CN117649905A - Data prediction method, device and storage medium for battery organic positive electrode material - Google Patents
Data prediction method, device and storage medium for battery organic positive electrode material Download PDFInfo
- Publication number
- CN117649905A CN117649905A CN202410123079.0A CN202410123079A CN117649905A CN 117649905 A CN117649905 A CN 117649905A CN 202410123079 A CN202410123079 A CN 202410123079A CN 117649905 A CN117649905 A CN 117649905A
- Authority
- CN
- China
- Prior art keywords
- positive electrode
- organic positive
- electrode material
- battery
- predicted
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 239000007774 positive electrode material Substances 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000000463 material Substances 0.000 claims description 136
- 238000007614 solvation Methods 0.000 claims description 65
- 230000009467 reduction Effects 0.000 claims description 49
- 230000000875 corresponding effect Effects 0.000 claims description 43
- 239000010406 cathode material Substances 0.000 claims description 13
- 238000013461 design Methods 0.000 claims description 7
- 239000010405 anode material Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 125000000524 functional group Chemical group 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 18
- 238000013528 artificial neural network Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 15
- 238000004364 calculation method Methods 0.000 description 13
- 238000011161 development Methods 0.000 description 13
- 238000012827 research and development Methods 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 150000001728 carbonyl compounds Chemical class 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000002484 cyclic voltammetry Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011368 organic material Substances 0.000 description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005421 electrostatic potential Methods 0.000 description 3
- 238000004770 highest occupied molecular orbital Methods 0.000 description 3
- 229910052744 lithium Inorganic materials 0.000 description 3
- 229910001416 lithium ion Inorganic materials 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000005486 organic electrolyte Substances 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- AZQWKYJCGOJGHM-UHFFFAOYSA-N 1,4-benzoquinone Chemical compound O=C1C=CC(=O)C=C1 AZQWKYJCGOJGHM-UHFFFAOYSA-N 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000004090 dissolution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004776 molecular orbital Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000003775 Density Functional Theory Methods 0.000 description 1
- 241001178520 Stomatepia mongo Species 0.000 description 1
- 150000008064 anhydrides Chemical class 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 125000002915 carbonyl group Chemical group [*:2]C([*:1])=O 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 125000006575 electron-withdrawing group Chemical group 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 150000003949 imides Chemical class 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004768 lowest unoccupied molecular orbital Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 150000002898 organic sulfur compounds Chemical class 0.000 description 1
- 210000002381 plasma Anatomy 0.000 description 1
- -1 radical compound Chemical class 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010421 standard material Substances 0.000 description 1
- 239000011232 storage material Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/26—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating electrochemical variables; by using electrolysis or electrophoresis
- G01N27/416—Systems
- G01N27/48—Systems using polarography, i.e. measuring changes in current under a slowly-varying voltage
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Analytical Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Immunology (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Electrochemistry (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Battery Electrode And Active Subsutance (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a data prediction method, equipment and a storage medium of an organic positive electrode material of a battery.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a storage medium for predicting data of an organic positive electrode material of a battery.
Background
The development of material big data is promoted by the proposal of material genetic engineering, the comprehensive application of artificial intelligence technology in the material field is promoted, the development of data-driven material is formed, and the research on the development of the fourth Fan Shizheng is more and more important. The advantages of battery organic cathode materials, such as abundant reserves, high theoretical specific capacities, structural diversity, etc., are considered as very attractive candidates for secondary battery cathode materials, which generally have relatively good cycling stability and high theoretical specific capacities.
However, the organic positive electrode compound still has problems of low conductivity (affecting rate performance) and easy dissolution of the organic electrolyte (affecting cycle stability), which severely limits the further development of the organic positive electrode compound.
The current material research and development mainly relies on repeated experiments of researchers to find the organic material with the optimal working voltage, which clearly prolongs the research and development period of the material.
In view of this, the present invention has been made.
Disclosure of Invention
In order to solve the technical problems, the invention provides a data prediction method, equipment and storage medium for an organic positive electrode material of a battery, which can be used for predicting the battery performance of the organic positive electrode material, guiding the development of the battery and solving the problem of overlong research and development period caused by artificial experiment on the performance of the organic material in the prior art.
The embodiment of the invention provides a data prediction method of an organic positive electrode material of a battery, which comprises the following steps:
obtaining structural information of a material to be detected of an organic positive electrode material to be predicted, and obtaining experimental property data of a target battery applying the organic positive electrode material to be predicted;
inputting the structural information of the material to be detected into a voltage solvation energy model to obtain the predicted reduction voltage and the predicted solvation energy of the target battery; inputting the structural information of the material to be detected into a theoretical parameter model to obtain a predicted theoretical parameter of the target battery; inputting the structural information of the material to be detected and experimental property data of the target battery into a capacity model to obtain the predicted capacity of the target battery;
determining battery performance data corresponding to the organic positive electrode material to be predicted based on the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameter and the predicted capacity;
wherein the voltage solvation energy model, the theoretical parametric model and the capacity model are trained based on a pre-constructed material database.
The embodiment of the invention provides electronic equipment, which comprises:
A processor and a memory;
the processor is configured to execute the steps of the data prediction method of the organic positive electrode material of a battery according to any embodiment by calling the program or the instructions stored in the memory.
