Data-driven material oxygen release performance analysis, prediction and screening method, system and medium

By constructing a data-driven system for analyzing, predicting, and screening the oxygen release performance of materials, and utilizing machine learning models and text mining techniques, this system solves the problem of difficulty in screening high-performance materials in traditional methods, achieving efficient and accurate material screening and promoting the advancement of low-carbon energy utilization technologies.

CN119049589BActive Publication Date: 2026-11-10SOUTHEAST UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411269065.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2026-11-10
Estimated Expiration
2044-09-11

AI Technical Summary

Technical Problem

In existing technologies, the methods for studying the oxygen release performance of oxygen carrier materials mainly rely on trial-and-error experiments and calculations, which makes it difficult to screen high-performance materials, inefficient, and unable to quickly identify high-performance materials.

Method used

Using a data-driven approach, we constructed a machine learning-based system for analyzing, predicting, and screening the oxygen release performance of materials. By utilizing published literature for text mining and dataset construction, and combining it with machine learning models, we achieved high-throughput screening of high-performance oxygen-releasing materials.

Benefits of technology

It significantly improves the accuracy and efficiency of oxygen-releasing material screening, reduces experimental costs and time, provides a rapid identification tool for high-performance materials, and supports the development of low-carbon energy utilization technologies.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119049589B_ABST
    Figure CN119049589B_ABST
Patent Text Reader

Abstract

The application relates to a data-driven material oxygen release performance analysis, prediction and screening method, system and medium, wherein the method comprises the following steps: text mining is performed on published literature data of research oxygen release materials, structure information and oxygen release performance related data of the materials are acquired, and a material structure-oxygen release performance integrated data set is constructed; based on the data set, a machine learning model is constructed, material structure characteristics are input, and regression prediction of oxygen release performance is obtained; based on an open source crystal database, structure data of possible oxygen release materials are acquired, input into the trained and optimized model, and high-throughput screening of the oxygen release materials is realized. Compared with the prior art, the application mines data from published literature, and a mapping relationship between material structure data and oxygen release performance is constructed through a machine learning model, so that the cost is low, the reliability is high, the screening range of the oxygen release materials is greatly reduced, and problems such as time-consuming and labor-consuming of traditional material experiment testing are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the fields of chemically looped oxygen decoupled combustion and chemically looped air separation technology, and in particular to a data-driven method, system, and medium for analyzing, predicting, and screening the oxygen release performance of materials. Background Technology

[0002] The massive emission of carbon dioxide has caused severe climate problems such as global warming, posing new challenges to the development of low-carbon energy utilization technologies. Chemical looping oxygen decoupling combustion and chemical looping air separation are both clean, efficient, and low-energy-consumption low-carbon energy utilization technologies, both based on the principle of metal oxides releasing oxygen at high temperatures. Therefore, the oxygen release performance of metal oxide materials as oxygen carriers is the most important research focus, and insufficient oxygen release performance is one of the main reasons limiting their commercial application.

[0003] At present, the main research methods for oxygen release performance of oxygen carrier materials are: (1) experimental trial and error method, which uses XRD and other methods to characterize the material structure and thermogravimetric analysis to characterize oxygen release performance and cycle stability. The focus of experimental research is on material modification and enhancement. By changing the preparation method, crystal structure, micromorphology, etc., the oxygen release performance and anti-sintering macroscopic performance of oxygen carrier materials can be improved; (2) computational screening method, which uses density functional theory, molecular simulation and other computational methods to explore the specific mechanism of chemical chain reaction process and the oxygen release potential of materials from the microscopic perspective, calculates lattice oxygen activity and adsorption energy, and reveals atomic-level reaction mechanism, reaction path, rate-controlling steps and other information. However, experimental and computational research can only be considered as trial and error research, which can only provide limited empirical guidance. The huge combination of elements and structural types of multi-metal oxides means that the design and development of high-performance oxygen carriers must break through the research mode based on trial and error. How to quickly screen high-performance oxygen carriers is still a huge challenge. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing technology by providing a data-driven method, system, and medium for analyzing, predicting, and screening the oxygen release performance of materials. Compared with traditional trial-and-error research methods, this method is low-cost, highly reliable, and significantly reduces the screening range of oxygen-releasing materials, thus facilitating the discovery of high-performance oxygen-releasing materials.

[0005] The applicant believes that data-driven research paradigms have broad application prospects for objects where basic principles are incomplete and original prior knowledge is lacking, but where real data is readily available. Utilizing a data-driven paradigm to study the oxygen release performance of materials allows for the construction of datasets by collecting structural and oxygen release data of metal oxide materials, training machine learning models, and ultimately enabling the analysis, prediction, and screening of materials' oxygen release performance.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] This invention provides a data-driven method for analyzing, predicting, and screening the oxygen release performance of materials, comprising the following steps:

[0008] S1: Conduct text mining on publicly published literature on oxygen-releasing materials to extract data related to structure and oxygen-releasing performance, and construct a "material structure-oxygen-releasing performance" dataset;

[0009] S2: Based on the machine learning model, using the X-ray diffraction data corresponding to the material structure information in the dataset as input and the oxygen release performance data corresponding to the material performance information in the dataset as output, a regression prediction model for the material oxygen release performance is constructed.

[0010] S3: Obtain the material's structural files using an open-source crystal database, convert them into XRD data, input them into a trained model, and output regression predictions of the material's oxygen release performance to achieve high-throughput screening of materials.

[0011] Furthermore, in S1, the dataset construction process includes:

[0012] S1-1: Based on keywords, search and collect publicly published literature in the literature index database;

[0013] S1-2: Perform text mining on the collected literature data to extract data related to material structure and performance;

[0014] S1-3: Digitally extract the spectral information and construct the "Material Structure-Oxygen Release Performance" dataset using material name, structural data, performance data, image number, and unique digital object identifier as dataset identifiers.

[0015] Furthermore, in S1-1, the keywords include, but are not limited to: oxygen release, chemical chaining, and oxygen decoupling;

[0016] In S1-1, the literature index databases include, but are not limited to, CNKI, Web of Science, Elsevier, etc.

[0017] In S1-2, the data related to the material structure include, but are not limited to, XRD patterns, specific surface area, and elemental composition;

[0018] In S1-2, the data related to the material properties include, but are not limited to, thermogravimetric curves, oxygen release amount, and oxygen release rate.

[0019] In S1-2, the specific text mining method includes: based on XRD patterns, thermogravimetric curves, and other spectral data that can uniformly characterize the structure and properties of materials, and according to the keywords that appear frequently in the spectral titles, using text mining tools to extract the spectral number information as the extraction target. Finally, using the unique digital object identifiers and spectral numbers from published literature, the information of each spectral is located and extracted, realizing the extraction of material structure and property-related data from published literature data. Text mining tools include, but are not limited to: manual retrieval, natural language processing, large language models, artificial intelligence, etc.

[0020] Furthermore, in S1-3, the digital extraction process includes:

[0021] Image processing tools are used to digitally extract XRD patterns and normalize them to unify the data range of diffraction intensity. The data range is then expanded or reduced according to the diffraction angle range to achieve the structuring of XRD data.

[0022] After digitizing the thermogravimetric curve and other oxygen release performance-related graphs, the oxygen release amount and oxygen release rate information are extracted, the starting oxygen release point and the ending oxygen release point are defined, the oxygen release amount is calculated, and the derivative thermogravimetric curve is obtained by performing a differential operation on the thermogravimetric curve to determine the optimal oxygen release point and the maximum oxygen release rate.

[0023] Furthermore, the structuring process of XRD patterns includes: addressing the different diffraction intensity and angle ranges selected for XRD patterns in different literature, on the one hand, normalizing the diffraction intensity of each individual XRD pattern using image processing tools to unify the data range of diffraction intensity between 0 and 1; on the other hand, expanding or reducing the diffraction angle range given by the pattern, using the initial or final angle diffraction intensity of the original pattern as a benchmark, unifying the diffraction angle range to 10–85° with an angle step of 0.05°, thus achieving the structuring of XRD data.

[0024] The process of determining oxygen release data, the optimal oxygen release point, and the maximum oxygen release rate from thermogravimetric curves includes: defining the inflection point where the thermogravimetric curve shows obvious weight loss as the initial oxygen release point, defining the point where the thermogravimetric curve gradually smooths out as the final oxygen release point, and the difference in mass percentage between the two points as the oxygen release amount. Differentiating the thermogravimetric curve yields the derivative thermogravimetric curve, and the highest point of the derivative thermogravimetric curve is the optimal oxygen release point, which corresponds to the maximum oxygen release rate.

[0025] Furthermore, the machine learning model includes one or more of convolutional neural networks, artificial neural networks, random forests, and Transformers, and the machine learning model is used to achieve regression prediction of the oxygen release performance of materials.

[0026] Furthermore, in S3, the high-throughput screening includes the following steps:

[0027] S3-1: Batch obtain crystal information files of potential oxygen-releasing metal oxides from open-source crystal databases and convert them into XRD data that meet the model input requirements;

[0028] S3-2: Input structured XRD data into the trained material oxygen release performance regression prediction model, and output the regression prediction of oxygen release performance to achieve high-throughput screening of oxygen-releasing materials.

[0029] Furthermore, the open-source crystal database includes, but is not limited to, one or more of the following: Materials Project Database, Open Quantum Materials Database, Inorganic Crystal Structure Database, and PowderDiffraction File Database.

[0030] A second aspect of the present invention provides a data-driven material oxygen release performance analysis, prediction, and screening system, comprising:

[0031] The data processing module performs text mining on publicly published literature on oxygen-releasing materials, extracts data related to structure and oxygen-releasing performance, and constructs a "material structure-oxygen-releasing performance" dataset.

[0032] The model building module, based on a machine learning model, takes X-ray diffraction data corresponding to the material structure information in the dataset as input and oxygen release performance data corresponding to the material performance information in the dataset as output to build a regression prediction model for the material's oxygen release performance.

[0033] The materials screening module uses an open-source crystal database to obtain the structural files of materials, converts them into XRD data, inputs them into a trained model, and outputs regression predictions of the oxygen release performance of the materials, thus achieving high-throughput screening of materials.

[0034] A third aspect of the present invention provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, is used to perform the data-driven material oxygen release performance analysis, prediction, and screening method described above.

[0035] Compared with the prior art, the present invention has the following technical advantages:

[0036] 1) This invention utilizes advanced text mining technology and digital processing methods to efficiently extract key data on material structure and oxygen release performance from a large number of published documents, effectively solving the problems of difficult and inefficient data acquisition in traditional material screening processes. This data-driven analysis and prediction method can quickly identify materials with potentially high oxygen release performance at a lower cost, greatly improving the efficiency and economy of the research.

[0037] 2) By constructing a mapping relationship between material structure data and oxygen release performance based on machine learning, this invention significantly improves the accuracy and reliability of oxygen-releasing material screening. This method reduces dependence on experimental conditions, avoids errors caused by experimental operations and environmental factors, and ensures the stability and repeatability of screening results. Compared with traditional experimental testing, the method of this invention is more objective and accurate, providing researchers in the field of materials science with a powerful tool.

[0038] 3) The high-throughput screening mechanism of this invention significantly reduces the screening range of oxygen-releasing materials, enabling researchers to concentrate resources on in-depth research and experimental verification of the best-performing materials in the predicted results. This method not only saves valuable time and human resources but also reduces material and energy consumption, aligning with the principles of green chemistry and sustainable development. By rapidly identifying and optimizing oxygen-releasing materials, this invention provides an important scientific foundation and technical support for advancing energy conversion and storage technologies. Attached Figure Description

[0039] Figure 1 A flowchart illustrating the data-driven method for analyzing, predicting, and screening the oxygen release performance of materials according to an embodiment of the present invention.

[0040] Figure 2 This is a schematic diagram of the structure of a data-driven material oxygen release performance analysis, prediction, and screening system provided in an embodiment of the present invention;

[0041] Figure 3 This is a comparison chart of the predicted and actual values ​​of the oxygen release performance of materials based on a random forest model according to an embodiment of the present invention.

[0042] Figure 4 This is a comparison chart of the predicted and actual values ​​of the oxygen release performance of materials based on an artificial neural network model according to an embodiment of the present invention.

[0043] Figure 5 This is a comparison chart of the predicted and actual values ​​of the oxygen release performance of materials based on a convolutional neural network model according to an embodiment of the present invention.

[0044] Figure 6This is a comparison chart of the predicted and actual values ​​of the oxygen release performance of materials based on the Transformer model according to an embodiment of the present invention.

[0045] In the diagram: Data processing module - 10, Model building module - 20, Material screening module - 30. Detailed Implementation

[0046] Overall, this invention provides a data-driven method and system for analyzing, predicting, and screening the oxygen release performance of materials. Specifically, the method involves: performing text mining on publicly available literature data on oxygen-releasing materials to obtain structural information and related data on oxygen release performance, constructing an integrated dataset of "material structure-oxygen release performance"; building a machine learning model based on the dataset, inputting material structural features to obtain regression predictions for oxygen release performance; and obtaining structural data of potential oxygen-releasing materials from an open-source crystal database, inputting this data into the trained and optimized model to achieve high-throughput screening of oxygen-releasing materials. This invention mines data from publicly available literature and constructs a mapping relationship between material structural data and oxygen release performance through a machine learning model. It is low-cost, highly reliable, significantly reduces the screening range of oxygen-releasing materials, and avoids the time-consuming and labor-intensive problems of traditional material experimental testing.

[0047] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. Component models, material names, connection structures, control methods, algorithms, and other features not explicitly described in this technical solution are considered common technical features disclosed in the prior art.

[0048] Example 1

[0049] This embodiment discloses a data-driven method for analyzing, predicting, and screening the oxygen release performance of materials, referencing... Figure 1 As shown, the specific steps include the following:

[0050] S1 involves text mining of publicly published literature on oxygen-releasing materials to extract data related to structure and oxygen-releasing performance. Among these, spectral data is digitally extracted to construct an integrated dataset of "material structure-oxygen-releasing performance".

[0051] S2: Based on the machine learning model, using the X-ray diffraction data corresponding to the material structure information in the dataset as input and the oxygen release performance data corresponding to the material performance information in the dataset as output, a regression prediction model for the material oxygen release performance is constructed.

[0052] S3 utilizes an open-source crystal database to obtain the material's structural files, converts them into XRD data, inputs them into a trained model, and outputs regression predictions of the material's oxygen release performance, thus achieving high-throughput screening of materials.

[0053] Specifically,

[0054] In step S1, the extraction of material structure and performance-related data and the construction of the dataset based on text mining includes:

[0055] First, based on keywords such as oxygen release, chemical chain, and oxygen decoupling, we searched and collected publicly published literature in literature index databases, including but not limited to CNKI, Web of Science, and Elsevier.

[0056] Secondly, text mining is performed on publicly published literature data to extract data related to the material's structure and properties. Structural data includes, but is not limited to, XRD patterns, specific surface area, and elemental composition, while performance data includes, but is not limited to, thermogravimetric curves, oxygen release capacity, and oxygen release rate. Text mining methods include, but are not limited to, manual retrieval, natural language processing, large language models, and artificial intelligence.

[0057] Then, the spectral information related to structure and performance is digitally extracted. The spectral information includes, but is not limited to, XRD patterns, thermogravimetric analysis curves, and N2 adsorption curves.

[0058] Finally, using the material names, structural data, performance data, image serial numbers, and unique identifiers of digital objects from published literature as dataset identifiers, an integrated dataset of "material structure-oxygen release performance" containing 451 sets of data was constructed.

[0059] In step S1, the specific process and details of the text mining method include:

[0060] Text mining tools are used to extract structural and performance data of materials studied in the literature. Structural data includes, but is not limited to, XRD patterns, specific surface area, and elemental composition. Performance data includes, but is not limited to, thermogravimetric curves, oxygen release amount, and oxygen release rate. Addressing the widespread discrepancies in descriptions of structural and performance data in published literature, particularly regarding oxygen release performance, the text mining focus is on XRD patterns widely used to characterize structures, as well as thermogravimetric curves and derivative thermogravimetric curves that provide a unified characterization of oxygen release behavior. Based on frequently occurring keywords in the curve titles, text mining tools are used to extract curve sequence numbers. Finally, using the unique digital object identifiers and curve sequence numbers from published literature, the information from each curve is located and extracted, enabling the extraction of structural and performance data from published literature. Text mining tools include, but are not limited to, manual retrieval, natural language processing, large language models, and artificial intelligence.

[0061] In step S1, the method for digital extraction and data structuring includes:

[0062] To achieve the digital extraction of spectral information using image processing tools, the XRD data was first structured. Given the varying diffraction intensity and angle ranges in different literature, the image processing tools were used to normalize the diffraction intensity of each individual XRD pattern, unifying the data range between 0 and 1. Furthermore, based on the diffraction angle range provided by the pattern, the range was expanded or reduced. Using the initial or final angle diffraction intensity of the original pattern as a benchmark, the diffraction angle range was unified to 10–85°, with an angle step of 0.05°, thus achieving the structuring of the XRD data.

[0063] Then, after digitizing performance-related graphs such as thermogravimetric curves, information such as oxygen release amount and oxygen release rate is further extracted. The inflection point where significant weight loss occurs on the thermogravimetric curve is defined as the initial oxygen release point, and the point where the thermogravimetric curve gradually smooths out is defined as the termination oxygen release point. The difference in mass percentage between the two points is the oxygen release amount. By differentiating the thermogravimetric curve, the derivative thermogravimetric curve is obtained. The highest point of the derivative thermogravimetric curve is the optimal oxygen release point, which corresponds to the maximum oxygen release rate.

[0064] In step S2, the construction of the oxygen release performance analysis and prediction model based on machine learning algorithms includes:

[0065] Using structured XRD data as input and oxygen release performance data as output, a machine learning model is constructed to achieve regression prediction of the oxygen release performance of materials. Machine learning models include, but are not limited to, convolutional neural networks, artificial neural networks, random forests, and Transformers.

[0066] In this step, structural feature XRD data from the constructed integrated dataset of "material structure-oxygen release performance" were used as model input, and the oxygen release data of the material was used as model output. Four machine learning models were constructed, such as... Figures 3 to 6 As shown, these are the random forest models ( Figure 3 Artificial neural network models Figure 4 ), Convolutional Neural Network Model ( Figure 5 ), Transformer model ( Figure 6 The dataset is divided into training and testing sets in a 9:1 ratio. The training set is used to train the model, and the testing set is used to test the model's prediction performance. After training, the model is evaluated based on the mean squared error.

[0067] The XRD data of the material's structural features were input into four different machine learning models to obtain predicted values ​​for the material's oxygen release. In this step, the training random forest model achieved a mean squared error of 0.2677 for the training set and 1.3912 for the test set. A comparison of the predicted oxygen release with the actual values ​​is shown in the figure below. Figure 3 As shown; the trained artificial neural network model achieved a mean squared error of 0.0881 on the training set and 1.1714 on the test set. A comparison of the predicted oxygen release from the material with the actual value is shown in the figure below. Figure 4 As shown, the trained convolutional neural network model achieved a mean squared error of 0.0685 on the training set and 0.7396 on the test set. A comparison of the predicted oxygen release from the material with the actual value is shown in the figure below. Figure 5 As shown in the figure. The trained Transformer model achieved a mean squared error of 0.0559 on the training set and 0.9516 on the test set. A comparison of the predicted oxygen release from the material with the actual value is shown in the figure. Figure 6 As shown.

[0068] In step S3, the high-throughput screening of materials based on an open-source crystal database includes:

[0069] First, crystal information files of potential oxygen-releasing metal oxides are acquired in batches from open-source crystal databases and converted into XRD data that meet the model input requirements. Open-source crystal databases include, but are not limited to, one or more of the following: Materials Project Database, Open Quantum Materials Database, Inorganic Crystal Structure Database, and Powder Diffraction File Database.

[0070] Secondly, structured XRD data is input into the trained model to output regression predictions of oxygen release performance, thereby achieving high-throughput screening of oxygen-releasing materials.

[0071] In this embodiment of the invention, text mining is performed on publicly published literature data to extract data related to the structure and properties of materials. After image digitization and data structuring, an integrated dataset of "material structure-oxygen release performance" is constructed. Based on the constructed dataset, structural feature XRD data is used as input variables to accurately predict the oxygen release amount of the material. Structural files are obtained from an open-source crystal database and converted into XRD data that conforms to the model input, outputting a prediction of the oxygen release amount of the material. The model achieves high-throughput screening of high-performance oxygen-releasing materials, significantly reducing the screening range of oxygen-releasing materials and avoiding the problems of time-consuming and labor-intensive traditional material experimental testing.

[0072] This invention also discloses a data-driven system for analyzing, predicting, and screening the oxygen release performance of materials, as described in the embodiments of the present invention. Figure 2 As shown, it specifically includes:

[0073] Data processing module 10 performs text mining on publicly published literature on oxygen-releasing materials, extracts data related to structure and oxygen-releasing performance, and constructs a "material structure-oxygen-releasing performance" dataset.

[0074] The model building module 20, based on a machine learning model, uses X-ray diffraction data corresponding to the material structure information in the dataset as input and oxygen release performance data corresponding to the material performance information in the dataset as output to build a regression prediction model for the material oxygen release performance.

[0075] The material screening module 30 uses an open-source crystal database to obtain the structural files of materials, converts them into XRD data, inputs them into a trained model, and outputs regression predictions of the oxygen release performance of the materials, thereby achieving high-throughput screening of materials.

[0076] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0077] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional units.

[0078] This embodiment also proposes a computer-readable storage medium storing computer instructions for instructing a computer to execute the aforementioned data-driven material oxygen release performance analysis, prediction, and screening method. The storage medium can be an electronic medium, magnetic medium, optical medium, electromagnetic medium, infrared medium, or a semiconductor system or propagation medium. The storage medium may also include semiconductor or solid-state memory, magnetic tape, removable computer disk, random access memory (RAM), read-only memory (ROM), hard disk, and optical disk. Optical disks may include optical disc-read-only memory (CD-ROM), optical disc-read-write (CD-RW), and DVD.

[0079] The above description of the embodiments is provided to enable those skilled in the art to understand and use the invention. It will be apparent to those skilled in the art that various modifications can be made to these embodiments, and the general principles described herein can be applied to other embodiments without inventive effort. Therefore, the present invention is not limited to the above embodiments, and any improvements and modifications made by those skilled in the art based on the disclosure of the present invention without departing from the scope of the invention should be within the protection scope of the present invention.

Claims

1. A data-driven method for analyzing, predicting, and screening the oxygen release performance of materials, characterized in that, Includes the following steps: S1: Conduct text mining on publicly published literature on oxygen-releasing materials to extract data related to structure and oxygen-releasing performance, and construct a "material structure-oxygen-releasing performance" dataset; In S1, the dataset construction process includes: S1-1: Based on keywords, search and collect publicly published literature in the literature index database; S1-2: Perform text mining on the collected literature data to extract data related to material structure and performance; S1-3: Digitally extract the spectral information and construct the "Material Structure-Oxygen Release Performance" dataset using material name, structural data, performance data, image number, and unique identifier of digital object as dataset identifiers; In S1-1, the keywords include: oxygen release, chemical chaining, and oxygen decoupling; In S1-1, the literature index databases include CNKI, Web of Science, and Elsevier; In S1-2, the data related to the material structure include XRD patterns, specific surface area, and elemental composition; In S1-2, the data related to the material properties include thermogravimetric curves, oxygen release amount, and oxygen release rate; In S1-2, the specific process of text mining includes: Based on XRD patterns and thermogravimetric curves, which can uniformly characterize the structure and properties of materials, text mining tools were used to extract the image number information of each image based on the keywords that appear frequently in the image titles. Finally, by utilizing the unique digital object identifiers and figure numbers from published literature, the location and extraction of information from each figure were achieved, enabling the extraction of structural and performance-related data of materials from published literature data; The text mining tools include: manual retrieval, natural language processing, and large language models; In S1-3, the digital extraction process includes: Image processing tools are used to digitally extract XRD patterns and normalize them to unify the data range of diffraction intensity. The data range is then expanded or reduced according to the diffraction angle range to achieve the structuring of XRD data. After digitizing the oxygen release performance related spectrum, the oxygen release amount and oxygen release rate information are extracted, the starting oxygen release point and the ending oxygen release point are defined, the oxygen release amount is calculated, and the derivative thermogravimetric curve is obtained by performing a differential operation on the thermogravimetric curve to determine the optimal oxygen release point and the maximum oxygen release rate. The process of structuring XRD data and extracting thermogravimetric curve data includes: To address the issue of varying diffraction intensity and angle ranges in different literature for XRD patterns, we employ two approaches. First, in image processing tools, we normalize the diffraction intensity of each individual XRD pattern, unifying the data range of diffraction intensity between 0 and 1. Second, based on the diffraction angle range provided by the pattern, we expand or reduce it, using the initial or final angle diffraction intensity of the original pattern as a benchmark to unify the diffraction angle range to 10–85° with an angle step of 0.05°, thereby achieving the structuring of XRD data. The process of determining the oxygen release amount, the optimal oxygen release point, and the maximum oxygen release rate from the thermogravimetric curve includes: defining the inflection point where the thermogravimetric curve shows obvious weight loss as the initial oxygen release point, defining the point where the thermogravimetric curve gradually smooths out as the final oxygen release point, the difference in mass percentage between the two points as the oxygen release amount, performing a differential operation on the thermogravimetric curve to obtain the derivative thermogravimetric curve, and the highest point of the derivative thermogravimetric curve is the optimal oxygen release point, which corresponds to the maximum oxygen release rate. S2: Based on the machine learning model, using the X-ray diffraction data corresponding to the material structure information in the dataset as input and the oxygen release performance data corresponding to the material performance information in the dataset as output, a regression prediction model for the material oxygen release performance is constructed. S3: Obtain the material's structural files using an open-source crystal database, convert them into XRD data, input them into a trained model, and output regression predictions of the material's oxygen release performance to achieve high-throughput screening of materials.

2. The data-driven method for analyzing, predicting, and screening the oxygen release performance of materials according to claim 1, characterized in that, The machine learning model includes one or more of convolutional neural networks, artificial neural networks, random forests, and Transformers, and is used to achieve regression prediction of the oxygen release performance of materials.

3. The data-driven method for analyzing, predicting, and screening the oxygen release performance of materials according to claim 1, characterized in that, In S3, the high-throughput screening includes the following steps: S3-1: Batch obtain crystal information files of potential oxygen-releasing metal oxides from open-source crystal databases and convert them into XRD data that meet the model input requirements; S3-2: Input structured XRD data into the trained material oxygen release performance regression prediction model, and output the regression prediction of oxygen release performance to achieve high-throughput screening of oxygen-releasing materials.

4. The data-driven method for analyzing, predicting, and screening the oxygen release performance of materials according to claim 3, characterized in that, The open-source crystal database includes one or more of the following: Materials Project Database, Open Quantum Materials Database, Inorganic Crystal Structure Database, and Powder Diffraction File Database.

5. A data-driven system for analyzing, predicting, and screening the oxygen release performance of materials, characterized in that, The method for implementing the data-driven material oxygen release performance analysis, prediction, and screening method as described in any one of claims 1 to 4 includes: The data processing module performs text mining on publicly published literature on oxygen-releasing materials, extracts data related to structure and oxygen-releasing performance, and constructs a "material structure-oxygen-releasing performance" dataset. The model building module, based on a machine learning model, takes X-ray diffraction data corresponding to the material structure information in the dataset as input and oxygen release performance data corresponding to the material performance information in the dataset as output to build a regression prediction model for the material's oxygen release performance. The materials screening module uses an open-source crystal database to obtain the structural files of materials, converts them into XRD data, inputs them into a trained model, and outputs regression predictions of the oxygen release performance of the materials, thus achieving high-throughput screening of materials.

6. A storage medium containing computer-executable instructions, characterized in that, When executed by a computer processor, the computer-executable instructions are used to perform the data-driven material oxygen release performance analysis, prediction, and screening method as described in any one of claims 1 to 4.