention rate of the graphite negative electrode after 100 cycles is ≥90%.

[0054] S102. Set constraints and optimization goals.

[0055] Setting constraints includes: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on a first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte.

[0056] Optimization goals are set, including: maximizing the graphite negative electrode compatibility of the target phosphate ester electrolyte as a first optimization goal, maximizing the flame retardancy of the target phosphate ester electrolyte as a second optimization goal, and maximizing the ion transmission capacity of the target phosphate ester electrolyte as a third optimization goal.

[0057] S103. Construct a phosphate electrolyte ratio optimization model based on the set constraints and optimization objectives.

[0058] Specifically, in the design process of non-flammable phosphate electrolyte compatible with graphite negative electrode, the phosphate electrolyte is pursued to have graphite negative electrode compatibility, flame retardancy (non-flammability) and fast ion transmission capability. Based on this, constraints and optimization objectives are set, and a phosphate electrolyte ratio optimization model with multiple constraints and multiple optimization objectives is constructed.

[0059] Among them, there is a conflict between the compatibility and flame retardancy of the graphite negative electrode of the phosphate electrolyte. It is impossible to maximize them at the same time, and a trade-off solution needs to be found. Ionic conductivity refers to the ability of ions to conduct current in electrolytic salts, reflecting the rate and efficiency of ion migration. Generally speaking, the higher the ionic conductivity, the faster the ion migration in the electrolyte, the better the ion transmission capacity, and the better the conductivity of the electrolyte.

[0060] S104, solving the phosphate ester electrolyte formula optimization model to determine the optimal ratio of the target phosphate ester electrolyte.

[0061] Specifically, by solving a phosphate ester electrolyte formulation optimization model with multiple constraints and multiple optimization objectives, the optimal ratio of the phosphate ester electrolyte containing fixed components is obtained.

[0062] The multi-constraint and multi-optimization target phosphate electrolyte formulation optimization model includes multiple constraints and multiple optimization targets, where there is a conflict between the first optimization target and the second optimization target. There are many ways to solve it, including weighted method, Pareto optimal solution method, genetic algorithm, particle swarm optimization algorithm, etc.

[0063] Preferably, the second generation non-dominated sorting genetic algorithm (NSGA-II) is used to solve the phosphate electrolyte formulation optimization model with multiple constraints and multiple optimization objectives. The core idea of ​​the NSGA-II algorithm is to use a genetic algorithm to find the Pareto frontier of a multi-objective optimization problem. First, the population is non-dominatedly sorted, that is, the population is stratified according to the dominance relationship between the solutions; then the crowding ratio is used to maintain the diversity of the population to ensure that the algorithm can search for a uniformly distributed Pareto optimal solution set.

[0064] The embodiment of the present application provides a method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning. The first molar ratio critical value of the main solvent and the phosphate solvent in the target phosphate electrolyte containing fixed components is obtained by a machine learning model to characterize the critical number of phosphate molecules allowed to exist in the target phosphate electrolyte under the condition of compatibility with the graphite negative electrode; while considering the graphite negative electrode compatibility, flame retardancy and ion transmission capacity of the target phosphate electrolyte, constraints and optimization objectives are set, and a phosphate electrolyte ratio optimization model with multiple constraints and multiple optimization objectives is constructed. The model is solved to obtain the optimal ratio of the target phosphate electrolyte when taking into account the graphite negative electrode compatibility, flame retardancy and ion transmission capacity.

[0065] In some embodiments, the machine learning model in S101 is trained based on the following steps:

[0066] Obtaining the molar ratio of the main solvent to the phosphate ester solvent in non-flammable phosphate ester electrolyte samples containing different components and different ratios, and the corresponding performance parameters of the graphite negative electrode;

[0067] Based on the performance parameters of the graphite negative electrode, the critical value of the first molar ratio of the main solvent and the phosphate ester solvent in the non-flammable phosphate ester electrolyte samples containing different components is determined to construct a training sample;

[0068] The machine learning model is trained based on the training samples to learn the mapping relationship between the components contained in the non-flammable phosphate electrolyte sample and the first molar ratio critical value.