An embodiment of the present invention provides a computer-readable storage medium storing a program or instructions that cause a computer to execute the steps of the method for predicting data of a battery organic cathode material according to any one of the embodiments.
The embodiment of the invention has the following technical effects:
the method comprises the steps of obtaining structural information of a material to be detected of an organic positive electrode material to be predicted, and obtaining experimental property data of a target battery applying the organic positive electrode material to be predicted, so that the structural information of the material to be detected is input into a voltage solvation energy model and a theoretical parameter model; the structure information and experimental property data of the material to be detected are input into a capacity model to obtain the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameters and the predicted capacity of the target battery, so that the battery performance data corresponding to the organic positive electrode material to be predicted are obtained, the prediction of the battery performance of various organic positive electrode materials can be realized, the method can be used for guiding the development of batteries with the characteristics of high reduction voltage, low solvation energy, high capacity and the like, the problem that the battery research and development period is overlong due to the performance of the artificial experimental organic material in the prior art is solved, and the battery research and development efficiency is greatly improved while the accuracy of the battery performance analysis of the organic positive electrode material is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a data prediction method of an organic positive electrode material of a battery according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the construction of a material database according to an embodiment of the present invention;
FIG. 3 is a functional schematic of a materials database according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
The data prediction method for the organic positive electrode material of the battery is mainly suitable for predicting the battery performance data of the organic positive electrode material, so that the battery can be designed according to the battery performance data of each organic positive electrode material. The data prediction method of the battery organic positive electrode material provided by the embodiment of the invention can be executed by electronic equipment integrated in a computer.
Fig. 1 is a flowchart of a data prediction method of an organic positive electrode material of a battery according to an embodiment of the present invention. Referring to fig. 1, the data prediction method of the battery organic cathode material specifically includes:
s110, obtaining structural information of a material to be detected of the organic positive electrode material to be predicted, and obtaining experimental property data of a target battery applying the organic positive electrode material to be predicted.
The organic positive electrode material to be predicted may be a carbonyl positive electrode material, such as quinone, imide, or anhydride, or the like, or may be an organic sulfur compound, an organic radical compound, or the like. In this embodiment, different organic positive electrode materials to be predicted may be constructed by changing structural parameters such as electron withdrawing groups, the number or density of conjugated rings, and the like.
Specifically, for the organic positive electrode material to be predicted, structural information of the material to be predicted of the organic positive electrode material to be predicted can be obtained, wherein the structural information of the material to be predicted can include molecular formula, density, relative molecular mass, conjugated ring number and the like of the organic positive electrode material to be predicted. The material structure information to be measured may be in the form of a file (format may be. Xyz,. Sdf,. Cif).
And experimental property data of the target battery applying the organic positive electrode material to be predicted can be obtained. The experimental property data may include, among other things, a cyclic voltammetry characteristic curve, rate capability, first-turn coulombic efficiency, and battery cycle life curve, where the battery cyclic voltammetry characteristic curve may include a battery charge current characteristic, a battery charge voltage characteristic, a battery discharge current characteristic, and a battery discharge voltage characteristic.
S120, inputting structural information of a material to be detected into a voltage solvation energy model to obtain predicted reduction voltage and predicted solvation energy of the target battery, inputting structural information of the material to be detected into a theoretical parameter model to obtain predicted theoretical parameters of the target battery, and inputting structural information of the material to be detected and experimental property data of the target battery into a capacity model to obtain predicted capacity of the target battery.
The voltage solvation energy model, the theoretical parameter model and the capacity model are obtained through training based on a pre-constructed material database.
In an embodiment of the present invention, the material database may include material structure information of each organic positive electrode material, corresponding calculated property data (reduction voltage and solvation energy), and experimental property data and theoretical parameters of a battery to which each organic positive electrode material is applied.
Optionally, the method provided by the embodiment of the invention further includes:
acquiring material structure information, corresponding reduction voltage and solvation energy of each organic positive electrode material and theoretical parameters of a battery applying each organic positive electrode material from a theoretical data set stored in advance, and constructing a material database;
for each organic positive electrode material in the material database, searching experimental property data of a battery applying each organic positive electrode material in a pre-stored literature data set, and storing the searched theoretical parameters and the organic positive electrode materials in the material database in a correlated mode.
Wherein the theoretical dataset may be constituted by data in a pubhem database. The PubChem database contains 1.12 million relevant data for organic positive electrode materials.
Specifically, the data in the pubhem database can be stored as a theoretical data set, and then the material structure information, the corresponding reduction voltage and the solvation energy of each organic positive electrode material and the theoretical parameters of the battery applying each organic positive electrode material are extracted from the theoretical data set to construct a material database. The theoretical parameters may include theoretical specific capacity, front molecular orbital, molecular electrostatic potential, migration energy barrier, etc.
In order to improve the training efficiency of the model, considering that the conjugated ring number of the organic positive electrode material is not less than 3 and the battery performance of the organic positive electrode material with the specific capacity of 200 mAh/g-400 mAh/g is better, data in the theoretical data set can be firstly screened to save relevant data of part of the organic positive electrode material, so that the model training data amount is reduced and the training efficiency of the model is improved while the model accuracy is ensured.
