Design method of high-entropy NASICON sodium ion battery positive electrode material based on machine learning, battery and equipment

Abstract

The invention relates to the field of design of a high-entropy NASICON sodium-ion battery positive electrode material, in particular to a design method of a high-entropy NASICON sodium-ion battery positive electrode material based on machine learning, a battery and equipment. The method comprises the following steps: establishing an electrode material data set; performing screening and normalization processing on data in the electrode material data set to obtain an electrode material screening data set; dividing the electrode material screening data set to obtain an electrode material screening training set and an electrode material screening test set; based on the electrode material screening training set and the electrode material screening test set, constructing a machine learning model; generating a design data set; and calculating, verifying and optimizing through a density functional theory to obtain design data of the high-entropy NASICON sodium-ion battery positive electrode material. According to the embodiment, the design efficiency and accuracy of the high-entropy NASICON sodium ion battery positive electrode material are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of high-entropy NASICON sodium-ion battery positive electrode material design, and specifically to a design method, battery, and equipment for high-entropy NASICON sodium-ion battery positive electrode materials based on machine learning. Background Art

[0002] Developing new energy storage materials and building a clean, low-carbon, safe and efficient modern energy system are important supports for solving problems such as energy shortages and environmental pollution and achieving my country's strategic goals of "carbon peak" and "carbon neutrality". Among many energy storage devices, sodium ion batteries (SIBs) have the advantages of high safety, good high and low temperature performance, abundant resources and low cost. They can cater to a variety of market application scenarios and are widely used in home energy storage, photovoltaic power generation and electric vehicles. They are gradually becoming a viable alternative to lithium-ion batteries.

[0003] At present, my country's sodium-ion battery industry is still in the development stage of optimizing performance and improving the industrial chain. Among them, the cathode material is the link with the largest market scale and the highest output value in the battery industry chain. Its performance directly determines the energy density, working life, working voltage, safety and application scenarios of the battery, and is the core key to improving the performance of sodium-ion batteries. In the current research, common cathode materials for sodium-ion batteries include layered transition metal oxides, polyanion compounds, Prussian blue compounds and organic compounds. Among them, sodium superion conductor (NASICON), as the most representative polyanion compound, has a higher voltage window and smaller volume change, and is one of the most promising cathode materials for sodium-ion batteries. However, problems such as low theoretical specific capacity and slow ion / electron transport rate limit the industrial production and commercial application of NASICON cathode materials.

[0004] By using high entropy strategy to control the elemental composition of non-metal ions at the A site and metal ions at the M site in NASICON materials, its electronic conduction rate and specific capacity can be effectively improved. Figure 3 As shown in the figure, the high entropy doping strategy can effectively increase the local lattice distortion of the material, causing the energy distribution of the M-site metal ions to overlap and reduce the Na + The diffusion energy barrier of NASICON cathode materials is improved, and the intrinsic electron conduction rate and ion diffusion kinetics of high entropy NASICON cathode materials are improved. At the same time, the introduction of multi-component elements at the A and M positions can regulate the Na +In the embedding / de-embedding process in NASICON materials, multiple active centers for electrochemical reactions are introduced to improve their specific capacity and operating voltage. On this basis, the increase in overall configuration entropy can effectively inhibit the structural collapse of NASICON cathode materials during charge and discharge, and improve the rate performance and cycle stability of such materials at high current density. The team of Professor Mai Liqiang of Wuhan University of Technology has constructed a series of high-entropy NASICON cathode materials for sodium-ion batteries. 3+x MnTi 1-x V x The entropy regulation of the (PO4)3 cathode and the introduction of multi-electron reaction centers can effectively improve the working voltage and specific capacity of sodium-ion batteries. Professor Liang Shuquan's team at Central South University used high entropy strategies to construct Na3V 1.8 (CrMnFeZnAl) 0.2 (PO4)3 cathode material, in the voltage window of 2.5-4.3V, through V 3+ / V 4+ / V 5+ A continuous redox reaction occurred, showing 119.8 mAh g -1 The specific capacity of the battery is as high as 80% after 3000 cycles at a current density of 10C.

