Petroleum-based carbon material performance prediction method, device, equipment and storage medium

Abstract

The invention discloses a petroleum-based carbon material performance prediction method, device and equipment and a storage medium, and the prediction method comprises the steps: constructing a refinery data database; setting the structure data of the carbon material in the refinery data as first preset data; preprocessing the refinery data, including updating first preset data; taking various data of the refinery plant data as characteristic data, and establishing a prediction model for predicting the performance of the target carbon material; according to the method, multi-dimensional analysis is carried out on the raw material data of the petroleum-based carbon material, the process control data of the carbon material, the structure data of the carbon material and the performance data of the carbon material, the refinery data is preprocessed, and a high-accuracy prediction model is established, so that the guidance on the production of the petroleum-based carbon material is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon materials, and in particular to a method, device, equipment and storage medium for predicting the performance of petroleum-based carbon materials. Background Art

[0002] Oil is one of the most important energy sources in the world. It is not only used in fuel and petrochemical industries, but also an important raw material for manufacturing oil-based carbon materials. In recent years, with the development of science and technology and the application of innovative technologies, oil-based carbon materials have shown great potential and broad application prospects in various fields.

[0003] As an important carbon material, petroleum-based carbon materials have the characteristics of high purity, high crystallinity, high thermal stability and excellent conductivity. They are widely used in batteries, capacitors, photovoltaics and catalysts. With the continuous development of science and technology and the application of innovative technologies, the application prospects of petroleum-based carbon materials in the energy industry will be broader. However, the raw materials of petroleum-based carbon materials come from a wide range of sources, and their types and compositions are complex, making it difficult to directly compare and reference existing technologies.

[0004] The inventors have found through research that the prediction methods for petroleum-based carbon materials in the prior art still have at least the following defects:

[0005] The deviation between the predicted results and the actual results is too large, and the predicted results cannot provide effective data support for the optimization of the performance of petroleum-based carbon materials.

[0006] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0007] The purpose of the present invention is to provide effective data support for optimizing the performance of petroleum-based carbon materials.

[0008] The present invention provides a method for predicting the performance of petroleum-based carbon materials, comprising the steps of:

[0009] S11, constructing a database of refinery data; setting the structural data of the carbon material in the refinery data as first preset data;

[0010] S12, preprocessing the refinery data, including updating the first preset data;

[0011] Updating the first preset data includes:

[0012] The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0013] S13. Using various data of the refinery data as characteristic data, a prediction model is established for the purpose of predicting the performance of the target carbon material.

[0014] Preferably, in an embodiment of the present invention, the preprocessing further includes:

[0015] Updating the second preset data includes:

[0016] By re-encoding, each item of data in the second preset data is converted into binary data; the second preset data is the raw material source data and the process condition data for producing the raw materials in the refinery data.

[0017] Preferably, in an embodiment of the present invention, the preprocessing further includes:

[0018] The third preset data is updated, including:

[0019] Calculate the difference between each data in the third preset data and the corresponding standard data respectively, and update each data in the third preset data with the difference; determine the standard data including, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical property data in the refinery data and the process control data of the carbon material.

[0020] Preferably, in an embodiment of the present invention, the preprocessing further includes:

[0021] The fourth preset data is updated, including:

[0022] According to the preset weight setting rules, the scores corresponding to the various performance data of the target carbon material are calculated respectively; the fourth preset data is the performance data of the carbon material.

[0023] Preferably, in the embodiment of the present invention, updating the first preset data further includes:

[0024] The covariance of the first preset data is normalized, and data with high correlation is eliminated to perform the first dimensionality reduction.

[0025] Preferably, in an embodiment of the present invention, the preprocessing further includes:

[0026] The updated first preset data, the second preset data and the third preset data are all subjected to secondary dimensionality reduction to obtain new feature data for each item.

[0027] In another aspect of the present invention, there is also provided a petroleum-based carbon material performance prediction device, comprising:

[0028] A data classification unit, used to construct a database of refinery data; and set the structural data of the carbon material in the refinery data as first preset data;

[0029] A preprocessing unit, for preprocessing the refinery data, comprising a first updating module;

[0030] The first updating module is used to update the first preset data, including:

[0031] The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0032] The modeling unit is used to establish a prediction model for the purpose of predicting the performance of the target carbon material by taking various data of the refinery data as feature data.

[0033] Preferably, in the embodiment of the present invention, the pre-processing unit further includes:

[0034] The second updating module is used to update the second preset data, including:

[0035] By re-encoding, each item of data in the second preset data is converted into binary data; the second preset data is the raw material source data and the process condition data for producing the raw materials in the refinery data.

[0036] Preferably, in the embodiment of the present invention, the pre-processing unit further includes:

[0037] The third updating module is used to update the third preset data, including:

[0038] Calculate the difference between each data in the third preset data and the corresponding standard data respectively, and update each data in the third preset data with the difference; determine the standard data including, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical property data in the refinery data and the process control data of the carbon material.

[0039] Preferably, in the embodiment of the present invention, the pre-processing unit further includes:

[0040] The fourth updating module is used to update the fourth preset data, including:

[0041] According to the preset level classification rules, the levels corresponding to the various performance data of the target carbon material are determined respectively; the fourth preset data is the performance data of the carbon material.

[0042] On the other hand, an embodiment of the present invention further provides a petroleum-based carbon material performance prediction device, which includes a computer program stored on a medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the methods described in the above aspects and achieves the same technical effects.

[0043] In another aspect of the embodiment of the present invention, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, each step of the method for predicting the performance of a petroleum-based carbon material as described above is implemented.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention provides a method for predicting the performance of petroleum-based carbon materials, firstly constructing a database of refinery data; setting the structural data of carbon materials in the refinery data as first preset data; then updating the first preset data when preprocessing the refinery data; including: using the structural data as input to calculate the data value of the preset attribute of the carbon material according to the preset carbon material model; establishing the carbon material model according to the structural data of the carbon material; using the preset attribute of the carbon material as a new data item; the preset attribute includes one or more of electron density, energy band structure, density state density, lattice constant, atomic spacing and chemical bond length; using the various data of the refinery data as feature data, establishing a prediction model for the purpose of predicting the performance of the target carbon material. The present invention effectively improves the prediction accuracy of the prediction model for the performance of the target carbon material by generating data that cannot be directly collected, such as electron density, energy band structure, density state density, lattice constant, atomic spacing and chemical bond length.

[0046] Furthermore, in the present invention, a multi-dimensional analysis can be performed on the raw material data of petroleum-based carbon materials, the process control data of carbon materials, the structural data of carbon materials and the performance data of carbon materials, and the refinery data can be preprocessed; the correlation between various data of the refinery data and the production target carbon materials can be determined, and a high-accuracy prediction model can be established, thereby providing effective data support for the optimization of the performance of petroleum-based carbon materials.

[0047] In addition, the present invention is mainly based on feature data identification and prediction of target carbon materials, and establishes a technology that can quickly identify feature data and extract raw materials of petroleum-based carbon materials, forming an intelligent decision-making method that integrates raw material property analysis, optimal route selection, target carbon material product performance prediction and economic cost accounting of petroleum-based carbon materials.

[0048] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, and to make the above and other purposes, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a step diagram of the method for predicting the performance of petroleum-based carbon materials in the present invention;

[0051] Figure 2 It is a schematic diagram of the structure of the device for predicting the performance of petroleum-based carbon materials of the present invention;

[0052] Figure 3 It is a schematic diagram of the structure of the petroleum-based carbon material performance prediction device of the present invention. DETAILED DESCRIPTION

[0053] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific implementation modes.

[0054] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0055] In this document, the terms "first", "second", etc. are used to distinguish two different elements or parts, and are not used to limit a specific position or relative relationship. In other words, in some embodiments, the terms "first", "second", etc. can also be interchangeable.

[0056] Embodiment 1

[0057] In order to provide effective data support for the optimization of petroleum-based carbon materials performance, such as Figure 1As shown, in an embodiment of the present invention, a method for predicting the performance of a petroleum-based carbon material is provided, comprising the steps of:

[0058] S11, constructing a database of refinery data; setting the structural data of the carbon material in the refinery data as first preset data;

[0059] The inventive ideas of the present invention include: since the raw materials of petroleum-based carbon materials are widely sourced and the types and components are complex, most of the existing prediction methods adopt single-factor analysis methods; under this method, there is a defect that the analysis of refinery data is not comprehensive enough, so the deviation between the predicted results and the actual results is too large, and therefore it is impossible to provide effective data support for the optimization of the performance of petroleum-based carbon materials.

[0060] In order to solve the above problems, the present invention conducts multi-dimensional analysis on the raw material data of petroleum-based carbon materials, the process control data of carbon materials, the structural data of carbon materials and the performance data of carbon materials, and pre-processes the refinery data; determines the correlation between various data of the refinery data and the production target carbon materials, and establishes a high-accuracy prediction model.

[0061] In an embodiment of the present invention, the refinery data are classified, and the structural data of the carbon material in the refinery data are set as the first preset data; wherein the structural data of the carbon material may include specific surface area, pore volume, tap density, and the like.

[0062] S12, preprocessing the refinery data, including updating the first preset data;

[0063] Updating the first preset data includes: using the structure data as input to calculate the data value of the preset property of the carbon material according to the preset carbon material model; the carbon material model is established according to the structure data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, energy band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0064] For the production of petroleum-based carbon materials, refinery data includes a large number of data items; if the original values ​​of these data items are used as feature data for model training and verification during modeling, the generated prediction model has poor prediction accuracy.

[0065] The inventors have found through research that some data items in the refinery data, such as the structural data of carbon materials, can be supplemented or replaced by the values ​​of new data items of carbon materials to improve the prediction accuracy of the prediction model.

[0066] Next, in the embodiment of the present invention, new data items of the carbon material are set, such as: the electron density, energy band structure, density of states, lattice constant, interatomic distance and chemical bond length of the carbon material;

[0067] After the above settings, the specific process of preprocessing the first preset data may include:

[0068] With the specific surface area, pore volume and tap density of carbon materials as input, first principle calculations are performed according to the carbon material model to obtain data values ​​of preset properties of carbon materials such as electron density, energy band structure and density of states, lattice constant, atomic spacing and chemical bond length. The obtained values ​​of the preset properties are then used as new data item values ​​to replace the original structural data of carbon materials such as specific surface area, pore volume and tap density.

[0069] It should be noted that the carbon material model is established based on the structural data of the carbon material; wherein the categories of the carbon material model may include needle coke, diamond, petroleum coke electrode, carbon fiber, carbon nanotube and graphene, etc.

[0070] Since the value of the new data item of the carbon material in the first preset data has a clearer influence on the performance of the carbon material, the prediction accuracy of the prediction model can be effectively improved through the above preprocessing.

[0071] Furthermore, in order to better improve the accuracy of the prediction model, the preprocessing process in the embodiment of the present invention may also include: updating the second preset data, including: converting each item of data in the second preset data into binary data by re-encoding; the second preset data is the raw material source data and the process condition data for producing raw materials in the refinery data.

[0072] In the implementation of the present invention, the raw material source data and the process condition data for producing the raw materials (i.e., the second preset data) are re-encoded according to one-hot coding because the conditions are relatively fixed, and each data is converted into binary data.

[0073] Furthermore, in order to further improve the accuracy of the prediction model, in an embodiment of the present invention, the preprocessing process may also include: updating the third preset data, including: respectively calculating the difference between each data in the third preset data and the corresponding standard data, and updating each data in the third preset data with the difference; determining the standard data includes, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical properties data and the process control data of the carbon material in the refinery data.

[0074] The physical and chemical property data of raw materials and the process control data of carbon materials. For the production process of petroleum-based carbon materials, the values ​​of these data items can determine their respective optimal values ​​according to the carbon material performance of the product carbon; for example, under a certain carbon material performance standard, the optimal value of each data in the corresponding physical and chemical property data of raw materials, as well as the optimal value of each data in the process control data.

[0075] Next, in the embodiment of the present invention, for the set carbon material performance, the optimal value corresponding to each data item in the third preset data is predetermined, and the optimal value of each data item is used as the standard data.

[0076] After the above settings, the specific process of preprocessing the third preset data may include:

[0077] For a certain data item, the difference between the data of the data item and the standard data is calculated according to the corresponding standard data, and the data of the corresponding data item is updated with the difference result, thereby replacing the original data; for example: the standard data for determining the thermal expansion coefficient in the physical and chemical properties of raw materials is A, and the original thermal expansion coefficient obtained from the refinery data is B, and the difference between B and A is used to update the original thermal expansion coefficient data.

[0078] Since the difference between the third preset data and the standard data has a clearer influence on the performance of the carbon material, the prediction accuracy of the prediction model can be further effectively improved through the above preprocessing.

[0079] Among them, the physical and chemical properties data of raw materials may specifically include fraction distribution, distillation range, density, viscosity, carbon-hydrogen ratio, elemental composition, volatile matter, porosity and thermal expansion coefficient; the process control data of carbon materials may specifically include temperature, pressure, residence time and processing volume corresponding to each process type.

[0080] Further, in an embodiment of the present invention, updating the third preset data may also include: normalizing the covariance of the third preset data, removing data with large correlation, and performing a first dimensionality reduction. In this embodiment, a correlation coefficient analysis is performed on each data in the newly obtained raw material physical and chemical property data and the process control data of the carbon material. The correlation coefficient analysis is the normalized covariance between each data, and the data with large correlation is removed to perform a preliminary dimensionality reduction.

[0081] Furthermore, in an embodiment of the present invention, the updated first preset data, the second preset data and the third preset data can be subjected to secondary dimensionality reduction to obtain new feature data for each item; in practical applications, the principal component analysis (PCA) method can be used to further reduce the dimensionality of the above three types of preset data to obtain new feature data for each item after reduction.

[0082] Furthermore, in an embodiment of the present invention, preprocessing may also include: updating fourth preset data, including: determining the levels corresponding to various performance data of the target carbon material according to preset level classification rules; the fourth preset data is the performance data of the carbon material.

[0083] Since whether the performance of the carbon material meets the standard is judged based on whether each indicator is within a set range, in order to reduce the difficulty of correspondence between the independent variable data and the dependent variable data in the prediction model and reduce the difficulty of modeling the prediction model, in the embodiment of the present invention, a method of characterizing the data of each indicator (i.e., each data) of the performance of the carbon material with a set grade score is also adopted, specifically:

[0084] For each performance data item of carbon materials, a corresponding grading interval is set. For example, the data item of needle coke can be divided into multiple grades. In this way, the corresponding level can be determined according to the specific values ​​of the needle coke performance data. Similarly, other data items such as carbon fiber and negative electrode can be divided into multiple grades.

[0085] It should be noted that, in the embodiments of the present invention, the number of classifications of each performance data item of the carbon material can be determined by those skilled in the art according to needs and experience, and is not specifically limited here.

[0086] S13. Using various data of the refinery data as characteristic data, a prediction model is established for the purpose of predicting the performance of the target carbon material.

[0087] In the embodiment of the present invention, the prediction model may select a neural network model or an integrated learning model according to the actual application; the neural network model or the integrated learning model is established according to the preprocessed data.

[0088] The prediction model is trained by the constructed training set, and the score of the target carbon material performance is output; the accuracy of the prediction model is verified by the constructed test set; in the embodiment of the present invention, the data set is composed of the scores of the new feature data and the various performance data of the target carbon material; and the data set is reasonably divided into a training set and a test set.

[0089] The prediction model is machine-learned through the training set, and the prediction model outputs the scores of various properties of the target carbon materials produced by different raw materials in each process route. The accuracy of the prediction model is then continuously cross-validated through the test set to obtain a prediction model with high accuracy.

[0090] The following is a specific example to illustrate the accuracy of the prediction model. For example, the ethylene tar produced by a refinery in Nanjing was analyzed and tested by experimenters. The tar's fraction distribution, distillation range, density, viscosity, carbon-hydrogen ratio, elemental composition, volatile matter and other physical and chemical properties and information about the tar-producing device were submitted to the prediction platform including the prediction model. The prediction platform was able to query that this type of raw material can be used to produce needle coke, and the best route is to produce 8-point quality needle coke products by delayed coking. According to this process route, the actual result is high-quality needle coke material, which also verifies the accuracy of the prediction model.

[0091] In summary, an embodiment of the present invention provides a method for predicting the performance of petroleum-based carbon materials, which first constructs a database of refinery data; sets the structural data of carbon materials in the refinery data as first preset data; then preprocesses the refinery data, including updating the first preset data; including: using the structural data as input to calculate the data value of the preset attribute of the carbon material according to a preset carbon material model; establishing the carbon material model according to the structural data of the carbon material; using the preset attributes of the carbon material as new data items; the preset attributes include one or more of electron density, energy band structure, density of states, lattice constant, atomic spacing and chemical bond length; using each item of refinery data as feature data, establishing a prediction model for the purpose of predicting the performance of the target carbon material.

[0092] The embodiments of the present invention effectively improve the prediction accuracy of the prediction model for the performance of the target carbon material by generating data that cannot be directly collected, such as electron density, band structure, density of states, lattice constant, atomic spacing and chemical bond length.

[0093] Furthermore, in an embodiment of the present invention, a multi-dimensional analysis can be performed on the raw material data of petroleum-based carbon materials, the process control data and production condition data of carbon materials, the structural data of carbon materials and the performance data of carbon materials, and the refinery data can be preprocessed; the correlation between various data of the refinery data and the performance of the production target carbon materials can be determined, and a high-accuracy prediction model can be established, thereby providing effective data support for the optimization of the performance of petroleum-based carbon materials.

[0094] In addition, the embodiment of the present invention is mainly based on feature data identification and prediction of target carbon materials, and establishes a technology that can quickly identify feature data and extract raw materials of petroleum-based carbon materials, forming an intelligent decision-making method that integrates raw material property analysis, optimal route selection, target carbon material product performance prediction and economic cost accounting of petroleum-based carbon materials.

[0095] Embodiment 2

[0096] Corresponding to the method embodiment, in another aspect of the embodiment of the present invention, a petroleum-based carbon material performance prediction device is also provided. Figure 2The schematic diagram of the structure of the petroleum-based carbon material performance prediction device provided by the embodiment of the present invention is shown. Figure 1 The device corresponding to the petroleum-based carbon material performance prediction method described in the corresponding embodiment, that is, the virtual device is used to realize Figure 1 In the corresponding embodiment of the petroleum-based carbon material performance prediction method, each virtual module constituting the petroleum-based carbon material performance prediction device can be executed by an electronic device, such as a network device, a terminal device or a server. Specifically, the petroleum-based carbon material performance prediction device in the embodiment of the present invention includes:

[0097] The data classification unit 01 is used to construct a database of refinery data; the structural data of the carbon material in the refinery data is set as the first preset data;

[0098] The preprocessing unit 02 is used to preprocess the refinery data, including a first updating module;

[0099] The first updating module is used to update the first preset data, including:

[0100] The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0101] In the embodiment of the present invention, new data items of carbon materials are set, such as: electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length of carbon materials;

[0102] After the above settings, the specific process of preprocessing the first preset data may include:

[0103] With the specific surface area, pore volume and tap density of carbon materials as input, first principle calculations are performed according to the carbon material model to obtain data values ​​of preset properties of carbon materials such as electron density, energy band structure and density of states, lattice constant, atomic spacing and chemical bond length. The obtained values ​​of the preset properties are then used as new data item values ​​to replace the original structural data of carbon materials such as specific surface area, pore volume and tap density.

[0104] Since the value of the new data item of the carbon material in the first preset data has a clearer influence on the performance of the carbon material, the prediction accuracy of the prediction model can be effectively improved through the above preprocessing.

[0105] Furthermore, in an embodiment of the present invention, the preprocessing unit 02 may also include: a second update module, used to update the second preset data, including: converting each item of data in the second preset data into binary data by re-encoding; the second preset data is the raw material source data and the process condition data for producing raw materials in the refinery data.

[0106] In the embodiment of the present invention, the raw material source data and the process condition data for producing the raw materials (i.e., the second preset data) are re-encoded according to one-hot coding because the conditions are relatively fixed, and each item of data is converted into binary data.

[0107] Furthermore, in the embodiment of the present invention, the preprocessing unit 02 may further include: a third updating module, configured to update the third preset data, including:

[0108] Calculate the difference between each data in the third preset data and the corresponding standard data respectively, and update each data in the third preset data with the difference; determine the standard data including, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical property data in the refinery data and the process control data of the carbon material.

[0109] Furthermore, in the embodiment of the present invention, the preprocessing unit 02 may further include: a fourth updating module, configured to update the fourth preset data, including:

[0110] According to the preset level classification rules, the levels corresponding to the various performance data of the target carbon material are determined respectively; the fourth preset data is the performance data of the carbon material.

[0111] The modeling unit 03 is used to establish a prediction model for predicting the performance of the target carbon material by taking various data of the refinery data as feature data.

[0112] In an embodiment of the present invention, the prediction model is trained by a constructed training set to output the score of the target carbon material performance; the accuracy of the prediction model is verified by a constructed test set; in an embodiment of the present invention, a data set is composed of new feature data and the scores of various performance data of the target carbon material; and the data set is reasonably divided into a training set and a test set.

[0113] The prediction model is machine-learned through the training set, and the prediction model outputs the scores of various properties of the target carbon materials produced by different raw materials in each process route. The accuracy of the prediction model is then continuously cross-validated through the test set to obtain a prediction model with high accuracy.

[0114] It should be noted that the specific implementation method and technical effect of the petroleum-based carbon material performance prediction device in the embodiment of the present invention can be referred to Figure 1 The corresponding petroleum-based carbon material performance prediction method will not be described in detail here.

[0115] Embodiment 3

[0116] Corresponding to the method embodiment, in the embodiment of the present invention, a petroleum-based carbon material performance prediction device is also provided, such as a terminal, a server, etc. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto.

[0117] An example diagram of a hardware structure block diagram of a petroleum-based carbon material performance prediction device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, it may include:

[0118] Processor 1, communication interface 2, memory 3 and communication bus 4;

[0119] The processor 1, the communication interface 2, and the memory 3 communicate with each other via the communication bus 4;

[0120] Optionally, the communication interface 2 may be an interface of a communication module, such as an interface of a GSM module;

[0121] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0122] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0123] The processor 1 is specifically used to execute the computer program stored in the memory 3 to perform the following steps:

[0124] S11, constructing a database of refinery data; setting the structural data of the carbon material in the refinery data as first preset data;

[0125] S12, preprocessing the refinery data, including updating the first preset data;

[0126] Updating the first preset data includes:

[0127] The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0128] S13. Using various data of the refinery data as characteristic data, a prediction model is established for the purpose of predicting the performance of the target carbon material.

[0129] The above product can execute the method provided in the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the petroleum-based carbon material performance prediction method provided in the embodiment of the present invention.

[0130] Embodiment 4

[0131] In an embodiment of the present invention, a storage medium is further provided, which may store a program suitable for execution by a processor, wherein the program is used to:

[0132] S11, constructing a database of refinery data; setting the structural data of the carbon material in the refinery data as first preset data;

[0133] S12, preprocessing the refinery data, including updating the first preset data;

[0134] Updating the first preset data includes:

[0135] The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length;

[0136] S13. Using various data of the refinery data as characteristic data, a prediction model is established for the purpose of predicting the performance of the target carbon material.

[0137] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0138] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the methods provided by other embodiments of the present invention.

[0139] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0143] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0144] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0145] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting properties of petroleum-based carbon materials, characterized in that: Includes steps: S11, constructing a database of refinery data; setting the structural data of the carbon material in the refinery data as first preset data; S12, preprocessing the refinery data, including updating the first preset data; Updating the first preset data includes: The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length; S13. Using various data of the refinery data as characteristic data, a prediction model is established for the purpose of predicting the performance of the target carbon material.

2. The petroleum-based carbon material performance prediction method according to claim 1, characterized in that: The preprocessing further comprises: Updating the second preset data includes: By re-encoding, each item of data in the second preset data is converted into binary data; the second preset data is the raw material source data and the process condition data for producing the raw materials in the refinery data.

3. The petroleum-based carbon material performance prediction method according to claim 2, characterized in that: The preprocessing further comprises: Updating the third preset data includes: Calculate the difference between each data in the third preset data and the corresponding standard data respectively, and update each data in the third preset data with the difference; determine the standard data including, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical property data in the refinery data and the process control data of the carbon material.

4. The petroleum-based carbon material performance prediction method according to claim 3, characterized in that: The preprocessing further comprises: The fourth preset data is updated, including: According to the preset level classification rules, the levels corresponding to the various performance data of the target carbon material are determined respectively; the fourth preset data is the performance data of the carbon material.

5. The petroleum-based carbon material performance prediction method according to claim 4, characterized in that: Updating the first preset data further includes: The covariance of the first preset data is normalized, and data with high correlation is eliminated to perform the first dimensionality reduction.

6. The petroleum-based carbon material performance prediction method according to claim 5, characterized in that: The preprocessing further comprises: The updated first preset data, the second preset data and the third preset data are all subjected to secondary dimensionality reduction to obtain new feature data for each item.

7. A petroleum-based carbon material performance prediction device, characterized in that: include: A data classification unit, used to construct a database of refinery data; Setting the structural data of the carbon material in the refinery data as first preset data; A preprocessing unit, for preprocessing the refinery data, comprising a first updating module; The first updating module is used to update the first preset data, including: The data value of the preset property of the carbon material is calculated according to the preset carbon material model with the structural data as input; the carbon material model is established according to the structural data of the carbon material; the preset property of the carbon material is used as a new data item; the preset property includes one or more of electron density, band structure, density of states, lattice constant, interatomic distance and chemical bond length; The modeling unit is used to establish a prediction model for the purpose of predicting the performance of the target carbon material by taking various data of the refinery data as feature data.

8. The petroleum-based carbon material performance prediction device according to claim 7, characterized in that: The pre-processing unit further includes: The second updating module is used to update the second preset data, including: By re-encoding, each item of data in the second preset data is converted into binary data; the second preset data is the raw material source data and the process condition data for producing the raw materials in the refinery data.

9. The petroleum-based carbon material performance prediction device according to claim 8, characterized in that: The pre-processing unit further includes: The third updating module is used to update the third preset data, including: Calculate the difference between each data in the third preset data and the corresponding standard data respectively, and update each data in the third preset data with the difference; determine the standard data including, based on the set carbon material performance, determining the standard data corresponding to each data in the third preset data; the third preset data is the raw material physical and chemical property data in the refinery data and the process control data of the carbon material.

10. The petroleum-based carbon material performance prediction device according to claim 9, characterized in that: The pre-processing unit further includes: The fourth updating module is used to update the fourth preset data, including: According to the preset level classification rules, the levels corresponding to the various performance data of the target carbon material are determined respectively; the fourth preset data is the performance data of the carbon material.

11. A petroleum-based carbon material performance prediction device, characterized in that: include: Memory for storing computer programs; A processor is used to call and execute the computer program to implement the steps of the method for predicting the performance of petroleum-based carbon materials as described in any one of claims 1 to 6.

12. A storage medium, characterized in that: The method comprises a software program, wherein the software program is suitable for executing the steps of the method for predicting the properties of petroleum-based carbon materials as claimed in any one of claims 1 to 6 by a processor.

Images