In one example, in a pre-stored theoretical data set, material structure information, corresponding reduction voltage and solvation energy of each organic positive electrode material, and theoretical parameters of a battery to which each organic positive electrode material is applied are obtained, and a material database is constructed, including:
Screening organic positive electrode materials with the number of conjugated rings not less than a preset number in a theoretical data set stored in advance to obtain candidate organic positive electrode materials;
screening organic positive electrode materials with specific capacity within a preset range from all candidate organic positive electrode materials to obtain organic positive electrode materials to be written;
and writing the material structure information, the corresponding reduction voltage and solvation energy of all the organic positive electrode materials to be written and the theoretical parameters of the battery applying the organic positive electrode materials to be written into a material database.
That is, the organic positive electrode materials having the number of conjugated rings not less than the preset number (may be 3) may be first selected from the theoretical data set to determine the organic positive electrode materials having the number of conjugated rings not less than the preset number as candidate organic positive electrode materials.
Further, the organic positive electrode materials with specific capacities within a preset range (which may be 200mAh/g to 400 mAh/g) may be selected from all the candidate organic positive electrode materials continuously, so that the organic positive electrode materials with the number of the conjugated rings not less than the preset number and the specific capacities within the preset range are determined as the organic positive electrode materials to be written.
Further, the theoretical data set, the material structure information of all the organic positive electrode materials to be written, the corresponding reduction voltage and solvation energy, and the theoretical parameters of the battery applying each organic positive electrode material to be written can be written into the material database.
In the above example, by selecting a part of the organic cathode materials by the number of conjugated rings and specific capacity, constructing a material database for training of a model, it is possible to improve the construction efficiency of the material database and, while ensuring the model training accuracy, improve the training efficiency of the model.
After extracting the material structure information, the corresponding reduction voltage and the solvation energy of the organic positive electrode material in the theoretical data set, and the theoretical parameters of the battery applying each organic positive electrode material, further, the experimental property data of the organic positive electrode material can be continuously extracted from the literature data set. Wherein, the literature data set can be composed of data in each literature.
Fig. 2 is a schematic diagram illustrating construction of a material database according to an embodiment of the present invention. Wherein theoretical parameters of each organic positive electrode material can be collected from a pubhem database (i.e., theoretical data set), and experimental property data of each organic positive electrode material can be collected from a literature (i.e., literature data set). In addition to theoretical parameters and experimental property data, material structure information of each organic positive electrode material, and corresponding reduction voltage and solvation energy may also be collected from a theoretical data set.
As shown in fig. 2, the constructed material database may be used for machine learning prediction, i.e., a training model is used for predicting parameters such as reduction voltage of the organic positive electrode material, or may be used for open sharing data, i.e., relevant data supporting a user searching for a specific organic positive electrode material, relevant data for a user uploading a specific organic positive electrode material, and the like.
Wherein the materials database can be used to train a voltage solvation energy model, a theoretical parametric model, and a capacity model.
In a specific embodiment, the voltage solvation energy model is trained based on a first sample set, the theoretical parameter model is trained based on a second sample set, and the capacity model is trained based on a third sample set;
the first sample set is composed of material structure information of each organic positive electrode material in a material database, corresponding reduction voltage and solvation energy, the second sample set is composed of material structure information of each organic positive electrode material in the material database and theoretical parameters of a battery applying each organic positive electrode material, and the third sample set is composed of material structure information of each organic positive electrode material in the material database, experimental property data of the battery applying each organic positive electrode material and corresponding capacity.
Exemplary, training of the voltage solvation energy model includes the steps of: constructing a first sample set based on material structure information of each organic positive electrode material in a material database and corresponding reduction voltage and solvation energy; training parameters in a first neural network based on a first sample set to obtain a voltage solvation energy model;
the training of the theoretical parameter model comprises the following steps: constructing a second sample set based on material structure information of each organic positive electrode material in the material database and theoretical parameters of a battery applying each organic positive electrode material; training parameters in a second neural network based on the second sample set to obtain a theoretical parameter model;
the training of the capacity model comprises the following steps: constructing a third sample set based on material structure information of each organic positive electrode material in the material database, experimental property data of a battery applying each organic positive electrode material and corresponding capacity; and training parameters in a third neural network based on the third sample set to obtain a capacity model.
That is, the parameters in the first neural network may be trained by taking the material structure information of each organic positive electrode material in the material database as input, and the corresponding reduction voltage and solvation energy as output. If the material structure information of each organic positive electrode material is input into the first neural network, the loss function is calculated according to the prediction result output by the first neural network and the corresponding reduction voltage and solvation energy, and the parameters in the first neural network are reversely adjusted according to the calculation result of the loss function until the calculation result of the loss function converges, and then the voltage solvation energy model can be obtained.
And, the material structure information of each organic positive electrode material in the material database can be used as input, the theoretical parameters of the battery applying each organic positive electrode material can be used as output, and the parameters in the second neural network can be trained. If the material structure information of each organic positive electrode material is input into the second neural network, the loss function is calculated according to the prediction result output by the second neural network and the theoretical parameters of the corresponding battery, and the parameters in the second neural network are reversely adjusted according to the calculation result of the loss function until the calculation result of the loss function is converged, and then the theoretical parameter model can be obtained.
In addition, the material structure information of each organic positive electrode material in the material database and experimental property data of the battery applying each organic positive electrode material can be used as input, the corresponding capacity can be used as output, and parameters in the third neural network can be trained. For example, the material structure information of each organic positive electrode material and the experimental property data of the battery are input into the third neural network, the loss function is calculated according to the prediction result output by the third neural network and the capacity of the corresponding battery, and the parameters in the third neural network are reversely adjusted according to the calculation result of the loss function until the calculation result of the loss function converges, and at the moment, the capacity model can be obtained.
The capacity model outputs corresponding capacities based on the material structure information and the experimental property data, and can also predict corresponding capacities by combining the number of Li, na or Zn embedded plasmas.
In the embodiment of the present invention, considering that the material structure information includes a plurality of parameters and the experimental property data includes a plurality of parameters, in order to further improve the efficiency of model prediction, a first related parameter related to the reduction voltage and the solvation energy may be determined in the material structure information before the material structure information is input to the voltage solvation energy model, and then the first related parameter is input to the voltage solvation energy model. And before the material structure information is input into the theoretical parameter model, determining a second associated parameter related to the theoretical parameter in the material structure information, and further inputting the second associated parameter into the theoretical parameter model. And determining a third associated parameter related to the capacity in the material structure information and the experimental property data before inputting the material structure information and the experimental property data to the capacity model, and further inputting the third associated parameter to the capacity model.
By way of example, the correlation between the parameters in the material structure information and the reduction voltage and the solvation energy, the correlation between the parameters in the material structure information and the theoretical parameters, the correlation between the parameters in the material structure information and the parameters in the experimental property data and the capacity can be calculated by the data in the material database, and then the first correlation parameter, the second correlation parameter and the third correlation parameter are selected based on the correlation. By the method, the data dimension of the model can be reduced while the prediction accuracy of the model is ensured, and the prediction efficiency of the model is further improved.
Specifically, after a voltage solvation energy model, a theoretical parameter model and a capacity model are obtained based on training of a material database, for an organic positive electrode material to be predicted, structural information of the material to be detected of the organic positive electrode material to be predicted can be input into the voltage solvation energy model and the theoretical parameter model to obtain a predicted reduction voltage, a predicted solvation energy and a predicted theoretical parameter; and inputting the structural information and experimental property data of the to-be-predicted organic positive electrode material to a capacity model to obtain the predicted capacity.
And S130, determining battery performance data corresponding to the organic positive electrode material to be predicted based on the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameters and the predicted capacity.
Specifically, the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameter and the predicted capacity of the organic positive electrode material to be predicted may constitute battery performance data corresponding to the organic positive electrode material to be predicted. The predicted theoretical parameters may include, among others, theoretical specific capacity, theoretical mass, theoretical volumetric energy density, theoretical voltage, LUMO-HOMO (front molecular orbital) properties, and conductivity.
In the embodiment of the invention, the prediction of the battery performance data can be respectively carried out on a plurality of organic positive electrode materials to be predicted, so that the high-flux calculation on the organic positive electrode materials is realized, and the performance design of the battery is conveniently guided.
After predicting the battery performance data corresponding to the plurality of organic positive electrode materials to be predicted, respectively, the organic positive electrode materials to be predicted and the corresponding battery performance data can be stored in a material database in an associated manner. In addition, performance evaluation can be carried out on a plurality of organic positive electrode materials to be predicted based on battery performance data, and organic positive electrode materials meeting the battery design target can be screened out.
For example, in a specific implementation manner, the method provided by the embodiment of the invention further includes:
the method comprises the steps of searching a final organic positive electrode material from all organic positive electrode materials to be predicted according to battery performance data corresponding to all the organic positive electrode materials to be predicted by taking high reduction voltage, low solvation energy and high capacity battery performance as targets; a cell material design list was constructed from all final organic positive electrode materials.
Among them, the high-capacity battery performance may include high theoretical specific capacity and high conductivity.
For example, for all the organic positive electrode materials to be predicted, the organic positive electrode materials to be predicted may be ranked in order of reduction voltage from large to small, solvation energy from small to large, theoretical specific capacity from large to small, conductivity from large to small, and capacity from large to small, respectively, to obtain a plurality of ranking results.
Further, a performance evaluation function may be constructed according to the ranking of the reduction voltage, the ranking of the solvation energy, the ranking of the theoretical specific capacity, the ranking of the conductivity, and the ranking of the capacity, for example, the performance evaluation function may be a weighted calculation of the ranking result of the reduction voltage, the ranking result of the solvation energy, the ranking result of the theoretical specific capacity, the ranking result of the conductivity, and the ranking result of the capacity by using the corresponding weights.
Further, the ranking result of the reduction voltage, the ranking result of the solvation energy, the ranking result of the theoretical specific capacity, the ranking result of the conductivity and the ranking result of the capacity of each organic positive electrode material to be predicted may be substituted into the performance evaluation function to calculate the performance evaluation value of each organic positive electrode material to be predicted.
Further, with the aim of high reduction voltage, low solvation energy and high capacity battery performance, performance evaluation values of all the organic positive electrode materials to be predicted can be ranked, and the first N organic positive electrode materials are selected as final organic positive electrode materials, so that a battery material design list is constructed.
