Oxidation kinetics index calculation method, apparatus, electronic device, and storage medium

Abstract

An oxidation kinetics index calculation method, an apparatus, an electronic device, and a storage medium, which relate to the technical field of alloys. An embodiment comprises: acquiring a pre-constructed oxidation feature tree, the oxidation feature tree being a binary tree and comprising nodes and node edges, the nodes comprising a root node and end nodes, and the node edges storing alloy data values. Then, the nodes undergo separation from among alloy data according to alloy feature data; starting from the root node, target node edges are determined one-by-one according to a comparison result of alloy feature data with alloy feature values on the node edges until an end node is reached, and the end node is determined as a target end node. Finally, an oxidation kinetics index in the target end node is used as the oxidation kinetics index for the alloy data. As a consequence, an oxidation kinetics index and an oxidation kinetics equation can be accurately calculated and obtained according to the pre-constructed oxidation feature tree; the present invention has important significance for describing the process of oxidation, research of the principles of oxidation-resistant materials, and oxidation resistant designs, and consequently providing the impetus for related research and development.

Description

Oxidation kinetic index calculation method, device, electronic device and storage medium Technical Field

[0001] The present application relates to the field of alloy technology, and in particular to an oxidation kinetic index calculation method, device, electronic device and storage medium. Background Art

[0002] Alloy oxidation is a crucial process that significantly impacts material performance and lifespan. Understanding the kinetics of alloy oxidation—the rate and pattern of weight gain during oxidation—is crucial for studying the mechanisms of oxidation-resistant materials and designing their resistance to oxidation. Establishing oxidation kinetic equations allows for better description and prediction of alloy weight gain, as well as understanding the relationship between the oxidation reaction rate and test conditions such as time, temperature, and pressure.

[0003] The oxidation kinetic index is a key parameter in developing oxidation kinetic equations. In related technologies, the oxidation kinetic index is typically a fixed value used to describe the oxidation behavior of a specific alloy under specific oxidation conditions. However, this method cannot quantitatively determine the relationship between the oxidation kinetic index itself and the alloy composition and test conditions, nor can it comprehensively describe the oxidation characteristics of multiple alloys under different test conditions. Consequently, it is difficult to calculate the oxidation kinetic index and corresponding oxidation kinetic equation for different alloy data, hindering further research.

[0004] Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art. To this end, the embodiments of this application provide a method, device, electronic device, and storage medium for calculating the oxidation kinetic index, which can calculate the oxidation kinetic index for different alloy data and promote the development of related research.

[0006] In a first aspect, the present invention provides a method for calculating an oxidation kinetic index, comprising:

[0007] Obtaining a pre-constructed oxidation characteristic tree, wherein the oxidation characteristic tree is a binary tree, the binary tree including a plurality of nodes and node edges, the nodes including a root node and at least two end nodes, the node edges storing alloy characteristic values, the alloy characteristic values ​​being boundaries for dividing alloy data;

[0008] Dividing the nodes from the alloy data according to the alloy characteristic data, starting from the root node, determining target node edges one by one according to a comparison result of the alloy characteristic data with the alloy characteristic values ​​on the node edges, until reaching the end node, and determining the end node as the target end node;

[0009] The oxidation kinetics index stored in the target end node is used as the oxidation kinetics index of the alloy data.

[0010] In some embodiments of the present application, constructing the oxidation feature tree includes:

[0011] Acquire an oxidation data set; wherein the oxidation data set includes a plurality of alloy samples, each of the alloy samples including a plurality of kinetic characteristics and corresponding kinetic characteristic values;

[0012] A kinetic feature differentiation process is performed based on the oxidation data set to construct the oxidation feature tree; the kinetic feature differentiation process includes:

[0013] Constructing a parent node; the parent node stores the alloy sample; the initial value of the parent node is the root node, and the root node is constructed based on the oxidation feature set;

[0014] Traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node, and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom;

[0015] Splitting the alloy sample in the parent node according to the target dynamic characteristic and the target dynamic characteristic value to obtain a first child node and a second child node of the parent node, and storing the target dynamic characteristic value in the corresponding node edge;

[0016] It is determined that the first child node and / or the second child node do not meet the stopping differentiation condition, and the first child node and / or the second child node are used as the parent node to perform the dynamic feature differentiation process.

[0017] In some embodiments of the present application, the kinetic characteristics of the alloy sample include oxidation time and alloy composition, and the alloy sample also includes oxidation weight gain; after obtaining the oxidation data set, the method further includes:

[0018] Performing logarithm preprocessing on the oxidation time and the oxidation weight gain;

[0019] performing combined calculations on the alloy components to generate a preset number of secondary alloy features;

[0020] The secondary alloy features are added to the oxidation dataset.

[0021] In some embodiments of the present application, traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom includes:

[0022] Selecting a partitioning parameter from the dynamic characteristics; the partitioning parameter includes a candidate characteristic and a candidate characteristic value, and the candidate characteristic value is selected from the dynamic characteristic value of the candidate characteristic in the alloy sample;

[0023] Dividing the alloy samples in the parent node into a first candidate set and a second candidate set according to the numerical values ​​of the candidate feature values;

[0024] Obtaining a first fitting result of the first candidate set and a second fitting result of the second candidate set using an oxidation kinetics equation;

[0025] Calculating a linear gain value of the partitioning parameter according to a first linearity value of the first fitting result, a second linearity value of the second fitting result, and a total linearity value of the parent node;

[0026] The candidate feature values ​​are updated by traversing the dynamic feature values, and the candidate features are updated by traversing the dynamic features, and the target dynamic feature and the target dynamic feature value are obtained according to the division parameter with the largest linear gain value.

[0027] In some embodiments of the present application, the calculating the linear gain value of the partitioning parameter according to the first linearity value of the first fitting result, the second linearity value of the second fitting result, and the total linearity value of the parent node includes:

[0028] Calculating the first linearity value based on the first fitting result and the alloy samples in the first candidate set;

[0029] Calculating the second linearity value based on the second fitting result and the alloy samples in the second candidate set;

[0030] Obtaining the total number of samples of the alloy samples in the parent node, the first number of samples of the alloy samples in the first candidate set, and the second number of samples of the alloy samples in the second candidate set;

[0031] Calculate a first sample ratio based on the first sample size and the total sample size, and calculate a second sample ratio based on the second sample size and the total sample size;

[0032] multiplying the first sample ratio and the first linearity value to obtain a first linearity index, and multiplying the second sample ratio and the second linearity value to obtain a second linearity index;

[0033] The first linearity index and the second linearity index are added and the total linearity value is subtracted to obtain a linear gain value of the partitioning parameter.

[0034] In some embodiments of the present application, the first fitting result is an oxidation kinetics fitting equation, the kinetic characteristic value includes an oxidation time value, and the alloy sample also includes an oxidation weight gain value; calculating the first linearity value based on the first fitting result and the alloy sample in the first candidate set includes:

[0035] Substituting the oxidation time value of the alloy sample in the first candidate set into the oxidation kinetics fitting equation to calculate the oxidation weight gain fitting value;

[0036] Calculating the covariance of the oxidation weight gain value and the oxidation weight gain fitting value to obtain a first intermediate result;

[0037] Calculating the standard deviation of the oxidation weight gain value to obtain a first standard deviation, calculating the standard deviation of the oxidation weight gain fitting value to obtain a second standard deviation, and multiplying the first standard deviation and the second standard deviation to obtain a second intermediate result;

[0038] Dividing the first intermediate result by the second intermediate result to obtain the first linearity value;

[0039] or,

[0040] Calculating the sum of squares of the errors between the oxidation weight gain value and the oxidation weight gain fitting value to obtain a third intermediate result;

[0041] Calculating the total square sum of the oxidation weight gain values ​​to obtain a fourth intermediate result;

[0042] The third intermediate result is divided by the fourth intermediate result to obtain a fifth intermediate result, and the first linearity value is obtained by subtracting 1 from the fifth intermediate result.

[0043] In some embodiments of the present application, splitting the alloy sample in the parent node according to the target dynamic characteristic and the target dynamic characteristic value to obtain the first child node and the second child node of the parent node includes:

[0044] According to the target dynamic characteristic, comparing the dynamic characteristic value corresponding to the alloy sample in the parent node with the target dynamic characteristic value;

[0045] If the dynamic characteristic value is less than or equal to the target dynamic characteristic value, dividing the alloy sample into the first sub-node;

[0046] If the dynamic characteristic value is greater than the target dynamic characteristic value, the alloy sample is divided into the second sub-node.

[0047] In some embodiments of the present application, the stopping differentiation condition includes a linearity threshold and / or a singleness threshold; the method further includes:

[0048] If the first linearity value of the first subnode meets the linearity threshold, taking the first subnode as the end node;

[0049] If the second linearity value of the second sub-node meets the linearity threshold, taking the second sub-node as the end node;

[0050] and / or,

[0051] If the oxidation time of the alloy sample in the first child node meets the singleness threshold, the parent node of the first child node is used as the end node;

[0052] If the oxidation time of the alloy sample in the second child node meets the singleness threshold, the parent node of the second child node is used as the end node.

[0053] In some embodiments of the present application, the end node includes a plurality of alloy samples, and an oxidation kinetics fitting equation of the alloy samples is obtained using an oxidation kinetics equation, wherein the oxidation kinetics fitting equation includes the oxidation kinetics index; the method further includes:

[0054] inputting the oxidation kinetic index of the end node and the alloy sample into a symbolic regression model;

[0055] The oxidation kinetic index is used as a regression target, and a symbolic regression is performed on the kinetic characteristics in the alloy sample to obtain an analytical equation for the oxidation kinetic index.

