Inorganic crystal sample library generation method, apparatus and device, and storage medium
By constructing an inorganic crystal sample library and utilizing crystal structure prototypes and replaceable ion generation methods, the problems of lack of innovation and high cost in the design of new materials for battery systems have been solved, and efficient new material discovery has been achieved.
Patent Information
- Application Number
- CN202411650294.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-18
- Publication Date
- 2025-10-17
AI Technical Summary
Existing technologies in the design of new materials for battery systems have problems such as insufficient innovation, low hit rate, low experimental success rate, long R&D cycle and high cost.
By obtaining a prototype data set of crystal structures, identifying replaceable ions, and generating an inorganic crystal sample library, we use physical mechanisms to construct a crystal generation algorithm, combine valence information and synthetic scores, expand the material library, and remove redundant samples.
It increases the possibility of discovering new materials for battery systems, reduces R&D costs, improves the quality and efficiency of the material library, and shortens the R&D cycle.
Smart Images
Figure CN120808966A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of computational materials science, and in particular to an inorganic crystal sample library generation method, device, equipment and storage medium. BACKGROUND
[0002] At present, the design scheme of new battery system materials is mostly based on doping modification of known material systems. Although these methods can improve the performance of materials to some extent, there are obvious deficiencies. First, doping modification is difficult to create a novel material structure with high novelty, resulting in insufficient innovation. Second, the hit rate of these methods is low, and the experimental success rate is not high, and a large number of experiments are needed to find materials with superior performance. In addition, the traditional experimental method is time-consuming, and the entire research and development cycle is long, and the cost is high, because each experiment needs to start from scratch, consuming a large amount of raw materials and human resources.
[0003] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY
[0004] The main purpose of the present application is to provide an inorganic crystal sample library generation method, device, equipment and storage medium, which aims to solve the technical problem of low material generation quality in the prior art.
[0005] To achieve the above purpose, the present application provides an inorganic crystal sample library generation method, which comprises the following steps:
[0006] Obtain a crystal structure prototype data set, the crystal structure data set comprising a plurality of crystal structure prototypes; determine at least one replaceable ion corresponding to each crystal structure prototype according to the crystal structure prototype, and generate at least one inorganic material sample according to each crystal structure prototype and the corresponding replaceable ion; generate an inorganic crystal sample library according to the inorganic material sample corresponding to each crystal structure prototype.
[0007] It should be noted that constructing an inorganic crystal candidate material database by combining physical mechanisms with crystal generation algorithm construction can greatly improve the discovery of new battery system materials. The structure prototype covers most of the known crystal structures, and the construction of the crystal generation algorithm combined with the physical mechanism greatly improves the possibility of discovering new battery system materials, improves the novelty of the structure, and reduces the research and development cost; at the same time, this work can be widely applied in the battery system of inorganic crystals, further accelerating the discovery of new inorganic materials.
[0008] In some embodiments, the determining the at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype comprises: determining a multi-atom ion with the same valence according to the valence information of each ion in the crystal structure prototype; and determining the at least one replaceable ion corresponding to the crystal structure prototype according to each multi-atom ion.
[0009] It should be noted that, by the valence information of each ion in the crystal structure prototype, the multi-atom ion with the same valence is found according to the valence of each element, a large number of crystal structures with different components can be replaced, the number of the sample library is improved by orders of magnitude, and the charge conservation law and the physical mechanism of doping modification are provided, which is very novel and improves the probability of discovering new battery system materials.
[0010] In some embodiments, the determining the at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype comprises: determining a multi-atom ion with the same valence according to the valence information of each ion in the crystal structure prototype; and determining the at least one replaceable ion corresponding to the crystal structure prototype according to each multi-atom ion.
[0011] It should be noted that, since the historical material data is all materials that have been realized or appeared in real materials, the corresponding relationship between the ions with the same valence is very clear, and the higher the frequency is, the higher the synthesizability is. Based on the existing experience, the materials generated by the replacement method have high synthesizability in theory, because the structure similar to the experimental material has certain reference value for synthesis and preparation.
[0012] In some embodiments, before the determining the target replacement ion and the synthesizability score corresponding to the target replacement ion according to the preset synthesis relationship table, the method further comprises: obtaining a historical material data set; determining the synthesizability score between ions according to the combination information of inorganic crystals in the historical material data set; determining the mapping relationship between ions according to the components of inorganic crystals in the historical material data set; and determining the preset synthesis relationship table according to the mapping relationship between ions and the corresponding synthesizability score.