In addition to the above-mentioned construction of the performance evaluation function based on the sorting result, the final organic cathode material may be selected from the sorting of the performance evaluation values, or the first M organic cathode materials may be selected from the sorting (sorting of the reduction voltage, sorting of the solvation energy, sorting of the theoretical specific capacity, sorting of the conductivity, and sorting of the capacity) directly as the final organic cathode materials, respectively, to obtain 5×m final organic cathode materials, so as to achieve the goals of high reduction voltage, low solvation energy, and high capacity battery performance.
Specifically, the generated battery material design list can be displayed on a front-end display interface, so that a user can know each organic positive electrode material with high reduction voltage, low solvation energy and high capacity battery performance conveniently, and then battery design is performed.
In the embodiment of the invention, the material database can be used for searching data besides the battery performance data for predicting the organic positive electrode material by training a model. Optionally, the method provided by the embodiment of the invention further includes:
Responding to search information input by a user for the organic positive electrode material to be searched in a front-end display interface, and inquiring material structure information, corresponding reduction voltage and solvation energy of the organic positive electrode material to be searched, experimental property data and theoretical parameters of a battery applying the organic positive electrode material to be searched in a material database based on the search information; and displaying the query result on the front-end display interface.
Specifically, the user may enter search information of the organic positive electrode material to be searched in the front-end display interface, and based on the search information, the corresponding material structure information, the corresponding reduction voltage and the solvation energy, experimental property data (such as a multiplying power curve, a cycle life curve, a CV curve, etc.) and theoretical parameters (such as LUMO-HOMO, a molecular electrostatic potential, a lithium potential, etc.) of the battery applying the organic positive electrode material to be searched may be searched in the material database, so that the searched result is displayed on the front-end display interface.
In one example, the search information is a SMILES string, name, functional group, operating voltage, or theoretical specific capacity of the organic positive electrode material to be searched. Among them, the SMILES character string can be understood as a molecular linear input specification (Simplified Molecular Input Line Entry System) character string. The name may be a generic name, short name, or molecular formula of the organic positive electrode material to be searched.
For example, in response to a paste operation by a user on the front-end presentation interface, a SMILES string may be extracted from content copied by the user; alternatively, in response to a user drawing operation within a drawing box in the front-end presentation interface, the SMILES string may be determined according to a structure manually drawn by the user within the drawing box.
That is, the front-end presentation interface supports searching material structure information of the organic positive electrode material, corresponding reduction voltage and solvation energy, and experimental property data and theoretical parameters of a battery to which the organic positive electrode material to be searched is applied, according to a SMILES character string, a name, a functional group, an operating voltage or a theoretical specific capacity.
Fig. 3 is a functional schematic of a material database according to an embodiment of the present invention. The material database may be connected to a back-end service, and after a user enters a SMILES character string, a name, a functional group, a working voltage or a theoretical specific capacity in a search page of a front-end display interface, the corresponding detailed information (mongo db) may be queried in the material database by a search engine (such as MySQL) of the back-end service, so that the corresponding detailed information may be displayed on a detail page of the front-end display interface, for example, the material structure information may be displayed in a manner of visualizing a molecular structure, or, curves such as a cyclic voltammetry characteristic curve, a rate performance curve, a cyclic lifetime curve, and the like may be displayed as interactable data (for example, a point triggered by the user on the curve is displayed in response to the point), and the user may be further supported to download the displayed detailed information on the detail page.
As can be seen from fig. 3, the back-end service may also be used to parse the batch data in the materials database through a data parsing program, thereby training to obtain the neural network.
In the embodiment of the invention, the material database can be used for data searching and model prediction and also can support the uploading of data by users.
Optionally, the method provided by the embodiment of the invention further includes:
responding to a file uploaded by the organic anode material to be uploaded in a front-end display interface by a user, and performing format verification on the file; after the format verification is passed, the organic positive electrode material to be uploaded and material structure information, reduction voltage, solvation energy, experimental property data or theoretical parameters in the file are stored in a material database in a correlated manner.
Specifically, the user may upload the file on an upload page of the front-end presentation interface. As shown in fig. 3, the user may upload a plurality of files of the organic positive electrode material at a time, i.e., batch upload, or may upload only a single file of the organic positive electrode material, i.e., a single upload.
Wherein, the user can upload the file describing the structural information of the material in the format of cif, sdf, mol, xyz, gif, pdb, etc. Alternatively, the user may upload a file describing theoretical parameters, such as LUMO, HOMO, and molecular electrostatic potential (determining active sites of the material) of the organic positive electrode material, which may be in the format of. Cub,. Fchk, etc. Alternatively, the user may upload a file describing experimental property data, such as a cyclic voltammetry characteristic curve, a rate performance curve, a cyclic lifetime curve, etc., which may be in the format of jpg, opj, etc.
Aiming at the file uploaded by the user, the file can be audited, such as format verification and data accuracy, and the data auditing result is fed back through an auditing page, and the auditing page can also support data preview. Further, after the format verification is passed, the organic positive electrode material to be uploaded and the material structure information, the reduction voltage, the solvation energy, the experimental property data or the theoretical parameters in the file can be stored in a material database in a correlated manner.
The invention has the following technical effects: the structure information of the to-be-predicted organic positive electrode material is obtained, experimental property data of a target battery applying the to-be-predicted organic positive electrode material is obtained, so that the structure information of the to-be-predicted material is input into a voltage solvation energy model and a theoretical parameter model, the structure information of the to-be-detected material and the experimental property data are input into a capacity model, the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameter and the predicted capacity of the target battery are obtained, further battery performance data corresponding to the to-be-predicted organic positive electrode material are obtained, prediction of battery performance of various organic positive electrode materials can be achieved, the method can be used for guiding development of batteries with the characteristics of low reduction voltage, high solvation energy or high capacity and the like, the problem that the battery research and development period is overlong due to performance of artificial experimental organic materials in the prior art is solved, and battery research and development efficiency is greatly improved while the accuracy of battery performance analysis of the organic positive electrode material is ensured.
The data prediction method of the organic positive electrode material of the battery provided by the embodiment of the invention has the following technical effects:
1. in recent years, the rapid development of communication electronic devices and electric vehicles has placed higher demands on the energy density of lithium ion batteries. In the current commercial lithium ion battery, the actual specific capacity (140-200 mAh/g) of the positive electrode material is far lower than that of the negative electrode (> 300 mAh/g), and the ratio of the positive electrode material to the single battery is the largest, so that the development of a novel positive electrode material with high specific capacity and low cost is a key for the development of the lithium ion battery. The organic positive electrode material is widely paid attention to due to the characteristics of rich resources, environmental friendliness, high structural designability and the like. Among them, carbonyl compounds have advantages of high theoretical capacity and outstanding chemical stability, and have been paid attention to by researchers. However, carbonyl compounds still have problems of low conductivity (affecting rate capability) and easy dissolution in organic electrolyte (affecting cycle stability), which severely limits further development of carbonyl compounds.
Therefore, in order to solve the problems that carbonyl compounds are easy to dissolve in organic electrolyte and low in conductivity, and the like, the embodiment of the invention utilizes high-flux calculation to count battery performance data of various organic anode materials in a large scale, the organic anode materials are rapidly and efficiently summarized by a theory-calculation-experiment coupling method, electrochemical performance, lithium storage mechanism and structure-performance relation of various compounds are comprehensively researched, so that the organic anode materials with excellent prediction performance are designed, the system deep research of researchers on battery performance is facilitated, a high-flux intelligent screening method is developed by a density functional theory and machine learning framework, the commonality of experiments and theories is found, and a new battery organic anode material is further designed.
Moreover, the model obtained by training can be used for high-flux calculation, the code autonomous controllable rate is 100%, and the quick prediction of the battery performance can be realized on tens of millions of small molecular materials.
2. The existing battery material has complex scientific data types and multiple metadata types and formats, and the battery data has extremely high application value in the embodiment of the invention, so that character set matching is performed by adopting artificial intelligent acquisition according to documents and PubCHem databases, such as experimental property data and theoretical parameters of theoretical specific capacity, front line molecular orbit, working voltage, cycle life, multiplying power performance and the like, data acquisition is realized, and the research and development process of the battery material is accelerated to a certain extent. And the method fills the blank of fusion of the existing data and the artificial intelligent prediction algorithm, and effectively solves the problems of interaction of the front end, the rear end and the super computing end, calculation, result extraction, warehousing, analysis, visualization and automatic completion of intelligent prediction full-link.
In addition, the material database can be popularized and applied to the platform, serve related enterprises of materials, and support the realization of the substantial reduction of material research and development cost and research and development period. Meanwhile, in the process, the method can be used for realizing material simulation calculation, scientific data exchange and virtuous circle and sustainable development of industrial service.
3. Aiming at the problem of lack of a battery data island type storage and sharing mechanism, the embodiment of the invention supports audience groups of different enterprises, schools, experiments and specialized scientific researchers, autonomously uploads data, realizes a hierarchical dynamic extensible high-efficiency storage material database, supports user development, integration and extension of material calculation tools, supports batch or single uploading, and forms a standard material database.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, electronic device 400 includes one or more processors 401 and memory 402.
The processor 401 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities and may control other components in the electronic device 400 to perform desired functions.
Memory 402 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 401 to implement the data prediction method and/or other desired functions of the battery organic positive electrode material of any of the embodiments of the present invention described above. Various content such as initial arguments, thresholds, etc. may also be stored in the computer readable storage medium.
In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, and the like. The output device 404 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 404 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 400 that are relevant to the present invention are shown in fig. 4 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, electronic device 400 may include any other suitable components depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the invention may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps of the method for data prediction of a battery organic cathode material provided by any of the embodiments of the invention.
The computer program product may write program code for performing operations of embodiments of the present invention in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present invention may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform the steps of the method for predicting data of a battery organic cathode material provided by any embodiment of the present invention.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for predicting data of an organic positive electrode material of a battery, comprising:
obtaining structural information of a material to be detected of an organic positive electrode material to be predicted, and obtaining experimental property data of a target battery applying the organic positive electrode material to be predicted;
inputting the structural information of the material to be detected into a voltage solvation energy model to obtain the predicted reduction voltage and the predicted solvation energy of the target battery; inputting the structural information of the material to be detected into a theoretical parameter model to obtain a predicted theoretical parameter of the target battery; inputting the structural information of the material to be detected and experimental property data of the target battery into a capacity model to obtain the predicted capacity of the target battery;
Determining battery performance data corresponding to the organic positive electrode material to be predicted based on the predicted reduction voltage, the predicted solvation energy, the predicted theoretical parameter and the predicted capacity;
wherein the voltage solvation energy model, the theoretical parametric model and the capacity model are trained based on a pre-constructed material database.
2. The method of claim 1, wherein the voltage solvation energy model is trained based on a first sample set, the theoretical parameter model is trained based on a second sample set, and the capacity model is trained based on a third sample set;
the first sample set is composed of material structure information of each organic positive electrode material in the material database, corresponding reduction voltage and solvation energy, the second sample set is composed of material structure information of each organic positive electrode material in the material database and theoretical parameters of a battery applying each organic positive electrode material, and the third sample set is composed of material structure information of each organic positive electrode material in the material database, experimental property data of a battery applying each organic positive electrode material and corresponding capacity.
3. The method according to claim 1, wherein the method further comprises:
acquiring material structure information, corresponding reduction voltage and solvation energy of each organic positive electrode material and theoretical parameters of a battery applying each organic positive electrode material from a theoretical data set stored in advance, and constructing a material database;
searching experimental property data of a battery applying each organic positive electrode material in a pre-stored literature data set aiming at each organic positive electrode material in a material database, and storing the searched experimental property data and the organic positive electrode material in the material database in a correlated mode.
4. The method according to claim 3, wherein the obtaining material structure information, corresponding reduction voltage and solvation energy of each organic positive electrode material, and theoretical parameters of a battery using each organic positive electrode material in a pre-stored theoretical data set, and constructing a material database, comprises:
screening organic positive electrode materials with the number of conjugated rings not less than a preset number in a theoretical data set stored in advance to obtain candidate organic positive electrode materials;
screening organic positive electrode materials with specific capacity within a preset range from all candidate organic positive electrode materials to obtain organic positive electrode materials to be written;
And writing the material structure information, the corresponding reduction voltage and solvation energy of all the organic positive electrode materials to be written and the theoretical parameters of the battery applying the organic positive electrode materials to be written into a material database.
5. A method according to claim 3, characterized in that the method further comprises:
responding to search information input by a user for an organic positive electrode material to be searched in a front-end display interface, and inquiring material structure information, corresponding reduction voltage and solvation energy of the organic positive electrode material to be searched, experimental property data and theoretical parameters of a battery applying the organic positive electrode material to be searched in the material database based on the search information;
and displaying the query result on the front-end display interface.
6. The method of claim 5, wherein the search information is a SMILES string, name, functional group, operating voltage, or theoretical specific capacity of the organic positive electrode material to be searched.
7. A method according to claim 3, characterized in that the method further comprises:
responding to a file uploaded by the organic anode material to be uploaded in a front-end display interface by a user, and performing format verification on the file;
And after the format verification is passed, the organic positive electrode material to be uploaded and material structure information, reduction voltage, solvation energy, experimental property data or theoretical parameters in the file are stored in a material database in a correlated manner.
8. The method according to claim 1, wherein the method further comprises:
the method comprises the steps of searching a final organic positive electrode material from all organic positive electrode materials to be predicted according to battery performance data corresponding to all the organic positive electrode materials to be predicted by taking high reduction voltage, low solvation energy and high capacity battery performance as targets;
a cell material design list was constructed from all final organic positive electrode materials.
9. An electronic device, the electronic device comprising:
a processor and a memory;
the processor is configured to execute the steps of the data prediction method of the organic cathode material of a battery according to any one of claims 1 to 8 by calling a program or instructions stored in the memory.
10. A computer-readable storage medium storing a program or instructions that cause a computer to perform the steps of the data prediction method of a battery organic cathode material according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410123079.0A CN117649905B (en) | 2024-01-30 | 2024-01-30 | Data prediction method, device and storage medium for battery organic positive electrode material |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410123079.0A CN117649905B (en) | 2024-01-30 | 2024-01-30 | Data prediction method, device and storage medium for battery organic positive electrode material |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117649905A true CN117649905A (en) | 2024-03-05 |
CN117649905B CN117649905B (en) | 2024-04-05 |
Family
ID=90046393
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410123079.0A Active CN117649905B (en) | 2024-01-30 | 2024-01-30 | Data prediction method, device and storage medium for battery organic positive electrode material |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117649905B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014216249A (en) * | 2013-04-26 | 2014-11-17 | 三菱自動車工業株式会社 | Sodium ion secondary battery |
CN115221795A (en) * | 2022-08-03 | 2022-10-21 | 一汽解放汽车有限公司 | Training method, prediction method, device, equipment and medium of capacity prediction model |
CN116299008A (en) * | 2023-02-27 | 2023-06-23 | 武汉动力电池再生技术有限公司 | Battery SOH prediction method and device, electronic equipment and storage medium |
CN116629658A (en) * | 2023-04-10 | 2023-08-22 | 电子科技大学 | Lithium battery anode material production quality evaluation and process optimization method |
US11827993B1 (en) * | 2020-09-18 | 2023-11-28 | GRU Energy Lab Inc. | Methods of forming active materials for electrochemical cells using low-temperature electrochemical deposition |
CN117214728A (en) * | 2023-11-09 | 2023-12-12 | 溧阳中科海钠科技有限责任公司 | Method and device for determining degradation degree of battery, electronic equipment and storage medium |
CN117407795A (en) * | 2023-11-07 | 2024-01-16 | 广东电网有限责任公司 | Battery safety prediction method and device, electronic equipment and storage medium |
CN117423898A (en) * | 2023-10-25 | 2024-01-19 | 南开大学 | Solid polymer electrolyte with local high-concentration structure, lithium battery and method |
-
2024
- 2024-01-30 CN CN202410123079.0A patent/CN117649905B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014216249A (en) * | 2013-04-26 | 2014-11-17 | 三菱自動車工業株式会社 | Sodium ion secondary battery |
US11827993B1 (en) * | 2020-09-18 | 2023-11-28 | GRU Energy Lab Inc. | Methods of forming active materials for electrochemical cells using low-temperature electrochemical deposition |
CN115221795A (en) * | 2022-08-03 | 2022-10-21 | 一汽解放汽车有限公司 | Training method, prediction method, device, equipment and medium of capacity prediction model |
CN116299008A (en) * | 2023-02-27 | 2023-06-23 | 武汉动力电池再生技术有限公司 | Battery SOH prediction method and device, electronic equipment and storage medium |
CN116629658A (en) * | 2023-04-10 | 2023-08-22 | 电子科技大学 | Lithium battery anode material production quality evaluation and process optimization method |
CN117423898A (en) * | 2023-10-25 | 2024-01-19 | 南开大学 | Solid polymer electrolyte with local high-concentration structure, lithium battery and method |
CN117407795A (en) * | 2023-11-07 | 2024-01-16 | 广东电网有限责任公司 | Battery safety prediction method and device, electronic equipment and storage medium |
CN117214728A (en) * | 2023-11-09 | 2023-12-12 | 溧阳中科海钠科技有限责任公司 | Method and device for determining degradation degree of battery, electronic equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
CHADE LV等: "Machine Learning: An Advanced Platform for Materials Development and State Prediction in Lithium-Ion Batteries", 《ADVANCED SCIENCENEWS》, 31 December 2022 (2022-12-31), pages 1 - 17 * |
CHENGJUN HAN等: "Solvation Structure Modulation of High-Voltage Electrolyte for High-Performance K-Based Dual-Graphite Battery", <RESEARCH ARTICLE>, 31 December 2023 (2023-12-31), pages 1 - 9 * |
锂电派: "从电池性能角度来讲讲锂电池对正极材料的要求", 《HTTPS://MP.WEIXIN.QQ.COM/S?__BIZ=MZUXMZQ1NTI3NG==&MID=2247492669&IDX=1&SN=72D013BB5610CFB8845706DA27D27276&CHKSM=F95641FECE21C8E8A9FD3A4AD535ACA3931C5CBF518E1740BC1BE4EA49B157C1F755631B8FF8&SCENE=27》, 10 June 2019 (2019-06-10), pages 1 - 11 * |
Also Published As
Publication number | Publication date |
---|---|
CN117649905B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2012503824A (en) | Geo-time based forecast ad refinement | |
CN111831808B (en) | Data-driven artificial intelligent material prediction system | |
CN116609668B (en) | Lithium ion battery health state and residual life prediction method | |
CN116384487A (en) | Knowledge graph construction method for fault diagnosis and analysis of lithium ion battery of energy storage station | |
JP2021176131A (en) | Learning model generation method, program, storage medium and learned model | |
CN117649905B (en) | Data prediction method, device and storage medium for battery organic positive electrode material | |
CN117996242B (en) | Intelligent balance control method and system for power battery | |
CN116795969A (en) | Battery data collection method based on GPT large language model and data set thereof | |
Bai et al. | A feature reuse based multi-model fusion method for state of health estimation of lithium-ion batteries | |
Ra et al. | Optimizing vanadium redox flow battery system power loss using particle swarm optimization technique under different operating conditions | |
CN117289167A (en) | Battery remaining life prediction method, device and medium based on multiple neural network | |
CN111985226B (en) | Method and device for generating annotation data | |
CN116596574A (en) | Power grid user portrait construction method and system | |
Chen et al. | State-of-charge estimation of lithium-ion batteries using convolutional neural network with self-attention mechanism | |
EP4343691A1 (en) | Training method and training device for defect detection model of battery cell | |
JP7487155B2 (en) | Information processing device, program, and information processing method | |
CN115544903A (en) | Battery data processing method, device and equipment based on big data and storage medium | |
Li et al. | Lead air battery: prototype design and mathematical modelling | |
CN114118812A (en) | Hydropower station energy efficiency analysis and evaluation method and device based on improved fuzzy mean clustering | |
CN117669713B (en) | Battery information processing method, device, electronic equipment and storage medium | |
De Angelis et al. | BatteryArchive. org? Insights from a public repository for visualization analysis and comparison of battery data across institutions. | |
CN117609846B (en) | Battery performance parameter acquisition method and device, electronic equipment and storage medium | |
Jiang et al. | An Accurate and Interpretable Lifetime Prediction Method for Batteries using Extreme Gradient Boosting Tree and TreeExplainer | |
CN118378666B (en) | Distributed energy management monitoring method and system based on cloud computing | |
Haugaard et al. | Development of electrolyte descriptors for predicting cycling performance of electrochemical cells |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |