Electrolyte design method, device, equipment, medium and program product
Through high-throughput calculation and component prediction model, the problems of high experimental cost and low efficiency in electrolyte design are solved, the low-cost and efficient design of electrolyte is realized, and the electrolyte design process is simplified.
Patent Information
- Application Number
- CN202111492691.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-08
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2041-12-08
AI Technical Summary
In the prior art, the electrolyte design method requires a lot of experiments, resulting in a long R&D cycle, high cost, poor mobility, and it is difficult to summarize the internal laws of electrolyte design.
Using high-throughput calculation methods and component prediction models, we simulate multiple electrolytes through simulation models, calculate their physical and chemical parameters, create training samples, train component prediction models, and then predict the component information of the electrolyte to be designed to achieve low cost of the electrolyte , efficient design.
It reduces the experimental cost and time of electrolyte design, improves design efficiency, and can directly design electrolyte components that meet the requirements according to performance requirements, achieving a low-cost and efficient electrolyte design.
Smart Images

Figure CN114255826B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of secondary batteries, and in particular, relates to an electrolyte design method, device, equipment, computer storage medium and computer program product. Background Art
[0002] In recent years, as the application scope of secondary batteries represented by lithium-ion batteries has become more and more extensive, lithium-ion batteries are widely used in energy storage power systems such as hydropower, thermal power, wind power and solar power stations, as well as power tools, electric bicycles, electric motorcycles, electric vehicles, military equipment, aerospace and other fields. As secondary ion batteries have made great progress, higher requirements have been put forward for their energy density, cycle performance and safety performance.
[0003] The electrolyte is an important component of secondary batteries, playing the role of conducting active ions and insulating electrons. The positive and negative active materials determine the theoretical capacity of the secondary battery, but its charging and discharging rate, long cycle performance and other performance are closely related to the electrolyte. From the development history of lithium-ion battery technology, the choice of electrolyte system largely determines the success of secondary batteries. Therefore, the development of advanced electrolytes is one of the cores of developing the next generation of secondary battery technology.
[0004] However, due to the complex composition of the electrolyte, a lot of work is often required to design an electrolyte that meets actual needs. Summary of the invention
[0005] The embodiments of the present application provide an electrolyte design method, device, equipment, computer storage medium and computer program product, which can achieve high-efficiency and low-cost design of the electrolyte.
[0006] In a first aspect, an embodiment of the present application provides an electrolyte design method, the method comprising:
[0007] Obtaining first physical and chemical parameters of the electrolyte to be designed;
[0008] Inputting the first physical and chemical parameter into a trained component prediction model, and predicting the component information of the electrolyte to be designed by the component prediction model to obtain the component information of the electrolyte to be designed, wherein the component prediction model is trained by training samples obtained based on a high-throughput computing method;
[0009] The electrolyte to be designed is designed according to the component information of the electrolyte to be designed.
[0010] In some embodiments of the first aspect, before inputting the first physicochemical parameter into the trained composition prediction model and predicting the composition information of the electrolyte to be designed by the composition prediction model to obtain the composition information of the electrolyte to be designed, the method further includes:
[0011] Simulating a plurality of first electrolytes with different composition information through a pre-trained simulation model;
[0012] Calculating the first electrolyte using a high-throughput calculation method to obtain a second physical and chemical parameter corresponding to the first electrolyte;
[0013] Creating training samples using the second physicochemical parameter of each first electrolyte and the component information of each first electrolyte respectively;
[0014] The component prediction model is trained according to a plurality of training samples until a training stop condition is met, thereby obtaining a trained component prediction model.
[0015] In some embodiments of the first aspect, training a component prediction model according to a plurality of training samples until a training stop condition is met to obtain a trained component prediction model includes:
[0016] For each training sample, perform the following steps:
[0017] Inputting the training sample into a preset component prediction model to obtain predicted component information corresponding to the second physicochemical parameter;
[0018] Determining a loss function value of a composition prediction model according to the predicted composition information and the composition information of the first electrolyte;
[0019] When the loss function value does not meet the training stop condition, the model parameters of the component prediction model are adjusted, and the component prediction model with the adjusted parameters is trained using training samples until the training stop condition is met, thereby obtaining a trained component prediction model.
[0020] In some embodiments of the first aspect, the high-throughput computational method comprises at least one of density functional theory calculations, molecular dynamics simulations, and finite element calculations.
[0021] In some embodiments of the first aspect, the first physicochemical parameter includes at least one of a physicochemical parameter of a solvent molecule constituting the electrolyte and a physicochemical parameter of the electrolyte.
[0022] In some embodiments of the first aspect, the physicochemical parameters of the solvent molecules constituting the electrolyte include at least one of the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point of the solvent molecules.
[0023] In some embodiments of the first aspect, the physicochemical parameters of the electrolyte include at least one of the dielectric constant, viscosity, melting point, boiling point, and ionic conductivity of the electrolyte.
[0024] In some embodiments of the first aspect, the ingredient information includes material composition and ratio.
[0025] In some embodiments of the first aspect, the component prediction model includes at least one of a linear regression analysis model, a logistic regression analysis model, a support vector machine, a nearest neighbor algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
[0026] In some embodiments of the first aspect, the electrolyte to be designed includes an aqueous electrolyte and a non-aqueous electrolyte.
[0027] In some embodiments of the first aspect, the electrolyte to be designed includes a solvent, an electrolyte salt, and optional additives.
[0028] The solvent includes one or more organic small molecules, and the organic small molecules are composed of at least two elements of C, H, O, N, F, Cl, S, P, and B;
[0029] The electrolyte salt includes at least one of hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, perchlorate, sulfate, sulfite, and hexafluoroarsenate, and the cation in the electrolyte salt is selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of;
[0030] The optional additives include at least one of a film-forming additive, a flame retardant additive, an anti-overcharge additive, an overcharge protection additive, and a multifunctional additive.
[0031] In a second aspect, an embodiment of the present application provides an electrolyte design device, the device comprising:
[0032] An acquisition module, used for acquiring the first physical and chemical parameters of the electrolyte to be designed;
[0033] A prediction module, used for inputting the first physical and chemical parameter into a trained component prediction model, predicting the component information of the electrolyte to be designed through the component prediction model, and obtaining the component information of the electrolyte to be designed, wherein the component prediction model is trained by training samples obtained based on a high-throughput computing method;
[0034] The design module is used to design the electrolyte to be designed according to the component information of the electrolyte to be designed.
[0035] In a third aspect, an embodiment of the present application provides an electrolyte design device, the device comprising: a processor and a memory storing computer program instructions;
[0036] When the processor executes the computer program instructions, the electrolyte design method as described in any embodiment of the first aspect of the present application is implemented.
[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, an electrolyte design method as in any embodiment of the first aspect of the present application is implemented.
[0038] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the electrolyte design method as described in any embodiment of the first aspect of the present application.
[0039] The electrolyte design method, device, equipment, computer storage medium, and computer program product of the embodiments of the present application can obtain the composition information corresponding to the physical and chemical parameters by inputting the physical and chemical parameters of the electrolyte into the composition prediction model. In this way, without the need for actual experimental work, the composition of the electrolyte can be designed according to the performance requirements of the electrolyte to obtain an electrolyte that meets the performance requirements. In addition, since the training samples of the composition prediction model are obtained based on a high-throughput computing method, there is no need to conduct a large number of experiments to obtain training samples, which reduces the experimental cost. The embodiments of the present application can achieve low-cost and high-efficiency electrolyte design. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0041] Figure 1 It is a schematic diagram of a flow chart of an electrolyte design method provided by an embodiment of the present application;
[0042] Figure 2 is a flow chart of an electrolyte design method provided by another embodiment of the present application;
[0043] Figure 3 is a structural schematic diagram of an electrolyte design device provided in yet another embodiment of the present application;
[0044] Figure 4It is a structural schematic diagram of an electrolyte design device provided in yet another embodiment of the present application. DETAILED DESCRIPTION
[0045] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.
[0046] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0047] As described in the background art, in the prior art, designing electrolytes often requires a large number of experiments. For example, researchers need to design the material composition and ratio of a variety of different electrolytes based on experience, and then verify the performance of the electrolytes, or optimize the formula based on existing electrolytes. The inventors found that the electrolyte design method of the prior art not only has a long R&D cycle, high cost, and poor mobility, but also makes it difficult to summarize the inherent laws of electrolyte design and development.
[0048] In the biological field, high throughput screening (HTS) technology refers to a technical system that is based on experimental methods at the molecular and cellular levels, uses microplates as experimental tool carriers, executes the experimental process with an automated operating system, collects experimental result data with sensitive and fast detection instruments, analyzes and processes experimental data with computers, detects tens of millions of samples at the same time, and supports the operation with the corresponding database obtained. It has the characteristics of trace, rapid, sensitive and accurate. In short, it can obtain a lot of information through one experiment and find valuable information from it.
[0049] After extensive research, the inventors found that applying high-throughput computational methods based on high-throughput screening to electrolyte design can effectively reduce experimental costs and obtain the intrinsic connection between electrolyte composition information and performance.
[0050] In order to solve the problems of the prior art, the embodiments of the present application provide an electrolyte design method, device, equipment, computer storage medium and computer program product.
[0051] The electrolyte design method provided in the embodiment of the present application is introduced below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.
[0052] Figure 1 A flow chart of an electrolyte design method provided in one embodiment of the present application is shown, which may specifically be a training method for a component prediction model used in the electrolyte design method provided in an embodiment of the present application.
[0053] like Figure 1 As shown, the composition prediction model used in the electrolyte design method provided in the embodiment of the present application may include steps S110 to S140.
[0054] S110, simulating a plurality of first electrolytes having different composition information through a pre-trained simulation model.
[0055] S120, calculating the first electrolyte using a high-throughput calculation method to obtain a second physical and chemical parameter corresponding to the first electrolyte.
[0056] S130, creating training samples using the second physicochemical parameter of each first electrolyte and the component information of each first electrolyte.
[0057] S140, training a component prediction model according to a plurality of training samples until a training stop condition is met, thereby obtaining a trained component prediction model.
[0058] In an embodiment of the present application, a plurality of electrolytes with different composition information are simulated by a simulation model, and then the electrolytes simulated by the simulation model are calculated by a high-throughput calculation method to obtain the second physicochemical parameters corresponding to the first electrolyte, and the composition information of each first electrolyte and the corresponding second physicochemical parameters are respectively used to construct training samples, so that the composition prediction model can be trained to obtain a trained composition prediction model. Then, the physicochemical parameters of the electrolyte to be designed can be processed based on the trained composition prediction model to obtain the composition information of the electrolyte to be designed, and the electrolyte can be designed according to the composition information of the electrolyte to be designed, thereby realizing low-cost and efficient design of the electrolyte.
[0059] The training process of the component prediction model is described in detail below.
[0060] First, step S110 is introduced, in which a plurality of first electrolytes having different composition information are simulated by a pre-trained simulation model.
[0061] The simulation model may be a commonly used simulation model in the prior art, for example, a simulation model constructed and trained by at least one of an analog computer, a digital computer, and a hybrid computer. As an example, the simulation model may be a simulation model constructed and trained by an analog computer, and specifically, the simulation model may be used to obtain electrolyte calculation workflows with multiple scales such as material composition and material ratio, thereby simulating multiple electrolytes with different component information.
[0062] In an optional embodiment, the first electrolyte may include an aqueous electrolyte and a non-aqueous electrolyte. As an example, the first electrolyte may include an electrolyte with water as a solvent and an organic electrolyte with an organic substance as a solvent. In an optional embodiment, the first electrolyte may include an electrolyte used in a lithium ion battery, a lithium metal battery, a sodium ion battery, a sodium metal battery, a potassium ion battery, a potassium metal battery, a magnesium ion battery, a magnesium metal battery, a calcium ion battery, a calcium metal battery, a zinc ion battery, a zinc metal battery, an aluminum ion battery, and an aluminum metal battery.
[0063] In an optional embodiment, the first electrolyte may include a solvent, an electrolyte salt and optional additives.
[0064] The solvent may include one or more organic small molecules, and the organic small molecules are composed of at least two elements of C, H, O, N, F, Cl, S, P, and B.
[0065] The electrolyte salt may include at least one of hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride salt, chloride salt, bromide salt, iodide salt, difluorophosphate, difluoro oxalate borate, dioxalate borate, tetrafluoro oxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, perchlorate, sulfate, sulfite, hexafluoroarsenate, and the cation in the electrolyte salt is selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of .
[0066] The optional additives may include at least one of a film-forming additive, a flame retardant additive, an overcharge prevention additive, an overcharge protection additive, and a multifunctional additive.
[0067] The component information may be information related to the composition of the electrolyte. In an optional implementation, the component information may include the composition and ratio of substances in the electrolyte.
[0068] By simulating the above-mentioned first electrolytes with different composition information through the simulation model, a large amount of comprehensive information related to the electrolyte can be obtained, so that more comprehensive training samples can be obtained in the subsequent steps. In this way, the trained composition prediction model can be applied to the design of various secondary battery electrolytes, improving the applicability of the composition prediction model.
[0069] Then, step S120 is introduced, in which the first electrolyte is calculated using a high-throughput calculation method to obtain a second physical and chemical parameter corresponding to the first electrolyte.
[0070] In step S120, the second physicochemical parameters corresponding to the first electrolyte are parameters of physical and chemical properties related to the performance of the first electrolyte.
[0071] In an optional embodiment, the second physicochemical parameter may include at least one of the physicochemical parameters of the solvent molecules constituting the electrolyte and the physicochemical parameters of the electrolyte.
[0072] Specifically, the physicochemical parameters of the solvent molecules constituting the electrolyte may include the physicochemical parameters of the solvent molecules in a non-solution environment, such as the physicochemical parameters when in a vacuum environment, and may also include the physicochemical parameters of the solvent molecules in a solution environment, such as the physicochemical parameters when in an electrolyte. In an optional embodiment, the physicochemical parameters of the solvent molecules constituting the electrolyte may include at least one of the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point of the solvent molecules.
[0073] In an optional embodiment, the physicochemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ionic conductivity of the electrolyte.
[0074] The high-throughput calculation method may include multiple calculation methods. In an optional embodiment, the high-throughput calculation method includes at least one of density functional theory calculation, molecular dynamics simulation and finite element calculation.
[0075] For ease of understanding, some implementations of the high-throughput computing method in this application are exemplified below. It should be noted that the following examples are only for explaining this application, not for limiting this application.
[0076] As an example of using density functional theory to calculate the physicochemical parameters of electrolyte solvent molecules under a vacuum environment, for 1,2-dimethoxyethane (DME) molecules, the initial geometric configuration of the DME molecule can be first constructed using GaussView software; then the Gaussian16 software can be used to optimize the constructed initial geometric configuration of the DME molecule and calculate the relevant physicochemical properties on the optimal structure. The specific method used is density functional theory, the basis set is 6-311++G(d,p), and the functional is B3LYP; then the vibration frequency analysis can be used to determine that the obtained optimized structure is the ground state structure, and the NBO charge is used to analyze the charge distribution of the DME molecule; finally, the geometric structure (bond length, bond angle, dihedral angle), electronic structure (NBO charge distribution), thermodynamic energy, electron affinity, dipole moment, Raman spectrum, infrared spectrum, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energy levels, redox potential and other physicochemical parameters of the optimized DME molecule can be analyzed.
[0077] As an example of using molecular dynamics simulation to calculate the dielectric constant and viscosity of an electrolyte solvent, for 1,3-dioxolane (DOL), Packmol software can be used to construct a DOL solvent model containing multiple solvent molecules. For example, a DOL solvent model containing 1000 solvent molecules can be constructed; then LAMMPS software can be used to perform molecular dynamics simulation on the DOL solvent model. The simulation process can include the following steps (1) to (4).
[0078] (1) An isothermal and isobaric ensemble (NPT ensemble) calculation was performed at 298 K, with a pressure of 1 atm, a time of 3 ns, and a time step of 1 fs;
[0079] (2) The temperature was raised from 298 K to 400 K, the ensemble was NPT, the pressure was 1 atm, the heating rate was 20 K / ns, and finally the temperature was kept constant at 400 K for 2 ns, with a time step of 1 fs.
[0080] (3) Cooling from 400 K to 298 K, the ensemble is NPT, the pressure is 1 atm, the cooling rate is 20 K / ns, and finally the temperature is maintained at 298 K for 5 ns, with a time step of 1 fs.
[0081] (4) Canonical ensemble (NVT ensemble) calculations were performed at 298 K with a time of 10 ns and a time step of 1 fs.
[0082] The molecular dynamics simulation based on the second half of the NVT calculation trajectory is used to calculate the dielectric constant and viscosity of the DOL solvent. The dielectric constant calculation formula is:
[0083]
[0084] Where ε is the dielectric constant, ε0 is the dielectric constant of vacuum, is the total dipole moment of the system, T is the temperature, V is the volume of the electrolyte, k B is the Boltzmann constant.
[0085] The viscosity calculation formula is:
[0086]
[0087] Where η is the viscosity, T is the temperature, V is the volume of the electrolyte, and k B is the Boltzmann constant, P xz The system pressure.
[0088] As an example of using density functional theory to calculate the physicochemical parameters of solvent molecules in electrolyte under solution environment, for dimethyl carbonate (DMC) molecule, GaussView software can be used to construct the initial geometric configuration of DMC molecule; then Gaussian16 software can be used to optimize the constructed initial geometric configuration of DMC molecule, and calculate the relevant physicochemical properties on the optimal structure. The specific method used is density functional theory, the basis set is 6-311++G(d,p), the functional is B3LYP, and the implicit solvation model (SMD solvation model) is used to describe the solution environment. The dielectric constant of the SMD solvation model can be obtained by molecular dynamics simulation calculation; then the vibration frequency analysis can be used to determine that the obtained optimized structure is the ground state structure, and the NBO charge analysis is used to analyze the charge distribution of DMC molecule; finally, the geometric structure (bond length, bond angle, dihedral angle), electronic structure (NBO charge distribution), thermodynamic energy, electron affinity, dipole moment, Raman spectrum, infrared spectrum, HOMO and LUMO energy levels, redox potential and other physicochemical parameters of the optimized DMC molecule can be analyzed. Combined with the physicochemical parameters of electrolyte solvent molecules under vacuum environment calculated by density functional theory, we can compare the differences in physicochemical parameters of solvent molecules in vacuum environment and solution environment, and based on the differences in these physicochemical parameters, explore the intrinsic relationship between the electrolyte solvent environment and the physicochemical parameters of solvent molecules in the electrolyte.
[0089] As an example of using density functional theory to calculate the physicochemical parameters of the ion-solvent structure formed by the electrolyte solvent molecules and cations in solution environment, for propylene carbonate (PC) molecules and Li + First, we can use GaussView software to construct PC molecules and Li + The formed Li + -PC ion-solvent initial structure, specifically, the initial structure constructed includes PC molecules and Li +All possible structures formed; then the Gaussian16 software can be used to construct the Li + -PC's ion-solvent initial structure is optimized, and the relevant physical and chemical properties are calculated on the optimal structure. The specific method used is density functional theory, the basis set is 6-311++G(d,p), the functional is B3LYP, and the SMD solvation model is used to describe the solution environment. The dielectric constant of the SMD solvation model can be obtained by molecular dynamics simulation calculation; then the vibration frequency analysis can be used to determine that the obtained optimized structure is the ground state structure, and the NBO charge analysis Li + -PC charge distribution; finally, the optimized PC molecule geometry (bond length, bond angle, dihedral angle), electronic structure (NBO charge distribution), thermodynamic energy, electron affinity, dipole moment, Raman spectrum, infrared spectrum, HOMO and LUMO energy levels, redox potential and other physical and chemical parameters can be analyzed. Combined with the physical and chemical parameters of the electrolyte solvent molecules in the solution environment calculated by density functional theory, the PC molecule can be compared with Li + The differences in physicochemical parameters before and after the action are studied, and based on this, the intrinsic relationship between the interaction between solvent molecules and cations in the electrolyte and the physicochemical parameters of the solvent molecules is studied.
[0090] As an example of using molecular dynamics simulation to calculate the physicochemical parameters of an electrolyte, for a DOL / DME electrolyte of lithium bis(trifluoromethanesulfonyl)imide (LiTFSI), Packmol software can be used to first construct a solvent model comprising a plurality of DOL solvent molecules and DME solvent molecules. Specifically, a solvent model comprising 500 DOL molecules and 500 DME molecules can be constructed, and 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 LiTFSI molecules are added thereto, respectively, to obtain a LiTFSI DOL / DME electrolyte model. Then, LAMMPS software can be used to perform molecular dynamics simulation on the LiTFSI DOL / DME electrolyte model, and the simulation process may include the following steps (1) to (4).
[0091] (1) NPT ensemble calculations were performed at 298 K, with a pressure of 1 atm, a time of 3 ns, and a time step of 1 fs;
[0092] (2) The temperature was raised from 298 K to 400 K, the ensemble was NPT, the pressure was 1 atm, the heating rate was 20 K / ns, and finally the temperature was kept constant at 400 K for 2 ns, with a time step of 1 fs.
[0093] (3) Cooling from 400 K to 298 K, the ensemble is NPT, the pressure is 1 atm, the cooling rate is 20 K / ns, and finally the temperature is maintained at 298 K for 5 ns, with a time step of 1 fs.
[0094] (4) NVT ensemble calculations were performed at 298 K with a duration of 10 ns and a time step of 1 fs.
[0095] The molecular dynamics simulation based on the second half of the NVT calculation trajectory was used to calculate the dielectric constant, viscosity and ionic conductivity of the DOL / DME solvent. The dielectric constant calculation formula is:
[0096]
[0097] Where ε is the dielectric constant, ε0 is the dielectric constant of vacuum, is the total dipole moment of the system, T is the temperature, V is the volume of the electrolyte, k B is the Boltzmann constant.
[0098] The viscosity calculation formula is:
[0099]
[0100] Where η is the viscosity, T is the temperature, V is the volume, and k B is the Boltzmann constant, P xy The system pressure.
[0101] The formula for calculating ionic conductivity is:
[0102]
[0103] Where D is the ionic conductivity, t is the time, d is the diffusion dimension (the value of three-dimensional diffusion is 3), N is the number of lithium ions, and r i is the displacement of the i-th lithium ion.
[0104] Based on the calculation results, the effect of lithium salt concentration on the dielectric constant, viscosity and ionic conductivity of LiTFSI DOL / DME electrolyte can be analyzed.
[0105] As an example of using the finite element method to simulate and calculate the physicochemical parameters of the electrolyte, for the DOL / DME electrolyte of lithium bistrifluoromethanesulfonyl imide (LiTFSI) for lithium metal batteries, first, similar steps to the above-mentioned example of using molecular dynamics simulation to calculate the dielectric constant, viscosity and ionic conductivity of the electrolyte can be used to calculate the physicochemical parameters such as the dielectric constant, viscosity and ionic conductivity of the DOL / DME electrolyte of 0.1-4.0 mol / L (every 0.1 mol / L); after the physicochemical parameters of the above LiTFSI DOL / DME electrolyte are input as input parameters into the finite element calculation model, the COMSOL software can be used to perform finite element simulation on the LiTFSI DOL / DME electrolyte model to calculate the lithium ion concentration distribution, electric field distribution and metal lithium negative electrode deposition or release morphology in the electrolyte at 0.1, 0.5, 1.0, 2.0, 5.0, 10.0C charge or discharge rates. Furthermore, the coulombic efficiency during the battery cycle can be calculated based on the morphology of the metal lithium negative electrode during charging and discharging. Based on the calculation results, the effects of lithium salt concentration and charge and discharge rate on the lithium ion concentration distribution, electric field distribution, metal lithium negative electrode morphology and coulombic efficiency of LiTFSIDOL / DME electrolyte can be analyzed.
[0106] As an example of using multiple high-throughput computing methods to automatically calculate the physicochemical parameters of electrolytes, for fluoroethylene carbonate (FEC) molecules used in lithium battery electrolytes, the physicochemical parameters of the FEC molecules in a vacuum environment can be first calculated using density functional theory; then the physicochemical parameters of the FEC molecules in a vacuum environment can be used as input for molecular dynamics simulation, and the physicochemical parameters of the FEC solvent, such as the dielectric constant and viscosity, can be calculated using steps similar to the above example of using molecular dynamics simulation to calculate the dielectric constant and viscosity of the electrolyte solvent; then the physicochemical parameters of the FEC molecules in a vacuum environment can be used as parameters of the solvation model, and the physicochemical parameters of the FEC molecules in a solution environment can be calculated using steps similar to the above example of using density functional theory to calculate the physicochemical parameters of the solvent molecules in the electrolyte under a solution environment, and the Li can be calculated using steps similar to the above example of using density functional theory to calculate the physicochemical parameters of the ion-solvent structure formed by the electrolyte solvent molecules and the cations under a solution environment. +-The physicochemical parameters of the ion-solvent structure of FEC in a solution environment; the solvation structure, ion conductivity, viscosity, dielectric constant and other physicochemical parameters of the FEC electrolyte in which LiTFSI, LiFSI and LiPF6 are dissolved can be calculated by a method similar to the above-mentioned example of using molecular dynamics simulation to calculate the physicochemical parameters of the electrolyte; the lithium ion concentration distribution, electric field distribution, metal lithium negative electrode morphology and coulomb efficiency and other physicochemical parameters of the FEC electrolyte in which LiTFSI, LiFSI and LiPF6 are dissolved during the charge and discharge process can be calculated by a method similar to the above-mentioned example of using finite element simulation to calculate the physicochemical parameters of the electrolyte.
[0107] As an example of using multiple high-throughput calculation methods to simultaneously calculate the physicochemical parameters of electrolytes, high-throughput calculation of lithium battery electrolytes is used as an example for explanation. First, small molecule structure models can be extracted in batches from existing small molecule databases (such as GDB-11 or GDB-13 databases); then the calculation method in the above-mentioned example of using density functional theory, molecular dynamics simulation and finite element automated calculation methods to calculate the physicochemical parameters of electrolytes can be used to simultaneously calculate the physicochemical parameters of each small molecule and the corresponding electrolyte in high throughput; and then a large database of lithium battery electrolytes can be constructed, including the geometric structure (bond length, bond angle, dihedral angle) of electrolyte solvent molecules and corresponding ion-solvent structures, electronic structure (NBO charge distribution), thermodynamic energy, electron affinity, dipole moment, Raman spectrum, infrared spectrum, HOMO and LUMO energy levels, redox potential and other physicochemical parameters, as well as ionic conductivity, viscosity, dielectric constant, melting and boiling point and other physicochemical parameters of the electrolyte model.
[0108] In step S120, a large amount of first electrolytes obtained in step S110 can be calculated by a high-throughput calculation method to obtain a large amount of correspondence between electrolyte composition information and physical and chemical parameters. In this way, the processing rate of the correspondence between electrolyte composition information and physical and chemical parameters can be accelerated, the efficiency of electrolyte design can be improved, and the cost of electrolyte design can be saved.
[0109] Next, step S130 is introduced, in which the second physicochemical parameter of each first electrolyte and the component information of each first electrolyte are used to create training samples.
[0110] In step S130, the physicochemical parameters obtained by the high-throughput calculation method in step S120 and the corresponding component information can be used to create training samples. If a large number of comprehensive training samples can be obtained, the component prediction model obtained by training will have higher accuracy and wider applicability.
[0111] Finally, step S140 is introduced, in which a component prediction model is trained according to a plurality of training samples until a training stop condition is met, thereby obtaining a trained component prediction model.
[0112] Among them, the component prediction model can be a machine learning model. In an optional embodiment, the component prediction model may include a linear regression analysis model, a logistic regression analysis model, a support vector machine (SVM), a nearest neighbor (KNN) algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, and at least one of the gradient enhancement algorithm model. It is easy to understand that the component prediction model can be any one of the above models, or it can be a model obtained by combining two or more of the above models. As an example, for the various models listed above, the prediction effects of different models can be compared, so as to select a suitable model to achieve accurate prediction of the properties of the electrolyte. For example, the prediction effect of each model on the electrolyte composition information under a specific application scenario (high temperature, low temperature, fast charge, high specific energy, etc.) can be compared, or the prediction effect of each model on the electrolyte composition information corresponding to one or more specific physical and chemical parameters, so as to select a suitable model.
[0113] The above training stop condition may be a pre-set condition for stopping the component prediction model training. As an example, the training stop condition may be that the loss function of the component prediction model is less than a certain threshold, or that the number of iterations of the component prediction model training reaches a certain number. The specific training stop condition may be selected according to user needs and is not limited here.
[0114] In an optional implementation, step S140 may specifically include:
[0115] For each training sample, perform the following steps:
[0116] Inputting the training sample into a preset component prediction model to obtain predicted component information corresponding to the second physicochemical parameter;
[0117] Determining a loss function value of a composition prediction model according to the predicted composition information and the composition information of the first electrolyte;
[0118] When the loss function value does not meet the training stop condition, the model parameters of the component prediction model are adjusted, and the component prediction model with the adjusted parameters is trained using training samples until the training stop condition is met, thereby obtaining a trained component prediction model.
[0119] In an embodiment of the present application, a plurality of electrolytes with different composition information are simulated by a simulation model, which can save a lot of economic and time costs. The electrolyte simulated by the simulation model is calculated by a high-throughput computing method, and the physical and chemical parameters corresponding to the electrolyte can be obtained efficiently and at low cost, thereby creating a training sample. The training samples created by the above process are applied to the training of the composition prediction model, and the obtained composition prediction model can be based on the intrinsic connection between the electrolyte composition information and the performance, and can be processed according to the physical and chemical parameters corresponding to the actual required electrolyte performance, so as to achieve efficient and low-cost design of the electrolyte.
[0120] The following is combined with Figure 2 The electrolyte design method provided in the embodiments of the present application is described in detail.
[0121] Figure 2 A schematic diagram of a flow chart of an electrolyte design method provided in an embodiment of the present application is shown, such as Figure 2 As shown, the data processing method provided in the embodiment of the present application may include steps S210 to S230.
[0122] S210, obtaining first physical and chemical parameters of the electrolyte to be designed.
[0123] The first physicochemical parameter and the second physicochemical parameter have the same meaning, except that the first physicochemical parameter corresponds to the electrolyte performance required in practical applications, and the second physicochemical parameter corresponds to the physicochemical parameter corresponding to the first electrolyte.
[0124] S220, inputting the first physical and chemical parameter into a trained component prediction model, and predicting the component information of the electrolyte to be designed through the component prediction model to obtain the component information of the electrolyte to be designed, wherein the component prediction model is trained by training samples obtained based on a high-throughput computing method.
[0125] The component prediction model is trained based on a plurality of training samples obtained based on a high-throughput computing method, and each training sample may include a second physicochemical parameter of a first electrolyte and component information corresponding to the first electrolyte.
[0126] S230, designing the electrolyte to be designed according to the component information of the electrolyte to be designed.
[0127] In step S230, one or more formulations of the electrolyte to be designed can be determined based on the component information obtained in step S220, and the electrolyte can be configured and experimentally verified. The configuration and verification process of the electrolyte can also be simulated by a computer.
[0128] The electrolyte design method of the embodiment of the present application can obtain the composition information corresponding to the physical and chemical parameters by inputting the physical and chemical parameters of the electrolyte into the composition prediction model. In this way, the composition of the electrolyte can be designed according to the performance requirements of the electrolyte without performing actual experimental work, and an electrolyte that meets the performance requirements can be obtained. In addition, since the training samples of the composition prediction model are obtained based on a high-throughput computing method, there is no need to perform a large number of experiments to obtain training samples, which reduces the experimental cost. The embodiment of the present application can achieve low-cost and high-efficiency electrolyte design.
[0129] In an optional embodiment, the first physicochemical parameter may include at least one of the physicochemical parameters of the solvent molecules constituting the electrolyte and the physicochemical parameters of the electrolyte.
[0130] Specifically, the first physicochemical parameter can be determined by determining the physicochemical parameters of the solvent molecules in the electrolyte to be designed and / or the physicochemical parameters of the electrolyte as a whole according to the performance requirements of the electrolyte to be designed.
[0131] In an optional embodiment, the physicochemical parameters of the solvent molecules constituting the electrolyte may include at least one of the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point of the solvent molecules.
[0132] The physicochemical parameters of the solvent molecules constituting the electrolyte include at least one of the above-mentioned multiple physicochemical parameters, so that the designed electrolyte can better meet the user's expectations in terms of performance, thereby avoiding unnecessary duplication of work and saving experimental costs.
[0133] In an optional embodiment, the physicochemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ionic conductivity of the electrolyte.
[0134] The physicochemical parameters of the electrolyte include at least one of the above-mentioned multiple physicochemical parameters, so that the designed electrolyte can better meet the user's expectations in terms of performance, thereby avoiding unnecessary duplication of work and saving experimental costs.
[0135] In an optional implementation, the component information may include material composition and ratio. In this way, the formula of the electrolyte to be designed can be directly obtained according to the component information of the electrolyte to be designed, further reducing the experimental cost.
[0136] In an optional embodiment, the component prediction model may include at least one of a linear regression analysis model, a logistic regression analysis model, a support vector machine, a nearest neighbor algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
[0137] In an optional embodiment, the electrolyte to be designed may include an aqueous electrolyte and a non-aqueous electrolyte.
[0138] In an optional embodiment, the electrolyte to be designed may include a solvent, an electrolyte salt and optional additives.
[0139] The solvent may include one or more organic small molecules, and the organic small molecules may be composed of at least two elements of C, H, O, N, F, Cl, S, P, and B;
[0140] The electrolyte salt may include at least one of hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride salt, chloride salt, bromide salt, iodide salt, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, perchlorate, sulfate, sulfite, hexafluoroarsenate, and the cation in the electrolyte salt may be selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of;
[0141] The optional additives may include at least one of a film-forming additive, a flame retardant additive, an overcharge prevention additive, an overcharge protection additive, and a multifunctional additive.
[0142] As an example, the optional additives may include one or more organic small molecules composed of carbon, hydrogen, oxygen, nitrogen, fluorine, chlorine, sulfur, phosphorus, and boron elements, and one or more salts such as hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride salt, chloride salt, bromide salt, iodide salt, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazole, perchlorate, sulfate, sulfite, and hexafluoroarsenate. The cation of the above salts may be selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of .
[0143] Based on the same inventive concept, the embodiment of the present application also provides an electrolyte design device 300.
[0144] like Figure 3 As shown, the electrolyte design device 300 may include an acquisition module 301 , an input module 302 and a design module 303 .
[0145] The acquisition module 301 is used to acquire the first physical and chemical parameters of the electrolyte to be designed.
[0146] The prediction module 302 is used to input the first physical and chemical parameter into the trained component prediction model, and predict the component information of the electrolyte to be designed through the component prediction model to obtain the component information of the electrolyte to be designed, wherein the component prediction model is trained by training samples obtained based on a high-throughput computing method.
[0147] The design module 303 is used to design the electrolyte to be designed according to the component information of the electrolyte to be designed.
[0148] In an optional implementation, the apparatus 300 may further include a simulation module, a calculation module, a creation module, and a training module.
[0149] The simulation module is used to simulate a plurality of first electrolytes with different composition information through a pre-trained simulation model.
[0150] The calculation module is used to calculate the first electrolyte using a high-throughput calculation method to obtain a second physical and chemical parameter corresponding to the first electrolyte.
[0151] The creation module is used to create training samples based on the second physicochemical parameter of each first electrolyte and the composition information of each first electrolyte.
[0152] The training module is used to train the component prediction model according to multiple training samples until the training stop condition is met to obtain the trained component prediction model.
[0153] In an optional implementation, the training module is used to train the component prediction model according to a plurality of training samples until a training stop condition is met to obtain a trained component prediction model, which may specifically include:
[0154] For each training sample, perform the following steps:
[0155] Inputting the training sample into a preset component prediction model to obtain predicted component information corresponding to the second physicochemical parameter;
[0156] Determining a loss function value of a composition prediction model according to the predicted composition information and the composition information of the first electrolyte;
[0157] When the loss function value does not meet the training stop condition, the model parameters of the component prediction model are adjusted, and the component prediction model with the adjusted parameters is trained using training samples until the training stop condition is met, thereby obtaining a trained component prediction model.
[0158] In an optional embodiment, the high-throughput computing method may include at least one of density functional theory calculations, molecular dynamics simulations, and finite element calculations.
[0159] In an optional embodiment, the first physicochemical parameter includes at least one of the physicochemical parameters of the solvent molecules constituting the electrolyte and the physicochemical parameters of the electrolyte.
[0160] In an optional embodiment, the physicochemical parameters of the solvent molecules constituting the electrolyte may include at least one of the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point of the solvent molecules.
[0161] In an optional embodiment, the physicochemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ionic conductivity of the electrolyte.
[0162] In an optional implementation, the ingredient information may include material composition and ratio.
[0163] In an optional embodiment, the component prediction model may include at least one of a linear regression analysis model, a logistic regression analysis model, a support vector machine, a nearest neighbor algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
[0164] In an optional embodiment, the electrolyte to be designed may include an aqueous electrolyte and a non-aqueous electrolyte.
[0165] In an optional embodiment, the electrolyte to be designed may include a solvent, an electrolyte salt and optional additives.
[0166] The solvent may include one or more organic small molecules, and the organic small molecules may be composed of at least two elements of C, H, O, N, F, Cl, S, P, and B;
[0167] The electrolyte salt may include at least one of hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride salt, chloride salt, bromide salt, iodide salt, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, perchlorate, sulfate, sulfite, hexafluoroarsenate, and the cation in the electrolyte salt may be selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of;
[0168] The optional additives may include at least one of a film-forming additive, a flame retardant additive, an overcharge prevention additive, an overcharge protection additive, and a multifunctional additive.
[0169] Figure 4 A schematic diagram of the hardware structure of the electrolyte design device provided in an embodiment of the present application is shown.
[0170] The apparatus for electrolyte design may include a processor 401 and a memory 402 storing computer program instructions.
[0171] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0172] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.
[0173] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.
[0174] The processor 401 implements any one of the electrolyte design methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .
[0175] In one example, the electrolyte design device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.
[0176] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0177] Bus 410 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.
[0178] The electrolyte design device can execute the method for designing the electrolyte in the embodiment of the present application based on the first physical and chemical parameters of the electrolyte to be designed, thereby realizing the combination Figure 2 and Figure 3 The electrolyte design method and apparatus are described.
[0179] In addition, in combination with the electrolyte design method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the electrolyte design methods in the above embodiment is implemented.
[0180] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.
[0181] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0182] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.
[0183] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0184] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.
Claims
1. A method for designing an electrolyte, characterized in that: include: Obtaining first physical and chemical parameters of the electrolyte to be designed; Inputting the first physicochemical parameter into a trained component prediction model, and predicting the component information of the electrolyte to be designed by using the component prediction model to obtain the component information of the electrolyte to be designed, wherein the component prediction model is trained by training samples obtained based on a high-throughput computing method; Designing the electrolyte to be designed according to the component information of the electrolyte to be designed; Wherein, before inputting the first physical and chemical parameter into the trained composition prediction model and predicting the composition information of the electrolyte to be designed by the composition prediction model to obtain the composition information of the electrolyte to be designed, the method further includes: Simulating a plurality of first electrolytes with different composition information through a pre-trained simulation model; Calculating the first electrolyte using a high-throughput calculation method to obtain a second physicochemical parameter corresponding to the first electrolyte; Creating training samples using the second physicochemical parameter of each of the first electrolytes and the composition information of each of the first electrolytes; The component prediction model is trained according to the plurality of training samples until a training stop condition is met, thereby obtaining the trained component prediction model.
2. The method according to claim 1, characterized in that The step of training the component prediction model according to the plurality of training samples until a training stop condition is met to obtain the trained component prediction model comprises: For each of the training samples, the following steps are performed respectively: Inputting the training sample into a preset component prediction model to obtain predicted component information corresponding to the second physicochemical parameter; Determining a loss function value of the composition prediction model according to the predicted composition information and the composition information of the first electrolyte; When the loss function value does not meet the training stop condition, the model parameters of the component prediction model are adjusted, and the component prediction model with adjusted training parameters is trained using the training samples until the training stop condition is met, thereby obtaining the trained component prediction model.
3. The method according to claim 1, characterized in that The high-throughput computational method includes at least one of density functional theory calculations, molecular dynamics simulations, and finite element calculations.
4. The method according to claim 1, characterized in that: The first physicochemical parameter includes at least one of a physicochemical parameter of a solvent molecule constituting the electrolyte and a physicochemical parameter of the electrolyte.
5. The method according to claim 4, characterized in that The physicochemical parameters of the solvent molecules constituting the electrolyte include at least one of the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point of the solvent molecules.
6. The method according to claim 4, characterized in that The physicochemical parameters of the electrolyte include at least one of the dielectric constant, viscosity, melting point, boiling point, and ionic conductivity of the electrolyte.
7. The method according to claim 1, characterized in that The ingredient information includes material composition and ratio.
8. The method according to claim 1, wherein: The component prediction model includes at least one of a linear regression analysis model, a logistic regression analysis model, a support vector machine, a nearest neighbor algorithm model, a K-means clustering algorithm model, a decision tree model, a naive Bayes model, a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
9. The method according to any one of claims 1 to 8, characterized in that: The electrolyte to be designed includes an aqueous electrolyte and a non-aqueous electrolyte.
10. The method according to any one of claims 1 to 8, characterized in that: The electrolyte to be designed includes a solvent, an electrolyte salt and optional additives, Wherein, the solvent comprises one or more organic small molecules, and the organic small molecules are composed of at least two elements of C, H, O, N, F, Cl, S, P, and B; The electrolyte salt includes at least one of hexafluorophosphate, bisfluorosulfonyl imide salt, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonyl imide salt, bistrifluoromethanesulfonyl imide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, perchlorate, sulfate, sulfite, and hexafluoroarsenate, and the cation in the electrolyte salt is selected from Li + 、Na + , K + Mg 2+ , Ca 2+ 、Zn 2+ 、Al 3+ At least one of; The optional additives include at least one of a film-forming additive, a flame retardant additive, an anti-overcharge additive, an overcharge protection additive, and a multifunctional additive.
11. An electrolyte design device, characterized in that: The device comprises: An acquisition module, used for acquiring the first physical and chemical parameters of the electrolyte to be designed; A prediction module, used for inputting the first physical and chemical parameter into a trained component prediction model, predicting the component information of the electrolyte to be designed by using the component prediction model, and obtaining the component information of the electrolyte to be designed, wherein the component prediction model is obtained by training with training samples obtained based on a high-throughput computing method; A design module, used for designing the electrolyte to be designed according to the composition information of the electrolyte to be designed; A simulation module, used for simulating a plurality of first electrolytes with different composition information through a pre-trained simulation model; A calculation module, used to calculate the first electrolyte using a high-throughput calculation method to obtain a second physical and chemical parameter corresponding to the first electrolyte; A creation module, used to create training samples using the second physicochemical parameter of each first electrolyte and the composition information of each first electrolyte; The training module is used to train the component prediction model according to multiple training samples until the training stop condition is met to obtain the trained component prediction model.
12. An electrolyte design device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the electrolyte design method as described in any one of claims 1-10 is implemented.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the electrolyte design method according to any one of claims 1 to 10 is implemented.
14. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the electrolyte design method as described in any one of claims 1 to 10.