[0005] However, high-entropy NASICON materials have a complex composition system, and the types of elements involved in the design and synthesis of high-entropy NASICON materials may exceed 30. The current research model based on trial and error or accidental processes can no longer meet the development needs of high-entropy NASICON sodium-ion battery positive electrodes. Summary of the invention

[0006] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] The design method of high entropy NASICON sodium-ion battery cathode material based on machine learning includes:

[0008] Establish electrode material dataset;

[0009] Screening and normalizing the data in the electrode material data set to obtain an electrode material screening data set;

[0010] Dividing the electrode material screening data set to obtain an electrode material screening training set and an electrode material screening test set;

[0011] Based on the electrode material screening training set and the electrode material screening test set, a machine learning model for high entropy NASICON sodium-ion battery positive electrode material design is constructed;

[0012] Based on the machine learning model for high entropy NASICON sodium-ion battery positive electrode material design, generate a high entropy NASICON sodium-ion battery positive electrode material design data set;

[0013] The high entropy NASICON sodium ion battery cathode material design data set is verified and optimized by density functional theory calculation to obtain high entropy NASICON sodium ion battery cathode material design data.

[0014] Preferably, the electrode material data set includes: Materials Project database, O3 sodium ion battery positive electrode database, insertion / extraction sodium ion battery positive electrode database, ion battery electrode material database, high entropy-NASICON positive electrode material database.

[0015] Preferably, the electrode material data set is divided and processed, and part of the data is randomly selected as an electrode material training set and an electrode material test set, and a five-fold cross-validation method is used to improve the accuracy of model training.

[0016] Preferably, constructing a machine learning model for designing a high-entropy NASICON sodium-ion battery cathode material comprises: generating an effective feature set by selecting a chemical descriptor and an additional descriptor, selecting the effective feature set to generate a machine learning model for designing a high-entropy NASICON sodium-ion battery cathode material, and calculating the E of the high-entropy NASICON sodium-ion battery cathode material. form 、E hull , Δv, C grav Make predictions. form is the formation energy; Δv is the volume change rate of the electrode material during the charge and discharge process; C grav is the mass specific capacity of the battery positive electrode.

[0017] Preferably, the chemical descriptors are used to describe the chemical structure of the electrode material, and the chemical descriptors include stoichiometric properties, elemental statistics, electronic structure properties and ion complex properties; the additional descriptive features include mass specific capacity, ion extraction degree and space group number.

[0018] Preferably, a high entropy NASICON sodium ion battery positive electrode material design data set is generated; including: establishing a high entropy NASICON sodium ion battery positive electrode material target data set, using the machine learning model designed for the NASICON sodium ion battery positive electrode material to screen the high entropy NASICON sodium ion battery positive electrode material target data set, and generating a high entropy NASICON sodium ion battery positive electrode material design data set.

[0019] Preferably, establishing a high entropy NASICON sodium-ion battery cathode material data set includes: designing a high entropy NASICON cathode material Na x VM y M' z M” 1-y-z (AO4)3, 0<x≤4, (y, z): (0, 0.5), (0.5, 0), (0.5, 0.5), (0.333, 0.333). There are 27 substitution elements at the M position, namely: Mg, Al, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Ga, Ge, Y, Zr, Nb, Cd, In, Sn, Sb, Hf, Ta, La, Yb, Lu. There are 6 substitution elements at the A position, namely: Si, P, S, As, Se, Mo.

[0020] Preferably, screening a high entropy NASICON sodium ion battery cathode material target data set using the machine learning model designed for the NASICON sodium ion battery cathode material comprises:

[0021] Prediction of the E of high-entropy NASICON cathode materials for sodium-ion batteries form 、E hull , Δv, C grav , screen high entropy NASICON sodium ion battery cathode materials,

[0022] In response to the screening of the high entropy NASICON sodium-ion battery cathode material design data set to meet the preset optimization conditions, when E form <0eV / atom, E hull <0.025, Δv≤4%, and C grav High-entropy NASICON sodium-ion battery positive electrode material ≥100mAh / g is determined as the target high-entropy NASICON sodium-ion battery positive electrode material design data.

[0023] Preferably, in response to the screening of the high entropy NASICON sodium ion battery positive electrode material design data set not satisfying the preset optimization conditions, the high entropy NASICON sodium ion battery positive electrode material screening step is performed again.