[0013] It can be understood that the specific historical material data set determines the expansion of the comprehensive degree of the crystal sample by the combination mode of the known materials, and therefore the quality of the historical material data set is very important. The combination information of inorganic crystals in the historical material data set in the historical material data set is used to statistically determine the synthesis possibility, and it is determined according to the components of inorganic crystals which ions can have a corresponding relationship between ions, so as to construct the preset synthesis relationship table.
[0014] In some embodiments, determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype comprises: traversing valence states of each element according to valence states of the crystal structure prototype, determining target ions having the same valence state; and determining at least one replaceable ion corresponding to the crystal structure prototype according to each of the target ions.
[0015] It can be understood that the determination of at least one replaceable ion corresponding to the crystal structure prototype according to each of the target ions is achieved by judging possible valence states of each element in the structure prototype through an algorithm, and then replacing the elements with ions having the same valence state, thereby achieving charge conservation and greatly ensuring the rationality of the generated structure.
[0016] In some embodiments, before the obtaining of the crystal structure prototype dataset, the method further comprises: obtaining a crystal structure dataset containing a plurality of crystal structures; determining a similarity parameter according to crystal structure information and component information of each crystal structure; and screening the crystal structure dataset according to the similarity parameter to obtain the crystal structure prototype dataset.
[0017] It should be noted that, in order to leave representative structure prototypes, the acquisition of the similarity of two crystal structures by comparing site, bond length and bond angle and other crystal structure information of the two crystal structures can screen out representative structures as the basis, and the structure prototypes of representative crystal structures are obtained from a mainstream material database, and candidate materials are further generated based on the structure prototype database, which greatly expands the material space and improves the expansion efficiency and quality of the material library, and avoids the occurrence of a large number of repeated structures.
[0018] In some embodiments, the generating of the inorganic crystal sample library according to each of the inorganic material samples corresponding to the crystal structure prototype comprises: determining structure information of the corresponding inorganic material sample according to each of the inorganic material samples corresponding to the crystal structure prototype; and deduplicating the inorganic material samples according to the structure information of the inorganic material samples to obtain the inorganic crystal sample library.
[0019] It can be understood that although different targeted material expansion methods can obtain a novel and comprehensive material sample library, different material expansion methods can also generate materials with high similarity, thereby wasting a large amount of computing resources and screening costs. Therefore, deduplicating the inorganic material samples according to the structure information of the inorganic material samples can improve the quality of the sample library.
[0020] In a second aspect, to achieve the above object, the present application provides an inorganic crystal sample library generation device, characterized in that the device comprises: an acquisition module configured to acquire a crystal structure prototype dataset, wherein the crystal structure dataset comprises a plurality of crystal structure prototypes; a processing module configured to determine at least one replaceable ion corresponding to each crystal structure prototype, and generate at least one inorganic material sample according to each crystal structure prototype and the corresponding replaceable ion; and the processing module is configured to generate an inorganic crystal sample library according to the inorganic material samples corresponding to each crystal structure prototype.
[0021] In a third aspect, to achieve the above object, the present application provides an inorganic crystal sample library generation device, characterized in that the device comprises: a memory, a processor, and an inorganic crystal sample library generation program stored in the memory and executable on the processor, wherein the inorganic crystal sample library generation program is configured to implement the steps of the inorganic crystal sample library generation method.
[0022] In a fourth aspect, to achieve the above object, the present application provides a storage medium, wherein the storage medium stores an inorganic crystal sample library generation program, and the inorganic crystal sample library generation program, when executed by a processor, implements the steps of the inorganic crystal sample library generation method as described above. BRIEF DESCRIPTION OF DRAWINGS
[0023] Figure 1 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0024] Figure 2 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0025] Figure 3 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0026] Figure 4 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0027] Figure 5 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0028] Figure 6 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0029] Figure 7 FIG. 1 is a flowchart of an embodiment of the inorganic crystal sample library generation method of the present application;
[0030] Figure 8A flowchart of a method for generating an inorganic crystal sample library according to some embodiments of the present application;
[0031] Figure 9 A structural block diagram of a device for generating an inorganic crystal sample library according to a first embodiment of the present application;
[0032] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION
[0033] The embodiments of the technical solutions of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.
[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application; the terms "include" and "have" and any variations thereof used in the specification and the claims and the above description of the drawings are intended to cover the non-exclusive inclusion.
[0035] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise explicitly and specifically limited.
[0036] In this paper, the phrase "embodiment" means that the specific features, structures or properties described in conjunction with the embodiment can 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 mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. The skilled person in the art explicitly and implicitly understands that the embodiments described herein can be combined with other embodiments.
[0037] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents a "or" relationship between the front and rear associated objects.
[0038] In the description of the embodiments of the present application, the term "multiple" refers to two or more (including two), and similarly, "multiple groups" refers to two or more groups (including two groups), and "multiple pieces" refers to two or more pieces (including two pieces).
[0039] In the description of the embodiments of the present application, the orientations or positional relationships indicated by the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like are based on the orientations or positional relationships shown in the 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 devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.
[0040] In the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the technical terms "mounting", "connecting", "connecting", "fixing" and the like should be understood broadly, for example, can be fixedly connected, or can be detachably connected, or can be integrated; can be mechanically connected, or can be electrically connected; can be directly connected, or can be indirectly connected through an intermediate medium, or can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.
[0041] The content disclosed in the embodiments of the present application is mainly applied to the construction process of the inorganic crystal candidate material database. The inorganic crystal candidate material database can be used for the discovery of new materials. The technical personnel can set up corresponding material properties for screening to find the required materials from the inorganic crystal candidate material database according to the use of the new materials. Therefore, the inorganic crystal candidate material database needs to have comprehensive and novel properties, which is the basis for the discovery of new materials.
[0042] In some embodiments, the present scheme uses a structure prototype extraction algorithm to obtain a structure prototype representing a crystal structure from a mainstream material database. The inorganic crystal candidate material database is constructed by combining a physical mechanism with a crystal generation algorithm, which can greatly improve the discovery of new materials for battery systems. The structure prototype can cover most of the known crystal structures. The combination of the physical mechanism and the crystal generation algorithm greatly improves the possibility of discovering new materials for battery systems, reduces the research and development cost while improving the novelty of the structure; at the same time, this work can be widely applied in the battery system of inorganic crystals, and accelerate the discovery of new inorganic materials such as positive electrodes, solid electrolytes and solar cells.
[0043] According to some embodiments of the present application, as Figure 1 shown, a method for generating an inorganic crystal sample library is provided, the method comprising the following steps:
[0044] Acquire a crystal structure prototype data set, wherein the crystal structure data set includes multiple crystal structure prototypes; determine at least one replaceable ion corresponding to the crystal structure prototype based on the crystal structure prototype, and generate at least one inorganic material sample based on each of the crystal structure prototypes and the corresponding replaceable ion; and generate an inorganic crystal sample library based on the inorganic material samples corresponding to each of the crystal structure prototypes.
[0045] It should be noted that the crystal structure prototype dataset is a data set containing a large number of crystal structure prototypes, which can be obtained directly from a third-party database or integrated based on a large number of existing extraction structures, and representative crystal structures are selected as structural prototypes and integrated into a crystal structure prototype dataset. This embodiment does not limit this. Among them, crystal structure prototypes refer to basic models that can represent a class of crystal structures. These models usually have simple geometric shapes and can be used to understand more complex crystal structures, that is, representative crystal structures representing a series of similar structures, so that the most comprehensive crystal structure can be covered with the least order of magnitude.
[0046] It can be understood that after the crystal structure prototype is determined, the structure of this type of crystal can be determined, that is, the connecting bonds between the atoms in the structure. Based on the valence information, it can be determined whether other ions can be used to replace this position. The ions with replacement conditions are the replaceable ions in this embodiment. After the replacement, a new inorganic material sample can be obtained. By replacing the ions at each position in the crystal structure prototype, a large number of inorganic material samples can be obtained based on a crystal structure prototype. By performing the same operation on each crystal structure prototype, a large number of generated inorganic crystal samples can be obtained, thereby generating an inorganic crystal sample library.
[0047] Specifically, we can collect some common crystal structure models. These models act like templates; simply by introducing different elements, we can generate different crystal structure prototypes. Examples include simple cubic, body-centered cubic, face-centered cubic, and other structures, as well as the materials corresponding to each structure. We then identify which atoms in each crystal structure can be replaced by other atoms without changing the overall structure. For example, in a certain crystal structure, calcium ions can be replaced by magnesium ions. Using these crystal structure models and replaceable atoms, we can create new inorganic material samples. For example, we can construct a sample using calcium ions and oxygen ions, and then another using magnesium ions and oxygen ions. Finally, we organize these newly generated inorganic material samples into a database containing a variety of inorganic materials after ion substitution. When we need a specific material, we can directly search and use it from this database.
[0048] It should be noted that the construction of the inorganic crystal candidate material database by combining the physical mechanism with the crystal generation algorithm can greatly improve the discovery of new battery system materials. The structural prototype covers most of the known crystal structures, and the construction of the crystal generation algorithm by combining the physical mechanism greatly improves the possibility of discovering new battery system materials, reduces the research and development cost while improving the structural novelty; at the same time, this work can be widely applied in the battery system of inorganic crystals, further accelerating the discovery of new inorganic materials.
[0049] In some embodiments, as shown in Figure 3 determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype includes: determining a polyatomic ion with the same valence according to the valence information of each ion in the crystal structure prototype; and determining at least one replaceable ion corresponding to the crystal structure prototype according to each polyatomic ion.
[0050] It should be noted that the polyatomic ion is a charged particle composed of multiple atoms, for example: hydroxyl ion (OH - ), phosphate ion (PO4 3- ), and determining at least one replaceable ion corresponding to the crystal structure prototype according to each polyatomic ion is to replace one ion with the same combined valence with multiple ions, which is called mixed replacement in the embodiments. Figure 2 (b) shows that mixed replacement is to replace one ion with the same combined valence with 1-n ions, which has the physical mechanism of charge conservation law and doping modification, and has high novelty, and is expected to discover new battery system materials.
[0051] It can be understood that in the present embodiment, the way of determining at least one replaceable ion corresponding to the crystal structure prototype according to the valence information of each ion in the crystal structure prototype and determining a polyatomic ion with the same valence according to each polyatomic ion can be used as one of the ways of determining replaceable ions, or can be used as a material expansion method alone.
[0052] It should be noted that by the valence information of each ion in the crystal structure prototype, by the valence of each element, a large number of different component crystal structures can be replaced by finding polyatomic ions with the same valence, which can improve the order of magnitude of the sample library, has the physical mechanism of charge conservation law and doping modification, and has high novelty, and improves the probability of discovering new battery system materials.
[0053] In some embodiments, as shown in Figure 4As shown, the determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype includes: determining a target replacement ion and a synthetic score corresponding to the target replacement ion according to a preset synthetic relationship table of the crystal structure prototype, wherein the preset synthetic relationship table is determined according to ion combination information in historical material data; and determining a target replacement ion whose synthetic score corresponding to the target replacement ion is greater than a preset score as a replaceable ion.
[0054] It should be noted that, in order to expand a certain number of materials with higher availability and syntheticity in the database, the selection of replaceable ions is guided by the combination of elements in a large number of existing materials that have been synthesized, and the preset synthetic relationship table can be obtained through experimental data or through known open source databases, which is not limited in the embodiment.
[0055] In a specific implementation, the embodiment refers to the way of guiding the determination of replaceable ions by using existing materials as a probability replacement method, as shown in Figure 2 (c). It is a crystal generation method based on known experimental materials, and the probability relationship is constructed by mining the mapping relationship between similar experimental materials. The synthetic score can be represented as a probability or other synthetic probability parameters. Theoretically, the materials generated by this method have high syntheticity, because the structure similar to the experimental material has certain reference value in synthesis and preparation.
[0056] It should be noted that, because the historical material data are all materials that have appeared in the implementation or real materials, the corresponding relationship between the ions of the same valence is very clear, and the higher the frequency, the higher the syntheticity. Based on existing experience, the materials generated by this replacement method theoretically have high syntheticity, because the structure similar to the experimental material has certain reference value in synthesis and preparation.
[0057] In some embodiments, as shown in Figure 5 Before the determining a target replacement ion and a synthetic score corresponding to the target replacement ion according to a crystal structure prototype searching a preset synthetic relationship table, the method further includes: obtaining a historical material data set; determining a synthetic score between ions according to combination information of inorganic crystals in the historical material data set; determining a mapping relationship between ions according to components of inorganic crystals in the historical material data set; and determining a preset synthetic relationship table according to the mapping relationship between ions and the corresponding synthetic score.
[0058] It should be noted that the historical material data set is the existing material sample set, and the collected data is sorted and standardized to ensure consistent data format for subsequent analysis. According to the composition of the inorganic crystal, a corresponding relationship between different elements and ions can be established, and there is synthetic related data under each corresponding relationship. Data sorting can include: each ion combination; synthesis method and condition; quantitative synthesis result, such as success / failure, performance index, etc. Thus, the synthesis probability or synthesis score can be determined according to these parameters. The mapping relationship between ions can be formed into ion pairs as keys, and the synthetic related parameters as values, which are stored in the preset synthesis relationship table in the form of key-value pairs.
[0059] Further, the synthesis score can be confirmed in various ways, such as: the probability of successful synthesis, such as calculating the proportion of successful synthesis of each ion combination in multiple experiments; material performance evaluation, such as evaluating the physical and chemical properties, electrochemical performance, thermal stability, optical properties, etc. of the synthesized material; synthesis difficulty, such as evaluating the difficulty of the synthesis process, including the harshness of the reaction conditions, the complexity of the operation, etc.
[0060] It can be understood that the specific historical material data set determines the comprehensiveness of expanding the crystal sample through the combination of known materials, so the quality of the historical material data set is very important. The combination information of inorganic crystals in the historical material data set is used to statistically analyze the synthesis possibility, and the corresponding relationship between ions is determined according to the composition of the inorganic crystal, thereby constructing the preset synthesis relationship table.
[0061] In some embodiments, as shown in Figure 6 According to the valence of the crystal structure prototype, the valence of each element is traversed to determine the target ion with the same valence; and at least one replaceable ion corresponding to the crystal structure prototype is determined according to each target ion.
[0062] It should be noted that according to the valence of the crystal structure prototype, the valence of each element is traversed to determine the target ion with the same valence, and the target ion is a single-atom ion. The advantage of this replaceable ion is comprehensive and efficient.
[0063] Specifically, the possible valence of each element in the structure prototype is identified to determine all possible valences, and the combination of the possible valences is traversed to complete the replacement. In this scheme, the equivalent replacement method is named, such as Figure 2(a) as shown. Equivalent replacement is to determine the possible valence of each element in the structural prototype by algorithm, and then replace it with ions of the same valence to achieve charge conservation, which greatly ensures the rationality of the generated structure and covers as large a component space as possible. For example: determine the valence of the original ion in the target crystal structure. For example, assume we want to modify LiFePO4 (lithium iron phosphate), we need to replace Fe3 + ions. Traverse all possible candidate ions to determine which ions have the same valence as the target ion. For LiFePO4, the target ion is Fe3 + , which has a valence of +3. Consult the database to collect all possible +3 valence ions. For example: Al3 + (Al ion), Cr3 + (Cr ion), Ga3 + (Ga ion), In3 + (In ion), etc. These ions are used as replaceable ions to complete the equivalent replacement method.
[0064] It can be understood that the equivalent replacement method, the mixed replacement method and the probability replacement method can be used alone or in combination. Similarly, the three can be expanded simultaneously to obtain a comprehensive, efficient and highly synthesizable inorganic crystal sample library. The preferred embodiment proposed in the present scheme is to determine a large number of replaceable ions according to the equivalent replacement method, the mixed replacement method and the probability replacement method to expand the material database.
[0065] It can be understood that the at least one replaceable ion corresponding to the crystal structure prototype determined according to each target ion is determined by algorithm to determine the possible valence of each element in the structural prototype, and then replaced with ions of the same valence to achieve charge conservation, which greatly ensures the rationality of the generated structure.
[0066] In some embodiments, as shown in Figure 7 , before the crystal structure prototype data set is obtained, the crystal structure data set is obtained, the crystal structure data set contains a plurality of crystal structures; determine the similarity parameter according to the crystal structure information and the component information of each crystal structure; filter the crystal structure data set according to the similarity parameter to obtain the crystal structure prototype data set.
[0067] It should be noted that the crystal structure data set can be an open source third party crystal structure data set, but generally the open source data set is large and redundant, and the quality of the crystal structures in it is uneven. Therefore, from the perspective of theoretical calculation, the calculation cost and the rationality of the structure can be considered, for example, according to the energy, atomic spacing and other dimensions to remove unreasonable structures, reduce the calculation cost by reducing the number of atoms, to filter out the first crystal structure data set with higher rationality.
[0068] Further, in order to improve the quality of each crystal structure in the first crystal structure data set and reduce the order of magnitude of the crystal structure prototype, a part of representative crystal structures can be selected as the crystal structure prototype according to the similarity between the crystals. The specific selection process can be, for example: leaving representative structure prototypes, constructing a structure prototype extraction algorithm, and obtaining the similarity of two crystal structures by comparing the site, bond length and bond angle and other information of the two crystal structures. In addition, the efficiency of prototype comparison is considered (if a structure prototype is directly sought to represent other similar structures in 75w structures, a very large time span is needed). Therefore, according to the physical understanding and the crystal information such as stoichiometry, space group and atom number, the structure is preliminarily divided, then compared two by two, n structures are used to represent n groups of structures, and then the structure is divided again by crystal system and atom number, and finally the structure prototype is extracted by comparison two by two, which greatly reduces the prototype extraction time. That is, the similarity parameter is determined according to the crystal structure information and the component information of each crystal structure, including: classifying the crystal structures according to the stoichiometry, space group and atom number of each crystal structure, obtaining a plurality of crystal structure subsets, and obtaining the similarity parameter between two crystal structures according to the site, bond length and bond angle and other information of each crystal structure in the crystal structure.
[0069] Among them, the traditional structure prototype is often limited to experimental structures, and the structure prototype extraction method proposed in the present scheme obtains the structure prototype representing the crystal structure from the mainstream material database, and further generates candidate materials based on the structure prototype database, which greatly expands the material space and improves the possibility of new material discovery.
[0070] It should be noted that, in order to leave representative structure prototypes, the similarity of two crystal structures can be screened out as the basis by comparing the crystal structure information such as the site, bond length and bond angle of the two crystal structures. The structure prototype representing the crystal structure is obtained from the mainstream material database, and further candidate materials are generated based on the structure prototype database, which greatly expands the material space and improves the expansion efficiency and quality of the material library, and avoids the appearance of a large number of repeated structures.
[0071] In some embodiments, as shown in Figure 8 According to the corresponding inorganic material sample of each crystal structure prototype, the inorganic crystal sample library is generated, including: determining the structure information of the corresponding inorganic material sample according to the corresponding inorganic material sample of each crystal structure prototype; and removing the inorganic material sample according to the structure information of the inorganic material sample, to obtain the inorganic crystal sample library.
[0072] It is understandable that since the samples generated by different material expansion methods must be repetitive, in order to reduce the data redundancy of the inorganic crystal sample library and provide a data basis for subsequent material discovery and material selection work, it is very important to remove redundancy. The structural information of the corresponding inorganic material sample is determined based on the inorganic material sample corresponding to each of the crystal structure prototypes, and deduplication is performed by comparing the site, bond length, bond angle and other information of the two crystal structures.
[0073] It is understandable that although material expansion through different targeted material expansion methods can obtain a novel and comprehensive material sample library, different material expansion methods will inevitably generate materials with high similarity, thereby wasting a lot of computing resources and screening costs. Therefore, the quality of the sample library can be improved by deduplicating inorganic material samples based on the structural information of the inorganic material samples.
[0074] Secondly, to achieve the above objectives, Figure 9 As shown, the present invention also provides an inorganic crystal sample library generating device, characterized in that the inorganic crystal sample library generating device includes: an acquisition module for acquiring a crystal structure prototype data set, wherein the crystal structure data set includes multiple crystal structure prototypes; a processing module for determining at least one replaceable ion corresponding to the crystal structure prototype based on the crystal structure prototype, and generating at least one inorganic material sample based on each of the crystal structure prototypes and the corresponding replaceable ion; the processing module is used to generate an inorganic crystal sample library based on the inorganic material samples corresponding to each of the crystal structure prototypes.
[0075] In the third aspect, in order to achieve the above-mentioned purpose, the present invention also provides an inorganic crystal sample library generation device, characterized in that the device includes: a memory, a processor and an inorganic crystal sample library generation program stored in the memory and runnable on the processor, and the inorganic crystal sample library generation program is configured to implement the steps of the inorganic crystal sample library generation method.
[0076] In a fourth aspect, in order to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which an inorganic crystal sample library generation program is stored. When the inorganic crystal sample library generation program is executed by a processor, the steps of the inorganic crystal sample library generation method as described above are implemented.
[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some or all of the technical features can be replaced equivalently. Such modifications or replacements do not change the essence of the corresponding technical solutions, which should be covered in the scope of the claims and the specification of the present application. In particular, the technical features mentioned in each embodiment can be combined in any manner as long as there is no structural conflict. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.
Claims
1. A method for generating an inorganic crystal sample library, characterized in that: The method for generating an inorganic crystal sample library comprises: obtaining a crystal structure prototype data set, wherein the crystal structure data set comprises a plurality of crystal structure prototypes; Determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype, and generating at least one inorganic material sample according to each of the crystal structure prototypes and the corresponding replaceable ion; An inorganic crystal sample library is generated according to the inorganic material samples corresponding to the crystal structure prototypes.
2. The method according to claim 1, wherein The determining, based on the crystal structure prototype, at least one replaceable ion corresponding to the crystal structure prototype comprises: determining polyatomic ions having the same valence state according to the valence state information of each ion in the crystal structure prototype; At least one replaceable ion corresponding to the crystal structure prototype is determined based on each of the polyatomic ions.
3. The method according to any one of claims 1 to 2, wherein: The step of determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype further comprises: Searching a preset synthesis relationship table according to the crystal structure prototype to determine the target replacement ion and the synthesis score corresponding to the target replacement ion, wherein the preset synthesis relationship table is determined based on the combination information of each ion in the historical material data; The target replacement ion whose synthesis score is greater than a preset score is determined as a replaceable ion.
4. The method according to claim 3, wherein Before searching the preset synthesis relationship table according to the crystal structure prototype to determine the target replacement ion and the synthesis score corresponding to the target replacement ion, the method further includes: Access to historical material datasets; determining a synthetic score between ions based on combined information of inorganic crystals in the historical material dataset; determining a mapping relationship between ions according to components of the inorganic crystals in the historical material dataset; A preset synthesis relationship table is determined according to the mapping relationship between the ions and the corresponding synthesis scores.
5. The method according to any one of claims 1 to 4, wherein The step of determining at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype further comprises: Traverse the valence states of each element according to the valence state of the crystal structure prototype and determine the target ion with the same valence state; At least one replaceable ion corresponding to the crystal structure prototype is determined according to each target ion.
6. The method according to claim 1, wherein Before obtaining the crystal structure prototype data set, the method further includes: obtaining a crystal structure dataset, wherein the crystal structure dataset comprises a plurality of crystal structures; Determining a similarity parameter based on the crystal structure information and component information of each crystal structure; The crystal structure dataset is screened according to the similarity parameter to obtain a crystal structure prototype dataset.
7. The method according to any one of claims 1 to 6, wherein The step of generating an inorganic crystal sample library according to the inorganic material samples corresponding to the crystal structure prototypes includes: Determining structural information of corresponding inorganic material samples according to the inorganic material samples corresponding to the crystal structure prototypes; The inorganic material samples are deduplicated according to the structural information of the inorganic material samples to obtain an inorganic crystal sample library.
8. An inorganic crystal sample library generation device, characterized in that: The inorganic crystal sample library generating device comprises: an acquisition module, configured to acquire a crystal structure prototype data set, wherein the crystal structure data set comprises a plurality of crystal structure prototypes; a processing module, configured to determine at least one replaceable ion corresponding to the crystal structure prototype according to the crystal structure prototype, and generate at least one inorganic material sample according to each of the crystal structure prototypes and the corresponding replaceable ion; The processing module is used to generate an inorganic crystal sample library according to the inorganic material samples corresponding to the crystal structure prototypes.
9. An inorganic crystal sample library generation device, characterized in that: The device includes: a memory, a processor, and an inorganic crystal sample library generation program stored in the memory and executable on the processor, wherein the inorganic crystal sample library generation program is configured to implement the steps of the inorganic crystal sample library generation method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores an inorganic crystal sample library generation program, and when the inorganic crystal sample library generation program is executed by the processor, the steps of the inorganic crystal sample library generation method according to any one of claims 1 to 7 are implemented.