[0056] In a second aspect, an embodiment of the present application further provides an oxidation kinetic index calculation device, which implements the oxidation kinetic index calculation method described in the embodiment of the first aspect of the present application, including:

[0057] A first acquisition module is configured to acquire a pre-constructed oxidation characteristic tree, wherein the oxidation characteristic tree is a binary tree including a plurality of nodes and node edges, wherein the nodes include a root node and at least two end nodes, and the node edges store alloy characteristic values, which are boundaries for dividing alloy data;

[0058] a data comparison module, configured to divide the nodes from the alloy data according to the alloy characteristic data, and to determine target node edges one by one from the root node according to a comparison result of the alloy characteristic data with the alloy characteristic values ​​on the node edges, until reaching the end node, and determining the end node as the target end node;

[0059] An index acquisition module is used to use the oxidation kinetics index stored in the target end node as the oxidation kinetics index of the alloy data.

[0060] In some embodiments of the present application, the apparatus further comprises:

[0061] A second acquisition module is configured to acquire an oxidation data set, wherein the oxidation data set includes a plurality of alloy samples, each of the alloy samples including a plurality of kinetic characteristics and corresponding kinetic characteristic values;

[0062] A differentiation module is configured to perform a kinetic feature differentiation process based on the oxidation data set to construct the oxidation feature tree; the kinetic feature differentiation process includes:

[0063] Constructing a parent node; the parent node stores the alloy sample; the initial value of the parent node is the root node, and the root node is constructed based on the oxidation feature set;

[0064] Traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node, and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom;

[0065] Splitting the alloy sample in the parent node according to the target dynamic characteristic and the target dynamic characteristic value to obtain a first child node and a second child node of the parent node, and storing the target dynamic characteristic value in the corresponding node edge;

[0066] It is determined that the first child node and / or the second child node do not meet the stopping differentiation condition, and the first child node and / or the second child node are used as the parent node to perform the dynamic feature differentiation process.

[0067] In some embodiments of the present application, the apparatus further comprises:

[0068] An analytical module is used to input the oxidation kinetic index of the end node and the alloy sample into a symbolic regression model; use the oxidation kinetic index as a regression target, perform symbolic regression on the kinetic characteristics in the alloy sample, and obtain an analytical equation for the oxidation kinetic index.

[0069] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for calculating the oxidation kinetic index as described in the embodiment of the first aspect of the present application is implemented.

[0070] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the oxidation kinetic index calculation method as described in the embodiment of the first aspect of the present application.

[0071] The embodiments of the present application include at least the following beneficial effects:

[0072] The present application provides an oxidation kinetic index calculation method, device, electronic device and storage medium, wherein the oxidation kinetic index calculation method obtains a pre-constructed oxidation characteristic tree, the oxidation characteristic tree is a binary tree, the binary tree includes multiple nodes and node edges, the node includes a root node and at least two end nodes, the node edge stores alloy data values, and the alloy characteristic value is the boundary for dividing the alloy data. Then, the nodes are divided according to the alloy characteristic data from the alloy data, specifically starting from the root node of the oxidation characteristic tree, and the target node edge is determined one by one according to the comparison result of the alloy characteristic data and the alloy characteristic value on the node edge until the end node is reached, and the end node is determined as the target end node. Finally, the oxidation kinetic index stored in the target end node is used as the oxidation kinetic index of the alloy data. Thus, according to the pre-constructed oxidation characteristic tree, the oxidation kinetic index corresponding to different alloy components is stored in the end node, and the target end node is gradually determined by comparing the alloy characteristic data in the alloy data and the oxidation characteristic tree node edge. The oxidation kinetic index and oxidation kinetic equation can be accurately calculated, which is of great significance for tasks such as oxidation process description, oxidation-resistant material mechanism research and oxidation resistance design, thereby promoting the development of related research.

[0073] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0075] FIG1 is a schematic flow chart of a method for calculating an oxidation kinetic index according to an embodiment of the present application;

[0076] FIG2 is a flow chart of a method for calculating an oxidation kinetic index according to another embodiment of the present application;

[0077] FIG3 is a schematic flow chart of step S302 in FIG2 ;

[0078] FIG4 is a schematic flow chart of step S404 in FIG3 ;

[0079] FIG5 is a schematic flow chart of step S501 in FIG4 ;

[0080] FIG6 is a schematic flow chart of step S303 in FIG2 ;

[0081] FIG7 is a schematic diagram of the process of step S304 in FIG2 ;

[0082] FIG8 is another schematic diagram of the process of step S304 in FIG2;

[0083] FIG9 is a flow chart of a method for calculating an oxidation kinetic index according to another embodiment of the present application;

[0084] FIG10 is a schematic diagram of an oxidation characteristic tree provided by one embodiment of the present application;

[0085] FIG11 is a schematic diagram of a module of an oxidation kinetic index calculation device provided in one embodiment of the present application;

[0086] FIG12 is a schematic diagram of a module of an oxidation kinetic index calculation device provided by another embodiment of the present application;

[0087] FIG13 is a schematic structural diagram of an electronic device provided in one embodiment of the present application.

[0088] Reference numerals: first acquisition module 100 , data comparison module 200 , index acquisition module 300 , second acquisition module 400 , differentiation module 500 , parsing module 600 , electronic device 1000 , processor 1001 , memory 1002 . DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0090] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0091] In the description of this application, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on this application.

[0092] In the description of this application, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly specifying the number or order of the technical features indicated.

[0093] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0094] Alloy oxidation is a crucial process that significantly impacts material performance and lifespan. Understanding the kinetics of alloy oxidation—the rate and pattern of weight gain during oxidation—is crucial for studying the mechanisms of oxidation-resistant materials and designing their resistance to oxidation. Establishing oxidation kinetic equations allows for better description and prediction of alloy weight gain, as well as understanding the relationship between the oxidation reaction rate and test conditions such as time, temperature, and pressure.

[0095] The oxidation kinetic index is a key parameter in developing oxidation kinetic equations. In related technologies, the oxidation kinetic index is typically a fixed value used to describe the oxidation behavior of a specific alloy under specific oxidation conditions. However, this method cannot quantitatively determine the relationship between the oxidation kinetic index itself and the alloy composition and test conditions, nor can it comprehensively describe the oxidation characteristics of multiple alloys under different test conditions. Consequently, it is difficult to accurately calculate the oxidation kinetic index for different alloy data and establish corresponding oxidation kinetic equations, hindering further research.

[0096] Based on this, embodiments of the present application provide a method, apparatus, electronic device, and storage medium for calculating an oxidation kinetic index. Based on a pre-constructed oxidation characteristic tree, the oxidation kinetic index corresponding to different alloy compositions is stored in end nodes. By comparing alloy characteristic data in the alloy data with the oxidation characteristic tree node edges, the target end node is gradually determined. This allows for accurate calculation of the oxidation kinetic index and oxidation kinetic equation, which is of great significance for tasks such as describing oxidation processes, studying the mechanisms of oxidation-resistant materials, and designing oxidation resistance, thereby promoting the development of related research.

[0097] The embodiments of the present application provide a method, device, electronic device, and storage medium for calculating the oxidation kinetic index, which are specifically illustrated by the following embodiments. First, the method for calculating the oxidation kinetic index in the embodiments of the present application is described.

[0098] The oxidation kinetic index calculation method provided in the embodiment of the present application relates to the field of materials technology, and in particular to the field of alloy technology. The oxidation kinetic index calculation method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be a computer program running in a terminal or a server side. For example, a computer program can be a native program or software module in an operating system; it can be a local (Native) application (APP, Application), that is, a program that needs to be installed in the operating system to run, such as a client that supports oxidation kinetic index calculation, that is, a program that can be run only by downloading it to a browser environment. In short, the above-mentioned computer program can be any form of application, module or plug-in. Among them, the terminal communicates with the server via a network. The oxidation kinetic index calculation method can be executed by a terminal or a server, or by a terminal and a server in collaboration.

[0099] In some embodiments, the terminal can be a smart phone, tablet computer, laptop computer, desktop computer or smart watch etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN) and basic cloud computing services such as big data and artificial intelligence platforms; It can also be a service node in a blockchain system, wherein each service node in the blockchain system forms a point-to-point (P2P, Peer To Peer) network, and the P2P protocol is an application layer protocol running on top of the transmission control protocol (TCP, Transmission Control Protocol) protocol. The server can be installed with a server end for the oxidation kinetic index calculation system, through which the server end can interact with the terminal, but is not limited to the above form. The terminal and the server can be connected by a communication connection method such as Bluetooth, USB (Universal Serial Bus, Universal Serial Bus) or a network, and this embodiment is not limited here.

[0100] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0101] The following describes the calculation method of the oxidation kinetic index in the examples of this application.

[0102] 1 , an embodiment of the present application provides a method for calculating an oxidation kinetic index, which includes but is not limited to the following steps S101 to S103 .

[0103] Step S101: obtaining a pre-built oxidation feature tree.

[0104] In some embodiments, the oxidation signature tree is a binary tree, wherein the nodes include a root node and at least two terminal nodes. It will be understood that a binary tree is a tree-like data structure, wherein the root node is the top node of the binary tree and serves as the starting point of the tree. A binary tree has only one root node. Each node in the binary tree has at most two child nodes. Nodes without child nodes are terminal nodes, also known as leaf nodes.

[0105] A node is connected to its upper and lower nodes through a node edge. In some embodiments, the node edge of the oxidation feature tree stores an alloy characteristic value. The alloy characteristic value is the boundary that divides the alloy data into different nodes. It can be the mass percentage of a certain alloy component in a multi-component alloy. Those skilled in the art can set it according to actual needs, and this embodiment does not limit this.

[0106] Step S102: Divide the alloy data into nodes according to the alloy characteristic data. Starting from the root node, determine the target node edges one by one according to the comparison results of the alloy characteristic data and the alloy characteristic values ​​on the node edges until the end node is reached, and determine the end node as the target end node.

[0107] Alloy data includes, but is not limited to, composition data, physical property data, and chemical property data. For example, composition data includes each alloy component and its mass percentage, physical property data includes the alloy's density, thermal conductivity, electrical conductivity, melting point, and hardness, and chemical property data includes chemical reactivity and corrosion resistance. In some embodiments, the alloy data is divided into nodes based on alloy characteristic data. Specifically, data such as the alloy composition of a multi-component alloy and the mass percentage of each alloy component are used as alloy characteristic data, although this embodiment does not impose a limitation on this.

[0108] In some embodiments, starting from the root node, the alloy characteristic data and the alloy characteristic values ​​on the node edge are compared to determine the target node edge. Exemplarily, the root node has two child nodes, namely the left child node and the right child node. The node edge from the root node to the left child node is the mass percentage of the iron element less than or equal to 30wt.%, and the node edge from the root node to the right child node is the mass percentage of the iron element greater than 30wt.%. Therefore, when the mass percentage of the iron element in the alloy composition is less than or equal to 30wt.%, it meets the alloy characteristic value on the node edge between the root node and the left child node, otherwise it meets the alloy characteristic value on the node edge between the root node and the right child node. Thus, by comparing the alloy characteristic data and the alloy characteristic values ​​on the node edge, the target node edge can be determined until the end node is reached, and then the end node is determined as the target end node of the alloy data.

[0109] Step S103: Using the oxidation kinetics index stored in the target end node as the oxidation kinetics index of the alloy data.

[0110] In some embodiments, an oxidation signature tree is pre-constructed based on the alloy samples in the oxidation dataset. Each end node in the oxidation signature tree stores the oxidation kinetic index corresponding to each alloy sample. The oxidation kinetic index stored in the target end node is used as the oxidation kinetic index for the alloy data. By comparing the alloy characteristic data in the alloy data with the node edges of the oxidation signature tree, the target end node is gradually determined, allowing accurate calculation of the oxidation kinetic index and oxidation kinetic equation. This approach is of great significance for tasks such as describing oxidation processes, studying the mechanisms of oxidation-resistant materials, and designing oxidation resistance, thereby promoting related research and development.

[0111] 2 , in some embodiments of the present application, constructing the oxidation feature tree may further include but is not limited to the following steps S201 to S202 .

[0112] Step S201: Obtain an oxidation data set.

[0113] In some embodiments, the oxidation dataset includes multiple alloy samples, each alloy sample including multiple kinetic features and corresponding kinetic feature values. Thus, each kinetic feature in the oxidation dataset has multiple kinetic feature values. Each alloy sample also includes oxidation weight gain and its corresponding oxidation weight gain value. It is understood that oxidation datasets for multi-component alloys can be accumulated by consulting literature and conducting experimental synthesis. The oxidation dataset is input into a spreadsheet file and stored as a CSV file.

[0114] For example, there are 95 supercritical CO2 alloy samples, and the kinetic characteristics of each alloy sample include alloy components, such as iron, nickel, chromium, aluminum, cobalt, manganese, silicon, titanium, copper, carbon, bismuth, etc., and the corresponding kinetic characteristic value is the mass percentage corresponding to the alloy component. The kinetic characteristics also include test conditions such as temperature, pressure, and oxidation time. Referring to Table 1 below, the table file includes the kinetic characteristics of the alloy samples and regression targets, such as oxidation weight gain. Specifically, each row in Table 1 represents an alloy sample, each column represents a kinetic characteristic, and the last column represents oxidation weight gain, where the oxidation time in the kinetic characteristics is placed in the second to last column of the table, and this embodiment does not impose any restrictions on this.

[0115] Table 1

[0116] In some embodiments, data preprocessing is performed on the oxidation dataset. Specifically, the oxidation time values ​​corresponding to the oxidation time in the kinetic characteristics are logarithmized, and the oxidation weight gain values ​​corresponding to the oxidation weight gain are uniformly converted to milligrams per square decimeter (mg / dm2) and logarithmized, resulting in a table file as shown in Table 2.

[0117] Table 2

[0118] In some embodiments, the alloy components in the kinetic characteristics are randomly combined by addition, subtraction and multiplication to generate a preset number of secondary alloy characteristics. For example, iron + nickel, cobalt-aluminum + manganese, (iron-cobalt) x silicon, etc. are randomly generated secondary alloy characteristics. Specifically, secondary alloy characteristics with twice the number of alloy component characteristics can be generated and then added to the oxidation data set, thereby characterizing a better nonlinear relationship. The secondary alloy characteristics and the original alloy components are kinetic characteristics of the same level, and both belong to alloy characteristics. The formed table file is shown in Table 3. The secondary alloy characteristics are placed before the second to last column corresponding to the oxidation time, and can also be placed before the alloy component. This embodiment does not limit this.

[0119] Table 3

[0120] Step S202 : performing a kinetic feature differentiation process based on the oxidation data set to construct an oxidation feature tree.

[0121] In some embodiments, a kinetic feature differentiation process is performed based on the kinetic feature values ​​of the alloy samples in the oxidation dataset to construct an oxidation feature tree. Specifically, the specific process of constructing the oxidation feature tree may include but is not limited to the following steps S301 to S304.

[0122] Step S301: construct a parent node.

[0123] In some embodiments, the parent node stores alloy samples from the oxidation dataset. The initial value of the parent node is the root node, which is constructed based on the oxidation dataset. Therefore, the root node stores all alloy samples from the oxidation dataset. It will be appreciated that in a binary tree structure, except for the root node, which has no parent node, each node has exactly one parent node.

[0124] Step S302 , traversing the dynamic characteristics and dynamic characteristic values ​​of the alloy samples in the parent node, and selecting target dynamic characteristics and target dynamic characteristic values ​​therefrom.

[0125] In some embodiments, the kinetic characteristics and corresponding kinetic characteristic values ​​of the alloy samples in the parent node are traversed, and a target kinetic characteristic and its corresponding target kinetic characteristic value are selected therefrom. For the same kinetic characteristic, different alloy samples have different corresponding kinetic characteristic values. For example, when the kinetic characteristic is the iron element, the corresponding kinetic characteristic value is the mass percentage of the iron element. The kinetic characteristic value in alloy sample 1 is 0.07wt.%, ..., and the kinetic characteristic value in alloy sample 95 is 3wt.%. Therefore, after selecting a kinetic characteristic as the target kinetic characteristic, it is necessary to further select a kinetic characteristic value as the target kinetic characteristic value, which provides branching conditions for constructing the oxidation characteristic tree.

[0126] Step S303: split the alloy sample in the parent node according to the target dynamic characteristics and the target dynamic characteristic value to obtain the first child node and the second child node of the parent node, and store the target dynamic characteristic value in the corresponding node edge.

[0127] In some embodiments, the alloy samples in the parent node are split according to the target dynamic characteristics and the target dynamic characteristic value to obtain the first child node and the second child node of the parent node. Specifically, the alloy samples in the parent node are compared with the target dynamic characteristics and the target dynamic characteristics, and the alloy samples are divided into two parts based on the comparison results, one part as the first child node and the other part as the second child node. Exemplarily, there are 95 alloy samples in the parent node. According to the target dynamic characteristics and the target dynamic characteristic value, the 95 alloy samples in the parent node are split to obtain a first child node containing 60 alloy samples and a second child node containing 35 alloy samples.

[0128] In some embodiments, after obtaining the first and second child nodes of a parent node, a node edge is used to connect the parent node and the first and second child nodes, respectively, and the target dynamic feature value is stored in the node edge. It is understood that the target dynamic feature may also be stored in the node edge, and this embodiment does not limit this.

[0129] Step S304: determine that the first child node and / or the second child node do not meet the differentiation stop condition, use the first child node and / or the second child node as the parent node, and perform the dynamic feature differentiation process.

[0130] In some embodiments, if the first child node meets the stop differentiation condition, the first child node is used as the terminal node and differentiation is stopped. Otherwise, the first child node is used as the parent node and the kinetic feature differentiation process is iteratively performed. Similarly, if the second child node meets the stop differentiation condition, the second child node is used as the terminal node and differentiation is stopped. Otherwise, the second child node is used as the parent node and the kinetic feature differentiation process is iteratively performed, thereby constructing an oxidation feature tree based on the oxidation dataset.

[0131] 3 , in some embodiments of the present application, the above step S302 may also include but is not limited to the following steps S401 to S405 .

[0132] Step S401: Selecting a partitioning parameter from the dynamic characteristics.

[0133] In some embodiments, the partitioning parameters include candidate features and candidate feature values, and the candidate feature values ​​are selected from the kinetic feature values ​​of the candidate features in the alloy sample. Specifically, any kinetic feature is first used as a candidate feature, and then one of the corresponding kinetic feature values ​​in the alloy sample is selected as the candidate feature value based on the candidate feature. For example, the iron element in the kinetic feature is used as a candidate feature, and there are 95 kinetic feature values ​​of the iron element corresponding to the parent node containing 95 alloy samples. The kinetic feature value of the iron element in the 22nd alloy sample is 49.74wt.%, which can be used as a candidate feature value. This embodiment does not impose any restrictions on this.

[0134] Step S402 : Divide the alloy samples in the parent node into a first candidate set and a second candidate set according to the numerical values ​​of the candidate feature values.

[0135] In some embodiments, the dynamic characteristic value corresponding to the candidate characteristic in the alloy sample in the parent node is compared with the candidate characteristic value based on the numerical value of the candidate characteristic value. If the dynamic characteristic value of the alloy sample is less than or equal to the candidate characteristic value, the alloy sample is classified into the first candidate set; if the dynamic characteristic value of the alloy sample is greater than the candidate characteristic value, the alloy sample is classified into the second candidate set, thereby dividing the alloy sample in the parent node into the first candidate set and the second candidate set.

[0136] For example, the candidate feature is the iron element in the kinetic feature, and the candidate feature value is the mass percentage of the iron element in the 22nd alloy sample, 49.74 wt.%. The 95 alloy samples in the parent node are divided according to the numerical value of the candidate feature value. If the kinetic feature value of the iron element in the alloy sample is less than or equal to 49.74 wt.%, the alloy sample is divided into the first candidate set; if the kinetic feature value of the iron element in the alloy sample is greater than 49.74 wt.%, the alloy sample is divided into the second candidate set. Ultimately, a first candidate set containing 65 alloy samples and a second candidate set containing 30 alloy samples can be obtained, which is not limited in this embodiment.

[0137] Step S403 : obtaining a first fitting result of the first candidate set and a second fitting result of the second candidate set using the oxidation kinetics equation.

[0138] The oxidation law of the alloy satisfies the oxidation kinetic equation y=kt n, where y is the oxidation weight gain value, k is the oxidation kinetic constant, t is the oxidation time value, and n is the oxidation kinetic index. In some embodiments, in order to conveniently and quickly fit the alloy sample using the oxidation kinetic equation, the oxidation time value and the oxidation weight gain value in the kinetic characteristics are logarithmically processed, and the oxidation kinetic equation is also logarithmically processed. That is, ln(y)=n·ln(t)+ln(k) is obtained, where ln(·) represents logarithmic processing, so that the expression of the oxidation kinetic method in the logarithmic space is a linear relationship. Therefore, in the embodiment of the present application, the oxidation weight gain value corresponds to ln(y), the oxidation time value corresponds to ln(t), and the fitting constant corresponds to ln(k).

[0139] In some embodiments, the oxidation kinetic equation after logarithmic processing is used to fit the alloy samples in the first candidate set to obtain a first fitting result; and the oxidation kinetic equation after logarithmic processing is used to fit the alloy samples in the second candidate set to obtain a second fitting result.

[0140] Specifically, the kinetic characteristics related to the oxidation kinetic equation are the oxidation time and the oxidation weight gain in the alloy sample. Since the expression of the oxidation kinetic method in the logarithmic space is a linear relationship, the embodiment of the present application takes the oxidation weight gain as the regression target and the oxidation time as the variable to fit the candidate set to obtain the corresponding fitting result, that is, the oxidation kinetic fitting equation, which is in the form of ln(y') = n·ln(t) + ln(k), wherein ln(y') is the oxidation weight gain fitting value, ln(k) is the oxidation kinetic constant, ln(t) is the oxidation time value, and n is the oxidation kinetic index. By calculating the Euclidean distance error between the oxidation weight gain fitting value ln(y') and the oxidation weight gain value ln(y) in the alloy sample, the size of the oxidation kinetic index n and the fitting constant ln(k) can be calculated, thereby taking other kinetic characteristics in the alloy sample as the basis for branching, and this embodiment does not limit this.

[0141] Step S404 : Calculate the linear gain value of the partitioning parameter according to the first linearity value of the first fitting result, the second linearity value of the second fitting result, and the total linearity value of the parent node.

[0142] In some embodiments, the linearity value is used to measure the data fitting accuracy of the alloy samples in the first candidate set and the second candidate set. Exemplarily, the linearity value is calculated using the Pearson correlation coefficient. It is understandable that the value range of the Pearson correlation coefficient is between -1 and 1, where -1 represents a complete negative correlation, 1 represents a complete positive correlation, and 0 represents no linear correlation. Therefore, the closer the linearity is to 1 or -1, the closer the alloy sample is to a linear relationship, and the better the linear fitting effect; while the linearity is close to 0, it means that there is a lack of linear relationship between the alloy samples, and the linear fitting effect is poor.

[0143] In some embodiments, a first linearity value of a first fitting result is calculated based on the alloy samples in the first candidate set, a second linearity value of a second fitting result is calculated based on the alloy samples in the second candidate set, and then the first linearity value, the second linearity value, and the total linearity value are combined to calculate a linear gain value of the differentiation result corresponding to the partitioning parameter. It is understood that when the parent node is the root node, the alloy samples in the oxidation dataset are first fitted using the oxidation kinetics equation after logarithmic processing to obtain a total fitting result, and then the total linearity value of the total fitting result is calculated based on the alloy samples in the oxidation dataset.

[0144] Step S405 , traversing the dynamic characteristic values ​​to update the candidate characteristic values, and traversing the dynamic characteristics to update the candidate characteristics, and obtaining the target dynamic characteristics and the target dynamic characteristic value according to the partition parameter with the largest linear gain value.

[0145] A dynamic feature corresponds to multiple dynamic feature values. For example, the parent node stores 95 alloy samples, so each dynamic feature corresponds to 95 dynamic feature values. Candidate feature values ​​are updated by traversing the dynamic feature values. Specifically, when the candidate feature is iron, the mass percentage of iron in the 95 alloy samples is sequentially used as the candidate feature value. The alloy samples in the parent node are thus split into a first candidate set and a second candidate set of 95 different partitioning parameters, and the linear gain value of each partitioning parameter is calculated.

[0146] In some embodiments, after 95 mass percentages of the iron element are traversed, the candidate features are updated by traversing the dynamic features. Specifically, the next dynamic feature of the nickel element in Table 3, for example, the nickel element, is used as a candidate feature, and the mass percentages of the nickel element in the 95 alloy samples are traversed as candidate feature values, and the alloy sample in the parent node is split to obtain a first candidate set and a second candidate set. Thus, the alloy sample in the parent node is split to obtain a first candidate set and a second candidate set with 95 different partitioning parameters, and the linear gain value of each partitioning parameter is calculated. It is assumed here that the nickel element has 95 different values, which is not limited in this embodiment.

[0147] In some embodiments, the dynamic characteristic values ​​in the alloy sample can be traversed in units of dynamic characteristics, or each dynamic characteristic in the alloy sample can be traversed in units of dynamic characteristic values, until each dynamic characteristic and each dynamic characteristic value in the parent node are used as a partitioning parameter. Finally, based on the partitioning parameter with the largest linear gain, the candidate characteristic in the partitioning parameter is used as the target dynamic characteristic value, and the candidate characteristic value in the partitioning parameter is used as the target dynamic characteristic value, thereby obtaining the target dynamic characteristic and target dynamic characteristic value.

[0148] 4 , in some embodiments of the present application, the above step S404 may further include but is not limited to the following steps S501 to S506 .

[0149] Step S501 : calculating a first linearity value according to a first fitting result and alloy samples in a first candidate set.

[0150] In some embodiments, a first linearity value for the first fitting result is calculated based on the oxidation kinetics fitting equation of the first fitting result and the alloy samples in the first candidate set. It will be appreciated that the first linearity value is used to measure the accuracy of the first fitting result. Specifically, the oxidation time values ​​of the alloy samples in the first candidate set are substituted into the oxidation kinetics fitting equation. Based on the known fitting constants and oxidation kinetic index, the oxidation kinetics fitting equation can be used to calculate the oxidation weight gain fitting value. Finally, the first linearity value is calculated based on the actual oxidation weight gain values ​​of the alloy samples and the calculated oxidation weight gain fitting value, which is not limited in this embodiment.

[0151] Step S502 : calculating a second linearity value according to the second fitting result and the alloy samples in the second candidate set.

[0152] In some embodiments, a second linearity value for the second fitting result is calculated based on the oxidation kinetics fitting equation of the second fitting result and the alloy samples in the second candidate set. It will be appreciated that the second linearity value is used to measure the accuracy of the second fitting result. Specifically, the oxidation time values ​​of the alloy samples in the second candidate set are substituted into the oxidation kinetics fitting equation. Based on the known fitting constants and oxidation kinetic index, the oxidation kinetics fitting equation can be used to calculate the oxidation weight gain fitting value. Finally, the second linearity value is calculated based on the actual oxidation weight gain values ​​of the alloy samples and the calculated oxidation weight gain fitting value, which is not limited in this embodiment.

[0153] Step S503 : obtaining the total sample quantity of alloy samples in the parent node, the first sample quantity of alloy samples in the first candidate set, and the second sample quantity of alloy samples in the second candidate set.

[0154] In some embodiments, the total number of alloy samples in the parent node is obtained, as well as the first number of alloy samples in the second candidate set and the second number of alloy samples in the second candidate set. It is understood that the total number of samples in the parent node is the sum of the first number of samples and the second number of samples. For example, if there are 60 alloy samples in the first candidate set and 35 alloy samples in the second candidate set, then there are 60 + 35 = 95 alloy samples in the parent node.

[0155] Step S504 , calculating a first sample ratio according to the first sample size and the total sample size, and calculating a second sample ratio according to the second sample size and the total sample size.

[0156] In some embodiments, the first sample ratio corresponding to the first candidate set can be calculated by dividing the first sample number by the total sample number; the second sample ratio corresponding to the second candidate set can be calculated by dividing the second sample number by the total sample number.

[0157] Step S505 : multiplying the first sample ratio and the first linearity value to obtain a first linearity index, and multiplying the second sample ratio and the second linearity value to obtain a second linearity index.

[0158] In some embodiments, the first linearity index is obtained by multiplying the first sample ratio and the first linearity value, and the second linearity index is obtained by multiplying the second sample ratio and the second linearity value. Specifically, K represents the total number of samples, k1 represents the first number of samples, k2 represents the second number of samples, and LG l Represents the first linearity value, LG r Represents the second linearity value. Then the first sample ratio is k1 / K, the second sample ratio is k2 / K, and the first linearity index is LG l k1 / K, the first linearity index is LG r ·k2 / K.

[0159] Step S506 : Add the first linearity index and the second linearity index and subtract the total linearity value to obtain a linear gain value of the partitioning parameter.

[0160] In some embodiments, the first linearity index and the second linearity index are added together, ie, LG l k1 / K+LG r k2 / K, then subtract the total linearity value LG p , that is, the linear gain value △LG of the partition parameter is obtained. Therefore △LG i,j =LG l k1 / K+LG r k2 / K-LG p, where i represents the i-th kinetic feature and j represents the j-th kinetic feature value of the kinetic feature, i.e., the kinetic feature value in the j-th alloy sample. This allows us to traverse each kinetic feature and kinetic feature value of the alloy sample in the parent node and use them as partitioning parameters to split the alloy sample in the parent node and calculate the linear gain value corresponding to the partitioning parameter.

[0161] 5 , in some embodiments of the present application, the above step S501 may also include but is not limited to the following steps S601 to S607 .

[0162] Step S601: Substitute the oxidation time values ​​of the alloy samples in the first candidate set into the oxidation kinetics fitting equation to calculate the oxidation weight gain fitting value.

[0163] In some embodiments, the oxidation time value of each alloy sample in the first candidate set is substituted into the oxidation kinetics fitting equation ln(y')=n·ln(t)+ln(k). Based on the known fitting constant and oxidation kinetic index, the oxidation kinetics equation can be used to calculate the oxidation weight gain fitting value. For example, if there are 60 alloy samples in the first candidate set, 60 oxidation weight gain fitting values ​​can be calculated based on their 60 oxidation time values.

[0164] Step S602: Calculate the covariance of the oxidation weight gain value and the oxidation weight gain fitting value to obtain a first intermediate result.

[0165] In some embodiments, the oxidation weight gain values ​​of the alloy samples in the first candidate set are obtained, the covariance between the oxidation weight gain values ​​and the corresponding oxidation weight gain fitted values ​​is calculated, and the covariance is used as the first intermediate result. It is understood that in this embodiment, the oxidation weight gain value is y and the oxidation weight gain fitted value is y'. Those skilled in the art may also select ln(y) as the oxidation weight gain value and ln(y') as the oxidation weight gain fitted value according to actual needs, and this embodiment does not limit this.

[0166] Step S603 , calculating the standard deviation of the oxidation weight gain value to obtain a first standard deviation, calculating the standard deviation of the oxidation weight gain fitting value to obtain a second standard deviation, and multiplying the first standard deviation and the second standard deviation to obtain a second intermediate result.

[0167] In some embodiments, a first standard deviation is obtained by calculating the oxidation weight gain values ​​of the alloy samples in the first candidate set. Specifically, the average oxidation weight gain of the alloy samples is first calculated, and then the average oxidation weight gain value is subtracted from the oxidation weight gain value of each alloy sample to obtain a difference result. The difference result is squared to obtain the square result of the alloy sample. Finally, the square results of all alloy samples are accumulated and squared to obtain the first standard deviation. Similarly, a second standard deviation is obtained by calculating the oxidation weight gain fitting value. Finally, the first standard deviation and the second standard deviation are multiplied to obtain a second intermediate result, which is not limited in this embodiment.

[0168] Step S604: Divide the first intermediate result by the second intermediate result to obtain a first linearity value.

[0169] In some embodiments, the first linearity value of the first fitting result can be calculated by dividing the first intermediate result by the second intermediate result. Specifically, the first linearity value satisfies the following calculation formula:

[0170] Wherein, k1 represents the first sample number of the alloy sample in the first candidate set, y represents the oxidation weight gain value, represents the average value of oxidation weight gain, y′ represents the fitted value of oxidation weight gain, represents the average value of the oxidative weight gain.

[0171] It can be understood that the specific implementation of the second linearity value calculation process is basically the same as the first linearity value, and satisfies the following calculation formula:

[0172] Wherein, k2 represents the second sample number of the alloy sample in the second candidate set, y represents the oxidation weight gain value, represents the average value of oxidation weight gain, y′ represents the fitted value of oxidation weight gain, represents the average value of the oxidative weight gain.

[0173] In some embodiments, the calculation of the first linearity may further include but is not limited to steps S704 to S707 .

[0174] Step S605 , calculating the sum of squares of the errors between the oxidation weight gain value and the oxidation weight gain fitting value to obtain a third intermediate result.

[0175] In some embodiments, the sum of squared errors between the oxidation weight gain value and the oxidation weight gain fitted value is calculated. Specifically, for each alloy sample in the first candidate set, the oxidation weight gain fitted value is subtracted from the oxidation weight gain value to obtain a fitted difference, which is then squared to obtain a squared result. Finally, all squared results are accumulated to obtain the sum of squared errors, which is used as the third intermediate result.

[0176] Step S606: Calculate the total square sum of the oxidation weight gain values ​​to obtain a fourth intermediate result.

[0177] In some embodiments, an average oxidation weight gain can be calculated based on the oxidation weight gain values ​​of the alloy samples in the first candidate set. For each alloy sample, the average oxidation weight gain value is subtracted from the oxidation weight gain value to obtain a difference result. The difference result is then squared to obtain a square result. Finally, all square results are accumulated to obtain a total square sum of the oxidation weight gain values, which is used as the fourth intermediate result.

[0178] Step S607 : Divide the third intermediate result by the fourth intermediate result to obtain a fifth intermediate result, and subtract 1 from the fifth intermediate result to obtain a first linearity value.

[0179] In some embodiments, the third intermediate result is divided by the fourth intermediate result to obtain a fifth intermediate result, and finally the first linearity value is calculated by subtracting the fifth intermediate result from 1. Specifically, the first linearity value satisfies the following formula:

[0180] Wherein, k1 represents the first sample number of the alloy sample in the first candidate set, y represents the oxidation weight gain value, represents the average value of oxidation weight gain, and y' represents the fitted value of oxidation weight gain.

[0181] It can be understood that the specific implementation of the second linearity value calculation process is basically the same as the first linearity value, and satisfies the following calculation formula:

[0182] Wherein, k2 represents the second sample number of the alloy sample in the second candidate set, y represents the oxidation weight gain value, represents the average value of oxidation weight gain, and y′ represents the fitted value of oxidation weight gain.

[0183] 6 , in some embodiments of the present application, the above-mentioned step S303 may also include but is not limited to the following steps S701 to S703 .

[0184] Step S701 : comparing the dynamic characteristic value corresponding to the alloy sample in the parent node with the target dynamic characteristic value according to the target dynamic characteristic.

[0185] In some embodiments, based on the target kinetic characteristic, the kinetic characteristic values ​​corresponding to the alloy samples in the parent node are compared with the target kinetic characteristic values. For example, when the target kinetic characteristic is iron and the target kinetic characteristic value is 49.74 wt.%, the mass percentages of iron in the 95 alloy samples in the parent node are compared with 49.74 wt.%.

[0186] Step S702: If the dynamic characteristic value is less than or equal to the target dynamic characteristic value, the alloy sample is divided into the first child node.

[0187] In some embodiments, if the kinetic characteristic value is less than or equal to the target kinetic characteristic value, for example, if the mass percentage of iron in the alloy sample is less than or equal to 49.74 wt.%, the alloy sample is classified as the first child node. It can be understood that in this case, the first child node is divided into the first candidate set corresponding to the partitioning parameters of iron and its mass percentage of 49.74 wt.%, and therefore the linearity value of the first child node is the first linearity value of the first candidate set. Similarly, the oxidation kinetics fitting equation of the first child node is the first fitting result of the first candidate set.

[0188] Step S703: If the dynamic characteristic value is greater than the target dynamic characteristic value, the alloy sample is divided into the second child node.

[0189] In some embodiments, if the kinetic characteristic value is greater than the target kinetic characteristic value, for example, if the mass percentage of iron in the alloy sample is greater than 49.74 wt.%, the alloy sample is classified as the second child node. It can be understood that in this case, the second child node is divided into the second candidate set corresponding to the partitioning parameters of iron and its mass percentage of 49.74 wt.%, and therefore the linearity value of the second child node is the second linearity value of the second candidate set. Similarly, the oxidation kinetics fitting equation of the second child node is the second fitting result of the second candidate set.

[0190] 7 and 8 , in some embodiments of the present application, the above step S304 may further include but is not limited to the following steps S801 to S802 and / or steps S901 to S902.

[0191] Step S801: If the first linearity value of the first child node meets the linearity threshold, the first child node is used as an end node.

[0192] In some embodiments, the stopping branching condition includes a linearity threshold, such as a linearity threshold of 0.9. If the first linearity value of the first child node satisfies the linearity threshold, for example, if the first linearity value is greater than 0.9, the first child node is treated as the terminal node. It is understood that if the first linearity value does not meet the linearity threshold, the first child node is treated as the parent node to perform the dynamic feature differentiation process, and the first linearity value of the first child node is used as the total linearity value of the parent node. This embodiment does not impose any limitation on this.

[0193] Step S802: If the second linearity value of the second child node meets the linearity threshold, the second child node is used as an end node.

[0194] In some embodiments, if the second linearity value of the second child node satisfies a linearity threshold, for example, if the second linearity value is greater than 0.9, the second child node is treated as an end node. It is understood that if the second linearity value does not meet the linearity threshold, the second child node is treated as a parent node to perform the dynamic feature differentiation process, and the second linearity value of the second child node is used as the total linearity value of the parent node. This embodiment does not impose any limitation on this.

[0195] Step S901: If the oxidation time of the alloy sample in the first child node meets the singleness threshold, the parent node of the first child node is used as the end node.

[0196] In some embodiments, the stopping branch condition may also include, but is not limited to, a simplex threshold, such as a simplex threshold of 2. If the oxidation time value corresponding to the oxidation time of the alloy sample in the first child node satisfies the simplex threshold, for example, the oxidation time value has only two different values ​​of 500 h and 1200 h, that is, the oxidation time value in the alloy sample is less than or equal to the two cases, then the parent node of the first child node is used as the terminal node. It is understood that since the oxidation time value of the alloy sample is less than or equal to the two cases, it is a clear overfitting linear equation, which will lead to regression instability of the oxidation kinetics equation. Therefore, this node is not allowed to exist, and its parent node needs to be used as the terminal node.

[0197] Step S902: If the oxidation time of the alloy sample in the second child node meets the singleness threshold, the parent node of the second child node is used as the end node.

[0198] In some embodiments, if the oxidation time value corresponding to the oxidation time of the alloy sample in the second child node meets the singleness threshold, for example, the oxidation time value has only two different values ​​of 100 hours and 300 hours, that is, the oxidation time value of the alloy sample is less than or equal to two cases, then the parent node of the second child node is used as the terminal node. It is understandable that because the oxidation time value of the alloy sample is less than or equal to two cases, it is obviously overfitted linearly, which will lead to regression instability of the oxidation kinetics equation. Therefore, this node is not allowed to exist, and its parent node needs to be used as the terminal node.

[0199] It can be understood that the stop branch condition can also be a comparison between the linearity value of the child node and the linearity value of its parent node. For example, if the linearity value of the child node is less than the linearity value of the parent node, the corresponding parent node will be used as the end node. Those skilled in the art can set different stop branch conditions according to actual needs, and this embodiment does not limit this.

[0200] 9 , in some embodiments of the present application, the oxidation kinetic index calculation method may further include but is not limited to the following steps S1001 to S1002 .

[0201] In step S1001 , the oxidation kinetic index of the end node and the alloy sample are input into a symbolic regression model.

[0202] In some embodiments, an end node includes at least one alloy sample, and an oxidation kinetics fitting equation for the alloy sample is obtained using an oxidation kinetics equation. The oxidation kinetics fitting equation includes the oxidation kinetics index. Therefore, each alloy sample in the end node is described by the same oxidation kinetics fitting equation, and these alloy samples have the same oxidation kinetics index.

[0203] In some embodiments, after constructing the oxidation signature tree, multiple end nodes can be obtained. The oxidation kinetic index of the end nodes and the corresponding alloy sample are input into a symbolic regression model. Exemplarily, the symbolic regression model is constructed based on an open-source regression algorithm, such as gplearn or SISSO, but this embodiment does not limit this.

[0204] Step S1002 : Using the oxidation kinetic index as a regression target, symbolic regression is performed on the kinetic characteristics of the alloy sample to obtain an analytical equation for the oxidation kinetic index.

[0205] In some embodiments, the oxidation kinetic index of the end node is used as the regression target, and the kinetic characteristics of the alloy sample at the end node are symbolically regressed to obtain an analytical expression between the oxidation kinetic index and the kinetic characteristics, i.e., an analytical equation for the oxidation kinetic index. The equation is of the form n = f (kinetic characteristic 1, kinetic characteristic 2, ..., kinetic characteristic m), where f represents the analytical function and n represents the oxidation kinetic index.

[0206] It can be understood that the function of n is substituted into the oxidation kinetic equation y′=kt n The analytical equation for oxidation weight gain can be obtained, and the final oxidation kinetic equation satisfies the kinetic process and is completely analytical, which effectively analyzes the oxidation mechanism of multi-component alloys, facilitates the design of new materials that are more resistant to oxidation, and promotes the development of related research.

[0207] The present application is described below through a complete embodiment:

[0208] Referring to the oxidation feature tree diagram shown in Figure 10, this example investigates the oxidation mechanism of supercritical CO2 alloys. The acquired oxidation dataset contains 95 supercritical CO2 alloy samples. The kinetic characteristics of each alloy sample include alloy components such as iron, nickel, chromium, aluminum, cobalt, manganese, silicon, titanium, copper, carbon, and bismuth, with the corresponding kinetic characteristic value representing the mass fraction of the corresponding alloy component. Kinetic characteristics also include temperature, pressure, and oxidation time.

[0209] It is understandable that different alloys have different material compositions, and their oxidation data exposed to various test conditions will produce very complex oxidation weight gain changes, which greatly complicates data analysis and oxidation research. Due to the high experimental cost of oxidizing samples, especially oxidation data under special environments such as supercritical water and supercritical CO2, it is impractical to conduct a large number of control experiments. This example uses a linear regression tree classifier oxidation kinetic index calculation method to study the analytical relationship between the oxidation kinetic index and the kinetic characteristics of the alloy samples, which has the advantages of simplicity, speed and accuracy.

[0210] First, a root node #95 was constructed based on the oxidation dataset. The alloy sample was fitted using the logarithmized oxidation kinetic equation, and the linearity value corresponding to this node was calculated. It is understandable that the oxidation dataset also includes secondary alloy features generated by random combinations of alloy components through addition, subtraction, and multiplication. The final fitting yielded an oxidation kinetic index n = 0.585 for the root node, a fitting constant ln(k) = -1.224, and a calculated linearity value LG = 0.284, which is less than the linearity threshold of 0.9. Therefore, the stop branching condition was not met, and the kinetic feature differentiation process needed to be performed.

[0211] Specifically, the dynamic characteristics and dynamic characteristic values ​​of the alloy samples in the root node are traversed, such as (iron + nickel), (chromium-aluminum +

[0212] Using dynamic characteristics and their values, such as manganese, iron, nickel, chromium, aluminum, cobalt, manganese, silicon, titanium, copper, carbon, bismuth, temperature, and pressure, as partitioning parameters, the alloy sample at the root node is split into a first candidate set and a second candidate set. The oxidation kinetics equation is then fitted to the first and second candidate sets to obtain the corresponding fitting results, namely the oxidation kinetics fitting equation. Finally, the linear gain corresponding to the partitioning parameters is calculated based on the first linearity value of the first fitting result, the second linearity value of the second fitting result, and the total linearity value of the parent node.

[0213] Through traversal comparison, it is found that when the dynamic characteristic is iron and the dynamic target characteristic value is 49.74wt.%, the linear gain value of the parent node differentiation is the largest. As shown in Figure 10, at this time, the total number of samples is 95, the number of first samples is 65, the number of second samples is 35, the first linearity value is 0.667, and the second linearity value is 0.612. Therefore, the calculated linear gain value corresponds to Therefore, the alloy samples in the parent node are split by taking the iron element as the target kinetic characteristic and its mass percentage of 49.74wt.% as the target kinetic characteristic value. 95 alloy samples are split into the first child node numbered #60 and the second child node numbered #34, where the value of the node number represents the number of alloy samples in the node.

[0214] Since neither the first child node nor the second child node meets the stopping differentiation condition, the kinetic characteristic differentiation process is performed on it as the parent node, and the branches continue to grow to the end node, and finally an oxidation characteristic tree with nine end nodes is obtained. In some embodiments, the end nodes are numbered, starting with NO_0 from left to right. As shown in Figure 11, the linearity LG of the oxidation kinetic equation is the smallest at the end node No_7, which is 0.76; and the largest at the leaf No_5, which is 0.96. It was also found that a secondary alloy feature (Co-(Al-Mn)) was used in the differentiation process, indicating that it has a significant effect on the oxidation kinetic index n.

[0215] Thus, the 95 alloy samples were divided into 9 end nodes, and each alloy sample was labeled with its corresponding oxidation kinetic index value, as shown in Table 4 below. By regressing the alloy samples in Table 4 using gplearn, with the oxidation kinetic index as the regression target, an analytical equation for the oxidation kinetic index can be obtained, namely, n = f(iron, nickel, chromium, aluminum, cobalt, manganese, silicon, titanium, copper, carbon, bismuth, temperature, pressure). This embodiment does not impose any restrictions on this.

[0216] Table 4: Data pairs of characteristics and oxidation kinetic indices

[0217] In the field of materials technology, combining machine learning with expert knowledge-based mechanistic analysis is of great significance. Machine learning can accelerate the materials discovery and design process by analyzing large-scale data to extract correlations between material properties and performance. For example, by analyzing data such as a material's composition, structure, and processing conditions, machine learning can predict its properties and performance. Expert knowledge-based mechanistic analysis, on the other hand, can provide a deep understanding of the fundamental principles and behavior of materials, providing targeted guidance and explanation capabilities for machine learning algorithms.

[0218] A linear regression tree classifier method for calculating the oxidation kinetic index was applied to oxidation data of multi-component alloys. Based on the correlation between features and targets, a loss function that satisfies the kinetic equation was constructed. This facilitates the incorporation of expert knowledge. Within the vast feature space, data satisfying different physical mechanisms can be distinguished by relying on the consistency of the data's description of the kinetic equation. The primary driving factors influencing the physical mechanism can be identified, and a mapping relationship between features and mechanisms can be constructed, thereby making the feature definition space continuous. This method is then combined with symbolic regression and explanatory algorithms to analytically describe the physical process of metal oxidation within a kinetic framework. This approach is of great significance for discovering and revising oxidation kinetic equations, describing oxidation processes, studying the mechanisms of oxidation-resistant materials, and designing oxidation-resistant materials.

[0219] It is understood that the embodiments of the present application are not limited to the study of oxidation kinetic equations, but can also be directly applied to the analysis of activation energy of thermal activation processes in thermodynamics. For example, in the thermal activation process where the data is satisfied by fitting the thermodynamic equation at the node, Wherein Q is the activation energy constant, R is the ideal gas constant, and T is the temperature, which is not limited in this embodiment.

[0220] The present application also provides an oxidation kinetic index calculation device that can implement the above-mentioned oxidation kinetic index calculation method. As shown in FIG11 , in some embodiments of the present application, the oxidation kinetic index calculation device includes:

[0221] A first acquisition module 100 is configured to acquire a pre-built oxidation feature tree, which is a binary tree comprising a plurality of nodes and node edges. The nodes comprise a root node and at least two end nodes. The node edges store alloy feature values, which are boundaries for dividing alloy data.

[0222] The data comparison module 200 is used to divide the alloy data into nodes according to the alloy characteristic data, and starting from the root node, determine the target node edge one by one according to the comparison result of the alloy characteristic data with the alloy characteristic value on the node edge, until reaching the end node, and determine the end node as the target end node;

[0223] The index acquisition module 300 is configured to use the oxidation kinetics index stored in the target end node as the oxidation kinetics index of the alloy data.

[0224] 12 , in some embodiments of the present application, the oxidation kinetic index calculation device further includes:

[0225] A second acquisition module 400 is configured to acquire an oxidation dataset, wherein the oxidation dataset includes a plurality of alloy samples, each alloy sample including a plurality of kinetic characteristics and corresponding kinetic characteristic values;

[0226] The differentiation module 500 is configured to perform a kinetic feature differentiation process based on the oxidation dataset to construct an oxidation feature tree. The kinetic feature differentiation process includes:

[0227] Construct a parent node; the parent node stores the alloy sample; the initial value of the parent node is the root node, and the root node is constructed based on the oxidation feature set;

[0228] Traverse the dynamic characteristics and dynamic characteristic values ​​of the alloy samples in the parent node, and select the target dynamic characteristics and target dynamic characteristic values ​​therefrom;

[0229] According to the target dynamic characteristics and target dynamic characteristic values, the alloy sample in the parent node is split to obtain the first child node and the second child node of the parent node, and the target dynamic characteristic values ​​are stored in the corresponding node edges;

[0230] It is determined that the first child node and / or the second child node do not meet the stopping differentiation condition, and the first child node and / or the second child node are used as parent nodes to perform the dynamic feature differentiation process.

[0231] The analytical module 600 is used to input the oxidation kinetic index of the end node and the alloy sample into the symbolic regression model; using the oxidation kinetic index as the regression target, the kinetic characteristics in the alloy sample are symbolically regressed to obtain the analytical equation of the oxidation kinetic index.

[0232] The specific implementation of the oxidation kinetic index calculation device of this embodiment is basically the same as the specific implementation of the oxidation kinetic index calculation method described above, and will not be described in detail here.

[0233] 13 shows an electronic device 1000 provided in an embodiment of the present application. The electronic device 1000 includes: a processor 1001, a memory 1002, and a computer program stored in the memory 1002 and executable on the processor 1001. When the computer program is executed, it is used to execute the above-mentioned oxidation kinetic index calculation method.

[0234] The processor 1001 and the memory 1002 may be connected via a bus or other means.

[0235] Memory 1002, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the oxidation kinetic index calculation method described in the embodiments of this application. Processor 1001 implements the above-described oxidation kinetic index calculation method by executing the non-transitory software program and instructions stored in memory 1002.

[0236] The memory 1002 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; and the data storage area may store and execute the above-mentioned oxidation kinetic index calculation method. In addition, the memory 1002 may include a high-speed random access memory 1002, and may also include a non-transitory memory 1002, such as at least one storage device memory device, a flash memory device or other non-transitory solid-state memory device. In some embodiments, the memory 1002 may optionally include a memory 1002 remotely arranged relative to the processor 1001, and these remote memories 1002 may be connected to the electronic device 1000 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0237] The non-transient software program and instructions required to implement the above-mentioned oxidation kinetic index calculation method are stored in the memory 1002. When executed by one or more processors 1001, the above-mentioned oxidation kinetic index calculation method is performed, for example, method steps S101 to S104 in Figure 1, method steps S201 to S202 and steps S301 to S304 in Figure 2, method steps S401 to S405 in Figure 3, method steps S501 to S506 in Figure 4, method steps S601 to S607 in Figure 5, method steps S701 to S703 in Figure 6, method steps S801 to S802 in Figure 7, method steps S901 to S902 in Figure 8, and method steps S1001 to S1002 in Figure 9.

[0238] The present application also provides a storage medium, which is a computer-readable storage medium, and the storage medium stores a computer program, which implements the above-mentioned oxidation kinetic index calculation method when the computer program is executed by the processor. The memory is a non-transient computer-readable storage medium that can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory optionally includes a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0239] The oxidation kinetic index calculation method, device, electronic device and storage medium provided in the embodiment of the present application are obtained by obtaining a pre-constructed oxidation characteristic tree, which is a binary tree. The binary tree includes multiple nodes and node edges, the nodes include a root node and at least two end nodes, and the node edges store alloy data values. Then, nodes are divided according to the alloy characteristic data in the alloy data. Starting from the root node of the oxidation characteristic tree, the target node edges are determined one by one according to the comparison results of the alloy characteristic data and the alloy characteristic values ​​on the node edges, until the end node is reached, and the end node is determined as the target end node. Finally, the oxidation kinetic index stored in the target end node is used as the oxidation kinetic index of the alloy data. Thus, according to the pre-constructed oxidation characteristic tree, the oxidation kinetic index corresponding to different alloy components is stored in the end node, and the target end node is gradually determined by comparing the alloy characteristic data in the alloy data and the oxidation characteristic tree node edges. The oxidation kinetic index and the oxidation kinetic equation can be accurately calculated, which is of great significance to tasks such as oxidation process description, oxidation-resistant material mechanism research and oxidation resistance design, thereby promoting the development of related research.

[0240] This application continuously partitions the oxidation data of alloy samples in the feature space by maximizing linear gain, allowing the oxidation data of alloy samples at the same end node to be described by the same oxidation kinetic equation. After obtaining all end node alloy samples and their oxidation kinetic indices, the symbolic regression algorithm gplearn is used to express the oxidation kinetic indices obtained for all end nodes as analytical equations for the studied features. This unified, analytical oxidation kinetic equation is then used to describe the oxidation behavior of different alloys under different conditions. This approach incorporates expert knowledge and, within the vast feature space, relies on the consistency of the data in describing the kinetic equation to distinguish data satisfying different physical mechanisms. The key driving factors influencing the physical mechanism can be identified, a mapping relationship between features and mechanisms can be established, and the definition space can be made continuous. Combined with symbolic regression and explanatory algorithms, machine learning accelerates the understanding of physical processes. This application can be used for tasks such as optimizing the properties of multi-component alloys, discovering and modifying oxidation kinetic equations, describing oxidation processes, studying the mechanisms of oxidation-resistant materials, and designing oxidation resistance. This application is a machine learning data analysis method based on oxidation kinetic relationships. The feasibility of this method for discovering and strengthening data associations and analyzing alloy oxidation mechanisms has been demonstrated in relevant data evaluations.

[0241] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0242] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, storage device storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0243] It should also be understood that the various implementations provided in the embodiments of this application can be arbitrarily combined to achieve different technical effects. The above is a specific description of the preferred implementation of this application, but this application is not limited to the above implementation. Those skilled in the art can also make various equivalent modifications or substitutions under the conditions that do not violate the spirit of this application.

Claims

1. A method for calculating an oxidation kinetic index, characterized in that: include: Obtaining a pre-constructed oxidation feature tree, wherein the oxidation feature tree is a binary tree, wherein the binary tree includes a plurality of nodes and node edges, wherein the nodes include a root node and at least two end nodes, and wherein the node edges store alloy feature values, wherein the alloy feature values ​​are boundaries for dividing alloy data; Dividing the nodes according to the alloy characteristic data from the alloy data, starting from the root node, determining the target node edges one by one according to the comparison result between the alloy characteristic data and the alloy characteristic value on the node edge, until reaching the end node, and determining the end node as the target end node; The oxidation kinetic index stored in the target end node is used as the oxidation kinetic index of the alloy data.

2. The method for calculating the oxidation kinetic index according to claim 1, characterized in that: Constructing the oxidation feature tree comprises: Acquire an oxidation data set; wherein the oxidation data set includes a plurality of alloy samples, each of the alloy samples includes a plurality of kinetic characteristics and corresponding kinetic characteristic values; A kinetic feature differentiation process is performed based on the oxidation data set to construct the oxidation feature tree; the kinetic feature differentiation process includes: Constructing a parent node; the parent node stores the alloy sample; the initial value of the parent node is the root node, and the root node is constructed based on the oxidation feature set; Traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node, and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom; According to the target dynamic characteristic and the target dynamic characteristic value, the alloy sample in the parent node is split to obtain a first child node and a second child node of the parent node, and the target dynamic characteristic value is stored in the corresponding node edge; Determine that the first child node and / or the second child node do not meet the stop differentiation condition, use the first child node and / or the second child node as the parent node, and execute the dynamic feature differentiation process.

3. The method for calculating the oxidation kinetic index according to claim 2, characterized in that: The kinetic characteristics of the alloy sample include oxidation time and alloy composition, and the alloy sample also includes oxidation weight gain; after obtaining the oxidation data set, the method further includes: Performing logarithm pretreatment on the oxidation time and the oxidation weight gain; performing combined calculations on the alloy components to generate a preset number of secondary alloy features; The secondary alloy features are added to the oxidation data set.

4. The method for calculating the oxidation kinetic index according to claim 2, characterized in that: The traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom comprises: Selecting a partition parameter from the kinetic characteristics; the partition parameter includes a candidate characteristic and a candidate characteristic value, and the candidate characteristic value is selected from the kinetic characteristic value of the candidate characteristic in the alloy sample; Dividing the alloy samples in the parent node into a first candidate set and a second candidate set according to the numerical values ​​of the candidate feature values; Obtaining a first fitting result of the first candidate set and a second fitting result of the second candidate set using an oxidation kinetic equation; The linear gain value of the partitioning parameter is calculated according to the first linearity value of the first fitting result, the second linearity value of the second fitting result and the total linearity value of the parent node; The candidate feature values ​​are updated by traversing the dynamic feature values, and the candidate features are updated by traversing the dynamic features, and the target dynamic feature and the target dynamic feature value are obtained according to the division parameter with the maximum linear gain value.

5. The method for calculating the oxidation kinetic index according to claim 4, characterized in that: The step of calculating the linear gain value of the partitioning parameter according to the first linearity value of the first fitting result, the second linearity value of the second fitting result, and the total linearity value of the parent node comprises: Calculating the first linearity value according to the first fitting result and the alloy sample in the first candidate set; Calculating the second linearity value according to the second fitting result and the alloy samples in the second candidate set; Obtaining the total sample quantity of the alloy samples in the parent node, the first sample quantity of the alloy samples in the first candidate set, and the second sample quantity of the alloy samples in the second candidate set; Calculate a first sample ratio according to the first sample size and the total sample size, and calculate a second sample ratio according to the second sample size and the total sample size; Multiplying the first sample ratio and the first linearity value to obtain a first linearity index, and multiplying the second sample ratio and the second linearity value to obtain a second linearity index; The first linearity index and the second linearity index are added and the total linearity value is subtracted to obtain a linear gain value of the partitioning parameter.

6. The method for calculating the oxidation kinetic index according to claim 5, characterized in that: The first fitting result is an oxidation kinetic fitting equation, the kinetic characteristic value includes an oxidation time value, and the alloy sample also includes an oxidation weight gain value; the first linearity value is calculated according to the first fitting result and the alloy sample in the first candidate set, including: Substituting the oxidation time value of the alloy sample in the first candidate set into the oxidation kinetics fitting equation to calculate the oxidation weight gain fitting value; Calculating the covariance of the oxidation weight gain value and the oxidation weight gain fitting value to obtain a first intermediate result; Calculating the standard deviation of the oxidation weight gain value to obtain a first standard deviation, calculating the standard deviation of the oxidation weight gain fitting value to obtain a second standard deviation, and multiplying the first standard deviation and the second standard deviation to obtain a second intermediate result; Dividing the first intermediate result by the second intermediate result to obtain the first linearity value; or, Calculating the sum of squares of errors between the oxidation weight gain value and the oxidation weight gain fitting value to obtain a third intermediate result; Calculating the total sum of squares of the oxidation weight gain values ​​to obtain a fourth intermediate result; The third intermediate result is divided by the fourth intermediate result to obtain a fifth intermediate result, and the first linearity value is obtained by subtracting 1 from the fifth intermediate result.

7. The method for calculating the oxidation kinetic index according to claim 2, characterized in that: The step of splitting the alloy sample in the parent node according to the target dynamic characteristic and the target dynamic characteristic value to obtain a first child node and a second child node of the parent node includes: According to the target dynamic characteristic, comparing the dynamic characteristic value corresponding to the alloy sample in the parent node with the numerical value of the target dynamic characteristic value; If the dynamic characteristic value is less than or equal to the target dynamic characteristic value, dividing the alloy sample into the first sub-node; If the dynamic characteristic value is greater than the target dynamic characteristic value, the alloy sample is divided into the second sub-node.

8. The method for calculating the oxidation kinetic index according to claim 2, characterized in that: The stopping differentiation condition includes a linearity threshold and / or a singleness threshold; the method further includes: If the first linearity value of the first subnode meets the linearity threshold, taking the first subnode as the end node; If the second linearity value of the second sub-node meets the linearity threshold, taking the second sub-node as the end node; and / or, If the oxidation time of the alloy sample in the first child node satisfies the single degree threshold, taking the parent node of the first child node as the end node; If the oxidation time of the alloy sample in the second child node meets the single degree threshold, the parent node of the second child node is used as the terminal node.

9. The method for calculating the oxidation kinetic index according to any one of claims 1 to 8, characterized in that: The end node includes a plurality of alloy samples, and an oxidation kinetics fitting equation of the alloy sample is obtained by using an oxidation kinetics equation, wherein the oxidation kinetics fitting equation includes the oxidation kinetics index; the method further includes: inputting the oxidation kinetic index of the end node and the alloy sample into a symbolic regression model; The oxidation kinetic index is used as a regression target, and a symbolic regression is performed on the kinetic characteristics in the alloy sample to obtain an analytical equation for the oxidation kinetic index.

10. An oxidation kinetic index calculation device, characterized in that: The method for calculating the oxidation kinetic index according to any one of claims 1 to 9 comprises: A first acquisition module is used to acquire a pre-constructed oxidation characteristic tree, wherein the oxidation characteristic tree is a binary tree, and the binary tree includes a plurality of nodes and node edges, wherein the nodes include a root node and at least two end nodes, and the node edges store alloy characteristic values, and the alloy characteristic values ​​are boundaries for dividing alloy data; A data comparison module, used to divide the nodes according to the alloy characteristic data from the alloy data, starting from the root node, and determining the target node edges one by one according to the comparison results of the alloy characteristic data and the alloy characteristic values ​​on the node edges, until reaching the end node, and determining the end node as the target end node; An index acquisition module is used to use the oxidation kinetic index stored in the target end node as the oxidation kinetic index of the alloy data.

11. The oxidation kinetic index calculation device according to claim 10, characterized in that: Also includes: A second acquisition module is used to acquire an oxidation data set; wherein the oxidation data set includes a plurality of alloy samples, each of which includes a plurality of kinetic characteristics and corresponding kinetic characteristic values; A differentiation module is used to perform a kinetic feature differentiation process based on the oxidation data set to construct the oxidation feature tree; the kinetic feature differentiation process includes: Constructing a parent node; the parent node stores the alloy sample; the initial value of the parent node is the root node, and the root node is constructed based on the oxidation feature set; Traversing the dynamic characteristics and the dynamic characteristic values ​​of the alloy sample in the parent node, and selecting a target dynamic characteristic and a target dynamic characteristic value therefrom; According to the target dynamic characteristic and the target dynamic characteristic value, the alloy sample in the parent node is split to obtain a first child node and a second child node of the parent node, and the target dynamic characteristic value is stored in the corresponding node edge; Determine that the first child node and / or the second child node do not meet the stop differentiation condition, and The second child node serves as the parent node to execute the dynamic feature differentiation process.

12. The oxidation kinetic index calculation device according to claim 11, characterized in that: Also includes: an analytical module for inputting the oxidation kinetic index of the end node and the alloy sample into a symbolic regression model; The oxidation kinetic index is used as a regression target, and a symbolic regression is performed on the kinetic characteristics in the alloy sample to obtain an analytical equation for the oxidation kinetic index.

13. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the oxidation kinetic index calculation method according to any one of claims 1 to 9 when executing the computer program.

14. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the oxidation kinetic index calculation method according to any one of claims 1 to 9.

Images