[0024] Preferably, the high entropy NASICON sodium ion battery cathode material design data set is verified and optimized by density functional theory calculation, including:

[0025] Calculate the V of the high-entropy NASICON sodium-ion battery positive electrode material in the high-entropy NASICON sodium-ion battery positive electrode material design data set screened by the machine learning model of the high-entropy NASICON sodium-ion battery positive electrode material design.avg ,

[0026] Filter out V avg The high entropy NASICON sodium-ion battery positive electrode material of ≥3.5V is the target high entropy NASICON sodium-ion battery positive electrode material.

[0027] A sodium ion battery uses a positive electrode material designed using the above-mentioned high entropy NASICON sodium ion battery positive electrode material design method based on machine learning as a positive electrode.

[0028] A computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program implements the steps of the above method when executed by the processor.

[0029] The present invention has the following beneficial effects:

[0030] The present invention is based on high-throughput computing assisted by machine learning and utilizes element doping methods assisted by high-entropy strategies to design high-entropy NASICON materials with high specific capacity, wide voltage window and low volume change. In addition, theoretical calculations and experimental methods are combined to screen out high-entropy NASICON materials that can be chemically synthesized and have not yet been used for the positive electrode of sodium-ion batteries, thereby accelerating the design and development of high-entropy NASICON sodium-ion battery positive electrode materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0032] Figure 1 is a flow chart of some embodiments of the design method of high entropy NASICON sodium ion battery positive electrode material based on machine learning according to the present application;

[0033] Figure 2 is a schematic diagram of a computer device suitable for implementing some embodiments of the present application;

[0034] Figure 3 This is a schematic diagram of the crystal structure of NASICON. DETAILED DESCRIPTION

[0035] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0036] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0037] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0038] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0039] The names of the messages or data exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or data.

[0040] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0041] Figure 1 The flowchart of some embodiments of the method for designing high-entropy NASICON sodium-ion battery positive electrode materials based on machine learning according to the present application is shown.

[0042] The design method of high entropy NASICON sodium-ion battery cathode material based on machine learning includes the following steps:

[0043] Step 101: Create an electrode material data set.

[0044] In some embodiments, the electrode material data set includes: Materials Project, O3-type sodium ion battery positive electrode, insertion / extraction type sodium ion battery positive electrode, ion battery electrode materials, high entropy-NASICON positive electrode materials.

[0045] The electrode material dataset is shown in Table 1.

[0046] Table 1 Electrode material dataset

[0047]

[0048] Step 102: The execution subject screens and normalizes the data in the electrode material data set to obtain an electrode material screening data set.

[0049] In some embodiments, the data in the electrode material data set are screened based on the electrochemical characteristics of the secondary ion battery during the charging and discharging process, such as the chemical formula of the material in the charging and discharging states, the effective ions of the battery, the average operating voltage, the volume change during the charging and discharging process, and the battery specific capacity.

[0050] Step 103: the execution entity divides the electrode material screening data set to obtain an electrode material screening training set and an electrode material screening test set; divides the electrode material data set, randomly selects a preset number of electrode material data as the electrode material training set, and determines the electrode material data in the electrode material data set except the electrode material training set as the electrode material test set.

[0051] As an example, the preset number may be the product of the number of electrode material data in the electrode material data set and a preset ratio. The preset ratio may be 80%.

[0052] Step 104: Based on the electrode material screening training set and the electrode material screening test set, a machine learning model for high entropy NASICON sodium-ion battery positive electrode material design is constructed.

[0053] In some embodiments, a valid feature set is generated by selecting a chemical descriptor and an additional descriptor, and a machine learning model for designing a high-entropy NASICON sodium-ion battery cathode material is generated by selecting the valid feature set. form 、E hull , Δv, C grav Make predictions.

[0054] In some embodiments, the execution subject constructs a machine learning model for high entropy NASICON sodium-ion battery positive electrode material design based on the electrode material screening training set and the electrode material screening test set. Wherein, the execution subject constructs a machine learning model for high entropy NASICON sodium-ion battery positive electrode material design based on the electrode material screening training set and the electrode material screening test set, which can be: first, the electrode material screening training set is used as sample data, and the machine learning model for the initial high entropy NASICON sodium-ion battery positive electrode material design is trained through a preset adjustment algorithm. Then, the electrode material screening test set is used as test data, and the pre-trained initial high entropy NASICON sodium-ion battery positive electrode material design machine learning model is optimized through a preset optimization algorithm. Finally, the optimized initial high entropy NASICON sodium-ion battery positive electrode material design machine learning model is determined as the high entropy NASICON sodium-ion battery positive electrode material design machine learning model.

[0055] As an example, the preset adjustment algorithm may be, but is not limited to, at least one of the following: XGBoost (distributed gradient boosting library) algorithm, random forest algorithm, Bayesian linear regression algorithm, support vector machine algorithm. The preset optimization algorithm may be M3GNet algorithm. The M3GNet algorithm is used to obtain structural features.

[0056] The regression algorithm model was evaluated by determination coefficient, mean absolute error and root mean square error, while the classification algorithm model was evaluated by F1score and accuracy.

[0057] In some embodiments, the execution entity generates effective features by selecting chemical descriptors and additional descriptors; the chemical descriptors are used to describe the chemical structure of the electrode material, including stoichiometric properties, elemental statistics, electronic structure properties and ion complex properties; the additional descriptive features include mass specific capacity, ion extraction degree and space group number.

[0058] The types and characteristics of chemical descriptors are shown in Table 2.

[0059] Table 2 Types and characteristics of chemical descriptors

[0060]

[0061] In addition, in order to better screen the positive electrode materials of batteries, additional descriptors related to battery materials are added, which are:

[0062] (1) Mass specific capacity. During the charging process, the calculation formula for the theoretical specific capacity is shown in formula (1):

[0063]

[0064] Where n is the number of electrons that have changed, F is the Faraday constant (96485.3329C / mol), M mw is the molecular weight, and C is the mass specific capacity. x VM y M' z M” 1-y-z (AO4)3 contains 50% Na + When released during charging, the calculated mass specific capacity is 100% Na + When it is released, the theoretical specific capacity is obtained.

[0065] (2) Ion extraction degree. Ion extraction degree refers to the number of working ions released from the positive electrode material during the charge and discharge process. The value of ion extraction degree will affect the volume change of the positive electrode material and the average working voltage of the battery. In the electrode material screening training set, the ion extraction degree is determined by the electrode chemical formula under the charge and discharge state. In the electrode material screening test set, the ion extraction degree is set to Na x VM y M' z M” 1-y-z (AO4)3 Na in the positive electrode + Half the content.

[0066] (3) Space group number. Considering that different crystal forms have different performances in the electrochemical reaction process, and chemical descriptors can only reflect the chemical properties based on the chemical formula, additional descriptors about the crystal form are added. type, and its corresponding space group descriptor is 167.

[0067] Step 105: Generate a high entropy NASICON sodium-ion battery cathode material design data set;

[0068] Generate a high-entropy NASICON sodium-ion battery positive electrode material design data set; including: establishing a high-entropy NASICON sodium-ion battery positive electrode material target data set, using the machine learning model designed for the NASICON sodium-ion battery positive electrode material to screen the high-entropy NASICON sodium-ion battery positive electrode material target data set, and generating a high-entropy NASICON sodium-ion battery positive electrode material design data set.

[0069] Establish a high entropy NASICON sodium-ion battery cathode material data set, including: Design high entropy NASICON cathode material Na x VM y M' z M” 1-y-z(AO4)3, where 0 < x ≤ 4, (y, z): (0, 0.5), (0.5, 0), (0.5, 0.5), (0.333, 0.333). The substitution elements at the M site include a total of 27 kinds, namely: Mg, Al, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Ga, Ge, Y, Zr, Nb, Cd, In, Sn, Sb, Hf, Ta, La, Yb, Lu. The substitution elements at the A site include 6 kinds, namely: Si, P, S, As, Se, Mo. The selected element types are all elements that have been reported to be frequently used in NASICON-type materials before. Among them, the ratio of y and z mainly considers the valence states of the three metals at the M site. For NASICON-type cathode materials, the range of x is 0 < x ≤ 4. Within this range, in order to achieve electrical neutrality and chemical stability, the number of sodium ions in the chemical formula, that is, the value of x, is adjusted so that the overall oxidation state of the chemical formula is 0. The dataset of high-entropy NASICON sodium-ion battery cathode materials is shown in Table 3.

[0070] Table 3 Dataset of High-Entropy NASICON Sodium-Ion Battery Cathode Materials

[0071]

[0072]

[0073] By predicting the E form 、E hull 、Δv、C grav of the high-entropy NASICON sodium-ion battery cathode materials, the high-entropy NASICON sodium-ion battery cathode materials are screened. E form is the formation energy; Δv is the volume change rate of the electrode material during charge and discharge; C grav is the mass specific capacity of the battery cathode.

[0074] In response to the screening that the design dataset of the high-entropy NASICON sodium-ion battery cathode materials meets the preset optimization conditions, when E form <0 eV / atom, E hull <0.025, generally speaking, when E form <0 eV / atom, and E hull <0.025 eV / atom, it indicates that the material can be chemically synthesized in the laboratory and can exist stably. When E form <0 eV / atom, E hull <0.025, further screening is carried out. When Δv ≤ 4%, and then further screening is carried out. When screening to C grav ≥100 mAh / g, stop the screening. C gravHigh-entropy NASICON sodium-ion battery positive electrode material ≥100mAh / g is determined as the target high-entropy NASICON sodium-ion battery positive electrode material design data.

[0075] In response to the screened high entropy NASICON sodium ion battery cathode material design data set not satisfying a preset optimization condition, the high entropy NASICON sodium ion battery cathode material screening step is performed again.

[0076] Step 106: The high entropy NASICON sodium-ion battery cathode material design data set is verified and optimized by density functional theory calculation to obtain high entropy NASICON sodium-ion battery cathode material design data.

[0077] Calculate the V of the high-entropy NASICON sodium-ion battery positive electrode material in the high-entropy NASICON sodium-ion battery positive electrode material design data set screened by the machine learning model of the high-entropy NASICON sodium-ion battery positive electrode material design. avg , filter out V avg The high entropy NASICON sodium-ion battery positive electrode material of ≥3.5V is the target high entropy NASICON sodium-ion battery positive electrode material.

[0078] Δv,V avg and E d Etc. are calculated using the following formula:

[0079]

[0080] E d [Wh / kg]=C grav ×V avg (4)

[0081] Among them, x1 and x2 are the Na in the high entropy NASICON material during the charging and discharging process. + quantity, E is the overall energy value, μ Na = -1.3122eV (chemical potential of sodium), e = 1.602176634×10 -19 . C grav It can be obtained by formula (1). charge and E discharge is the total energy of the system during the charge and discharge process, v is the volume value during the charge and discharge process, E d is the total energy of the battery.

[0082] A sodium ion battery uses a positive electrode material designed using the above-mentioned high entropy NASICON sodium ion battery positive electrode material design method based on machine learning as a positive electrode.

[0083] A computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the above method are implemented.

[0084] The present application also provides a computer device 400. Figure 2 As shown, the computer device 400 includes: a bus 401, a processor 402, a memory 403 and a communication interface 404. The processor 402, the memory 403 and the communication interface 404 communicate with each other through the bus 401. The computer device 400 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 400.

[0085] The bus 401 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 401 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 401 may include a path for transmitting data between various components of the computer device 400 (for example, the memory 403, the processor 402, and the communication interface 404).

[0086] The processor 402 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0087] The memory 403 may include a volatile memory, such as a random access memory (RAM). The memory 403 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0088] The memory 403 stores executable program codes, and the processor 402 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby realizing the above-mentioned design method of high entropy NASICON sodium-ion battery positive electrode material based on machine learning. That is, the memory 403 stores instructions for executing the foundation pile reverse design method of the design method of high entropy NASICON sodium-ion battery positive electrode material based on machine learning.

[0089] The communication interface 404 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 400 and other devices or a communication network.

[0090] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A design method for high entropy NASICON sodium-ion battery cathode material based on machine learning, characterized in that: include: Establish electrode material dataset; Screening and normalizing the data in the electrode material data set to obtain an electrode material screening data set; Dividing the electrode material screening data set to obtain an electrode material screening training set and an electrode material screening test set; Based on the electrode material screening training set and the electrode material screening test set, a machine learning model for high entropy NASICON sodium-ion battery positive electrode material design is constructed; Based on the machine learning model for high entropy NASICON sodium-ion battery positive electrode material design, a high entropy NASICON sodium-ion battery positive electrode material design data set is generated; The high entropy NASICON sodium-ion battery cathode material design data set is verified and optimized by density functional theory calculation to obtain high entropy NASICON sodium-ion battery cathode material design data.

2. The design method of high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 1 is characterized in that: Construct a machine learning model for high entropy NASICON sodium-ion battery cathode material design, including: generating an effective feature set by selecting chemical descriptors and additional descriptors, selecting an effective feature set to generate a machine learning model for high entropy NASICON sodium-ion battery cathode material design, and calculating the E form 、E hull , Δv, C grav Make predictions.

3. The design method of high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 2 is characterized in that: The chemical descriptors are used to describe the chemical structure of the electrode material, and the chemical descriptors include stoichiometric properties, elemental statistics, electronic structure properties and ion complex properties; the additional descriptive features include mass specific capacity, ion extraction degree and space group number.

4. The design method of high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 1 is characterized in that: Generate a high-entropy NASICON sodium-ion battery positive electrode material design data set; including: establishing a high-entropy NASICON sodium-ion battery positive electrode material target data set, using the machine learning model designed for the NASICON sodium-ion battery positive electrode material to screen the high-entropy NASICON sodium-ion battery positive electrode material target data set, and generating a high-entropy NASICON sodium-ion battery positive electrode material design data set.

5. The method for designing a high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 4, characterized in that: Establish a high entropy NASICON sodium-ion battery cathode material data set, including: Design high entropy NASICON cathode material Na x VM y M' z M” 1-y-z (AO4)3, 0<x≤4, (y, z): (0, 0.5), (0.5, 0), (0.5, 0.5), (0.333, 0.333). There are 27 substitution elements at the M position, namely: Mg, Al, Ca, Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn, Ga, Ge, Y, Zr, Nb, Cd, In, Sn, Sb, Hf, Ta, La, Yb, Lu. There are 6 substitution elements at the A position, namely: Si, P, S, As, Se, Mo.

6. The method for designing a high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 4, characterized in that: The machine learning model designed for the NASICON sodium-ion battery cathode material is used to screen the high-entropy NASICON sodium-ion battery cathode material target data set, including: Prediction of the E of high-entropy NASICON cathode materials for sodium-ion batteries form 、E hull , Δv, C grav , screen high entropy NASICON sodium ion battery cathode materials, In response to the screening of the high entropy NASICON sodium-ion battery cathode material design data set to meet the preset optimization conditions, when E form <0eV / atom, E hull <0.025, Δv≤4%, and C grav High-entropy NASICON sodium-ion battery positive electrode material ≥100mAh / g is determined as the target high-entropy NASICON sodium-ion battery positive electrode material design data.

7. The method for designing a high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 6, characterized in that: In response to the screened high entropy NASICON sodium ion battery cathode material design data set not satisfying a preset optimization condition, the high entropy NASICON sodium ion battery cathode material screening step is performed again.

8. The method for designing a high entropy NASICON sodium ion battery positive electrode material based on machine learning according to claim 1, characterized in that: The high entropy NASICON sodium-ion battery cathode material design data set is verified and optimized by density functional theory calculations, including: Calculate the V of the high-entropy NASICON sodium-ion battery positive electrode material in the high-entropy NASICON sodium-ion battery positive electrode material design data set screened by the machine learning model of the high-entropy NASICON sodium-ion battery positive electrode material design. avg , Filter out V avg The high entropy NASICON sodium-ion battery positive electrode material of ≥3.5V is the target high entropy NASICON sodium-ion battery positive electrode material.

9. A sodium ion battery, characterized in that The positive electrode material designed by the design method of high entropy NASICON sodium ion battery positive electrode material based on machine learning as claimed in claim 1 is used as the positive electrode.

10. A computer device, characterized in that: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images