[0069] Specifically, the machine learning model is obtained through pre-training, and the general process of pre-training is: to obtain as many phosphate ester molecules as possible of non-flammable phosphate ester electrolyte samples containing different components and different ratios, as well as the performance parameters of the corresponding graphite negative electrode. Since only non-flammable phosphate ester electrolytes are screened and optimized in the future, only non-flammable phosphate ester electrolyte samples are counted in the pre-training stage of machine learning. Optionally, whether the phosphate ester electrolyte sample is flammable can be evaluated by an ignition test. Optionally, the number of phosphate ester molecules can be obtained by Raman spectroscopy analysis. Specifically, statistics can be performed through a ternary array (non-flammability of phosphate ester electrolyte, performance parameters of graphite negative electrode, number of phosphate ester molecules).

[0070] In order to reduce the statistical requirements, the critical value of the molar ratio between the main solvent and the phosphate solvent (i.e., the first molar ratio critical value) is used to characterize the critical number of phosphate molecules. The performance parameters of the graphite negative electrode are observed, and the first molar ratio critical value of the main solvent and the phosphate solvent in the non-flammable phosphate electrolyte samples of different components is determined to construct training samples. The performance parameters of each non-flammable phosphate electrolyte sample are observed, including the first cycle charge and discharge efficiency of graphite, the reversible capacity of the graphite negative electrode during the cycle, and the capacity retention rate.

[0071] The machine learning model is trained based on the training samples to learn the mapping relationship between the components of the non-flammable phosphate ester electrolyte and the first molar ratio critical value. It is conceivable that, under the premise of strictly controlling the solvent solute content of the non-flammable phosphate ester electrolyte sample, the machine learning model can also be directly used to learn the mapping relationship between the components contained in the non-flammable phosphate ester electrolyte sample and the critical number of phosphate molecules.

[0072] In some embodiments, the phosphate electrolyte comprises a lithium salt, an organic non-flammable phosphate solvent, an organic carbonate solvent A, a low-viscosity organic carbonate solvent B, and an additive. The organic carbonate solvent A is used as the main solvent.

[0073] Optionally, the graphite negative electrode compatibility of the target phosphate electrolyte is characterized by a first molar ratio critical value between the organic carbonate solvent A and the organic non-flammable phosphate solvent. When the molar ratio of the organic carbonate solvent A to the organic non-flammable phosphate solvent in the target phosphate electrolyte is greater than or equal to the first molar ratio critical value, the target phosphate electrolyte is considered to be compatible with the graphite negative electrode. Thus, the first constraint condition is set as: the molar ratio of the organic carbonate solvent A to the organic non-flammable phosphate solvent in the target phosphate electrolyte is greater than or equal to the first molar ratio critical value.

[0074] Optionally, the flame retardancy of the target phosphate electrolyte is characterized by a second molar ratio critical value of the low viscosity organic carbonate solvent B and the organic non-flammable phosphate solvent. When the flame retardancy of the target phosphate electrolyte is characterized by a molar ratio of the low viscosity organic carbonate solvent B and the organic non-flammable phosphate solvent being less than or equal to the second molar ratio critical value, the target phosphate electrolyte is considered to be non-flammable. Thus, the second constraint condition is set as follows: the molar ratio of the low viscosity organic carbonate solvent B and the organic non-flammable phosphate solvent in the target phosphate electrolyte is less than or equal to the second molar ratio critical value.

[0075] Optionally, the ionic conductivity of the target phosphate electrolyte is characterized by a third molar ratio critical value of the lithium salt and the organic non-flammable phosphate ester solvent. When the molar ratio of the lithium salt and the organic non-flammable phosphate ester solvent in the target phosphate ester electrolyte is less than or equal to the third molar ratio critical value, the target phosphate ester electrolyte is considered to have fast ion transport capability. Thus, the third constraint condition is set as follows: the molar ratio of the lithium salt and the organic non-flammable phosphate ester solvent in the target phosphate ester electrolyte is less than or equal to the third molar ratio critical value.

[0076] Wherein, the second molar ratio critical value and the third molar ratio critical value are preset.

[0077] Optionally, the lithium salt is at least one of lithium hexafluorophosphate, lithium difluorophosphate, lithium bis(trifluoromethylsulfonyl)imide, lithium bis(fluorosulfonyl)imide, lithium tetrafluoroborate, and lithium bis(oxalatoborate). Optionally, the concentration of the lithium salt is 0.8 to 2.0 mol / L.

[0078] Optionally, the organic non-flammable phosphate solvent has the general structural formula:

[0079]

[0080] Here, R1 and R2 are each independently one of an alkyl group having 1 to 10 carbon atoms and a halogenated alkyl group having 1 to 10 carbon atoms, and R3 is an alkyl group having 1 to 10 carbon atoms or an alkoxy group having 1 to 10 carbon atoms.

[0081] Optionally, the organic carbonate solvent A is at least one of ethylene carbonate, propylene carbonate and fluoroethylene carbonate.

[0082] Optionally, the low-viscosity organic carbonate solvent B is at least one of dimethyl carbonate, diethyl carbonate, ethyl methyl carbonate, dipropyl carbonate, methyl trifluoroethyl carbonate, and di(2,2,2-trifluoroethyl) carbonate.

[0083] Optionally, the additive is at least one of ethylene carbonate, 1,3-propane sultone, bromobenzene, hexafluorobenzene, bis(2,2,2-trifluoroethyl) ether, 1,1,1,3,3,3-hexafluoroisopropyl methyl ether, 1,1,2,2-tetrafluoroethyl ether-2,2,3,3-tetrafluoropropyl ether, 1,1,2,2-tetrafluoroethyl-2,2,2-trifluoroethyl ether, tris(2,2,2-trifluoroethyl)orthoformate, 1H,1H,5H-octafluoropentyl-1,1,2,2-tetrafluoroethyl ether, 1-(2,2,2-trifluoroethoxy)-1,1,2,2-tetrafluoroethane, hexafluorocyclotriphosphazene, ethoxy(pentafluoro)cyclotriphosphazene, lithium difluorooxalatoborate, lithium dioxalatoborate, vinyl sulfate, 1,3-propane sultone, and lithium difluorodioxyphosphazene.

[0084] Figure 2 is a schematic diagram of the structure of a device for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning provided in an embodiment of the present application, such as Figure 2 As shown, the device at least includes:

[0085] An acquisition module 201 is used to input a fixed component contained in a target phosphate ester electrolyte into a machine learning model to obtain a first molar ratio critical value of a main solvent and a phosphate ester solvent in the target phosphate ester electrolyte, wherein the first molar ratio critical value is used to characterize a critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when it is compatible with a graphite negative electrode;

[0086] A setting module 202 is used to set constraints and optimization targets, including: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on the first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte; maximizing the compatibility of the target phosphate electrolyte with the graphite negative electrode as the first optimization target, maximizing the flame retardancy of the target phosphate electrolyte as the second optimization target, and maximizing the ion transmission capacity of the target phosphate electrolyte as the third optimization target;

[0087] A construction module 203 is used to construct a phosphate electrolyte ratio optimization model based on set constraints and optimization objectives;

[0088] The determination module 204 is used to solve the phosphate ester electrolyte formula optimization model to determine the optimal ratio of the target phosphate ester electrolyte.

[0089] In some embodiments, whether the phosphate electrolyte is compatible with the graphite negative electrode is characterized by the performance parameters of the graphite negative electrode, and the performance parameters include the first cycle charge and discharge efficiency of the graphite, the reversible capacity and capacity retention rate of the graphite negative electrode during the cycle.

[0090] In some embodiments, the machine learning model is trained based on the following steps:

[0091] Obtaining the molar ratio of the main solvent to the phosphate ester solvent in non-flammable phosphate ester electrolyte samples containing different components and different ratios, and the corresponding performance parameters of the graphite negative electrode;

[0092] Based on the performance parameters of the graphite negative electrode, the critical value of the first molar ratio of the main solvent and the phosphate ester solvent in the non-flammable phosphate ester electrolyte samples containing different components is determined to construct a training sample;

[0093] The machine learning model is trained based on the training samples to learn the mapping relationship between the components contained in the non-flammable phosphate electrolyte sample and the first molar ratio critical value.

[0094] In some embodiments, the target phosphate electrolyte comprises a lithium salt, an organic non-flammable phosphate solvent, an organic carbonate solvent, a low-viscosity organic carbonate solvent, and an additive, wherein the organic carbonate solvent is a main solvent.

[0095] In some embodiments, the flame retardancy of the target phosphate ester electrolyte is characterized by a second molar ratio critical value of the low viscosity organic carbonate solvent and the organic non-flammable phosphate ester solvent, and the ionic conductivity of the target phosphate ester electrolyte is characterized by a third molar ratio critical value of the lithium salt and the organic non-flammable phosphate ester solvent.

[0096] In some embodiments, the first constraint is:

[0097] The molar ratio of the organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is greater than or equal to a first molar ratio critical value;

[0098] The second constraint is:

[0099] The molar ratio of the low-viscosity organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is less than or equal to a second molar ratio critical value;

[0100] The third constraint is:

[0101] The molar ratio of the lithium salt to the organic non-flammable phosphate ester solvent in the target phosphate ester electrolyte is less than or equal to a third molar ratio critical value.

[0102] In some embodiments, the organic non-flammable phosphate ester solvent has the general structural formula:

[0103]

[0104] Here, R1 and R2 are each independently one of an alkyl group having 1 to 10 carbon atoms and a halogenated alkyl group having 1 to 10 carbon atoms, and R3 is an alkyl group having 1 to 10 carbon atoms or an alkoxy group having 1 to 10 carbon atoms.

[0105] In some embodiments, the phosphate electrolyte meets the following requirements when compatible with the graphite negative electrode: the first cycle charge and discharge efficiency of the graphite is ≥85%, the reversible capacity of the graphite negative electrode during the cycle is ≥360 mAh / g, and the capacity retention rate of the graphite negative electrode after 100 cycles is ≥90%.

[0106] In some embodiments, the determination module 204 is specifically configured to:

[0107] The phosphate electrolyte formulation optimization model was solved using the NSGA-II algorithm.

[0108] It is understandable that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the above-mentioned method embodiment, and will not be described in detail here. It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment, and the corresponding program module in the device has a similar implementation principle and technical effect as described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, and will not be described in detail here.

[0109] Based on the method in the above embodiment, an embodiment of the present application provides an electronic device. The device may include: at least one memory for storing programs and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the above embodiment.

[0110] Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. The processor 301 may call the software instructions in the memory 303 to execute the method described in the above embodiment.

[0111] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application.

[0112] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0113] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0114] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0115] The method steps in the embodiments of the present application can be implemented by hardware, or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (Random Access Memory, RAM), flash memory, read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, CD-ROMs or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, 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 loading and executing computer program instructions on a computer, the process or function according to 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 devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. 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)), etc.

[0117] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0118] It is easy for those skilled in the art to understand that the above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning, characterized in that: include: Inputting fixed components contained in the target phosphate ester electrolyte into a machine learning model to obtain a first molar ratio critical value of the main solvent and the phosphate ester solvent in the target phosphate ester electrolyte, wherein the first molar ratio critical value is used to characterize the critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when it is compatible with a graphite negative electrode; Setting constraints and optimization targets, including: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on the first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte; maximizing the compatibility of the target phosphate electrolyte with the graphite negative electrode as the first optimization target, maximizing the flame retardancy of the target phosphate electrolyte as the second optimization target, and maximizing the ion transport capacity of the target phosphate electrolyte as the third optimization target; Construct a phosphate electrolyte ratio optimization model based on the set constraints and optimization objectives; The phosphate ester electrolyte formula optimization model is solved to determine the optimal ratio of the target phosphate ester electrolyte.

2. The method according to claim 1, characterized in that Whether the phosphate electrolyte is compatible with the graphite negative electrode is characterized by the performance parameters of the graphite negative electrode, which include the first cycle charge and discharge efficiency of the graphite, the reversible capacity and capacity retention rate of the graphite negative electrode during the cycle.

3. The method according to claim 1, characterized in that The machine learning model is trained based on the following steps: Obtaining the molar ratio of the main solvent to the phosphate ester solvent in non-flammable phosphate ester electrolyte samples containing different components and different ratios, and the corresponding performance parameters of the graphite negative electrode; Based on the performance parameters of the graphite negative electrode, the critical value of the first molar ratio of the main solvent and the phosphate ester solvent in the non-flammable phosphate ester electrolyte samples containing different components is determined to construct a training sample; A machine learning model is trained based on the training samples to learn the mapping relationship between the components contained in the non-flammable phosphate electrolyte sample and the first molar ratio critical value.

4. The method according to claim 1, characterized in that: The target phosphate electrolyte comprises a lithium salt, an organic non-flammable phosphate solvent, an organic carbonate solvent, a low-viscosity organic carbonate solvent and an additive, wherein the organic carbonate solvent is the main solvent.

5. The method according to claim 4, characterized in that The flame retardancy of the target phosphate ester electrolyte is characterized by a second molar ratio critical value of the low-viscosity organic carbonate solvent and the organic non-flammable phosphate ester solvent, and the ionic conductivity of the target phosphate ester electrolyte is characterized by a third molar ratio critical value of the lithium salt and the organic non-flammable phosphate ester solvent.

6. The method according to claim 5, characterized in that The first constraint condition is: The molar ratio of the organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is greater than or equal to the first molar ratio critical value; The second constraint is: The molar ratio of the low-viscosity organic carbonate solvent to the organic non-flammable phosphate solvent in the target phosphate electrolyte is less than or equal to the second molar ratio critical value; The third constraint condition is: The molar ratio of the lithium salt to the organic non-flammable phosphate ester solvent in the target phosphate ester electrolyte is less than or equal to the third molar ratio critical value.

7. The method according to claim 4, characterized in that The general structural formula of the organic non-flammable phosphate solvent is: Here, R1 and R2 are each independently one of an alkyl group having 1 to 10 carbon atoms and a halogenated alkyl group having 1 to 10 carbon atoms, and R3 is an alkyl group having 1 to 10 carbon atoms or an alkoxy group having 1 to 10 carbon atoms.

8. The method according to claim 2, characterized in that: When the phosphate electrolyte is compatible with the graphite negative electrode, the following requirements are met: the first cycle charge and discharge efficiency of the graphite is ≥85%, the reversible capacity of the graphite negative electrode during the cycle is ≥360 mAh / g, and the capacity retention rate of the graphite negative electrode after 100 cycles is ≥90%.

9. The method according to claim 1, characterized in that: The method of solving the phosphate electrolyte formulation optimization model comprises: The phosphate electrolyte formulation optimization model is solved by the NSGA-II algorithm.

10. A device for designing a non-flammable phosphate electrolyte compatible with a graphite negative electrode using machine learning, characterized in that: include: An acquisition module is used to input a fixed component contained in a target phosphate ester electrolyte into a machine learning model to obtain a first molar ratio critical value of a main solvent and a phosphate ester solvent in the target phosphate ester electrolyte, wherein the first molar ratio critical value is used to characterize a critical number of phosphate molecules allowed to exist in the target phosphate ester electrolyte when it is compatible with a graphite negative electrode; A setting module, used to set constraints and optimization targets, including: setting a first constraint that the target phosphate electrolyte is compatible with the graphite negative electrode based on the first molar ratio critical value, setting a second constraint based on the flame retardancy of the target phosphate electrolyte, and setting a third constraint based on the ionic conductivity of the target phosphate electrolyte; maximizing the compatibility of the target phosphate electrolyte with the graphite negative electrode as the first optimization target, maximizing the flame retardancy of the target phosphate electrolyte as the second optimization target, and maximizing the ion transmission capacity of the target phosphate electrolyte as the third optimization target; A construction module is used to construct a phosphate electrolyte ratio optimization model based on set constraints and optimization objectives; The determination module is used to solve the phosphate electrolyte formula optimization model to determine the optimal ratio of the target phosphate electrolyte.

Images