WO2023103150A1 - 电解液设计方法、装置、设备、介质及程序产品 - Google Patents

电解液设计方法、装置、设备、介质及程序产品 Download PDF

Info

Publication number
WO2023103150A1
WO2023103150A1 PCT/CN2022/072387 CN2022072387W WO2023103150A1 WO 2023103150 A1 WO2023103150 A1 WO 2023103150A1 CN 2022072387 W CN2022072387 W CN 2022072387W WO 2023103150 A1 WO2023103150 A1 WO 2023103150A1
Authority
WO
WIPO (PCT)
Prior art keywords
electrolyte
physical
prediction model
model
chemical parameters
Prior art date
Application number
PCT/CN2022/072387
Other languages
English (en)
French (fr)
Inventor
陈翔
张强
姚楠
Original Assignee
清华大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 清华大学 filed Critical 清华大学
Publication of WO2023103150A1 publication Critical patent/WO2023103150A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/10—Analysis or design of chemical reactions, syntheses or processes
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C10/00—Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions

Definitions

  • 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.
  • lithium-ion batteries are widely used in energy storage power systems such as hydraulic, thermal, wind and solar power stations, as well as power tools, electric bicycles, Electric motorcycles, electric vehicles, military equipment, aerospace and other fields. Due to the great development of secondary ion batteries, higher requirements have been put forward for their energy density, cycle performance and safety performance.
  • Electrolyte is an important component of secondary batteries, which plays 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 charge and discharge rate, long cycle performance and other properties are closely related to the electrolyte. From the perspective of the development of lithium-ion battery technology, the choice of electrolyte system largely determines the success of the secondary battery. Therefore, developing advanced electrolytes is one of the technical cores for developing next-generation secondary batteries.
  • Embodiments of the present application provide an electrolyte design method, device, equipment, computer storage medium, and computer program product, which can realize high-efficiency and low-cost design of the electrolyte.
  • the embodiment of the present application provides an electrolyte design method, the method includes:
  • the electrolyte to be designed is designed according to the composition information of the electrolyte to be designed.
  • the method before inputting the first physical and chemical parameters into the trained composition prediction model, predicting the composition information of the electrolyte solution to be designed through the composition prediction model, and obtaining the composition information of the electrolyte solution to be designed, the method further include:
  • the component prediction model is trained until the training stop condition is satisfied, and a trained component prediction model is obtained.
  • the component prediction model is trained according to multiple training samples until the training stop condition is satisfied, and a trained component prediction model is obtained, including:
  • the high throughput computational method includes at least one of density functional theory calculations, molecular dynamics simulations, and finite element calculations.
  • the first physical and chemical parameters include at least one of physical and chemical parameters of solvent molecules constituting the electrolyte and physical and chemical parameters of the electrolyte.
  • the physicochemical parameters of the solvent molecules constituting the electrolyte include the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox potential of the solvent molecule , Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, at least one of boiling point.
  • the physical and chemical parameters of the electrolyte include at least one of dielectric constant, viscosity, melting point, boiling point, and ion conductivity of the electrolyte.
  • the composition information includes material composition and proportion.
  • the component prediction model includes 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 Bayesian model, At least one of a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
  • the electrolyte to be designed includes an aqueous electrolyte and a non-aqueous electrolyte.
  • the electrolyte to be designed includes a solvent, an electrolyte salt and optional additives,
  • the solvent includes one or more organic small molecules, and the organic small molecules are composed of at least two elements in C, H, O, N, F, Cl, S, P, and B;
  • Electrolyte salts include hexafluorophosphate, difluorosulfonyl imide, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate , dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonimide salt, bistrifluoromethanesulfonimide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, high At least one of chlorate, sulfate, sulfite, hexafluoroarsenate, the cation in the electrolyte salt is selected from Li + , Na + , K + , Mg 2+ , Ca 2+ , Zn 2+ , At least one of Al 3+ ;
  • Optional additives include at least one of film-forming additives, flame retardant additives, anti-overcharge additives, overcharge protection additives and multifunctional additives.
  • an electrolyte design device which includes:
  • An acquisition module configured to acquire the first physical and chemical parameters of the electrolyte to be designed
  • the prediction module is used to input the first physical and chemical parameters into the trained composition prediction model, predict the composition information of the electrolyte to be designed through the composition prediction model, and obtain the composition information of the electrolyte to be designed, wherein the composition prediction model is based on Qualcomm
  • the training sample training obtained by the quantity calculation method is obtained;
  • the design module is used to design the electrolyte to be designed according to the composition information of the electrolyte to be designed.
  • the embodiment of the present application provides an electrolyte design device, the device includes: a processor and a memory storing computer program instructions;
  • the electrolyte design method according to any embodiment of the first aspect of the present application is realized.
  • the embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the electrolysis method according to any embodiment of the first aspect of the application is realized. liquid design method.
  • the embodiment of the present application provides a computer program product.
  • the instructions in the computer program product are executed by the processor of the electronic device, the electronic device executes the electrolyte design method according to any embodiment of the first aspect of the present application.
  • 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.
  • the composition of the electrolyte can be designed according to the performance requirements of the electrolyte, and the electrolyte that meets the performance requirements can be obtained.
  • the training samples of the composition prediction model are obtained based on high-throughput computing methods, it is not necessary to conduct a large number of experiments to obtain training samples, which reduces the cost of experiments.
  • the embodiments of the present application can realize low-cost and high-efficiency electrolyte design.
  • Fig. 1 is a schematic flow chart of an electrolyte design method provided by an embodiment of the present application
  • Fig. 2 is a schematic flow chart of an electrolyte design method provided by another embodiment of the present application.
  • FIG. 3 is a schematic structural view of an electrolyte design device provided in another embodiment of the present application.
  • Fig. 4 is a schematic structural diagram of an electrolyte design device provided in another embodiment of the present application.
  • High throughput screening In the field of biology, high throughput screening (High throughput screening, HTS) technology refers to the experimental method based on the molecular level and cellular level, using the microplate form as the experimental tool carrier, using the automated operating system to execute the experimental process, and sensitive
  • the rapid detection instrument collects the experimental result data, analyzes and processes the experimental data with the computer, detects tens of millions of samples at the same time, and supports the operating technical system with the corresponding database.
  • HTS technology has the characteristics of trace, fast, sensitive and accurate. In short, HTS technology can obtain a large amount of information through one experiment, and find valuable information from it.
  • the embodiment of the present application provides an electrolyte design method, device, equipment, computer storage medium and computer program product.
  • Fig. 1 shows a schematic flow chart of the electrolyte design method provided by an embodiment of the present application, specifically, it may be a method for training the component prediction model used in the electrolyte design method provided by the embodiment of the present application.
  • the component prediction model used in the electrolyte design method provided in the embodiment of the present application may include steps S110-S140.
  • S130 Create training samples with the second physical and chemical parameters of each first electrolyte and the composition information of each first electrolyte.
  • a variety of electrolytes with different composition information are simulated by the simulation model, and then the electrolyte simulated by the simulation model is calculated by a high-throughput calculation method to obtain the second physical and chemical parameters corresponding to the first electrolyte , the composition information of each first electrolyte and the corresponding second physical and chemical parameters are respectively constructed as training samples, so that the composition prediction model can be trained to obtain a trained composition prediction model. Then, based on the trained composition prediction model, the physical and chemical parameters of the electrolyte to be designed can be processed 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, so as to realize the electrolyte. Low cost and efficient design.
  • step S110 is introduced, simulating a variety of first electrolytes with different composition information through a pre-trained simulation model.
  • the simulation model may be a simulation model commonly used in the prior art, for example, it may be a simulation model constructed and trained by at least one of an analog computer, a digital computer and a hybrid computer.
  • the simulation model can be a simulation model constructed and trained by a simulated computer.
  • the electrolyte calculation workflow with multiple scales such as material composition and/or material ratio can be obtained through this simulation model, thereby simulating Various electrolytes with different composition information.
  • the first electrolyte may include an aqueous electrolyte and a non-aqueous electrolyte.
  • the first electrolytic solution may include an electrolytic solution using water as a solvent and an organic electrolytic solution using organic matter as a solvent.
  • the first electrolyte may include lithium ion batteries, lithium metal batteries, sodium ion batteries, sodium metal batteries, potassium ion batteries, potassium metal batteries, magnesium ion batteries, magnesium metal batteries, Electrolyte in calcium ion battery, calcium metal battery, zinc ion battery, zinc metal battery, aluminum ion battery, aluminum metal battery.
  • the first electrolyte may include a solvent, an electrolyte salt and optional additives.
  • the solvent may include one or more organic small molecules, and the organic small molecules are composed of at least two elements among C, H, O, N, F, Cl, S, P, and B.
  • Electrolyte salts may include hexafluorophosphate, bisfluorosulfonyl imide, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate salt, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonimide salt, bistrifluoromethanesulfonimide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, At least one of perchlorate, sulfate, sulfite, hexafluoroarsenate, the cation in the electrolyte salt is selected from Li + , Na + , K + , Mg 2+ , Ca 2+ , Zn 2+ , at least one of Al 3+ .
  • Optional additives may include at least one of film-forming additives, flame retardant additives, anti-overcharge additives, overcharge protection additives and multifunctional additives.
  • the component information may be information related to the composition of the electrolytic solution.
  • the composition information may include the composition and ratio of substances in the electrolyte.
  • the trained composition prediction model can be applied to the design of various electrolytes for secondary batteries, which improves the applicability of the composition prediction model.
  • step S120 is introduced, using a high-throughput calculation method to calculate the first electrolyte solution to obtain the second physical and chemical parameters corresponding to the first electrolyte solution.
  • the second physical and chemical parameters corresponding to the first electrolyte are parameters of physical properties and chemical properties related to the performance of the first electrolyte.
  • the second physical and chemical parameters may include at least one of physical and chemical parameters of solvent molecules constituting the electrolyte and physical and chemical parameters of the electrolyte.
  • the physical and chemical parameters of the solvent molecules that make up the electrolyte may include the physical and chemical parameters that the solvent molecules have in a non-solution environment, such as the physical and chemical parameters that they have when they are in a vacuum environment, and may also include the physical and chemical parameters that the solvent molecules have in a solution environment.
  • the physical and chemical parameters of the battery such as the physical and chemical parameters it has when it is in the electrolyte.
  • the physical and chemical parameters of the solvent molecules constituting the electrolyte may include the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox At least one of electric potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point.
  • the physical and chemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ion conductivity of the electrolyte.
  • the above-mentioned high-throughput calculation method may include various calculation methods.
  • the high-throughput calculation method includes at least one of density functional theory calculation, molecular dynamics simulation and finite element calculation.
  • the initial geometric configuration of DME molecules can be constructed by GaussView software; Then Gaussian16 software can be used to optimize the initial geometric configuration of the constructed DME molecule, and calculate the relevant physical and chemical properties on the optimal structure.
  • the specific method used is density functional theory, and the basis set is 6-311++G (d, p), the functional is B3LYP; then the optimized structure can be determined to be the ground state structure by vibration frequency analysis, and the charge distribution of the DME molecule can be analyzed by using the NBO charge; finally, the geometric structure of the optimized DME molecule can be analyzed (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 level, oxidation-reduction potential and other physical and chemical parameters.
  • Packmol software can be used to construct a DOL solvent model that includes multiple solvent molecules, such as Construct a DOL solvent model containing 1000 solvent molecules; then LAMMPS software can be used to perform molecular dynamics simulation on the DOL solvent model, and the simulation process can include the following steps (1) to (4).
  • NDT ensemble The canonical ensemble (NVT ensemble) is calculated at 298K, the time is 10ns, and the time step is 1fs.
  • the molecular dynamics simulation is used to calculate the dielectric constant and viscosity of the DOL solvent, where the dielectric constant calculation formula is:
  • ⁇ is the permittivity
  • ⁇ 0 is the vacuum permittivity
  • T is the temperature
  • V is the volume of the electrolyte
  • k B is the Boltzmann constant.
  • the viscosity calculation formula is:
  • ⁇ is the viscosity
  • T is the temperature
  • V is the volume of the electrolyte
  • k B is the Boltzmann constant
  • P xz is the system pressure.
  • DMC dimethyl carbonate
  • GaussView software can be used to construct the initial geometric configuration of DMC molecules; then Gaussian16 software can be used Optimize the initial geometric configuration of the constructed DMC molecule, and calculate the relevant physical and chemical properties on the optimal structure.
  • the specific method used is density functional theory, and 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 calculated by molecular dynamics simulation; then the vibration frequency analysis can be used to determine the obtained optimization
  • the structure is the ground state structure, using NBO charge to analyze the charge distribution of DMC molecules; finally, the geometric structure (bond length, bond angle, dihedral angle), electronic structure (NBO charge distribution), thermodynamic energy, electronic Physical and chemical parameters such as affinity energy, dipole moment, Raman spectrum, infrared spectrum, HOMO and LUMO energy levels, redox potential, etc.
  • the specific method used is density functional theory, the basis set is 6-311++G(d,p), and the functional is B3LYP , using the SMD solvation model to describe the solution environment, the dielectric constant of the SMD solvation model can be calculated by molecular dynamics simulation; then the optimized structure can be determined to be the ground state structure by vibration frequency analysis, and the Li + -PC can be analyzed by NBO charge charge distribution; finally, the geometric structure (bond length, bond angle, dihedral angle), electronic structure (NBO charge distribution), thermodynamic energy, electron affinity, dipole moment, and Raman spectrum of the optimized PC molecule can be analyzed , infrared spectrum, HOMO and LUMO energy level, redox potential and other physical and chemical parameters.
  • Packmol software can be used to construct a The solvent model of solvent molecules, specifically, a solvent model containing 500 DOL molecules and 500 DME molecules can be constructed, and 10, 20, 30, 40, 50, 60, 70, 80, 90, 100 can be added to it respectively LiTFSI molecules to obtain the LiTFSI DOL/DME electrolyte model; then the LAMMPS software can be used to perform molecular dynamics simulation on the LiTFSI DOL/DME electrolyte model.
  • the simulation process may include the following steps (1) to (4).
  • the molecular dynamics simulation is used to calculate the dielectric constant, viscosity and ionic conductivity of the DOL/DME solvent, where the dielectric constant calculation formula is:
  • ⁇ is the permittivity
  • ⁇ 0 is the vacuum permittivity
  • T is the temperature
  • V is the volume of the electrolyte
  • k B is the Boltzmann constant.
  • the viscosity calculation formula is:
  • ⁇ is the viscosity
  • T is the temperature
  • V is the volume
  • k B is the Boltzmann constant
  • P xy is the system pressure
  • D is the ion conductivity
  • t is time
  • d is the diffusion dimension (the value of three-dimensional diffusion is 3)
  • N is the number of lithium ions
  • r i is the displacement of the i-th lithium ion.
  • LiTFSI lithium bistrifluoromethanesulfonimide
  • the Coulombic efficiency during the battery cycle can be calculated according to the morphology of the charged and discharged lithium metal anode. Based on the calculation results, the influence of lithium salt concentration and charge-discharge rate on the lithium ion concentration distribution, electric field distribution, metal lithium anode morphology and Coulombic efficiency of LiTFSI DOL/DME electrolyte can be analyzed.
  • the FEC molecule can be calculated by density functional theory first.
  • the physical and chemical parameters of the environment; the physical and chemical parameters of the FEC molecule in a vacuum environment can then be used as the input of the molecular dynamics simulation, and the steps similar to the above-mentioned example of using the molecular dynamics simulation to calculate the dielectric constant and viscosity of the electrolyte solvent are adopted, Calculate the physical and chemical parameters of the FEC solvent, such as dielectric constant, viscosity, etc.; then the physical and chemical parameters of the FEC molecule in a vacuum environment can be used as the parameters of the solvation model, and the density functional theory is used to calculate the solvent molecules in the solution environment.
  • the example of the physical and chemical parameters in the liquid is similar to the steps of calculating the physical and chemical parameters of the FEC molecule in the solution environment, and using the above-mentioned density functional theory to calculate the physical and chemical parameters of the ion-solvent structure formed by the electrolyte solvent molecule and the cation in the solution environment.
  • the similar steps in the example are used to calculate the physical and chemical parameters of the ion-solvent structure of Li + -FEC in a solution environment; the above-mentioned example of using molecular dynamics simulation to calculate the physical and chemical parameters of the electrolyte can also be used to calculate the dissolved LiTFSI, LiFSI , the solvation structure, ionic conductivity, viscosity, dielectric constant and other physical and chemical parameters of the FEC electrolyte of LiPF 6 ; it is also possible to calculate the dissolved LiTFSI respectively by using a method similar to the above-mentioned example of calculating the physical and chemical parameters of the electrolyte using finite element simulation, The physical and chemical parameters of LiFSI, LiPF 6 FEC electrolyte in the charge and discharge process of lithium ion concentration distribution, electric field distribution, metal lithium negative electrode morphology and coulombic efficiency.
  • the high-throughput calculation of the lithium battery electrolyte is used as an example to illustrate.
  • the small molecule structure model can be extracted in batches from the existing small molecule database (such as GDB-11 or GDB-13 database);
  • step S120 the large amount of first electrolyte solution obtained in step S110 can be calculated by a high-throughput calculation method, and the corresponding relationship between a large amount of electrolyte composition information and physical and chemical parameters can be obtained.
  • the processing rate of the correspondence between the composition information of the electrolyte and the physical and chemical parameters can be accelerated, the efficiency of electrolyte design can be improved, and the cost of electrolyte design can be saved.
  • step S130 is introduced, respectively creating training samples with the second physical and chemical parameters of each first electrolyte and the composition information of each first electrolyte.
  • step S130 the physical and chemical parameters and corresponding component information obtained by the high-throughput calculation method in step S120 can be used to create training samples. If a large number of comprehensive training samples can be obtained, the component prediction model obtained through training has more High accuracy and wider applicability.
  • step S140 is introduced. According to multiple training samples, the component prediction model is trained until the training stop condition is satisfied, and a trained component prediction model is obtained.
  • the component prediction model may be a machine learning model.
  • 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 , at least one of a naive Bayesian model, a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model. It is easy to understand that the component prediction model may be any one of the above models, or may be a model obtained by combining two or more of the above models.
  • the prediction effects of different models can be compared, so that an appropriate model can be selected to achieve accurate prediction of the properties of the electrolyte.
  • specific application scenarios high temperature, low temperature, fast charging, High specific energy, etc.
  • the above-mentioned training stop condition may be a preset condition for stopping the component prediction model training.
  • the training stop condition may be that the loss function of the component prediction model is smaller than a certain threshold, or that the number of iterations for training the component prediction model reaches a certain number.
  • the specific training stop conditions can be selected according to user needs, and are not limited here.
  • step S140 may specifically include:
  • a lot of economic cost and time cost can be saved by simulating a variety of electrolytes with different composition information through the simulation model.
  • the physical and chemical parameters corresponding to the electrolyte can be obtained efficiently and at low cost, thereby creating training samples.
  • the training samples created through the above process are applied to the training of the composition prediction model, and the obtained composition prediction model can be based on the internal relationship between the composition information and performance of the electrolyte, and can be processed according to the physical and chemical parameters corresponding to the actual performance of the electrolyte to achieve electrolyte efficient and low-cost design.
  • Fig. 2 shows a schematic flowchart of an electrolyte design method provided in the embodiment of the present application.
  • the data processing method provided in the embodiment of the present application may include steps S210-S230.
  • the first physical and chemical parameters have the same meaning as the second physical and chemical parameters, except that the first physical and chemical parameters are physical and chemical parameters corresponding to the performance of the electrolyte required in practical applications, and the second physical and chemical parameters correspond to the physical and chemical parameters corresponding to the first electrolyte. parameter.
  • the component prediction model is trained according to a plurality of training samples obtained based on high-throughput calculation methods, and each training sample may include a second physical and chemical parameter of a first electrolyte, and a component corresponding to the first electrolyte information.
  • step S230 one or more formulations of the electrolyte solution to be designed can be determined according to the composition information obtained in step S220, and the electrolyte solution can be configured for experimental verification, or the configuration and verification process of the electrolyte solution can be simulated by computer.
  • 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.
  • the composition of the electrolyte is designed to obtain an electrolyte that meets the performance requirements.
  • the training samples of the composition prediction model are obtained based on high-throughput computing methods, it is not necessary to conduct a large number of experiments to obtain training samples, which reduces the cost of experiments.
  • the embodiments of the present application can realize low-cost and high-efficiency electrolyte design.
  • the first physical and chemical parameters may include at least one of physical and chemical parameters of solvent molecules constituting the electrolyte and physical and chemical parameters of the electrolyte.
  • the physical and chemical parameters of the solvent molecules in the electrolyte to be designed and/or the physical and chemical parameters of the entire electrolyte can be determined, so as to determine the first physical and chemical parameters.
  • the physical and chemical parameters of the solvent molecules constituting the electrolyte may include the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox At least one of electric potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point.
  • the physical and chemical parameters of the solvent molecules constituting the electrolyte include at least one of the above-mentioned multiple physical and chemical parameters, which can make the performance of the designed electrolyte more in line with user expectations, thereby avoiding unnecessary duplication of labor and saving experimental costs.
  • the physical and chemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ion conductivity of the electrolyte.
  • the physical and chemical parameters of the electrolyte include at least one of the above-mentioned multiple physical and chemical parameters, which can make the performance of the designed electrolyte more in line with user expectations, thereby avoiding unnecessary duplication of labor and saving experimental costs.
  • the composition information may include material composition and proportion.
  • the formula of the electrolyte solution to be designed can be directly obtained according to the composition information of the electrolyte solution to be designed, which further reduces the cost of experiments.
  • the component prediction model may include 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, and a naive Bayesian model , at least one of a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
  • the electrolyte to be designed may include an aqueous electrolyte and a non-aqueous electrolyte.
  • the electrolyte solution to be designed may include a solvent, an electrolyte salt and optional additives.
  • the solvent may include one or more organic small molecules, and the organic small molecules may be composed of at least two elements in C, H, O, N, F, Cl, S, P, and B;
  • Electrolyte salts may include hexafluorophosphate, bisfluorosulfonyl imide, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate salt, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonimide salt, bistrifluoromethanesulfonimide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, At least one of perchlorate, sulfate, sulfite, hexafluoroarsenate, the cation in the electrolyte salt may be selected from Li + , Na + , K + , Mg 2+ , Ca 2+ , Zn 2 + , at least one of Al 3+ ;
  • Optional additives may include at least one of film-forming additives, flame retardant additives, anti-overcharge additives, overcharge protection additives and multifunctional additives.
  • optional additives may include one or more small organic molecules composed of carbon, hydrogen, oxygen, nitrogen, fluorine, chlorine, sulfur, phosphorus, boron, and hexafluorophosphate, difluorosulfonyl Imine salt, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate, dioxalate borate, tetrafluorooxalate borate salt, bisfluorosulfonimide salt, bistrifluoromethanesulfonimide salt, 4,5-dicyano-2-trifluoromethylimidazole, perchlorate, sulfate, sulfite, hexafluoro One or more of salts such as arsenate.
  • the cations of the above salts may be selected from at least one of Li + , Na + , K + , Mg 2+ , Ca 2
  • the embodiment of the present application also provides an electrolyte design device 300 .
  • the electrolyte design device 300 may include an acquisition module 301 , an input module 302 and a design module 303 .
  • the obtaining module 301 is used to obtain the first physical and chemical parameters of the electrolyte solution to be designed.
  • the prediction module 302 is used to input the first physical and chemical parameters into the trained composition prediction model, predict the composition information of the electrolyte to be designed through the composition prediction model, and obtain the composition information of the electrolyte to be designed, wherein the composition prediction model is based on high
  • the training samples obtained by the flux calculation method are trained.
  • the design module 303 is configured to design the electrolyte solution to be designed according to the composition information of the electrolyte solution to be designed.
  • the device 300 may further include a simulation module, a calculation module, a creation module and a training module.
  • the simulation module is used for simulating a variety of first electrolytes with different composition information through a pre-trained simulation model.
  • the calculation module is used to calculate the first electrolyte solution by using a high-throughput calculation method to obtain the second physical and chemical parameters corresponding to the first electrolyte solution.
  • the creation module is used to respectively create training samples from the second physical and chemical parameters 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 a plurality of training samples until the training stop condition is satisfied, and a trained component prediction model is obtained.
  • 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 a trained component prediction model, which may specifically include:
  • the high-throughput calculation method may include at least one of density functional theory calculation, molecular dynamics simulation and finite element calculation.
  • the first physical and chemical parameters include at least one of physical and chemical parameters of solvent molecules constituting the electrolyte and physical and chemical parameters of the electrolyte.
  • the physical and chemical parameters of the solvent molecules constituting the electrolyte may include the geometric structure, electronic structure, thermodynamic energy, molecular frontier orbital energy level, dipole moment, electron affinity, redox At least one of electric potential, Raman spectrum, infrared spectrum, dielectric constant, viscosity, melting point, and boiling point.
  • the physical and chemical parameters of the electrolyte may include at least one of the dielectric constant, viscosity, melting point, boiling point, and ion conductivity of the electrolyte.
  • composition information may include material composition and proportion.
  • the component prediction model may include 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, and a naive Bayesian model , at least one of a random forest model, a dimensionality reduction algorithm model, and a gradient enhancement algorithm model.
  • the electrolyte to be designed may include an aqueous electrolyte and a non-aqueous electrolyte.
  • the electrolyte solution to be designed may include a solvent, an electrolyte salt and optional additives,
  • the solvent may include one or more organic small molecules, and the organic small molecules may be composed of at least two elements in C, H, O, N, F, Cl, S, P, and B;
  • Electrolyte salts may include hexafluorophosphate, bisfluorosulfonyl imide, nitrate, nitrite, fluoride, chloride, bromide, iodide, difluorophosphate, difluorooxalate borate salt, dioxalate borate, tetrafluorooxalate borate, bisfluorosulfonimide salt, bistrifluoromethanesulfonimide salt, 4,5-dicyano-2-trifluoromethylimidazolium salt, At least one of perchlorate, sulfate, sulfite, hexafluoroarsenate, the cation in the electrolyte salt may be selected from Li + , Na + , K + , Mg 2+ , Ca 2+ , Zn 2 + , at least one of Al 3+ ;
  • Optional additives may include at least one of film-forming additives, flame retardant additives, anti-overcharge additives, overcharge protection additives, and multifunctional additives.
  • Fig. 4 shows a schematic diagram of the hardware structure of the electrolyte design device provided by the embodiment of the present application.
  • the device designed in the electrolyte may comprise a processor 401 and a memory 402 storing computer program instructions.
  • processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
  • CPU central processing unit
  • ASIC Application Specific Integrated Circuit
  • Memory 402 may include mass storage for data or instructions.
  • memory 402 may include a hard disk drive (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 (Universal Serial Bus, USB) drive or two or more Combinations of multiple of the above.
  • Storage 402 may include removable or non-removable (or fixed) media, where appropriate. Under appropriate circumstances, the storage 402 can be inside or outside the comprehensive gateway disaster recovery device.
  • memory 402 is a non-volatile solid-state memory.
  • 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.
  • ROM read only memory
  • RAM random access memory
  • magnetic disk storage media devices magnetic disk storage media devices
  • optical storage media devices flash memory devices
  • electrical, optical, or other physical/tangible memory storage devices include one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions, and when the software is executed (e.g., by one or multiple processors) operable to perform the operations described with reference to the method according to an aspect of the present application.
  • the processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any electrolyte design method in the above-mentioned embodiments.
  • the electrolyte design device may further include a communication interface 403 and a bus 410 .
  • the processor 401 , the memory 402 , and the communication interface 403 are connected through a bus 410 to complete mutual communication.
  • the communication interface 403 is mainly used to implement communication between modules, devices, units and/or devices in the embodiments of the present application.
  • the bus 410 includes hardware, software or both, and couples the components of the online data traffic charging device to each other.
  • the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) Bus, Infiniband Interconnect, Low Pin Count (LPC) Bus, Memory Bus, Micro Channel Architecture (MCA) Bus, Peripheral Component Interconnect (PCI) Bus, PCI-Express (PCI-X) Bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of these.
  • Bus 410 may comprise one or more buses, where appropriate. Although the embodiments of this application describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.
  • the electrolyte design device can execute the method for designing the electrolyte in the embodiments of the present application based on the first physical and chemical parameters of the electrolyte to be designed, thereby realizing the electrolyte design method and device described in conjunction with FIG. 2 and FIG. 3 .
  • the embodiments of the present application may provide a computer storage medium for implementation.
  • Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any electrolyte design method in the above-mentioned embodiments is realized.
  • the functional blocks shown in the structural block diagrams described above may be implemented as hardware, software, firmware, or a combination thereof.
  • hardware When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, or the like.
  • ASIC application specific integrated circuit
  • the elements of the present application are the programs or code segments employed to perform the required tasks.
  • Programs or code segments can be stored in machine-readable media, or transmitted over transmission media or communication links by data signals carried in carrier waves.
  • "Machine-readable medium" may include any medium that can store or transmit information.
  • machine-readable media examples include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like.
  • Code segments may be downloaded via a computer network such as the Internet, an Intranet, or the like.
  • processors may be, but are not limited to, general purpose processors, special purpose processors, application specific processors, or field programmable logic circuits. It can also be understood that each block in the block diagrams and/or flowcharts and combinations of blocks in the block diagrams and/or flowcharts can also be realized by dedicated hardware for performing specified functions or actions, or can be implemented by dedicated hardware and Combination of computer instructions to achieve.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Secondary Cells (AREA)

Abstract

本申请提供一种电解液设计方法、装置、设备、介质及程序产品。其中，方法包括：获取待设计电解液的第一理化参数；将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息，其中，成分预测模型通过基于高通量计算方法得到的训练样本训练得到；根据待设计电解液的成分信息设计待设计电解液。根据本申请实施例，能够实现低成本，高效率的电解液设计。

Description

电解液设计方法、装置、设备、介质及程序产品
相关申请的交叉引用
本申请要求享有于2021年12月08日提交的名称为“电解液设计方法、装置、设备、介质及程序产品”的中国专利申请202111492691.8的优先权，该申请的全部内容通过引用并入本文中。
技术领域
本申请属于二次电池技术领域，尤其涉及一种电解液设计方法、装置、设备、计算机存储介质及计算机程序产品。
背景技术
近年来，随着以锂离子电池为代表的二次电池的应用范围越来越广泛，锂离子电池广泛应用于水力，火力，风力和太阳能电站等储能电源系统，以及电动工具，电动自行车，电动摩托车，电动汽车，军事装备，航空航天等多个领域。由于二次离子电池取得了极大的发展，因此对其能量密度，循环性能和安全性能等也提出了更高的要求。
电解液是二次电池的重要组成，发挥着传导活性离子和电子绝缘的作用。正负极活性物质决定二次电池理论容量，但是其充放电速率，长循环性能等性能与电解液息息相关。从锂离子电池技术的发展历程来看，电解液体系的选择很大程度上决定二次电池的成功与否。因此，开发先进的电解液是开发下一代二次电池的技术核心之一。
但是，由于电解液成分复杂，往往需要投入大量的工作，才能设计出符合实际需要的电解液。
发明内容
本申请实施例提供一种电解液设计方法、装置、设备、计算机存储介 质及计算机程序产品，能够实现电解液的高效率和低成本设计。
第一方面，本申请实施例提供一种电解液设计方法，方法包括：
获取待设计电解液的第一理化参数；
将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息，其中，成分预测模型通过基于高通量计算方法得到的训练样本训练得到；
根据待设计电解液的成分信息设计待设计电解液。
在第一方面的一些实施例中，在将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息之前，方法还包括：
通过预先训练的仿真模型模拟多种具有不同成分信息的第一电解液；
利用高通量计算方法对第一电解液进行计算，得到第一电解液对应的第二理化参数；
分别将每种第一电解液的第二理化参数以及每种第一电解液的成分信息创建训练样本；
根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在第一方面的一些实施例中，根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型，包括：
对每个训练样本，分别执行如下步骤：
将训练样本输入至预设的成分预测模型中，得到与第二理化参数对应的预测成分信息；
根据预测成分信息和第一电解液的成分信息，确定成分预测模型的损失函数值；
在损失函数值不满足训练停止条件的情况下，调整成分预测模型的模型参数，并利用训练样本训练参数调整后的成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在第一方面的一些实施例中，高通量计算方法包括密度泛函理论计算，分子动力学模拟和有限元计算中的至少一者。
在第一方面的一些实施例中，第一理化参数包括构成电解液的溶剂分子的理化参数以及电解液的理化参数中的至少一者。
在第一方面的一些实施例中，构成电解液的溶剂分子的理化参数包括溶剂分子的几何结构，电子结构，热力学能量，分子前线轨道能级，偶极矩，电子亲和能，氧化还原电位，拉曼光谱，红外光谱，介电常数，粘度，熔点，沸点中的至少一者。
在第一方面的一些实施例中，电解液的理化参数包括电解液的介电常数，粘度，熔点，沸点，离子导率中的至少一者。
在第一方面的一些实施例中，成分信息包括物质组成和配比。
在第一方面的一些实施例中，成分预测模型包括线性回归分析模型，逻辑回归分析模型，支持向量机，最近邻算法模型，K均值聚类算法模型，决策树模型，朴素贝叶斯模型，随机森林模型，降维算法模型，梯度增强算法模型中的至少一者。
在第一方面的一些实施例中，待设计电解液包括水系电解液和非水电解液。
在第一方面的一些实施例中，待设计电解液中包括溶剂，电解质盐以及任选的添加剂，
其中，溶剂包括一种或多种有机小分子，有机小分子由C，H，O，N，F，Cl，S，P，B中的至少两种元素组成；
电解质盐包括六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑盐，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐中的至少一者，电解质盐中的阳离子选自Li +，Na +，K +，Mg 2+，Ca 2+，Zn 2+，Al 3+中的至少一者；
任选的添加剂包括成膜添加剂，阻燃添加剂，防过充添加剂，过充保护添加剂及多功能添加剂中的至少一者。
第二方面，本申请实施例提供一种电解液设计装置，装置包括：
获取模块，用于获取待设计电解液的第一理化参数；
预测模块，用于将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息，其中，成分预测模型通过基于高通量计算方法得到的训练样本训练得到；
设计模块，用于根据待设计电解液的成分信息设计待设计电解液。
第三方面，本申请实施例提供一种电解液设计设备，设备包括：处理器以及存储有计算机程序指令的存储器；
处理器执行计算机程序指令时实现如本申请第一方面任一实施例的电解液设计方法。
第四方面，本申请实施例提供一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序指令，计算机程序指令被处理器执行时实现如本申请第一方面任一实施例的电解液设计方法。
第五方面，本申请实施例提供一种计算机程序产品，计算机程序产品中的指令由电子设备的处理器执行时，使得电子设备执行如本申请第一方面任一实施例的电解液设计方法。
本申请实施例的电解液设计方法、装置、设备、计算机存储介质、计算机程序产品，能够通过将电解液的理化参数输入到成分预测模型中，得到与理化参数对应的成分信息，这样，不需要进行实际的实验工作，就能够根据对电解液的性能要求，设计电解液的成分，得到符合性能要求的电解液。并且，由于成分预测模型的训练样本是基于高通量计算方法得到的，无需进行大量的实验来获取训练样本，降低了实验成本。本申请实施例能够实现低成本和高效率的电解液设计。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单的介绍，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一个实施例提供的电解液设计方法的流程示意图；
图2是本申请另一个实施例提供的电解液设计方法的流程示意图；
图3是本申请又一个实施例提供的电解液设计装置的结构示意图；
图4是本申请再一个实施例提供的电解液设计设备的结构示意图。
具体实施方式
下面将详细描述本申请的各个方面的特征和示例性实施例，为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及具体实施例，对本申请进行进一步详细描述。应理解，此处所描述的具体实施例仅意在解释本申请，而不是限定本申请。对于本领域技术人员来说，本申请可以在不需要这些具体细节中的一些细节的情况下实施。下面对实施例的描述仅仅是为了通过示出本申请的示例来提供对本申请更好的理解。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
如背景技术所述，现有技术中，对电解液进行设计往往需要进行大量的实验，例如，需要研究人员按照经验设计多种不同电解液的物质组成及配比，再对电解液的性能进行验证，或者是基于现有的电解液进行配方优化。发明人发现，现有技术的电解液设计方法，不仅研发周期长，成本高，迁移性差，且难以总结电解液设计开发的内在规律。
在生物领域中，高通量筛选(High throughput screening，HTS)技术是指以分子水平和细胞水平的实验方法为基础，以微板形式作为实验工具载体，以自动化操作系统执行试验过程，以灵敏快速的检测仪器采集实验结果数据，以计算机分析处理实验数据，在同一时间检测数以千万的样品，并以得到的相应数据库支持运转的技术体系。HTS技术具有微量，快速，灵敏 和准确等特点。简言之，HTS技术可以通过一次实验获得大量的信息，并从中找到有价值的信息。
发明人经大量研究发现，将基于高通量筛选的高通量计算方法应用于电解液设计中，能够有效降低实验成本，还能够得到电解液成分信息与性能的内在联系。
为了解决现有技术问题，本申请实施例提供了一种电解液设计方法、装置、设备、计算机存储介质及计算机程序产品。
下面结合附图，通过具体的实施例及其应用场景对本申请实施例所提供的电解液设计方法进行介绍。
图1示出了本申请一个实施例提供的电解液设计方法的流程示意图，具体的可以是本申请实施例提供电解液设计方法中所采用的成分预测模型的训练方法。
如图1所示，本申请实施例提供的电解液设计方法中所采用的成分预测模型可以包括步骤S110～S140。
S110，通过预先训练的仿真模型模拟多种具有不同成分信息的第一电解液。
S120，利用高通量计算方法对第一电解液进行计算，得到第一电解液对应的第二理化参数。
S130，分别将每种第一电解液的第二理化参数以及每种第一电解液的成分信息创建训练样本。
S140，根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在本申请的实施例中，通过仿真模型模拟多种具有不同成分信息的电解液，然后通过高通量计算方法对仿真模型模拟的电解液进行计算，得到第一电解液对应的第二理化参数，分别将每种第一电解液的成分信息以及对应的第二理化参数构建训练样本，如此可对成分预测模型进行训练，得到训练好的成分预测模型。然后，即可基于训练好的成分预测模型对待设计的电解液的理化参数进行处理，得到待设计的电解液的成分信息，根据待设计的电解液的成分信息设计电解液，从而实现电解液的低成本和高效 设计。
下面对成分预测模型的训练过程进行详细说明。
首先介绍步骤S110，通过预先训练的仿真模型模拟多种具有不同成分信息的第一电解液。
其中，仿真模型可以为现有技术中常用的仿真模型，例如，可以为通过模拟计算机，数字计算机和混合计算机中的至少一者构建并训练的仿真模型。作为一个示例，仿真模型可以为通过模拟计算机构建并训练得到的仿真模型，具体地，通过该仿真模型可以得到具有物质组成和/或物质配比等多个尺度的电解液计算工作流，从而模拟多种具有不同成分信息的电解液。
在一种可选的实施方式中，第一电解液可以包括水系电解液和非水电解液。作为一个示例，第一电解液可以包括以水为溶剂的电解液以及以有机物为溶剂的有机电解液。在一种可选的实施方式中，第一电解液可以包括用于锂离子电池，锂金属电池，钠离子电池，钠金属电池，钾离子电池，钾金属电池，镁离子电池，镁金属电池，钙离子电池，钙金属电池，锌离子电池，锌金属电池，铝离子电池，铝金属电池中的电解液。
在一种可选的实施例方式中，第一电解液中可以包括溶剂，电解质盐以及任选的添加剂。
其中，溶剂可以包括一种或多种有机小分子，有机小分子由C，H，O，N，F，Cl，S，P，B中的至少两种元素组成。
电解质盐可以包括六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑盐，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐中的至少一者，电解质盐中的阳离子选自Li +，Na +，K +，Mg 2+，Ca 2+，Zn 2+，Al 3+中的至少一者。
任选的添加剂可以包括成膜添加剂，阻燃添加剂，防过充添加剂，过充保护添加剂及多功能添加剂中的至少一者。
成分信息可以为与电解液的构成相关的信息。在一种可选的实施方式 中，成分信息可以包括电解液中物质的组成和配比。
通过仿真模型模拟上述多种具有不同成分信息的第一电解液，能够得到大量且全面的与电解液相关的信息，从而能够在后续步骤中，获得更全面的训练样本。如此，训练好的成分预测模型能够适用于多种二次电池用电解液的设计，提高了成分预测模型的适用性。
然后介绍步骤S120，利用高通量计算方法对第一电解液进行计算，得到第一电解液对应的第二理化参数。
步骤S120中，第一电解液对应的第二理化参数为与第一电解液的性能相关的物理性质和化学性质的参数。
在一种可选的实施方式中，第二理化参数可以包括构成电解液的溶剂分子的理化参数以及电解液的理化参数中的至少一者。
具体地，构成电解液的溶剂分子的理化参数可以包括溶剂分子在非溶液环境中所具有的理化参数，例如处于真空环境中时所具有的理化参数，也可以包括溶剂分子在溶液环境中所具有的的理化参数，例如处于电解液中时所具有的理化参数。在一种可选的实施方式中，构成电解液的溶剂分子的理化参数可以包括溶剂分子的几何结构，电子结构，热力学能量，分子前线轨道能级，偶极矩，电子亲和能，氧化还原电位，拉曼光谱，红外光谱，介电常数，粘度，熔点，沸点中的至少一者。
在一种可选的实施方式中，电解液的理化参数可以包括电解液的介电常数，粘度，熔点，沸点，离子导率中的至少一者。
上述高通量计算方法可以包括多种计算方法。在一种可选的实施方式中，高通量计算方法包括密度泛函理论计算，分子动力学模拟和有限元计算中的至少一者。
为了便于理解，下面对本申请中的高通量计算方法的部分实现方式进行示例性说明。需要说明的是，以下示例仅是为了解释本申请，而不是为了限制本申请。
作为采用密度泛函理论计算真空环境下电解液溶剂分子的理化参数的一个示例，对于1，2-二甲氧基乙烷(DME)分子，可先通过GaussView软件构建DME分子初始几何构型；然后可以采用Gaussian16软件对所构建 的DME分子初始几何构型进行优化，并在最优结构上计算相关物理化学性质，所采用的具体方法为密度泛函理论，基组为6-311++G(d，p)，泛函为B3LYP；接着可以采用振动频率分析确定所得优化结构为基态结构，采用NBO电荷，分析DME分子的电荷分布；最后可分析优化得到的DME分子的几何结构(键长，键角，二面角)，电子结构(NBO电荷分布)，热力学能量，电子亲和能，偶极矩，拉曼光谱，红外光谱，最高占据分子轨道(HOMO)与最低未占据分子轨道(LUMO)能级，氧化还原电位等理化参数。
作为采用分子动力学模拟计算电解液溶剂的介电常数和粘度的一个示例，对于1，3-二氧戊环(DOL)，可以采用Packmol软件构建包含多个溶剂分子的DOL溶剂模型，例如可以构建包含1000个溶剂分子的DOL溶剂模型；然后可以采用LAMMPS软件对DOL溶剂模型进行分子动力学模拟，模拟过程可以包括以下步骤(1)～(4)。
(1)在298K下进行等温等压系综(NPT系综)计算，压力为1个大气压，时间为3ns，时间步长为1fs；
(2)从298K升温至400K，系综为NPT，压力为1个大气压，升温速率为20K/ns，并最终于400K下恒温2ns，时间步长为1fs。
(3)从400K降温至298K，系综为NPT，压力为1个大气压，降温速率为20K/ns，并最终在298K下恒温5ns，时间步长为1fs。
(4)在298K进行正则系综(NVT系综)计算，时间为10ns，时间步长为1fs。
基于NVT计算轨迹的后半段进行分子动力学模拟采用，计算DOL溶剂的介电常数与粘度，其中，介电常数计算公式为：
Figure PCTCN2022072387-appb-000001
其中，ε为介电常数，ε 0是真空介电常数，
Figure PCTCN2022072387-appb-000002
是体系的总偶极矩，T是温度，V是电解液的体积，k B是玻尔兹曼常数。
粘度计算公式为：
Figure PCTCN2022072387-appb-000003
其中，η为粘度，T是温度，V是电解液的体积，k B是玻尔兹曼常数，P xz为体系压力。
作为采用密度泛函理论计算溶液环境下溶剂分子在电解液中的理化参数的一个示例，对于碳酸二甲酯(DMC)分子，可以采用GaussView软件构建DMC分子初始几何构型；然后可以采用Gaussian16软件对所构建的DMC分子初始几何构型进行优化，并在最优结构上计算相关物理化学性质，所采用的具体方法为密度泛函理论，基组为6-311++G(d，p)，泛函为B3LYP，采用隐式溶剂化作用模型(SMD溶剂化模型)描述溶液环境，设置SMD溶剂化模型的介电常数可通过分子动力学模拟计算得到；接着可以采用振动频率分析确定所得优化结构为基态结构，采用NBO电荷分析DMC分子的电荷分布；最后可分析优化得到的DMC分子的几何结构(键长，键角，二面角)，电子结构(NBO电荷分布)，热力学能量，电子亲和能，偶极矩，拉曼光谱，红外光谱，HOMO与LUMO能级，氧化还原电位等理化参数。结合采用密度泛函理论计算得到的真空环境下电解液溶剂分子的理化参数，可以对比溶剂分子在真空环境与溶液环境下理化参数的差异，并基于这些理化参数的差异探究电解液溶剂环境与电解液中溶剂分子理化参数的内在联系。
作为采用密度泛函理论计算溶液环境下电解液溶剂分子与阳离子形成的离子-溶剂结构的理化参数的一个示例，对于碳酸丙烯酯(PC)分子和Li +，首先可以采用GaussView软件构建PC分子与Li +形成的Li +-PC的离子-溶剂初始结构，具体地，构建的初始结构包括了PC分子与Li +形成的所有可能的结构；然后可以采用Gaussian16软件对所构建的Li +-PC的离子-溶剂初始结构进行优化，并在最优结构上计算相关物理化学性质，所采用的具体方法为密度泛函理论，基组为6-311++G(d，p)，泛函为B3LYP，采用SMD溶剂化模型描述溶液环境，设置SMD溶剂化模型的介电常数可通过分子动力学模拟计算得到；接着可以采用振动频率分析确定所得优化结构为基态结构，采用NBO电荷分析Li +-PC的电荷分布；最后可以分析优化得到的PC分子的几何结构(键长，键角，二面角)，电子结构(NBO电荷分布)，热力学能量，电子亲和能，偶极矩，拉曼光谱，红外光谱， HOMO与LUMO能级，氧化还原电位等理化参数。结合采用密度泛函理论计算得到的溶液环境下电解液溶剂分子的理化参数，可以对比PC分子与Li +作用前后的理化参数的差异，并基于此研究电解液中溶剂分子与阳离子之间的相互作用与溶剂分子理化参数的内在联系。
作为采用分子动力学模拟计算电解液的理化参数的一个示例，对于双三氟甲磺酰亚胺锂(LiTFSI)的DOL/DME电解液，首先可以采用Packmol软件构建包含多个DOL溶剂分子及DME溶剂分子的溶剂模型，具体地，可以构建包含500个DOL分子和500个DME分子的溶剂模型，并在其中分别添加10，20，30，40，50，60，70，80，90，100个LiTFSI分子，得到LiTFSI DOL/DME电解液模型；然后可以采用LAMMPS软件对LiTFSI DOL/DME电解液模型进行分子动力学模拟，模拟过程可包括以下步骤(1)～(4)。
(1)在298K下进行NPT系综计算，压力为1个大气压，时间为3ns，时间步长为1fs；
(2)从298K升温至400K，系综为NPT，压力为1个大气压，升温速率为20K/ns，并最终于400K下恒温2ns，时间步长为1fs。
(3)从400K降温至298K，系综为NPT，压力为1个大气压，降温速率为20K/ns，并最终于298K下恒温5ns，时间步长为1fs。
(4)在298K进行NVT系综计算，时间为10ns，时间步长为1fs。
基于NVT计算轨迹的后半段进行分子动力学模拟采用，计算DOL/DME溶剂的介电常数，粘度和离子导率，其中，介电常数计算公式为：
Figure PCTCN2022072387-appb-000004
其中，ε为介电常数，ε 0是真空介电常数，
Figure PCTCN2022072387-appb-000005
是体系的总偶极矩，T是温度，V是电解液的体积，k B是玻尔兹曼常数。
粘度计算公式为：
Figure PCTCN2022072387-appb-000006
其中，η为粘度，T是温度，V是体积，k B是玻尔兹曼常数，P xy为体 系压力。
离子导率计算公式为：
Figure PCTCN2022072387-appb-000007
其中，D为离子导率，t为时间，d为扩散维度(三维扩散取值为3)，N为锂离子数目，r i为第i个锂离子的位移。
基于计算结果，可以分析锂盐浓度对LiTFSI DOL/DME电解液的介电常数，粘度和离子导率的影响。
作为采用有限元方法模拟计算电解液的理化参数的一个示例，对于用于锂金属电池双三氟甲磺酰亚胺锂(LiTFSI)的DOL/DME电解液，首先可以采用与上述采用分子动力学模拟计算电解液的介电常数，粘度和离子导率的示例类似的步骤，计算得到0.1-4.0mo/L(每隔0.1mol/L取值)LiTFSI的DOL/DME电解液的介电常数，粘度和离子导率等理化参数；将以上LiTFSI的DOL/DME电解液的理化参数作为输入参数输入有限元计算模型后，可以采用COMSOL软件对LiTFSI DOL/DME电解液模型进行有限元模拟，计算0.1，0.5，1.0，2.0，5.0，10.0C充电或放电倍率下电解液中锂离子浓度分布，电场分布和金属锂负极沉积或脱出形貌。更进一步，根据充电和放电的金属锂负极形貌，可以计算得到电池循环过程中的库伦效率。基于计算结果，可以分析锂盐浓度，充放电倍率对LiTFSI DOL/DME电解液的锂离子浓度分布，电场分布，金属锂负极形貌和库伦效率的影响。
作为采用多种高通量计算方法自动化计算电解液的理化参数的一个示例，对于用于锂电池电解液的氟代碳酸乙烯酯(FEC)分子，可以先通过密度泛函理论计算FEC分子在真空环境下的理化参数；然后可以以FEC分子在真空环境下的理化参数作为分子动力学模拟的输入，采用与上述采用分子动力学模拟计算电解液溶剂的介电常数和粘度的示例类似的步骤，计算得到FEC溶剂的理化参数，例如介电常数，粘度等；接着可以以FEC分子在真空环境下的理化参数作为溶剂化模型的参数，采用上述采用密度泛函理论计算溶液环境下溶剂分子在电解液中的理化参数的示例类似的步骤， 计算FEC分子在溶液环境下的理化参数，以及采用上述采用密度泛函理论计算溶液环境下电解液溶剂分子与阳离子形成的离子-溶剂结构的理化参数的示例中类似的步骤计算Li +-FEC的离子-溶剂结构在溶液环境下的理化参数；还可以采用上述采用分子动力学模拟计算电解液的理化参数的示例类似的方法分别计算溶解了LiTFSI，LiFSI，LiPF 6的FEC电解液的溶剂化结构，离子导率，粘度，介电常数等理化参数；还可以采用上述采用有限元模拟计算电解液的理化参数的示例类似的方法分别计算溶解了LiTFSI，LiFSI，LiPF 6的FEC电解液在充放电过程中的锂离子浓度分布，电场分布，金属锂负极形貌和库伦效率等等理化参数。
作为采用多种高通量计算方法对电解液理化参数进行同步计算的一个示例，以锂电池电解液高通量计算为例进行说明。首先从可以现有小分子数据库(例如GDB-11或者GDB-13数据库)中批量提取小分子结构模型；然后可以采用上述采用密度泛函理论，分子动力学模拟和有限元自动化计算方法对电解液的理化参数进行计算的示例中的计算方法高通量同步计算各个小分子及对应的电解液的理化参数；进而可以构建起锂电池电解液大数据库，其中包括电解液溶剂分子和对应离子-溶剂结构的几何结构(键长，键角，二面角)，电子结构(NBO电荷分布)，热力学能量，电子亲和能，偶极矩，拉曼光谱，红外光谱，HOMO与LUMO能级，氧化还原电位等理化参数，以及电解液模型的离子导率，粘度，介电常数，熔沸点等理化参数。
步骤S120中，可以通过高通量计算方法对步骤S110中得到的大量第一电解液进行计算，可以得到大量的电解液成分信息与理化参数的对应关系。如此，能够加快电解液成分信息与理化参数的对应关系的处理速率，提高电解液设计的效率，节约电解液设计的成本。
接着介绍步骤S130，分别将每种第一电解液的第二理化参数以及每种第一电解液的成分信息创建训练样本。
在步骤S130中，可以将步骤S120中通过高通量计算方法得到的理化参数与对应的成分信息创建训练样本，如果，能够得到大量且全面的训练样本，从而使训练得到的成分预测模型具有更高的准确性和更广的适用性。
最后介绍步骤S140，根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
其中，成分预测模型可以为机器学习模型。在一种可选的实施方式中，成分预测模型可以包括线性回归分析模型，逻辑回归分析模型，支持向量机(SVM)，最近邻(KNN)算法模型，K均值聚类算法模型，决策树模型，朴素贝叶斯模型，随机森林模型，降维算法模型，梯度增强算法模型中的至少一者。容易理解的，成分预测模型可以为上述模型中的任意一种模型，也可以为上述模型中的两种或两种以上模型组合得到的模型。作为一个示例，对于以上列举的多种模型，可以比较不同模型的预测效果，从而选用合适的模型，实现对电解液性质的精准预测，例如，可以比较特定应用场景(高温，低温，快充，高比能等)下各模型对电解液成分信息的预测效果，或者各模型对于特定的一种或多种理化参数对应的电解液成分信息的预测效果，从而选用合适的模型。
上述训练停止条件可以是预先设置的成分预测模型训练停止的条件。作为一个示例，训练停止条件可以是成分预测模型的损失函数小于某一个阈值，还可以是成分预测模型进行训练的迭代次数达到某一次数。具体的训练停止条件可以根据用户需求自行选取，在此不做限定。
在一种可选的实施方式中，步骤S140具体可以包括：
对每个训练样本，分别执行如下步骤：
将训练样本输入至预设的成分预测模型中，得到与第二理化参数对应的预测成分信息；
根据预测成分信息和第一电解液的成分信息，确定成分预测模型的损失函数值；
在损失函数值不满足训练停止条件的情况下，调整成分预测模型的模型参数，并利用训练样本训练参数调整后的成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在本申请的实施例中，通过仿真模型模拟多种具有不同成分信息的电解液，能够节省大量的经济成本和时间成本。通过高通量计算方法对仿真模型模拟的电解液进行计算，能够高效率且低成本地得到电解液对应的理 化参数，从而创建训练样本。通过上述过程创建的训练样本应用于成分预测模型的训练，得到的成分预测模型能够基于电解液成分信息与性能的内在联系，根据实际所需要的电解液性能对应的理化参数进行处理，实现电解液的高效和低成本设计。
下面结合附图2对本申请实施例提供的电解液设计方法进行详细说明。
图2示出了本申请实施例提供的一种电解液设计方法的流程示意图，如图2所示，本申请实施例提供的数据处理方法可以包括步骤S210～S230。
S210，获取待设计电解液的第一理化参数。
其中，第一理化参数与第二理化参数的含义相同，只是第一理化参数为与实际应用中所需要的电解液性能对应的理化参数，第二理化参数对应的是第一电解液对应的理化参数。
S220，将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息，其中，成分预测模型通过基于高通量计算方法得到的训练样本训练得到。
其中，成分预测模型为根据多个基于高通量计算方法得到的训练样本训练得到，每个训练样本可以包括一种第一电解液的第二理化参数，以及与该第一电解液对应的成分信息。
S230，根据待设计电解液的成分信息设计待设计电解液。
步骤S230中，可以根据步骤S220得到的成分信息确定待设计电解液的一种或多种配方，并配置电解液，进行实验验证，也可以通过计算机模拟电解液的配置及验证过程。
本申请实施例的电解液设计方法，能够通过将电解液的理化参数输入到成分预测模型中，得到与理化参数对应的成分信息，这样，不需要进行实际的实验工作，就能够根据对电解液的性能要求，设计电解液的成分，得到符合性能要求的电解液。并且，由于成分预测模型的训练样本是基于高通量计算方法得到的，无需进行大量的实验来获取训练样本，降低了实验成本。本申请实施例能够实现低成本和高效率的电解液设计。
在一种可选的实施方式中，第一理化参数可以包括构成电解液的溶剂分子的理化参数以及电解液的理化参数中的至少一者。
具体地，可以根据对待设计电解液的性能需要，确定待设计电解液中溶剂分子的理化参数和/或电解液整体的理化参数，从而确定第一理化参数。
在一种可选的实施方式中，构成电解液的溶剂分子的理化参数可以包括溶剂分子的几何结构，电子结构，热力学能量，分子前线轨道能级，偶极矩，电子亲和能，氧化还原电位，拉曼光谱，红外光谱，介电常数，粘度，熔点，沸点中的至少一者。
构成电解液的溶剂分子的理化参数包括上述多种理化参数中的至少一者，可以使得设计出的电解液在性能方面更符合用户的期望，从而避免不必要的重复劳动，节约实验成本。
在一种可选的实施方式中，电解液的理化参数可以包括电解液的介电常数，粘度，熔点，沸点，离子导率中的至少一者。
电解液的理化参数包括上述多种理化参数中的至少一者，可以使得设计出的电解液在性能方面更符合用户的期望，从而避免不必要的重复劳动，节约实验成本。
在一种可选的实施方式中，成分信息可以包括物质组成和配比。如此，可以根据待设计电解液的成分信息直接得到待设计电解液的配方，进一步减少了实验成本。
在一种可选的实施方式中，成分预测模型可以包括线性回归分析模型，逻辑回归分析模型，支持向量机，最近邻算法模型，K均值聚类算法模型，决策树模型，朴素贝叶斯模型，随机森林模型，降维算法模型，梯度增强算法模型中的至少一者。
在一种可选的实施方式中，待设计电解液可以包括水系电解液和非水电解液。
在一种可选的实施方式中，待设计电解液中可以包括溶剂，电解质盐以及任选的添加剂。
其中，溶剂可以包括一种或多种有机小分子，有机小分子可由C，H，O，N，F，Cl，S，P，B中的至少两种元素组成；
电解质盐可以包括六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草 酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑盐，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐中的至少一者，电解质盐中的阳离子可选自Li +，Na +，K +，Mg 2+，Ca 2+，Zn 2+，Al 3+中的至少一者；
任选的添加剂可以包括成膜添加剂，阻燃添加剂，防过充添加剂，过充保护添加剂及多功能添加剂中的至少一者。
作为一个示例，任选的添加剂可以包括由碳，氢，氧，氮，氟，氯，硫，磷，硼元素构成的一种或多种有机小分子，以及六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐等盐类中一种或多种。其中，上述盐类的阳离子可以选自Li +，Na +，K +，Mg 2+，Ca 2+，Zn 2+，Al 3+中的至少一者。
基于同样的发明构思，本申请实施例还提供了一种电解液设计装置300。
如图3所示，电解液设计装置300可以包括获取模块301，输入模块302和设计模块303。
获取模块301，用于获取待设计电解液的第一理化参数。
预测模块302，用于将第一理化参数输入训练好的成分预测模型，通过成分预测模型对待设计电解液的成分信息进行预测，得到待设计电解液的成分信息，其中，成分预测模型通过基于高通量计算方法得到的训练样本训练得到。
设计模块303，用于根据待设计电解液的成分信息设计待设计电解液。
在一种可选的实施方式中，装置300还可以包括模拟模块，计算模块，创建模块以及训练模块。
模拟模块，用于通过预先训练的仿真模型模拟多种具有不同成分信息的第一电解液。
计算模块，用于利用高通量计算方法对第一电解液进行计算，得到第一电解液对应的第二理化参数。
创建模块，用于分别将每种第一电解液的第二理化参数以及每种第一电解液的成分信息创建训练样本。
训练模块，用于根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在一种可选的实施方式中，训练模块用于根据多个训练样本，训练成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型，具体可以包括：
对每个训练样本，分别执行如下步骤：
将训练样本输入至预设的成分预测模型中，得到与第二理化参数对应的预测成分信息；
根据预测成分信息和第一电解液的成分信息，确定成分预测模型的损失函数值；
在损失函数值不满足训练停止条件的情况下，调整成分预测模型的模型参数，并利用训练样本训练参数调整后的成分预测模型，直至满足训练停止条件，得到训练好的成分预测模型。
在一种可选的实施方式中，高通量计算方法可以包括密度泛函理论计算，分子动力学模拟和有限元计算中的至少一者。
在一种可选的实施方式中，第一理化参数包括构成电解液的溶剂分子的理化参数以及电解液的理化参数中的至少一者。
在一种可选的实施方式中，构成电解液的溶剂分子的理化参数可以包括溶剂分子的几何结构，电子结构，热力学能量，分子前线轨道能级，偶极矩，电子亲和能，氧化还原电位，拉曼光谱，红外光谱，介电常数，粘度，熔点，沸点中的至少一者。
在一种可选的实施方式中，电解液的理化参数可以包括电解液的介电常数，粘度，熔点，沸点，离子导率中的至少一者。
在一种可选的实施方式中，成分信息可以包括物质组成和配比。
在一种可选的实施方式中，成分预测模型可以包括线性回归分析模型，逻辑回归分析模型，支持向量机，最近邻算法模型，K均值聚类算法模型，决策树模型，朴素贝叶斯模型，随机森林模型，降维算法模型，梯度增强 算法模型中的至少一者。
在一种可选的实施方式中，待设计电解液可以包括水系电解液和非水电解液。
在一种可选的实施方式中，待设计电解液中可以包括溶剂，电解质盐以及任选的添加剂，
其中，溶剂可包括一种或多种有机小分子，有机小分子可由C，H，O，N，F，Cl，S，P，B中的至少两种元素组成；
电解质盐可包括六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑盐，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐中的至少一者，电解质盐中的阳离子可选自Li +，Na +，K +，Mg 2+，Ca 2+，Zn 2+，Al 3+中的至少一者；
任选的添加剂可包括成膜添加剂，阻燃添加剂，防过充添加剂，过充保护添加剂及多功能添加剂中的至少一者。
图4示出了本申请实施例提供的电解液设计设备的硬件结构示意图。
在于电解液设计的设备可以包括处理器401以及存储有计算机程序指令的存储器402。
具体地，上述处理器401可以包括中央处理器(CPU)，或者特定集成电路(Application Specific Integrated Circuit，ASIC)，或者可以被配置成实施本申请实施例的一个或多个集成电路。
存储器402可以包括用于数据或指令的大容量存储器。举例来说而非限制，存储器402可包括硬盘驱动器(Hard Disk Drive，HDD)、软盘驱动器、闪存、光盘、磁光盘、磁带或通用串行总线(Universal Serial Bus，USB)驱动器或者两个或更多个以上这些的组合。在合适的情况下，存储器402可包括可移除或不可移除(或固定)的介质。在合适的情况下，存储器402可在综合网关容灾设备的内部或外部。在特定实施例中，存储器402是非易失性固态存储器。
存储器可包括只读存储器(ROM)，随机存取存储器(RAM)，磁 盘存储介质设备，光存储介质设备，闪存设备，电气、光学或其他物理/有形的存储器存储设备。因此，通常，存储器包括一个或多个编码有包括计算机可执行指令的软件的有形(非暂态)计算机可读存储介质(例如，存储器设备)，并且当该软件被执行(例如，由一个或多个处理器)时，其可操作来执行参考根据本申请的一方面的方法所描述的操作。
处理器401通过读取并执行存储器402中存储的计算机程序指令，以实现上述实施例中的任意一种电解液设计方法。
在一个示例中，电解液设计设备还可包括通信接口403和总线410。其中，如图4所示，处理器401、存储器402、通信接口403通过总线410连接并完成相互间的通信。
通信接口403，主要用于实现本申请实施例中各模块、装置、单元和/或设备之间的通信。
总线410包括硬件、软件或两者，将在线数据流量计费设备的部件彼此耦接在一起。举例来说而非限制，总线可包括加速图形端口(AGP)或其他图形总线、增强工业标准架构(EISA)总线、前端总线(FSB)、超传输(HT)互连、工业标准架构(ISA)总线、无限带宽互连、低引脚数(LPC)总线、存储器总线、微信道架构(MCA)总线、外围组件互连(PCI)总线、PCI-Express(PCI-X)总线、串行高级技术附件(SATA)总线、视频电子标准协会局部(VLB)总线或其他合适的总线或者两个或更多个以上这些的组合。在合适的情况下，总线410可包括一个或多个总线。尽管本申请实施例描述和示出了特定的总线，但本申请考虑任何合适的总线或互连。
该电解液设计设备可以基于待设计电解液的第一理化参数执行本申请实施例中的用于设计电解液的方法，从而实现结合图2和图3描述的电解液设计方法和装置。
另外，结合上述实施例中的电解液设计方法，本申请实施例可提供一种计算机存储介质来实现。该计算机存储介质上存储有计算机程序指令；该计算机程序指令被处理器执行时实现上述实施例中的任意一种电解液设计方法。
需要明确的是，本申请并不局限于上文所描述并在图中示出的特定配置和处理。为了简明起见，这里省略了对已知方法的详细描述。在上述实施例中，描述和示出了若干具体的步骤作为示例。但是，本申请的方法过程并不限于所描述和示出的具体步骤，本领域的技术人员可以在领会本申请的精神后，作出各种改变、修改和添加，或者改变步骤之间的顺序。
以上所述的结构框图中所示的功能块可以实现为硬件、软件、固件或者它们的组合。当以硬件方式实现时，其可以例如是电子电路、专用集成电路(ASIC)、适当的固件、插件、功能卡等等。当以软件方式实现时，本申请的元素是被用于执行所需任务的程序或者代码段。程序或者代码段可以存储在机器可读介质中，或者通过载波中携带的数据信号在传输介质或者通信链路上传送。“机器可读介质”可以包括能够存储或传输信息的任何介质。机器可读介质的例子包括电子电路、半导体存储器设备、ROM、闪存、可擦除ROM(EROM)、软盘、CD-ROM、光盘、硬盘、光纤介质、射频(RF)链路，等等。代码段可以经由诸如因特网、内联网等的计算机网络被下载。
还需要说明的是，本申请中提及的示例性实施例，基于一系列的步骤或者装置描述一些方法或系统。但是，本申请不局限于上述步骤的顺序，也就是说，可以按照实施例中提及的顺序执行步骤，也可以不同于实施例中的顺序，或者若干步骤同时执行。
上面参考根据本公开的实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各方面。应当理解，流程图和/或框图中的每个方框以及流程图和/或框图中各方框的组合可以由计算机程序指令实现。这些计算机程序指令可被提供给通用计算机、专用计算机、或其它可编程数据处理装置的处理器，以产生一种机器，使得经由计算机或其它可编程数据处理装置的处理器执行的这些指令使能对流程图和/或框图的一个或多个方框中指定的功能/动作的实现。这种处理器可以是但不限于是通用处理器、专用处理器、特殊应用处理器或者现场可编程逻辑电路。还可理解，框图和/或流程图中的每个方框以及框图和/或流程图中的方框的组合，也可以由执行指定的功能或动作的专用硬件来实现，或可由专用硬 件和计算机指令的组合来实现。
以上所述，仅为本申请的具体实施方式，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、模块和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。应理解，本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。

Claims (15)

  1. 一种电解液设计方法，包括：
    获取待设计电解液的第一理化参数；
    将所述第一理化参数输入训练好的成分预测模型，通过所述成分预测模型对所述待设计电解液的成分信息进行预测，得到所述待设计电解液的成分信息，其中，所述成分预测模型通过基于高通量计算方法得到的训练样本训练得到；
    根据所述待设计电解液的成分信息设计所述待设计电解液。
  2. 根据权利要求1所述的方法，其中，在所述将所述第一理化参数输入训练好的成分预测模型，通过所述成分预测模型对所述待设计电解液的成分信息进行预测，得到所述待设计电解液的成分信息之前，所述方法还包括：
    通过预先训练的仿真模型模拟多种具有不同成分信息的第一电解液；
    利用高通量计算方法对所述第一电解液进行计算，得到所述第一电解液对应的第二理化参数；
    分别将每种所述第一电解液的第二理化参数以及每种所述第一电解液的成分信息创建训练样本；
    根据多个所述训练样本，训练所述成分预测模型，直至满足训练停止条件，得到所述训练好的成分预测模型。
  3. 根据权利要求2所述的方法，其中，所述根据多个所述训练样本，训练所述成分预测模型，直至满足训练停止条件，得到所述训练好的成分预测模型，包括：
    对每个所述训练样本，分别执行如下步骤：
    将所述训练样本输入至预设的成分预测模型中，得到与所述第二理化参数对应的预测成分信息；
    根据所述预测成分信息和所述第一电解液的成分信息，确定所述成分预测模型的损失函数值；
    在所述损失函数值不满足训练停止条件的情况下，调整所述成分预测 模型的模型参数，并利用所述训练样本训练参数调整后的成分预测模型，直至满足所述训练停止条件，得到所述训练好的成分预测模型。
  4. 根据权利要求2所述的方法，其中，所述高通量计算方法包括密度泛函理论计算，分子动力学模拟和有限元计算中的至少一者。
  5. 根据权利要求1所述的方法，其中，所述第一理化参数包括构成所述电解液的溶剂分子的理化参数以及所述电解液的理化参数中的至少一者。
  6. 根据权利要求5所述的方法，其中，所述构成所述电解液的溶剂分子的理化参数包括所述溶剂分子的几何结构，电子结构，热力学能量，分子前线轨道能级，偶极矩，电子亲和能，氧化还原电位，拉曼光谱，红外光谱，介电常数，粘度，熔点，沸点中的至少一者。
  7. 根据权利要求5所述的方法，其中，所述电解液的理化参数包括所述电解液的介电常数，粘度，熔点，沸点，离子导率中的至少一者。
  8. 根据权利要求1所述的方法，其中，所述成分信息包括物质组成和配比。
  9. 根据权利要求1所述的方法，其中，所述成分预测模型包括线性回归分析模型，逻辑回归分析模型，支持向量机，最近邻算法模型，K均值聚类算法模型，决策树模型，朴素贝叶斯模型，随机森林模型，降维算法模型，梯度增强算法模型中的至少一者。
  10. 根据权利要求1-9任一项所述的方法，其中，所述待设计电解液包括水系电解液和非水电解液。
  11. 根据权利要求1-9任一项所述的方法，其中，所述待设计电解液中包括溶剂，电解质盐以及任选的添加剂，
    其中，所述溶剂包括一种或多种有机小分子，所述有机小分子由C，H，O，N，F，Cl，S，P，B中的至少两种元素组成；
    所述电解质盐包括六氟磷酸盐，双氟磺酰亚胺盐，硝酸盐，亚硝酸盐，氟化盐，氯化盐，溴化盐，碘化盐，二氟磷酸盐，二氟草酸硼酸盐，二草酸硼酸盐，四氟草酸硼酸盐，双氟磺酰亚胺盐，双三氟甲磺酰亚胺盐，4，5-二氰基-2-三氟甲基咪唑盐，高氯酸盐，硫酸盐，亚硫酸盐，六氟砷酸盐中的至少一者，所述电解质盐中的阳离子选自Li +，Na +，K +，Mg 2+，Ca 2+， Zn 2+，Al 3+中的至少一者；
    所述任选的添加剂包括成膜添加剂，阻燃添加剂，防过充添加剂，过充保护添加剂及多功能添加剂中的至少一者。
  12. 一种电解液设计装置，包括：
    获取模块，用于获取待设计电解液的第一理化参数；
    预测模块，用于将所述第一理化参数输入训练好的成分预测模型，通过所述成分预测模型对所述待设计电解液的成分信息进行预测，得到所述待设计电解液的成分信息，其中，所述成分预测模型通过基于高通量计算方法得到的训练样本训练得到；
    设计模块，用于根据所述待设计电解液的成分信息设计所述待设计电解液。
  13. 一种电解液设计设备，包括：处理器以及存储有计算机程序指令的存储器；
    所述处理器执行所述计算机程序指令时实现如权利要求1-11任意一项所述的电解液设计方法。
  14. 一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现如权利要求1-11任意一项所述的电解液设计方法。
  15. 一种计算机程序产品，所述计算机程序产品中的指令由电子设备的处理器执行时，使得所述电子设备执行如权利要求1-11任意一项所述的电解液设计方法。
PCT/CN2022/072387 2021-12-08 2022-01-17 电解液设计方法、装置、设备、介质及程序产品 WO2023103150A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111492691.8 2021-12-08
CN202111492691.8A CN114255826A (zh) 2021-12-08 2021-12-08 电解液设计方法、装置、设备、介质及程序产品

Publications (1)

Publication Number Publication Date
WO2023103150A1 true WO2023103150A1 (zh) 2023-06-15

Family

ID=80794273

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/072387 WO2023103150A1 (zh) 2021-12-08 2022-01-17 电解液设计方法、装置、设备、介质及程序产品

Country Status (2)

Country Link
CN (1) CN114255826A (zh)
WO (1) WO2023103150A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4322043A1 (en) * 2022-06-28 2024-02-14 Tata Consultancy Services Limited Method and system for identifying electrolyte composition for optimal battery performance
CN115114810B (zh) * 2022-08-31 2022-11-11 北京金羽新材科技有限公司 一种电解液模拟分析方法、装置、设备、介质
CN116092593B (zh) * 2023-04-10 2023-06-20 北京金羽新材科技有限公司 电解液成分预测方法、装置和计算机设备
CN116913423B (zh) * 2023-06-27 2024-06-14 浙江东大树脂科技股份有限公司 用于不饱和聚酯树脂的合成工艺优化方法及系统
CN117607227B (zh) * 2023-11-27 2024-06-21 南京机电职业技术学院 基于深度学习的电解质分析仪实时监测与异常预警方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102931436A (zh) * 2012-09-14 2013-02-13 高平唐一新能源科技有限公司 一种基于质量三角形模型的电解液组份优化方法
US20200294630A1 (en) * 2019-03-12 2020-09-17 California Institute Of Technology Systems and Methods for Determining Molecular Structures with Molecular-Orbital-Based Features
US20200321080A1 (en) * 2019-04-05 2020-10-08 Tata Consultancy Services Limited Method and system for in-silico optimization and design of electrolytes
CN113312807A (zh) * 2021-07-30 2021-08-27 南栖仙策(南京)科技有限公司 一种基于锂电池性能模拟环境的电解液配方推荐方法
JP2021176131A (ja) * 2020-05-01 2021-11-04 ダイキン工業株式会社 学習モデル生成方法、プログラム、記憶媒体、学習済みモデル

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108399210A (zh) * 2018-02-02 2018-08-14 电子科技大学 一种用于锂电池的电解质材料筛选方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102931436A (zh) * 2012-09-14 2013-02-13 高平唐一新能源科技有限公司 一种基于质量三角形模型的电解液组份优化方法
US20200294630A1 (en) * 2019-03-12 2020-09-17 California Institute Of Technology Systems and Methods for Determining Molecular Structures with Molecular-Orbital-Based Features
US20200321080A1 (en) * 2019-04-05 2020-10-08 Tata Consultancy Services Limited Method and system for in-silico optimization and design of electrolytes
JP2021176131A (ja) * 2020-05-01 2021-11-04 ダイキン工業株式会社 学習モデル生成方法、プログラム、記憶媒体、学習済みモデル
CN113312807A (zh) * 2021-07-30 2021-08-27 南栖仙策(南京)科技有限公司 一种基于锂电池性能模拟环境的电解液配方推荐方法

Also Published As

Publication number Publication date
CN114255826A (zh) 2022-03-29

Similar Documents

Publication Publication Date Title
WO2023103150A1 (zh) 电解液设计方法、装置、设备、介质及程序产品
Yao et al. Applying classical, ab initio, and machine-learning molecular dynamics simulations to the liquid electrolyte for rechargeable batteries
Ravikumar et al. Effect of salt concentration on properties of lithium ion battery electrolytes: a molecular dynamics study
Wang et al. Highly reversible zinc metal anode for aqueous batteries
Chen et al. Ion–solvent chemistry in lithium battery electrolytes: From mono-solvent to multi-solvent complexes
CN115114810B (zh) 一种电解液模拟分析方法、装置、设备、介质
Luo et al. A survey of artificial intelligence techniques applied in energy storage materials R&D
Liu et al. Insight into the nanostructure of “water in salt” solutions: A SAXS/WAXS study on imide-based lithium salts aqueous solutions
Araujo et al. Towards novel calcium battery electrolytes by efficient computational screening
Tao et al. Battery cross-operation-condition lifetime prediction via interpretable feature engineering assisted adaptive machine learning
Garcia-Quismondo et al. New technique for probing the protecting character of the solid electrolyte interphase as a critical but elusive property for pursuing long cycle life lithium-ion batteries
Zheng et al. Computational approach inspired advancements of solid-state electrolytes for lithium secondary batteries: from first-principles to machine learning
Xu et al. Theoretical and experimental design in the study of sulfide-based solid-state battery and interfaces
Tan et al. Decoding Electrochemical Processes of Lithium‐Ion Batteries by Classical Molecular Dynamics Simulations
Ghosh et al. Engineering design of battery module for electric vehicles: comprehensive framework development based on density functional theory, topology optimization, machine learning, multidisciplinary design optimization, and digital twins
Song et al. Correlating Solid Electrolyte Interphase Composition with Dendrite‐Free and Long Life‐Span Lithium Metal Batteries via Advanced Characterizations and Simulations
Xu et al. Machine learning-accelerated discovery and design of electrode materials and electrolytes for lithium ion batteries
Xiao et al. Advances and applications of computational simulations in the inhibition of lithium dendrite growth
Sundberg et al. High-throughput discovery of fluoride-ion conductors via a decoupled, dynamic, and iterative (DDI) framework
Angarita-Gomez et al. Ion mobility and solvation complexes at liquid–solid interfaces in dilute, high concentration, and localized high concentration electrolytes
Li et al. Status and Prospects of Research on Lithium-Ion Battery Parameter Identification
Chen et al. Artificial intelligence for the understanding of electrolyte chemistry and electrode interface in lithium battery
Liu et al. Elucidating solid electrolyte interphase formation in sodium-based batteries: key reductive reactions and inorganic composition
Feng et al. Kinetic resolution of thermal runaway for lithium-ion batteries: A Gaussian surrogate-assisted separate optimization approach
Zyubina et al. Quantum-chemical modeling of the charge transport properties of the ammonium form of Nafion

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22902595

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE