Method and device for testing the orderliness of materials

Abstract

The present application discloses a method and apparatus for testing the order of a material. The method includes: obtaining a set of electron diffraction patterns of the material, each electron diffraction pattern in the set corresponding to a corresponding one of a plurality of positions in the material; classifying the electron diffraction pattern as an ordered area electron diffraction pattern in response to the electron diffraction pattern in the set including a crystal diffraction feature associated with the material; and determining the order of the material based on the ordered area electron diffraction pattern.

Description

Technical Field

[0001] The present application relates to the field of batteries, and more particularly to a method and apparatus for testing the order of a material (such as, but not limited to, a carbon material). The present application also relates to a method for training an image recognition model for identifying ordered regions of a material, and a method for training an image recognition model for determining at least one of the order and a distribution map of ordered regions of a material. Furthermore, the present application also relates to electronic devices, computer-readable storage media, and computer program products associated with the aforementioned methods. Background Art

[0002] The degree of order in a material is one of the factors that determine its physical and chemical properties. For example, in lithium-ion batteries, the degree of order in carbon materials, commonly used to prepare negative electrodes, influences performance parameters such as specific capacity and cycling stability. Quantifying the degree of order not only helps reveal the intrinsic properties of a material but also provides a basis for regulating the performance of materials and products. Summary of the Invention

[0003] In view of this, the present application provides a method and device for testing the order of a material, which can accurately and reliably quantify the order of the material.

[0004] In a first aspect, the present application provides a method for testing the order of a material, comprising: obtaining a set of electron diffraction patterns of the material, each electron diffraction pattern in the set of electron diffraction patterns corresponding to a corresponding one of a plurality of positions in the material; classifying the electron diffraction patterns as ordered area electron diffraction patterns in response to the electron diffraction patterns in the set of electron diffraction patterns including crystal diffraction features associated with the material; and determining the order of the material based on the ordered area electron diffraction patterns.

[0005] The technical solution of the embodiments of this application, by collecting electron diffraction patterns at different locations in a material and identifying the crystal diffraction features therein, can effectively identify ordered regions within the material over a large range, thereby achieving quantitative characterization of the degree of order. Based on the analysis of electron diffraction signals, this method can locate and identify crystal diffraction features at the nanoscale or even atomic level. It is applicable not only to the characterization of long-range ordered materials, but also to the characterization of short-range ordered materials (which may be long-range disordered).

[0006] In some embodiments, the electron diffraction pattern set is obtained by scanning the material point by point using a transmission electron microscope. Scanning the material point by point using a transmission electron microscope can obtain high-resolution and multi-dimensional information, thereby enabling accurate characterization of the degree of order and the distribution of ordered regions within the scan range.

[0007] In some embodiments, the degree of order of a material is determined based on the number of ordered area electron diffraction patterns. By counting the number of ordered area electron diffraction patterns, a rapid quantitative assessment of the material's order can be achieved. This method is simple and reliable. The closer the electron diffraction patterns are collected, the more accurately the material's order can be assessed.

[0008] In some embodiments, the distribution of ordered regions in a material is determined based on the positions corresponding to the ordered region electron diffraction patterns. By correlating the electron diffraction patterns with the positions within the material, the spatial distribution of ordered regions within the material can be characterized over a large range, facilitating visualization of the material structure.

[0009] In some embodiments, the crystal diffraction signature includes the diffraction signature of crystals containing the same element as the material. By using the diffraction signature of crystals containing the same element as the material as the basis for classifying ordered area electron diffraction patterns, ordered regions within the material can be more accurately identified, reducing the likelihood of misinterpreting impurity diffraction signals as ordered features of the material, and improving the reliability of order testing.

[0010] In some embodiments, the crystals, which share the same elements as the material, are suitable for use in batteries. This allows for effective identification of crystal diffraction features that contribute significantly to battery performance when testing the order of battery materials or potential battery materials, allowing order assessment results to be correlated with battery performance, thus increasing practical value.

[0011] In some embodiments, the crystals containing the same element as the material are suitable for embedding and / or deintercalating the reactive element. By identifying the diffraction characteristics of crystals with good embedding / deintercalation properties, the order assessment results can be correlated with the material's ability to participate in / promote battery reactions, facilitating the evaluation of the material's performance when used in batteries.

[0012] In some embodiments, the method further comprises one or more of the following: in response to an electron diffraction pattern in the electron diffraction pattern set not including a crystal diffraction feature, classifying the electron diffraction pattern as a non-ordered region electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set not including a crystal diffraction feature but including a non-crystalline diffraction feature associated with the material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set not including any diffraction feature, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set including a diffraction feature, classifying the electron diffraction pattern as a valid electron diffraction pattern. By classifying the electron diffraction pattern, for example, distinguishing between an ordered region electron diffraction pattern and a non-ordered region electron diffraction pattern, or distinguishing between an invalid electron diffraction pattern and a valid electron diffraction pattern and further distinguishing between an ordered region electron diffraction pattern and a disordered region electron diffraction pattern in the valid electron diffraction pattern, etc., the order of the material can be more comprehensively analyzed. By identifying and excluding images that do not meet the expected diffraction characteristics, the interference of invalid information or noise can be reduced, thereby providing a more accurate basis for the evaluation of the orderliness of the material.

[0013] In some embodiments, in response to an electron diffraction pattern in a collection of electron diffraction patterns including at least one of multiple crystal diffraction features associated with a material, the electron diffraction pattern is classified as an ordered area electron diffraction pattern. This enables more comprehensive detection of ordered structures in a material, reducing the likelihood of missed detection, when multiple crystal diffraction features may be associated with the material.

[0014] In some embodiments, the classification of electron diffraction patterns is achieved through an image recognition model. By introducing the image recognition model, the crystal diffraction features in the electron diffraction pattern can be automatically and efficiently identified, thereby improving data processing efficiency.

[0015] In some embodiments, the image recognition model is configured to determine the material's degree of order and the distribution of ordered regions based on a received set of electron diffraction patterns. By intelligently parsing the entire set of electron diffraction patterns, the image recognition model not only automatically calculates the material's overall degree of order but also generates a spatial distribution map of the ordered regions, improving data processing and integration efficiency and facilitating visualization of test results.

[0016] In some embodiments, the plurality of locations are selected based on the following operations: selecting an area of ​​the material where particles are not stacked based on the material's topography; and selecting the plurality of locations from the selected area. By selecting regions of independently dispersed particles within the material for testing, diffraction signal interference caused by particle stacking is effectively reduced, thereby improving the accuracy of the test results.

[0017] In a second aspect, the present application provides a method for testing the order of a carbon material, comprising: obtaining a set of electron diffraction patterns of the carbon material, each electron diffraction pattern in the set of electron diffraction patterns corresponding to a corresponding one of multiple positions in the carbon material; classifying the electron diffraction pattern as an ordered area electron diffraction pattern in response to the electron diffraction pattern in the set of electron diffraction patterns including graphite diffraction features; and determining the order of the carbon material based on the ordered area electron diffraction pattern.

[0018] In the technical solution of the embodiment of the present application, by collecting electron diffraction patterns at different positions of the carbon material and identifying the graphite diffraction features therein, it is possible to effectively identify the ordered regions in the carbon material over a large range, thereby achieving quantitative characterization of the degree of order. This method is based on the analysis of electron diffraction signals and can locate and identify graphite diffraction features at the nanometer level or even the atomic level. It is not only applicable to the characterization of long-range ordered carbon materials, but also to the characterization of short-range ordered carbon materials (which may be long-range disordered). In addition, graphite is suitable for use in batteries and is suitable for the embedding and / or de-embedding of reactive elements such as lithium ions. Therefore, by locating and identifying graphite diffraction features in carbon materials, the order evaluation results can be associated with the ability of the carbon material to participate in / promote battery reactions, which is beneficial for evaluating the performance of carbon materials when used in batteries.

[0019] In some embodiments, the electron diffraction pattern set is obtained from 4D-STEM data of the carbon material. By scanning the carbon material point by point using a 4D-STEM, high-resolution and multi-dimensional information can be obtained, thereby enabling accurate characterization of the degree of order and the distribution of ordered regions within the scan range.

[0020] In some embodiments, the degree of order of the carbon material is determined based on the number of ordered area electron diffraction patterns and the number of effective electron diffraction patterns in the electron diffraction pattern set, and the method further includes: determining the ordered area distribution of the carbon material based on the position corresponding to the ordered area electron diffraction pattern. By counting the ratio of the number of ordered area electron diffraction patterns to all effective electron diffraction patterns, a rapid quantitative evaluation of the degree of order of the carbon material can be achieved, and the method is simple and reliable. As the collection positions of the electron diffraction patterns are denser, the degree of order of the carbon material can be evaluated more accurately. By correlating the electron diffraction patterns with the positions in the carbon material, the spatial distribution of the ordered areas in the carbon material can be characterized over a larger range, which is beneficial to the visualization of the structure of the carbon material.

[0021] In some embodiments, the method further comprises one or more of the following: in response to an electron diffraction pattern in the electron diffraction pattern set not including a graphite diffraction feature, classifying the electron diffraction pattern as a non-ordered region electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set not including a graphite diffraction feature but including a non-crystalline diffraction feature associated with a carbon material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set not including any diffraction feature, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or in response to an electron diffraction pattern in the electron diffraction pattern set including a diffraction feature, classifying the electron diffraction pattern as a valid electron diffraction pattern. By classifying the electron diffraction pattern, for example, distinguishing between an ordered region electron diffraction pattern and a non-ordered region electron diffraction pattern, or distinguishing between an invalid electron diffraction pattern and a valid electron diffraction pattern and further distinguishing between an ordered region electron diffraction pattern and a disordered region electron diffraction pattern in the valid electron diffraction pattern, etc., the order of the carbon material can be more comprehensively analyzed. By identifying and excluding images that do not meet the expected diffraction characteristics, the interference of invalid information or noise can be reduced, thereby providing a more accurate basis for the evaluation of the orderliness of carbon materials.

[0022] In some embodiments, the classification of electron diffraction patterns is achieved using an image recognition model, wherein the image recognition model includes a visual transformer (VIT) model, and wherein the image recognition model is configured to determine the order and ordered region distribution of the carbon material based on a received set of electron diffraction patterns of the carbon material. By introducing an image recognition model including a visual transformer model, graphite diffraction features in the electron diffraction patterns can be automatically and efficiently identified, thereby improving data processing efficiency. Through intelligent analysis of the entire set of electron diffraction patterns of the carbon material by the image recognition model, not only can the overall order of the carbon material be automatically calculated, but also a spatial distribution map of the ordered regions can be generated, thereby improving data processing and integration efficiency and facilitating visualization of test results.

[0023] In some embodiments, the multiple locations are selected based on the following operations: selecting an area of ​​the carbon material where particles are not stacked based on the carbon material's topography; and selecting multiple locations from the selected area. Carbon materials may be prone to agglomeration. By selecting an area of ​​independently dispersed particles within the carbon material for testing, interference in the diffraction signal caused by particle stacking is effectively reduced, thereby improving the accuracy of the test results.

[0024] In a third aspect, the present application provides a method for training an image recognition model for identifying ordered regions of a material, comprising: constructing a training image set, the training image set including multiple electron diffraction patterns of the material as samples, each electron diffraction pattern being labeled as an ordered region electron diffraction pattern; and training an image recognition model using the training image set, the image recognition model being configured to determine whether a received electron diffraction pattern is an ordered region electron diffraction pattern, wherein, in response to the electron diffraction pattern including crystal diffraction features associated with the material, the electron diffraction pattern is labeled as an ordered region electron diffraction pattern.

[0025] In the technical solution of the embodiments of this application, a training image set containing electron diffraction patterns labeled with ordered regions is constructed to train an image recognition model, enabling it to accurately identify ordered regions in materials. This method utilizes artificial intelligence to autonomously identify the type of electron diffraction pattern, improving the efficiency of ordered region identification. By adjusting the training image set, it can be adapted to the analysis requirements of different materials. This provides a reliable technical means for achieving automated and standardized detection of material order.

[0026] In a fourth aspect, the present application provides a method for training an image recognition model for determining at least one of the degree of order and the ordered area distribution map of a material, comprising: constructing a training image set, the training image set including a set of electron diffraction patterns of multiple materials as samples, each electron diffraction pattern in the electron diffraction pattern set corresponding to a corresponding one of multiple positions in the material, and each electron diffraction pattern set being labeled with at least one of the degree of order and the ordered area distribution map; and training an image recognition model with the training image set, the image recognition model being configured to output at least one of the degree of order and the ordered area distribution map based on the received electron diffraction pattern set, wherein, in response to the electron diffraction pattern in the electron diffraction pattern set including crystal diffraction features associated with the material, the electron diffraction pattern is determined to be an ordered area electron diffraction pattern, thereby obtaining at least one of the degree of order and the ordered area distribution map regarding the electron diffraction pattern set.

[0027] In the technical solutions of the embodiments of this application, an image recognition model is trained to directly output the material's degree of order and / or the distribution of ordered regions, enabling end-to-end analysis from electron diffraction data to quantitative and / or visual analysis results. This training approach, based on a complete set of electron diffraction patterns, enables the model to comprehensively assess the structural characteristics of each location in the material, outputting not only the overall degree of order but also intuitive information on the spatial distribution of ordered regions, providing multi-dimensional structural characterization data for material performance research.

[0028] In a fifth aspect, the present application provides an electronic device comprising: one or more processors; and a memory storing computer-executable instructions, which, when executed by the one or more processors, enable the one or more processors to execute a method according to any one of the embodiments of the first aspect, the second aspect, the third aspect, or the fourth aspect.

[0029] In a sixth aspect, the present application provides a computer-readable storage medium having computer-executable instructions stored thereon, which, when executed by a computer, enables the computer to execute a method according to any one of the embodiments of the first aspect, the second aspect, the third aspect, or the fourth aspect.

[0030] In a seventh aspect, the present application provides a computer program product, which includes instructions, and when the instructions are executed by a processor, implements the method according to any one of the embodiments of the first aspect, the second aspect, the third aspect, or the fourth aspect.

[0031] In an eighth aspect, the present application provides an apparatus for testing the order of a material, comprising: a transmission electron microscope configured to scan a material point by point to acquire a set of electron diffraction patterns of the material, each electron diffraction pattern in the set corresponding to a respective one of a plurality of positions in the material; and a processor. The processor is configured to: receive the set of electron diffraction patterns from the transmission electron microscope; classify the electron diffraction pattern as an ordered area electron diffraction pattern in response to an electron diffraction pattern in the set of electron diffraction patterns including a crystal diffraction feature associated with the material; and determine the order of the material based on the ordered area electron diffraction pattern.

[0032] In the technical solutions of the embodiments of this application, point-by-point scanning of the material using a transmission electron microscope can acquire high-resolution and multi-dimensional information, facilitating the identification of crystal diffraction features at the nanoscale and even atomic level. Furthermore, by using a processor to identify crystal diffraction features in electron diffraction patterns collected at different locations within the material, it is possible to effectively identify ordered regions within the material over a wide range, thereby achieving quantitative characterization of the degree of order.

[0033] In some embodiments, the processor is configured to perform at least one of the following operations: running an image recognition model trained using the method according to any embodiment of the third aspect to classify the electron diffraction pattern; or running an image recognition model trained using the method according to any embodiment of the fourth aspect to determine at least one of the degree of order and the ordered region distribution map of the material. By enabling the processor to be equipped with a specially trained image recognition model, the automation level of the device can be improved.

[0034] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0036] Figure 1 A flowchart of a method for testing the orderliness of materials according to some embodiments of the present application;

[0037] Figure 2 illustrative illustrations of electron diffraction pattern sets, ordered area electron diffraction patterns, and disordered area electron diffraction patterns of some embodiments of the present application;

[0038] Figure 3 is an exemplary illustration of the topography of materials according to some embodiments of the present application;

[0039] Figure 4 A flow chart of a method for testing the order of carbon materials according to some embodiments of the present application;

[0040] Figure 5 A flowchart of a method for training an image recognition model for identifying ordered regions of a material according to some embodiments of the present application;

[0041] Figure 6 A flowchart of a method for training an image recognition model for determining at least one of a degree of order and an ordered region distribution map of a material according to some embodiments of the present application;

[0042] Figure 7 An exemplary diagram of standard results annotated for a test electron diffraction pattern set and prediction results output by an image recognition model for the test electron diffraction pattern set according to some embodiments of the present application;

[0043] Figure 8 A schematic block diagram of an electronic device according to some embodiments of the present application;

[0044] Figure 9 is a schematic block diagram of a computer system on which some embodiments of the present application may be implemented;

[0045] Figure 10 This is a schematic block diagram of an apparatus for testing the orderliness of a material according to some embodiments of the present application. DETAILED DESCRIPTION

[0046] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0048] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0049] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0050] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0051] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0052] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0053] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0054] The degree of material order can be analyzed using methods such as Raman spectroscopy and X-ray diffraction (XRD). Raman spectroscopy indirectly reflects the degree of material order by analyzing the intensity ratio (e.g., ID / IG) of characteristic peaks in the spectrum (e.g., D peak and G peak). However, Raman spectroscopy cannot directly quantify the degree of material order. XRD is suitable for characterizing materials with long-range order, but due to the limitations of photon diffraction, it is insensitive to short-range order and amorphous materials.

[0055] This application provides a method for testing the order of a material. By acquiring electron diffraction patterns collected from various regions of the material and identifying the crystal diffraction features therein, the method can accurately determine the ordered regions within the material, thereby achieving a quantitative assessment of the material's order. This method utilizes the high resolution of electron diffraction to locate and identify ordered regions at the nanometer level or even the atomic level, thereby accurately and reliably assessing the overall order of the material.

[0056] According to some embodiments of the present application, referring to Figure 1 , Figure 1 Flowchart of method 100 for testing the orderliness of materials in some embodiments of the present application. Figure 1 As shown, the method 100 includes steps S102 to S106.

[0057] In step S102 , a set of electron diffraction patterns of the material is acquired, where each electron diffraction pattern in the set of electron diffraction patterns corresponds to a corresponding one of a plurality of positions in the material.

[0058] At step S104 , in response to an electron diffraction pattern in the set of electron diffraction patterns including a crystal diffraction feature associated with a material, the electron diffraction pattern is classified as an ordered area electron diffraction pattern.

[0059] In step S106 , the order degree of the material is determined based on the ordered area electron diffraction pattern.

[0060] For example, the material to be tested may be a completely disordered amorphous material, or a material with short-range order but long-range disorder, or a material with long-range order. It may also be a completely ordered single crystal material, or a polycrystalline material with order in different regions but different orientations. Furthermore, the material to be tested may be capable of being fabricated into electron-transparent thin sheets (e.g., with a thickness of approximately 100 nanometers) and resistant to electron beam irradiation. The crystal associated with the material may be a crystalline phase that is similar to or derived from the material in composition, structure, and / or properties.

[0061] The electron diffraction pattern set of a material may refer to a collection of diffraction patterns obtained by preparing an electron-transparent thin-film sample of the material to be tested and irradiating it with an electron beam. Figure 2 Non-limiting examples of electron diffraction pattern collections include Figure 2 As shown in Part A of FIG. Each electron diffraction pattern corresponds to a different position in the material sample, reflecting the local structural information of the material at that position. For each electron diffraction pattern, if it exhibits the diffraction characteristics of a crystal, it can be classified as an ordered area electron diffraction pattern, indicating that the material has a crystal structure at the position corresponding to the diffraction pattern. For example, Figure 2 The electron diffraction pattern shown in Part B of FIG includes crystal diffraction features in the form of sharp diffraction spots, and therefore the electron diffraction pattern can be classified as an ordered area electron diffraction pattern. After classifying each electron diffraction pattern in the electron diffraction pattern collection, the degree of order of the material can be quantitatively characterized based on the classification results.

[0062] By collecting electron diffraction patterns at multiple locations of the sample, it is possible to effectively identify ordered regions in the material over a large range with high resolution at the nanometer or even atomic level, thereby achieving accurate quantification of the degree of order.

[0063] According to some embodiments of the present application, optionally, the electron diffraction pattern set is obtained by scanning the material point by point using a transmission electron microscope.

[0064] A transmission electron microscope (TEM) is a high-resolution analytical instrument that uses a high-energy electron beam to penetrate a sample and obtain information about the material's microstructure and composition based on the interaction between the transmitted electrons and the sample. The electron beam is focused on a tiny area of ​​the sample, generating a corresponding electron diffraction pattern. By scanning the material point by point, a transmission electron microscope can produce a collection of high-resolution electron diffraction patterns.

[0065] For example, a collection of electron diffraction patterns can be obtained from four-dimensional scanning transmission electron microscopy (4D-STEM) data on a material. 4D-STEM uses a scanning electron probe to illuminate a sample point by point, recording a two-dimensional diffraction pattern at each location (the "four-dimensional" refers to the two-dimensional scanning position (real space) plus the two-dimensional diffraction space (reciprocal space)). This allows for simultaneous acquisition of real-space and reciprocal-space information, enabling high-resolution, multidimensional characterization of the material's structure.

[0066] According to some embodiments of the present application, optionally, the plurality of positions are selected based on the following operations: selecting an area in the material where particles are not stacked on each other based on a topography of the material; and selecting the plurality of positions from the selected area.

[0067] Please refer to Figure 3 , Figure 3 This is an exemplary schematic diagram of the morphology of materials in some embodiments of the present application. The morphology directly shows the surface or cross-sectional micromorphology of the sample (such as particle size, shape, pore distribution, etc.). It can be considered that the morphology is a real space image, while the electron diffraction pattern is an inverse space image. Figure 3 In the morphology shown, the thicker area is generally the sample stacking area, that is, multiple material particles overlap each other in the direction of electron beam irradiation; the thinner area is generally the sample single particle area, that is, multiple material particles are spread out in a single layer and not stacked on each other.

[0068] To accurately determine the degree of sample order, a thinner region can be selected to collect a collection of electron diffraction patterns. Selecting multiple locations within the thinner region for testing effectively reduces the crosstalk between diffraction signals from overlapping particles. Furthermore, thinner regions reduce the multiple scattering effects caused by the electron beam penetrating the sample, resulting in sharper diffraction features and facilitating accurate classification of the electron diffraction patterns.

[0069] According to some embodiments of the present application, the order degree of the material is optionally determined based on the number of ordered area electron diffraction patterns. As the electron diffraction patterns are collected at denser locations, the calculation results can be more accurate.

[0070] In some examples, the degree of order of the material can be determined based on the number of ordered area electron diffraction patterns and the total number of electron diffraction patterns in the collection of electron diffraction patterns.

[0071] In some examples, the degree of order of a material can be determined based on the number of ordered area electron diffraction patterns and the number of effective electron diffraction patterns in a set of electron diffraction patterns. An effective electron diffraction pattern may refer to an electron diffraction pattern including diffraction features, which is generated based on received effective electron diffraction signals. An effective electron diffraction pattern may indicate the presence of a material at a location corresponding to the electron diffraction pattern.

[0072] In some examples, the degree of order of a material can be determined based on the number of ordered area electron diffraction patterns and the number of invalid electron diffraction patterns in a set of electron diffraction patterns. An invalid electron diffraction pattern may refer to an electron diffraction pattern that does not include any diffraction features, meaning that no valid electron diffraction signals were received. An invalid electron diffraction pattern may indicate that the material is not present at the location corresponding to the electron diffraction pattern.

[0073] For example, since the scanning range of a transmission electron microscope is usually a square area, and the boundaries of the material sample may be irregular, there may be "no signal" (invalid) areas. If these invalid areas are included in the order calculation, the calculated results will be lower than the actual situation. Therefore, the order of the material can be quantitatively characterized by calculating the ratio of the number of electron diffraction patterns in the ordered area to the number of valid electron diffraction patterns, or by calculating the ratio of the number of electron diffraction patterns in the ordered area to the total number of electron diffraction patterns minus the number of invalid electron diffraction patterns. This can reduce the interference of invalid data and improve the accuracy of the order calculation.

[0074] In some examples, the order of the material can be determined based on the number of ordered region electron diffraction patterns and the number of disordered region electron diffraction patterns. The ordered region electron diffraction pattern may refer to an electron diffraction pattern that includes crystalline diffraction features. The disordered region electron diffraction pattern may refer to an electron diffraction pattern that does not include crystalline diffraction features but includes amorphous diffraction features. By using the crystalline diffraction features and amorphous diffraction features associated with the material as a basis for classification, the ordered region electron diffraction pattern may indicate that the position corresponding to the electron diffraction pattern falls into the ordered region of the material, while the disordered region electron diffraction pattern may indicate that the position corresponding to the electron diffraction pattern falls into the disordered region of the material. The order of the material can be quantitatively characterized by calculating the ratio of the number of ordered region electron diffraction patterns to the sum of the number of ordered region electron diffraction patterns and the number of disordered region electron diffraction patterns, so as to reduce the interference of the diffraction signals of substances that are not of interest and improve the accuracy of the order calculation.

[0075] According to some embodiments of the present application, optionally, method 100 further includes determining the ordered area distribution of the material based on the position corresponding to the ordered area electron diffraction pattern.

[0076] Based on the spatial coordinate information of the signal source of the ordered area electron diffraction pattern, the ordered area distribution of the material can be determined and visualized. For example, please refer to Figure 2 In part A of the electron diffraction pattern, each local area corresponding to the position identified as an ordered region can be identified as an ordered region. Connected ordered regions can be merged into the same ordered region, and separate ordered regions can be regarded as separate ordered regions. Optionally, the boundaries of each ordered region can be smoothed. In this way, an ordered region distribution map of the material can be obtained. The ordered region distribution map of the material can intuitively display the size and distribution of the ordered regions, providing important information for studying the microstructure of the material.

[0077] According to some embodiments of the present application, the crystal diffraction characteristics associated with the material may optionally include the diffraction characteristics of a crystal having the same element as the material. For example, for a carbon material, the crystal diffraction characteristics associated with the carbon material may include the diffraction characteristics of a graphite crystal; for a silicon-carbon material, the crystal diffraction characteristics associated with the silicon-carbon material may include the diffraction characteristics of a silicon carbide crystal; and for a lithium-titanium oxide material, the crystal diffraction characteristics associated with the lithium-titanium oxide material may include the diffraction characteristics of a lithium titanate crystal.

[0078] In some embodiments, for example, when testing a material comprising multiple elements, the diffraction characteristics of a crystal comprising at least one element of the material may be used as a basis for classification of the ordered area electron diffraction pattern.

[0079] By using the diffraction characteristics of crystals with the same element or elements as the material as the classification basis for the ordered area electron diffraction pattern, the ordered areas in the material can be identified more accurately, reducing the possibility of misjudging impurity diffraction signals as ordered characteristics of the material, and improving the reliability of order testing.

[0080] According to some embodiments of the present application, optionally, the crystal may be suitable for use in a battery.

[0081] The battery may be, but is not limited to, various electrochemical cells such as lithium batteries, and may take various forms such as, but is not limited to, button-type, soft-pack, and cylindrical batteries. The positive electrode material of the battery may include, for example, one or more elements such as lithium, sodium, nickel, cobalt, and manganese, or combinations thereof, such as lithium iron phosphate, ternary lithium, lithium sodium, and lithium manganese iron phosphate. The negative electrode material of the battery may include, for example, graphite, carbon silicon, and the like.

[0082] The material to be tested can be a material used in a battery or a precursor to a battery material. By using the diffraction characteristics of crystals suitable for use in batteries as the basis for classification of ordered area electron diffraction patterns, the material's ordering can be tested. This helps assess whether the material's crystal content is high enough to be suitable for battery use and predict the performance of batteries made from the material.

[0083] According to some embodiments of the present application, the crystal may optionally be adapted for the reactive element to be intercalated therein and / or deintercalated therefrom.

[0084] Reactive elements can be elements that participate in the battery's redox reaction, entering the electrolyte from the battery's positive electrode through oxidation and returning to the battery's positive electrode from the electrolyte through reduction. Reactive elements can include both metallic and non-metallic elements. For example, in lithium-ion batteries, the reactive element is lithium; in sodium-ion batteries, the reactive element is sodium; and in hydrogen fuel cells, the reactive element is hydrogen.

[0085] Crystals suitable for embedding and / or de-embedding of reactive elements may, for example, have a stable layered or channel-like structure, and the content of such crystal structures in the material will affect the mobility of the reactive elements. For example, for lithium-ion batteries using graphite as the negative electrode, the crystal structure of graphite is suitable for embedding and de-embedding of lithium ions. By using the diffraction characteristics of crystals suitable for embedding and / or de-embedding of reactive elements as the basis for classification of ordered area electron diffraction patterns to test the order of the material, it is helpful to evaluate whether the content of such crystal structures in the material is large enough to achieve a degree suitable for embedding and / or de-embedding of reactive elements, and thus predict the performance indicators such as capacity, rate performance and cycle life of the battery prepared from the material.

[0086] According to some embodiments of the present application, optionally, method 100 also includes one or more of the following: in response to the electron diffraction pattern in the electron diffraction pattern set not including crystal diffraction features, classifying the electron diffraction pattern as a non-ordered region electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set not including crystal diffraction features but including non-crystalline diffraction features associated with the material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set not including any diffraction features, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set including diffraction features, classifying the electron diffraction pattern as a valid electron diffraction pattern.

[0087] According to some embodiments of the present application, optionally, the amorphous diffraction features associated with the material may include amorphous diffraction features having the same element as the material.

[0088] In other words, in addition to classifying the electron diffraction pattern as an ordered region electron diffraction pattern, the electron diffraction pattern may also be additionally or alternatively classified as a non-ordered region electron diffraction pattern, a disordered region electron diffraction pattern, an invalid electron diffraction pattern, and / or a valid electron diffraction pattern. Generally speaking, a valid electron diffraction pattern may include an ordered region electron diffraction pattern and a disordered region electron diffraction pattern, while a non-ordered region electron diffraction pattern may include a disordered region electron diffraction pattern and an invalid electron diffraction pattern. The classification may be set according to specific test requirements.

[0089] For example, see Figure 2 In part C of the electron diffraction pattern, the electron diffraction pattern does not include crystalline diffraction features in the form of sharp diffraction points, so the electron diffraction pattern can be classified as a non-ordered region electron diffraction pattern. Furthermore, the electron diffraction pattern also includes amorphous diffraction features in the form of diffraction rings, so the electron diffraction pattern can be classified as a disordered region electron diffraction pattern, and it is considered that an amorphous structure exists at the corresponding position. It is understood that if the electron diffraction pattern does not include diffraction features (is completely black), the electron diffraction pattern can be classified as an invalid electron diffraction pattern, and it is considered that no material exists at the corresponding position. Figure 2 Both electron diffraction patterns in Part B and Part C can be classified as effective electron diffraction patterns.

[0090] In some embodiments, the degree of order can be calculated as: degree of order = number of ordered area electron diffraction patterns / number of effective electron diffraction patterns. In some embodiments, the degree of order can be calculated as: degree of order = number of ordered area electron diffraction patterns / (number of ordered area electron diffraction patterns + number of disordered area electron diffraction patterns). In some embodiments, the degree of order can be calculated as: degree of order = number of ordered area electron diffraction patterns / (total number of electron diffraction patterns - number of invalid area electron diffraction patterns). In some embodiments, the degree of order can be calculated as: degree of order = (number of effective electron diffraction patterns - number of disordered area electron diffraction patterns) / number of effective area electron diffraction patterns. Equivalent mathematical transformations and reasonable expansions of the above-mentioned degree of order calculation formulas all fall within the scope of protection of this application.

[0091] This embodiment improves the robustness and flexibility of order calculation by introducing multiple classification criteria for electron diffraction patterns. For example, when direct identification of ordered regions is difficult, order can be calculated indirectly through elimination (counting disordered / invalid regions).

[0092] Furthermore, more refined classification can allow the ordered region distribution map to include more information. For example, by also classifying the disordered region electron diffraction pattern and the invalid region electron diffraction pattern, the distribution of disordered and invalid regions can also be reflected in the ordered region distribution map. By integrating this data, the boundaries of the ordered regions can be more accurately determined.

[0093] According to some embodiments of the present application, optionally, in response to an electron diffraction pattern in the set of electron diffraction patterns comprising at least one crystal diffraction feature of a plurality of crystal diffraction features associated with the material, the electron diffraction pattern is classified as an ordered area electron diffraction pattern.

[0094] In some embodiments, additionally or alternatively, in response to an electron diffraction pattern in the set of electron diffraction patterns not including any of the multiple crystal diffraction features, the electron diffraction pattern is classified as a non-ordered region electron diffraction pattern; or in response to an electron diffraction pattern in the set of electron diffraction patterns not including any of the multiple crystal diffraction features but including at least one of the one or more non-crystalline diffraction features associated with the material, the electron diffraction pattern is classified as a disordered region electron diffraction pattern.

[0095] The multiple crystal diffraction features associated with a material may refer to diffraction features corresponding to multiple crystals associated with the material, or may refer to multiple diffraction features of a single crystal associated with the material. In some embodiments, the multiple crystals associated with the material may include multiple crystals each having one or more elements identical to the material. For example, for a lithium titanium oxyfluoride material, the multiple crystals associated with the lithium titanium oxyfluoride material may include lithium fluoride, lithium titanate, and lithium oxide.

[0096] By classifying electron diffraction patterns containing any crystal diffraction features associated with the material as ordered area electron diffraction patterns, the ordered structure in the material can be detected more comprehensively and the possibility of missed judgment can be reduced.

[0097] According to some embodiments of the present application, optionally, the classification of the electron diffraction pattern is achieved through an image recognition model.

[0098] An image recognition model is a machine learning model based on computer vision that automatically extracts and classifies image features. Any suitable image recognition model, currently known or later developed, can be used, such as, but not limited to, the Vision Transformer (VIT) model. The obtained electron diffraction pattern can be input to a trained image recognition model (the training method is described in detail below). The model automatically classifies and outputs the electron diffraction pattern type (e.g., ordered area electron diffraction pattern, disordered area electron diffraction pattern, etc.).

[0099] By introducing an image recognition model, we can automatically and efficiently identify crystal diffraction features in electron diffraction patterns, improving classification efficiency. The image recognition model can also identify weak or mixed diffraction signals, achieving higher accuracy than manual recognition.

[0100] According to some embodiments of the present application, optionally, the image recognition model is configured to determine the order degree and ordered region distribution of the material based on a received set of electron diffraction patterns of the material.

[0101] By feeding the entire electron diffraction pattern collection into the image recognition model, the model not only automatically classifies the electron diffraction patterns, but also counts the number of different electron diffraction pattern types, calculating and outputting the material's degree of order. Furthermore, by analyzing the classification results within the electron diffraction pattern collection, the image recognition model automatically identifies the specific location and distribution of ordered regions within the material and generates visualizations.

[0102] Method 100 can be applied to test the order of various materials, including but not limited to long-range ordered materials, short-range ordered materials, etc. The application of method 100 is specifically described below using carbon materials as an example. Among carbon materials, hard carbon, also known as non-graphitizable carbon, is a type of carbon material that cannot be transformed into a graphite crystal structure after high-temperature heat treatment (usually up to 3000°C). Its name "hard" comes from its high mechanical strength and difficult graphitization properties, in contrast to soft carbon (graphitizable carbon). Hard carbon usually has a structural feature of short-range order but long-range disorder, that is, there is a certain arrangement pattern between carbon atoms, but the overall structure is disordered. The complex disordered structure makes it difficult to apply traditional crystal structure analysis methods to it.

[0103] According to some embodiments of the present application, referring to Figure 4 , Figure 4 Flowchart of method 200 for testing the order of carbon materials according to some embodiments of the present application. Figure 4 As shown, the method 200 includes steps S202 to S206.

[0104] In step S202 , a set of electron diffraction patterns of the carbon material is obtained, where each electron diffraction pattern in the set of electron diffraction patterns corresponds to a corresponding one of a plurality of positions in the carbon material.

[0105] In step S204 , in response to an electron diffraction pattern in the set of electron diffraction patterns including a graphite diffraction feature, the electron diffraction pattern is classified as an ordered area electron diffraction pattern.

[0106] In step S206 , the order degree of the carbon material is determined based on the ordered area electron diffraction pattern.

[0107] Graphite is suitable for use in batteries due to its unique layered structure, making it suitable for the intercalation and deintercalation of reactive ions such as lithium ions. By using graphite crystal diffraction characteristics (for example, the presence of characteristic diffraction points in reciprocal space for 002-plane graphite-like fringes) as a basis for classifying ordered area electron diffraction patterns, the order of carbon materials can be tested, making the test results more practical in the battery field. In other words, testing the order of carbon materials using method 200 can be considered testing the degree of graphitization of carbon materials.

[0108] According to some embodiments of the present application, the electron diffraction pattern set is optionally obtained from 4D-STEM data of the carbon material. Using 4D-STEM to obtain the electron diffraction pattern set can record complete diffraction information at multiple locations on the sample, thereby more accurately calculating the distribution of graphitized regions.

[0109] According to some embodiments of the present application, optionally, the plurality of positions are selected based on the following operations: selecting an area in the carbon material where particles are not stacked on each other based on a topography of the carbon material; and selecting the plurality of positions from the selected area.

[0110] Carbon materials can easily agglomerate, resulting in multiple carbon particles sometimes stacked within a sample. Selecting areas where isolated carbon particles exist to test the order of the carbon material can improve test accuracy.

[0111] According to some embodiments of the present application, optionally, the degree of order of the carbon material is determined based on the number of ordered area electron diffraction patterns and the number of effective electron diffraction patterns in the electron diffraction pattern set. Method 200 may also include: determining the ordered area distribution of the carbon material based on the position corresponding to the ordered area electron diffraction pattern. By counting the proportion of the number of ordered area electron diffraction patterns to all effective electron diffraction patterns, a rapid and accurate quantitative assessment of the degree of order of the carbon material can be achieved. By correlating the electron diffraction pattern with the position in the carbon material, the spatial distribution of the ordered area in the carbon material can be characterized over a larger range, which is beneficial to the visualization of the carbon material structure.

[0112] According to some embodiments of the present application, optionally, method 200 also includes one or more of the following: in response to the electron diffraction pattern in the electron diffraction pattern set not including the graphite diffraction feature, classifying the electron diffraction pattern as a non-ordered region electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set not including the graphite diffraction feature but including the amorphous diffraction feature associated with the carbon material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set not including any diffraction feature, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or in response to the electron diffraction pattern in the electron diffraction pattern set including the diffraction feature, classifying the electron diffraction pattern as a valid electron diffraction pattern.

[0113] For example, amorphous diffraction features associated with carbon materials can include broad, diffusely scattered rings. Figure 2 , Figure 2 Parts B and C show electron diffraction patterns of ordered and disordered regions of an exemplary carbon material, respectively, and the black object in the center is an image of a blocker used to reduce the intensity of the transmitted electron beam. Figure 2 Part B includes sharp diffraction spots. Figure 2 The C part of does not include sharp diffraction spots but includes diffuse scattering rings. Therefore, it can be Figure 2 The electron diffraction pattern of part B is classified as an ordered area electron diffraction pattern, while Figure 2 The electron diffraction pattern of part C is classified as a disordered region electron diffraction pattern.

[0114] Similarly, the calculation of the order degree of carbon materials and the generation of the ordered region distribution map can refer to the previous description and be adaptively adjusted in combination with actual conditions, which will not be elaborated here.

[0115] According to some embodiments of the present application, the classification of the electron diffraction patterns is optionally implemented using an image recognition model. For example, the image recognition model includes a VIT model. Further, the image recognition model is configured to determine the order and ordered region distribution of the carbon material based on the received set of electron diffraction patterns of the carbon material.

[0116] Various embodiments of the method 200 may be similarly described with reference to the above description of the method 100 and will not be elaborated here.

[0117] For non-limiting illustrative purposes, an exemplary testing procedure for the degree of order of carbon materials is described in detail below.

[0118] In step A, the carbon material to be tested is prepared into a sample suitable for transmission electron microscopy observation. Since carbon materials are often aggregated, a volatile polar solvent such as ethanol or methanol can be used as a dispersing solvent to prepare the carbon material into a solution. Furthermore, an ultrasonicator can be used to disperse the solution to break up aggregated carbon material particles. The ultrasonication time depends on the aggregation state of the carbon material. Generally, the more aggregated the carbon material, the longer the ultrasonication time required. For example, the ultrasonication time can range from 5 to 20 minutes. In some cases, the ultrasonication time can be longer than 20 minutes. An appropriate amount (e.g., 1 ml) of the supernatant from the sonicated solution is selected and dropped onto a copper mesh (e.g., with a diameter of 3 mm) and allowed to dry. Drying methods include natural air drying, infrared lamp drying, and so on. Infrared lamp drying requires a shorter drying time than natural air drying, thereby reducing the possibility of sample contamination.

[0119] In step B, the transmission electron microscope is debugged to make it suitable for collecting 4D-STEM data. The electron beam acceleration voltage can be flexibly selected according to the test requirements, such as different gears such as 200 kV or 1300 kV. Increasing the acceleration voltage usually improves the quality of the electron diffraction pattern. In addition, the condenser aperture, parallel optical axis and other settings of the transmission electron microscope can also be adjusted so that the transmission electron microscope reaches a suitable state for collecting 4D-STEM data. For example, when the spot convergence angle is less than 1 millirad, it can be considered that the transmission electron microscope is suitable for collecting 4D-STEM data, and debugging is completed.

[0120] In step C, 4D-STEM data is collected. To improve the accuracy of the ordering test, a transmission electron microscope (TEM) can be used to obtain a topographic image of the sample. A thin region containing only a single particle can be set as the acquisition region for the 4D-STEM data. Furthermore, acquisition parameters such as the acquisition region size, acquisition step length, and exposure time can be configured. The acquisition region size is set to prevent sample drift during acquisition. For example, the acquisition region can be set as a square with a side length ranging from 10 to 500 nanometers. The acquisition step length (i.e., the distance between two adjacent acquisition positions) can be determined based on the sample conditions and can be set, for example, from 1 to 5 nanometers. These two parameters can be optimized in conjunction with each other. A larger acquisition region size and a smaller acquisition step length result in more acquisition positions, resulting in a larger number of electron diffraction patterns in the electron diffraction pattern set. For example, when the acquisition region size is 100 nanometers by 100 nanometers, the acquisition step length can be set to 3 nanometers or 5 nanometers; when the acquisition region size is 10 nanometers by 10 nanometers, the acquisition step length can be set to 1 nanometer, 2 nanometers, or 0.5 nanometers. The exposure time can be set, for example, between 8 microseconds and 500 milliseconds. The sample is scanned point by point using the set acquisition parameters to obtain a set of electron diffraction patterns of the sample.

[0121] In step D, the degree of order and the ordered spatial distribution are calculated. The electron diffraction patterns can be classified according to the characteristic diffraction points existing in the reciprocal space of the crystal features of the carbon material (e.g., 002 crystal plane graphite-like stripes). The electron diffraction patterns that include graphite diffraction features are classified as ordered area electron diffraction patterns, and invalid electron diffraction patterns are excluded. The degree of order of the carbon material is calculated according to the formula "degree of order = number of ordered area electron diffraction patterns / number of valid electron diffraction patterns = number of ordered area electron diffraction patterns / (total number of electron diffraction patterns - number of invalid electron diffraction patterns)". Furthermore, an ordered area distribution pattern can be generated based on the position corresponding to the ordered area electron diffraction pattern.

[0122] According to some embodiments of the present application, referring to Figure 5 , Figure 5Flowchart of method 300 for training an image recognition model for identifying ordered regions of a material in some embodiments of the present application. Figure 5 As shown, the method 300 includes steps S302 to S304.

[0123] In step S302, a training image set is constructed, the training image set including multiple electron diffraction patterns of the material as samples, each electron diffraction pattern is marked as an ordered area electron diffraction pattern, wherein the electron diffraction pattern is marked as an ordered area electron diffraction pattern in response to the electron diffraction pattern including crystal diffraction features associated with the material.

[0124] In step S304 , an image recognition model is trained using a training image set, and the image recognition model is configured to determine whether the received electron diffraction pattern is an ordered area electron diffraction pattern.

[0125] The training image set constructed in step S302 includes electron diffraction patterns and classification information of electron diffraction patterns. Different classifications can be set according to specific test requirements. Similar to the above, the electron diffraction pattern can be classified into one or more of an ordered area electron diffraction pattern, a non-ordered area electron diffraction pattern, a disordered area electron diffraction pattern, an invalid electron diffraction pattern, and a valid electron diffraction pattern. The sample image is annotated according to the set classification to construct a training image set. Correspondingly, the image recognition model trained using such a training image set can output the classification of the electron diffraction pattern it receives.

[0126] By constructing a training image set containing electron diffraction patterns labeled with ordered regions, an image recognition model is trained to accurately identify ordered regions in materials. This method leverages artificial intelligence to autonomously identify the type of electron diffraction pattern, improving the efficiency of ordered region identification. By adjusting the training image set, the model can be adapted to the analysis needs of different materials. This provides a reliable technical means for automated and standardized testing of material order.

[0127] In some embodiments, the image recognition model may be further configured to calculate the degree of order and / or generate an ordered area distribution map after predicting the type of each electron diffraction pattern in the received electron diffraction pattern set. For example, the degree of order may be calculated according to the corresponding order calculation formula mentioned above. The ordered area distribution map may be generated based on the spatial coordinate information of the signal source of the ordered area electron diffraction pattern.

[0128] For non-limiting illustrative purposes, an example training process for an image recognition model for identifying ordered regions of carbon materials is described in detail below.

[0129] The aforementioned steps A to C can be performed on each of the plurality of carbon materials, respectively, to obtain a plurality of electron diffraction patterns. These carbon materials may have different degrees of order and / or ordered region distributions.

[0130] Next, in step D', the type of the obtained electron diffraction pattern is labeled. Electron diffraction patterns can be classified based on the presence of characteristic diffraction points in reciprocal space, which are characteristic of the carbon material's crystal features (e.g., graphite-like fringes on the 002 crystal plane). For example, electron diffraction patterns can be classified as ordered region electron diffraction patterns, disordered region electron diffraction patterns, or invalid electron diffraction patterns.

[0131] In step E, the type-labeled electron diffraction patterns can be used as training data to train the VIT model. To improve model accuracy, the training data can be, for example, at least 100 sets. When the model accuracy exceeds a preset threshold (e.g., 95%), the model is considered successfully trained. The trained VIT model can then determine whether a received electron diffraction pattern is an ordered area electron diffraction pattern.

[0132] According to some embodiments of the present application, referring to Figure 6 , Figure 6 Flowchart of method 400 for training an image recognition model for determining at least one of the order degree and ordered region distribution map of a material in some embodiments of the present application. Figure 6 As shown, the method 400 includes steps S402 to S404.

[0133] In step S402, a training image set is constructed, the training image set including a set of electron diffraction patterns of multiple materials as samples, each electron diffraction pattern in the electron diffraction pattern set corresponds to a corresponding one of multiple positions in the material, and each electron diffraction pattern set is annotated with at least one of a degree of order and an ordered area distribution map, wherein, in response to the electron diffraction pattern in the electron diffraction pattern set including a crystal diffraction feature associated with the material, the electron diffraction pattern is determined to be an ordered area electron diffraction pattern, thereby obtaining the at least one of the degree of order and the ordered area distribution map of the electron diffraction pattern set.

[0134] In step S404 , an image recognition model is trained using a training image set, and the image recognition model is configured to output at least one of an order degree and an ordered area distribution map based on the received electron diffraction pattern set.

[0135] The training image set constructed in step S402 may include a set of electron diffraction patterns and the order degree and / or ordered area distribution map of the materials corresponding to the set. Unlike the embodiment described in connection with method 300, in which the image recognition model is configured to further calculate the order degree and / or generate the ordered area distribution map after autonomously classifying the electron diffraction patterns, the trained image recognition model in this embodiment can directly output the order degree and / or ordered area distribution map of a material after receiving the set of electron diffraction patterns of the material.

[0136] After training is complete, the model can be evaluated using the test set. The test set can be constructed in a similar way to the training set, but it does not participate in model training. Figure 7 . Figure 7 Part A of exemplarily shows the standard results annotated for the test electron diffraction pattern set, which includes an ordered region distribution diagram (showing not only ordered regions but also disordered regions and invalid regions) and an order degree of 59.8%. Figure 7 Part B shows the image recognition model's predictions for this test electron diffraction pattern set. As can be seen, the distribution of ordered regions in the predicted results is largely consistent with the standard results, and the model's predicted order of 60.6% closely matches the standard's order of 59.8%. This comparison fully demonstrates the excellent performance of the trained image recognition model.

[0137] By training an image recognition model to directly output the material's degree of order and / or the distribution of ordered regions, this approach enables end-to-end analysis from electron diffraction data to quantitative analysis results. Training on a complete set of electron diffraction patterns enables the model to comprehensively assess the structural characteristics of each location in the material. This output not only provides the overall degree of order but also generates intuitive information on the spatial distribution of ordered regions, providing multi-dimensional structural characterization data for material performance research.

[0138] For non-limiting illustrative purposes, an example training process of an image recognition model for determining the order degree and ordered region distribution map of a carbon material is described in detail below.

[0139] The aforementioned steps A to D can be performed separately for each of the plurality of carbon materials to obtain a set of electron diffraction patterns of the corresponding carbon materials, calculate their order, and generate an ordered area distribution map for them. These carbon materials may have different degrees of order and / or ordered area distributions.

[0140] Next, in step E', the VIT model can be trained using a collection of electron diffraction patterns annotated with the degree of order and the ordered area distribution diagram as training data. To improve the model's accuracy, the training data set can be, for example, at least 100 sets. When the model's accuracy exceeds a preset threshold (e.g., 95%), the model is considered successfully trained. The trained VIT model can then output the degree of order and the ordered area distribution diagram for the received collection of electron diffraction patterns.

[0141] Various embodiments of methods 300 and 400 can be similarly described with reference to the above descriptions of methods 100 and 200, and are not further elaborated here.

[0142] According to some embodiments of the present application, an electronic device is provided. Figure 8 , which shows a schematic block diagram of an electronic device 500 according to some embodiments of the present application. Figure 8 As shown, electronic device 500 includes one or more processors 502 and a memory 504 storing computer-executable instructions. When executed by the processor(s) 502, the computer-executable instructions cause the processor(s) 502 to perform the method according to any of the aforementioned embodiments of the present application. The processor(s) 502 may be, for example, a central processing unit (CPU) of the electronic device 500. The processor(s) 502 may be any type of general-purpose processor, or may be a processor specifically designed for testing materials or training models, such as an application-specific integrated circuit ("ASIC"). The memory 504 may include various computer-readable media accessible by the processor(s) 502. In various embodiments, the memory 504 described herein may include volatile and non-volatile media, removable and non-removable media. For example, the memory 504 may include any combination of random access memory ("RAM"), dynamic RAM ("DRAM"), static RAM ("SRAM"), read-only memory ("ROM"), flash memory, cache memory, and / or any other type of non-transitory computer-readable media. The memory 504 may store instructions that, when executed by the processor 502, cause the processor 502 to perform the method according to any of the aforementioned embodiments of the present application. For example, the electronic device 500 may be implemented as a server or server system, a personal computer, a laptop computer, a smart phone, a personal digital assistant, a tablet computer, etc., or any combination thereof.

[0143] According to some embodiments of the present application, a computer-readable storage medium having computer-executable instructions stored thereon is provided. When the computer-executable instructions are executed by a computer, the computer executes the method according to any of the aforementioned embodiments of the present application.

[0144] According to some embodiments of the present application, a computer program product is provided, which may include instructions that, when executed by a processor, may implement a method according to any of the foregoing embodiments of the present disclosure. The instructions may be any set of instructions to be executed directly by one or more processors, such as machine code, or any set of instructions to be executed indirectly, such as a script. The instructions may be stored in an object code format for direct processing by one or more processors, or in any other computer language, including a script or collection of independent source code modules that are interpreted on demand or compiled in advance.

[0145] Figure 9is a schematic block diagram illustrating a computer system 600 on which some embodiments of the present application may be implemented. Computer system 600 includes a bus 602 or other communication mechanism for communicating information, and a processing device 604 coupled to bus 602 for processing information. Computer system 600 also includes a memory 606 coupled to bus 602 for storing instructions to be executed by processing device 604. Memory 606 may be a random access memory (RAM) or other dynamic storage device. Memory 606 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by processing device 604. Computer system 600 also includes a read-only memory (ROM) 608 or other static storage device coupled to bus 602 for storing static information and instructions for processing device 604. A storage device 610, such as a magnetic disk or optical disk, is provided and coupled to bus 602 for storing information and instructions. Computer system 600 may be coupled via bus 602 to output devices 612 for providing output to a user, such as, but not limited to, a display (such as a cathode ray tube (CRT) or liquid crystal display (LCD)), speakers, and the like. Input devices 614, such as a keyboard, mouse, microphone, and the like, are coupled to bus 602 for communicating information and command selections to processing device 604. Computer system 600 may perform embodiments of the present disclosure. Consistent with certain implementations of the present disclosure, results are provided by computer system 600 in response to processing device 604 executing one or more sequences of one or more instructions contained in memory 606. Such instructions may be read into memory 606 from another computer-readable medium, such as storage device 610. Execution of the sequences of instructions contained in memory 606 causes processing device 604 to perform the methods described herein. Alternatively, hardwired circuitry may be used in place of or in combination with software instructions to implement the present teachings. Therefore, implementations of the present disclosure are not limited to any specific combination of hardware circuitry and software. In various embodiments, computer system 600 can be connected to one or more other computer systems like computer system 600 across a network via network interface 616 to form a networked system. The network can include a private network or a public network such as the Internet. In a networked system, one or more computer systems can store data and supply data to other computer systems. As used herein, the term "computer-readable medium" refers to any medium that participates in providing instructions to processing device 604 for execution. Such media can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks such as storage device 610. Volatile media include dynamic memory such as memory 606. Transmission media include coaxial cables, copper wire, and optical fibers, including the wiring comprising bus 602.Common forms of computer-readable media or computer program products include, for example, floppy disks, flexible disks, hard disks, magnetic tape, or any other magnetic medium, CD-ROMs, digital video disks (DVDs), Blu-ray discs, any other optical medium, thumb drives, memory cards, RAM, PROMs and EPROMs, flash EPROMs, any other memory chips or cartridges, or any other tangible medium from which a computer can read. Various forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to processing device 604 for execution. For example, the instructions may initially be carried on a diskette of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 600 may receive the data over the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector coupled to bus 602 may receive the data carried in the infrared signal and place the data on bus 602. Bus 602 carries the data to memory 606, from which processing device 604 retrieves the instructions and executes them. Optionally, the instructions received by memory 606 may be stored on storage device 610 either before or after execution by processing device 604 .

[0146] According to some embodiments of the present application, referring to Figure 10 , Figure 10 This is a schematic block diagram of an apparatus 700 for testing the orderliness of a material in some embodiments of the present application. Figure 10 As shown, apparatus 700 includes a transmission electron microscope 702 and a processor 704. Transmission electron microscope 702 is configured to scan a material point by point to acquire a set of electron diffraction patterns of the material, each electron diffraction pattern in the set corresponding to a respective one of a plurality of locations in the material. Processor 704 is configured to: receive the set of electron diffraction patterns from transmission electron microscope 702; classify the electron diffraction pattern as an ordered area electron diffraction pattern in response to an electron diffraction pattern in the set of electron diffraction patterns including a crystal diffraction feature associated with the material; and determine a degree of order of the material based on the ordered area electron diffraction pattern.

[0147] According to some embodiments of the present application, optionally, the processor 704 can be configured to run the image recognition model trained by the method 300 for training an image recognition model for identifying ordered regions of a material according to any embodiment of the present disclosure to classify the electron diffraction pattern. Additionally or alternatively, the processor 704 can also be configured to run the image recognition model trained by the method 400 for training an image recognition model for determining at least one of the degree of order of a material and the ordered region distribution map according to any embodiment of the present disclosure to determine at least one of the degree of order of the material and the ordered region distribution map. For example, the processor 704 can be configured to perform the method steps described in any embodiment of methods 100 and 200.

[0148] Various embodiments of the apparatus 700 may be similarly described with reference to the foregoing descriptions of methods 100 to 400 , and will not be elaborated herein.

[0149] According to various embodiments, instructions configured to be executed by a processing device or processor to perform a method are stored on a computer-readable medium. A computer-readable medium can be a device that stores digital information. For example, a computer-readable medium includes a compact disk read-only memory (CD-ROM) as is known in the art for storing software. The computer-readable medium is accessed by a processor adapted to execute the instructions configured to be executed.

[0150] The foregoing description describes one or more exemplary embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the exemplary embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a server system. Of course, this disclosure does not exclude that with the future development of computer technology, the computer that implements the functions of the above embodiments may be, for example, a personal computer, a laptop computer, an in-vehicle human-computer interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a game console, a tablet computer, a wearable device, or any combination thereof.

[0152] The terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, product, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, product, or apparatus that includes the elements is not precluded. For example, if words such as "first," "second," etc. are used to indicate names, they do not imply any particular order.

[0153] For the convenience of description, the above devices are described in terms of functions divided into various modules. Of course, when implementing one or more embodiments of the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.

[0155] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means that implement the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram. These computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0156] Those skilled in the art will appreciate that one or more embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, one or more embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0157] One or more embodiments of the present disclosure may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of the present disclosure may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0158] In addition, when used in this application, the words "herein," "above," "below," "hereunder," "supra," and words of similar meaning shall refer to this application as a whole and not to any particular portion of this application. Furthermore, unless expressly stated otherwise or otherwise understood in the context of use, conditional language used herein, such as "may," "might," "for example," "such as," and the like, is generally intended to express that certain embodiments include, while other embodiments do not include, certain features, elements, and / or states. Thus, such conditional language is generally not intended to imply that one or more embodiments in any way require features, elements, and / or states, or whether such features, elements, and / or states are included or performed in any particular embodiment.

[0159] Finally, it should be noted that 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, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for testing the order of a material, characterized in that: The method comprises: obtaining a set of electron diffraction patterns of the material, each electron diffraction pattern in the set of electron diffraction patterns corresponding to a respective one of a plurality of positions in the material; responsive to an electron diffraction pattern in the collection of electron diffraction patterns comprising a crystal diffraction feature associated with the material, classifying the electron diffraction pattern as an ordered area electron diffraction pattern; and Determining the degree of order of the material based on the number of ordered area electron diffraction patterns, Wherein, the classification of the electron diffraction pattern is achieved through an image recognition model.

2. The method according to claim 1, characterized in that The electron diffraction pattern set is obtained by scanning the material point by point using a transmission electron microscope.

3. The method according to claim 1, characterized in that The method further comprises: The ordered area distribution of the material is determined based on the position corresponding to the ordered area electron diffraction pattern.

4. The method according to claim 1, wherein The crystal diffraction characteristics include diffraction characteristics of a crystal having the same element as the material.

5. The method according to claim 4, characterized in that The crystals are suitable for use in batteries.

6. The method according to claim 4, characterized in that The crystals are suitable for the intercalation and / or deintercalation of reactive elements therein.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises one or more of the following: responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including the crystal diffraction feature, classifying the electron diffraction pattern as a non-ordered area electron diffraction pattern; or responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including the crystalline diffraction feature but including a non-crystalline diffraction feature associated with the material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including any diffraction features, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or In response to an electron diffraction pattern in the collection of electron diffraction patterns comprising a diffraction feature, the electron diffraction pattern is classified as a valid electron diffraction pattern.

8. The method according to any one of claims 1 to 6, characterized in that In response to an electron diffraction pattern in the collection of electron diffraction patterns including at least one crystal diffraction feature of a plurality of crystal diffraction features associated with the material, the electron diffraction pattern is classified as an ordered area electron diffraction pattern.

9. The method according to claim 1, characterized in that The image recognition model is configured to determine the order degree and ordered region distribution of the material based on the received set of electron diffraction patterns of the material.

10. The method according to any one of claims 1 to 6, characterized in that The plurality of locations are selected based on the following operations: selecting regions of the material where particles are not stacked on top of each other based on a topography of the material; and The plurality of locations are selected from the selected area.

11. A method for testing the order of carbon materials, characterized in that: The method comprises: obtaining a set of electron diffraction patterns of the carbon material, each electron diffraction pattern in the set of electron diffraction patterns corresponding to a respective one of a plurality of positions in the carbon material; responsive to an electron diffraction pattern in the collection of electron diffraction patterns comprising a graphitic diffraction feature, classifying the electron diffraction pattern as an ordered area electron diffraction pattern; and Determining the degree of order of the carbon material based on the number of ordered area electron diffraction patterns, Wherein, the classification of the electron diffraction pattern is achieved through an image recognition model.

12. The method according to claim 11, characterized in that The set of electron diffraction patterns is obtained from four-dimensional scanning transmission electron microscopy (4D-STEM) data of the carbon material.

13. The method according to claim 11, characterized in that Determining the degree of order of the carbon material based on the number of the ordered area electron diffraction patterns and the number of effective electron diffraction patterns in the electron diffraction pattern set, and the method further includes: The ordered area distribution of the carbon material is determined based on the position corresponding to the ordered area electron diffraction pattern.

14. The method according to any one of claims 11 to 13, characterized in that The method further comprises one or more of the following: responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including the graphitic diffraction feature, classifying the electron diffraction pattern as a non-ordered area electron diffraction pattern; or responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including the graphitic diffraction features but including amorphous diffraction features associated with the carbon material, classifying the electron diffraction pattern as a disordered region electron diffraction pattern; or responsive to an electron diffraction pattern in the collection of electron diffraction patterns not including any diffraction features, classifying the electron diffraction pattern as an invalid electron diffraction pattern; or In response to an electron diffraction pattern in the collection of electron diffraction patterns comprising a diffraction feature, the electron diffraction pattern is classified as a valid electron diffraction pattern.

15. The method according to any one of claims 11 to 13, characterized in that: The image recognition model includes a visual transformer (VIT) model; and The image recognition model is configured to determine the order degree and ordered region distribution of the carbon material based on the received set of electron diffraction patterns of the carbon material.

16. The method according to any one of claims 11 to 13, characterized in that The plurality of locations are selected based on the following operations: selecting an area in the carbon material where particles are not stacked on each other based on a topography of the carbon material; and The plurality of locations are selected from the selected area.

17. A method for training an image recognition model for identifying ordered regions of a material, characterized in that: The method comprises: constructing a training image set, wherein the training image set includes a plurality of electron diffraction patterns of the material as samples, each electron diffraction pattern being labeled as an ordered area electron diffraction pattern; and The image recognition model is trained using the training image set, wherein the image recognition model is configured to determine whether a received electron diffraction pattern is an ordered area electron diffraction pattern, Wherein, in response to the electron diffraction pattern comprising crystal diffraction features associated with the material, the electron diffraction pattern is annotated as an ordered area electron diffraction pattern.

18. A method for training an image recognition model for determining at least one of a degree of order and an ordered region distribution map of a material, characterized in that: The method comprises: constructing a training image set, the training image set including a plurality of electron diffraction pattern sets of the material as samples, each electron diffraction pattern in the electron diffraction pattern set corresponding to a corresponding one of a plurality of positions in the material, each electron diffraction pattern set being annotated with the at least one of the order degree and the ordered area distribution map; and training the image recognition model using the training image set, the image recognition model being configured to output the at least one of the order degree and the ordered area distribution map based on the received electron diffraction pattern set, Wherein, in response to the electron diffraction pattern in the electron diffraction pattern set including crystal diffraction features associated with the material, the electron diffraction pattern is determined to be an ordered area electron diffraction pattern, thereby obtaining the order degree and the ordered area distribution map of the electron diffraction pattern set.

19. An electronic device, characterized in that: include: one or more processors; as well as A memory storing computer executable instructions which, when executed by the one or more processors, cause the one or more processors to perform the method according to any one of claims 1 to 18.

20. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: The computer executable instructions, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 18.

21. A computer program product, characterized in that The computer program product comprises instructions which, when executed by a processor, implement the method according to any one of claims 1 to 18.

22. A device for testing the orderliness of a material, characterized in that: The device comprises: a transmission electron microscope configured to scan the material point by point to obtain a set of electron diffraction patterns of the material, each electron diffraction pattern in the set of electron diffraction patterns corresponding to a respective one of a plurality of positions in the material; and The processor is configured to: receiving the set of electron diffraction patterns from the transmission electron microscope; responsive to an electron diffraction pattern in the collection of electron diffraction patterns comprising a crystal diffraction feature associated with the material, classifying the electron diffraction pattern as an ordered area electron diffraction pattern; and Determining the degree of order of the material based on the ordered area electron diffraction pattern, The processor is further configured to perform at least one of the following operations: running an image recognition model trained by the method according to claim 17 to classify the electron diffraction pattern; or The image recognition model trained by the method according to claim 18 is run to determine the at least one of the order degree and the ordered area distribution map of the material.

Images