Method and system for evaluating alloying effect of high-vanadium steel

Abstract

The invention relates to the technical field of metal material performance evaluation, and discloses a high-vanadium steel alloying effect evaluation method and system. The method comprises the following steps: firstly, controlling a to-be-detected high-vanadium steel sample to be subjected to multi-stage heat treatment in a preset temperature range and rapidly cooling, collecting microstructure and component distribution data of the sample in each stage, calculating a vanadium segregation index and a grain boundary diffusion coefficient, and further constructing an alloying effect comprehensive evaluation model. And the model weight can be corrected through the corrosion rate of the sample in the corrosion medium. The system comprises a heat treatment control module, a data acquisition module, a calculation module and a model construction module. The high-vanadium steel alloying effect can be comprehensively and accurately evaluated, a basis is provided for alloy component design and heat treatment process optimization, the steel product quality is improved, and the technical development of the steel industry is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of metal material property evaluation, and particularly to a method and system for evaluating the alloying effect of high-vanadium steel. Background Art

[0002] In modern iron and steel industry, high-vanadium steel is widely used in many fields such as construction, machinery manufacturing, and automotive industry due to its excellent strength, toughness, wear resistance, and corrosion resistance. With the continuous development of industrial technology, the requirements for the properties of high-vanadium steel are becoming increasingly stringent, which makes it crucial to accurately evaluate the alloying effect of high-vanadium steel.

[0003] Traditional evaluation means for the alloying effect of high-vanadium steel have many limitations. In the early stage, it mainly relied on simple mechanical property tests such as tensile tests and hardness tests. Although these methods can reflect the macroscopic properties of high-vanadium steel to a certain extent, they cannot deeply reveal the changes in the microstructure and element distribution during the alloying process. For example, only through the tensile strength, it is impossible to understand the influence mechanism of the segregation state of vanadium element at grain boundaries and within grains on the material properties.

[0004] Later, some microscopic analysis techniques were gradually applied to the research of high-vanadium steel, such as observing the microstructure with a metallographic microscope. However, the resolution of the metallographic microscope is limited, and it is difficult to clearly observe and analyze some fine microscopic structure features, such as nano-scale vanadium element precipitation phases. Although the scanning electron microscope improves the resolution to a certain extent, when analyzing the element distribution, without the aid of other auxiliary equipment, it is impossible to accurately obtain the element concentration information.

[0005] In terms of the quantitative indexes for evaluating the alloying effect, there has been a lack of a systematic and comprehensive method in the past. Relying solely on a single performance index or a small number of microscopic structure parameters cannot accurately reflect the complex alloying process of high-vanadium steel. Moreover, most of the existing evaluation methods do not fully consider the influence of heat treatment processes on the alloying effect. Different heat treatment temperatures, holding times, and cooling rates will cause significant changes in the diffusion, segregation behavior, and microstructure of vanadium element in the steel, thereby affecting the alloying effect, but it is difficult for the existing technology to comprehensively and accurately evaluate this.

[0006] With the continuous expansion of the application of high-vanadium steel in high-end fields such as aerospace and ocean engineering, the requirements for its performance reliability and stability are extremely high. In these fields, any minor performance defect may cause serious consequences. Therefore, it is urgent to develop a method and system for evaluating the alloying effect of high-vanadium steel that can comprehensively consider multiple factors such as microstructure, composition distribution, and heat treatment process, which is of great significance for promoting the development and application of high-vanadium steel materials. Summary of the Invention

[0007] The purpose of the present invention is to provide a method and system for evaluating the alloying effect of high-vanadium steel to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: A method for evaluating the alloying effect of high-vanadium steel, the method comprising:

[0009] Controlling the test high-vanadium steel sample to undergo multi-stage heat treatment within a preset temperature range, and performing rapid cooling after each stage of heat treatment;

[0010] Collecting the microstructure data and composition distribution data of the sample after each stage of heat treatment;

[0011] Based on the microstructure data and composition distribution data, calculating the segregation index and grain boundary diffusion coefficient of vanadium element corresponding to each stage;

[0012] Based on the segregation index and grain boundary diffusion coefficient of vanadium element, constructing a comprehensive evaluation model for alloying effect;

[0013] The step of controlling the test high-vanadium steel sample to undergo multi-stage heat treatment within a preset temperature range includes:

[0014] Controlling the sample to be kept at a first preset temperature for a first preset duration and then cooled to room temperature at a first cooling rate;

[0015] Controlling the cooled sample to be kept at a second preset temperature for a second preset duration and then cooled to room temperature at a second cooling rate, where the second preset temperature is higher than the first preset temperature;

[0016] Controlling the sample after secondary cooling to be kept at a third preset temperature for a third preset duration and then cooled to room temperature at a third cooling rate, where the third preset temperature is lower than the first preset temperature;

[0017] Controlling the sample after tertiary cooling to be kept at a fourth preset temperature for a fourth preset duration and then cooled to room temperature at a fourth cooling rate, where the fourth preset temperature is between the first preset temperature and the second preset temperature.

[0018] Preferably, the first preset temperature is 500°C to 600°C, and the first cooling rate is 10°C / s to 20°C / s;

[0019] The second preset temperature is 800°C to 900°C, and the second cooling rate is 5°C / s to 15°C / s;

[0020] The third preset temperature is 300°C to 400°C, and the third cooling rate is 20°C / s to 30°C / s;

[0021] The fourth preset temperature is 650°C to 750°C, and the fourth cooling rate is 8°C / s to 12°C / s.

[0022] Preferably, the steps of collecting the microstructure data and composition distribution data of the specimens after heat treatment at each stage include:

[0023] Using a scanning electron microscope to obtain the grain size and grain boundary morphology data of the specimens at each stage;

[0024] Measuring the concentration distribution data of vanadium element at grain boundaries and within grains by an electron probe microanalyzer;

[0025] Using an X-ray diffractometer to determine the phase composition ratio and retained austenite content of the specimens at each stage.

[0026] Preferably, the steps of calculating the segregation index of vanadium element corresponding to each stage include:

[0027] Inputting the ratio of the vanadium element concentration at grain boundaries to the vanadium element concentration within grains into the first formula to calculate the segregation index of vanadium element, where the first formula is:

[0028]

[0029] where, I v is the segregation index of vanadium element, C gb is the vanadium element concentration at grain boundaries, C bulk is the vanadium element concentration within grains.

[0030] Preferably, the steps of calculating the grain boundary diffusion coefficient corresponding to each stage include:

[0031] Based on the grain size, holding temperature, and holding time of the specimens at each stage, calculate the grain boundary diffusion coefficient through the second formula, where the second formula is:

[0032]

[0033] where, D gb is the grain boundary diffusion coefficient, D0 is the diffusion constant, Q is the activation energy, R is the gas constant, T is the absolute temperature, δ is the grain boundary width, and d is the grain size.

[0034] Preferably, the steps of constructing a comprehensive evaluation model for alloying effect include:

[0035] Inputting the segregation index of vanadium element, grain boundary diffusion coefficient, phase composition ratio, and retained austenite content at each stage into a pre-trained multi-layer neural network model to output a comprehensive score for the alloying effect;

[0036] The multi-layer neural network model includes an input layer, at least three hidden layers, and an output layer, where the number of nodes in the input layer is the same as the number of characteristic parameters, and the number of nodes in the output layer is 1.

[0037] Preferably, the training steps of the multi-layer neural network model include:

[0038] Obtain the segregation index of vanadium element, grain boundary diffusion coefficient, phase composition ratio, retained austenite content and the alloying effect score manually marked corresponding to each heat treatment stage in the historical dataset;

[0039] Divide the historical data into a training set and a validation set according to a ratio of 7:3;

[0040] Use the backpropagation algorithm to optimize the network weights until the mean square error on the validation set is less than a preset threshold.

[0041] Preferably, the method further includes: after the heat treatment is completed, immerse the specimen in a corrosive medium and record the corrosion rate of the specimen; based on the corrosion rate and the comprehensive scoring of the alloying effect, correct the weight parameters in the comprehensive evaluation model.

[0042] Preferably, the corrosive medium is 3.5% sodium chloride solution, the immersion time is 24 to 72 hours, and the calculation formula for the corrosion rate is:

[0043]

[0044] Wherein, R c is the corrosion rate, ΔW is the mass loss of the specimen, A is the surface area, and t is the immersion time.

[0045] Preferably, the present invention further includes a high-vanadium steel alloying effect evaluation system, and the system includes:

[0046] Heat treatment control module: used to control the multi-stage heat treatment of the high-vanadium steel specimen to be tested within a preset temperature range. Specifically, it controls the specimen to be kept at the first preset temperature for the first preset duration and then cooled to room temperature at the first cooling rate, controls the cooled specimen to be kept at the second preset temperature for the second preset duration and then cooled to room temperature at the second cooling rate, wherein the second preset temperature is higher than the first preset temperature, controls the specimen after the secondary cooling to be kept at the third preset temperature for the third preset duration and then cooled to room temperature at the third cooling rate, wherein the third preset temperature is lower than the first preset temperature, controls the specimen after the third cooling to be kept at the fourth preset temperature for the fourth preset duration and then cooled to room temperature at the fourth cooling rate, wherein the fourth preset temperature is between the first preset temperature and the second preset temperature, and performs rapid cooling after each stage of heat treatment;

[0047] Data acquisition module: used to collect the microstructure data and composition distribution data of the specimen after each stage of heat treatment;

[0048] Calculation module: based on the microstructure data and composition distribution data, calculate the segregation index of vanadium element and the grain boundary diffusion coefficient corresponding to each stage;

[0049] Model construction module: Based on the vanadium element segregation index and the grain boundary diffusion coefficient, construct a comprehensive evaluation model for alloying effect.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0051] From the perspective of evaluation accuracy, through multi-stage heat treatment combined with the acquisition of microstructure and composition distribution data, the alloying behavior of high-vanadium steel under different heat treatment conditions can be analyzed comprehensively and meticulously. The multi-stage heat treatment sets different temperatures and cooling rates, simulating various heat treatment scenarios in actual production, making the obtained data more representative. Using a scanning electron microscope, an electron probe microanalyzer, and an X-ray diffractometer to collect microstructure data and composition distribution data, key information such as grain size, grain boundary morphology, vanadium element concentration distribution, and phase composition ratio is accurately obtained, providing a solid data foundation for accurately calculating the vanadium element segregation index and the grain boundary diffusion coefficient in the subsequent stage. This way of in-depth analysis at the microscopic level greatly improves the accuracy of alloying effect evaluation compared with traditional evaluation methods.

[0052] In terms of the quantitative evaluation of alloying effect, the constructed comprehensive evaluation model for alloying effect is innovative and practical. Inputting multiple key parameters such as the vanadium element segregation index, the grain boundary diffusion coefficient, the phase composition ratio, and the retained austenite content into a pre-trained multi-layer neural network model can comprehensively consider the influence of various factors on the alloying effect and output a comprehensive score that comprehensively reflects the alloying effect. This quantitative evaluation method avoids the limitations of relying only on single or a few indicators in traditional evaluation, providing a more scientific and intuitive basis for the quality control and performance optimization of high-vanadium steel.

[0053] From the perspective of optimizing the production process of high-vanadium steel, the present invention has important guiding significance. By analyzing the relationship between the changes in various parameters in different heat treatment stages and the alloying effect, the influence law of different process parameters on the alloying effect can be clarified. For example, according to the changes in the vanadium element segregation index and the grain boundary diffusion coefficient, adjust the heat treatment temperature and cooling rate to optimize the alloying process and improve the performance of high-vanadium steel. This helps steel production enterprises accurately control process parameters during production, reduce the trial-and-error cost during production, improve production efficiency, and reduce production costs.

[0054] In addition, the present invention also takes into account the corrosion resistance evaluation of high-vanadium steel. After the heat treatment is completed, the specimen is immersed in a corrosive medium and the corrosion rate is recorded, and the weight parameters in the comprehensive evaluation model are corrected based on the corrosion rate and the comprehensive score of the alloying effect. This not only makes the evaluation model more perfect and can more accurately reflect the performance of high-vanadium steel in the actual use environment, but also provides a more reliable performance evaluation basis for the application of high-vanadium steel in a corrosive environment, broadening the application range of high-vanadium steel. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 FIG. 1 is a schematic working diagram of the method for evaluating the alloying effect of high vanadium steel according to the present invention;

[0056] Figure 2 FIG. 2 is a flowchart of the acquisition of microstructure and composition data;

[0057] Figure 3 FIG. 3 is a flowchart of the construction of a comprehensive evaluation model for alloying effect. DETAILED DESCRIPTION OF THE INVENTION

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] Please refer to Figures 1-3 , the present invention provides a technical solution: a method for evaluating the alloying effect of high vanadium steel, the method comprising:

[0060] Controlling the multi-stage heat treatment of the high vanadium steel sample to be tested within a preset temperature range, and performing rapid cooling after each stage of heat treatment. Specifically: controlling the sample to be kept at the first preset temperature for the first preset duration and then cooled to room temperature at the first cooling rate; controlling the cooled sample to be kept at the second preset temperature for the second preset duration and then cooled to room temperature at the second cooling rate, where the second preset temperature is higher than the first preset temperature; controlling the sample after the secondary cooling to be kept at the third preset temperature for the third preset duration and then cooled to room temperature at the third cooling rate, where the third preset temperature is lower than the first preset temperature; controlling the sample after the tertiary cooling to be kept at the fourth preset temperature for the fourth preset duration and then cooled to room temperature at the fourth cooling rate, where the fourth preset temperature is between the first preset temperature and the second preset temperature.

[0061] Collecting the microstructure data and composition distribution data of the sample after each stage of heat treatment.

[0062] Calculating the segregation index of vanadium element and grain boundary diffusion coefficient corresponding to each stage based on the microstructure data and composition distribution data.

[0063] Constructing a comprehensive evaluation model for alloying effect based on the segregation index of vanadium element and grain boundary diffusion coefficient.

[0064] The present invention will be further described below with reference to Examples 1 to 5:

[0065] Example 1:

[0066] The function of this embodiment is to clarify specific heat treatment temperature and cooling rate parameters, making the multi-stage heat treatment process more operable and standardized, and ensuring the accuracy and repeatability of experimental results.

[0067] In this embodiment, the first preset temperature is set at 550 °C, which is within the range of 500 °C to 600 °C. This temperature is selected because in this temperature range, vanadium elements can start to diffuse and segregate to a certain extent in the steel matrix, and at the same time, excessive grain growth caused by too high temperature can be avoided, which affects subsequent microstructure analysis. The first cooling rate is set at 15 °C / s, between 10 °C / s and 20 °C / s. Such a cooling rate can not only ensure the rapid cooling of the specimen, inhibit the microstructure transformation at high temperature, but also avoid excessive thermal stress caused by too fast cooling, resulting in specimen cracking.

[0068] The second preset temperature is 850 °C, within the range of 800 °C to 900 °C. At this temperature, the austenitization process of the steel is relatively complete, which is conducive to the uniform distribution of vanadium elements in austenite, laying a foundation for subsequent cooling transformation and alloying effects. The second cooling rate is selected as 10 °C / s, between 5 °C / s and 15 °C / s. This cooling rate can make austenite transform in a suitable temperature range to obtain an ideal microstructure morphology.

[0069] The third preset temperature is 350 °C, within the range of 300 °C to 400 °C. This temperature is conducive to the segregation and precipitation of vanadium elements at grain boundaries, which is of great significance for studying the grain boundary behavior of vanadium elements. The third cooling rate is 25 °C / s, between 20 °C / s and 30 °C / s, which can quickly cool the specimen to room temperature and fix the segregation state of vanadium elements at this temperature.

[0070] The fourth preset temperature is 700 °C, between 650 °C and 750 °C. At this temperature, the diffusion and segregation behaviors of vanadium elements are relatively active, and they can interact with other elements, affecting the microstructure and properties of the steel. The fourth cooling rate is set at 10 °C / s, between 8 °C / s and 12 °C / s, which can ensure that the specimen is quickly cooled after being treated at this temperature, retaining the corresponding microstructure characteristics.

[0071] By precisely controlling these heat treatment parameters, it is possible to achieve the treatment of high-vanadium steel specimens in different states, providing stable and comparable samples for subsequent microstructure and composition analysis.

[0072] Example 2:

[0073] When collecting the microstructure data and composition distribution data of the samples after heat treatment at each stage, a scanning electron microscope (SEM) is used to obtain the grain size and grain boundary morphology data of the samples at each stage. The heat-treated samples are ground and polished to make their surfaces flat and smooth to meet the observation requirements of SEM. During the SEM observation process, a suitable magnification, such as 500-5000 times, is selected to clearly distinguish the boundaries and morphological features of the grains. The average size of the grains is measured through the image processing software provided by the SEM, and the shape, tortuosity and other information of the grain boundaries are recorded.

[0074] The concentration distribution data of vanadium at grain boundaries and within the crystals was measured by an electron probe microanalyzer (EPMA). EPMA uses an electron beam to excite the surface of the sample, causing it to emit characteristic X-rays, and determines the type and content of the element based on the wavelength and intensity of the X-rays. During the measurement process, the grain boundaries and intracrystalline areas of the sample are analyzed at fixed points, and multiple measurement points are selected to ensure the representativeness of the data. The spacing between the measurement points is determined based on the grain size and research accuracy, and is generally between 1-10μm. The average concentration of vanadium at the grain boundaries and within the crystals is obtained through statistical analysis of the data from multiple measurement points.

[0075] The phase composition ratio and retained austenite content of the samples at each stage were determined by X-ray diffractometer (XRD). The samples were made into sheets suitable for XRD measurement and placed in the XRD instrument. Appropriate measurement parameters were set, such as a scanning angle range of 20°-90° and a scanning speed of 2° / min. XRD determines the phase composition based on the position and intensity of the characteristic peaks by analyzing the diffraction pattern of the sample to X-rays. By comparing with the standard spectrum, the relative content of different phases and the content of retained austenite were calculated.

[0076] Through the coordinated use of the above three devices and methods, the microstructure data and composition distribution data of the samples after heat treatment at each stage can be obtained comprehensively and accurately, providing a solid data foundation for subsequent calculations and analysis.

[0077] Embodiment 3:

[0078] When calculating the vanadium element segregation index corresponding to each stage, the ratio of the vanadium element concentration at the grain boundary to the vanadium element concentration in the crystal is input into the first formula to calculate the vanadium element segregation index. The first formula is:

[0079]

[0080] Among them, I v is the vanadium element segregation index, C gb is the concentration of vanadium in the grain boundary, C bulk is the concentration of vanadium in the crystal.

[0081] For example, after a certain heat treatment stage, the grain boundary vanadium element concentration C is measured by an electron probe microanalyzer. gb is 0.15 wt%, and the intragranular vanadium element concentration C bulk is 0.05 wt%. Substituting these data into the above formula, we get:

[0082]

[0083] The larger the segregation index of vanadium element, the higher the segregation degree of vanadium element at the grain boundary. A higher segregation index means that vanadium element is enriched at the grain boundary, which may have an important impact on the properties of steel, such as improving the grain boundary strength and corrosion resistance. By calculating the segregation index of vanadium element at different heat treatment stages, the segregation behavior of vanadium element under different conditions can be intuitively understood, providing an important basis for evaluating the alloying effect.

[0084] Example 4:

[0085] The function of this example is to elaborate in detail the calculation method of the grain boundary diffusion coefficient. By considering factors such as grain size, holding temperature, and holding time, the diffusion ability of vanadium element at the grain boundary is quantified, and the behavior of vanadium element during the alloying process is further deeply evaluated.

[0086] Based on the grain size, holding temperature, and holding time of the specimens at each stage, the grain boundary diffusion coefficient is calculated by the second formula. The second formula is:

[0087]

[0088] where D gb is the grain boundary diffusion coefficient, D0 is the diffusion constant, Q is the activation energy, R is the gas constant, T is the absolute temperature, δ is the grain boundary width, and d is the grain size.

[0089] Suppose at a certain heat treatment stage, the relevant parameters of this stage are known: the diffusion constant D0 = 1×10 -5 m 2 / s, the activation energy Q = 150 kJ / mol, the gas constant R = 8.314 J / (mol·K), the holding temperature T = 1073 K (i.e., 800 °C), the grain boundary width δ = 5×10 -9 m, and the grain size d = 1×10 -4 m is measured by a scanning electron microscope.

[0090] First, the temperature is converted to the absolute temperature T = 1073 K, and then each parameter is substituted into the formula for calculation:

[0091]

[0092] The grain boundary diffusion coefficient reflects the diffusion rate of vanadium elements at the grain boundary, and its value affects the distribution uniformity and alloying effect of vanadium elements in steel. A lower grain boundary diffusion coefficient means that the diffusion of vanadium elements at the grain boundary is slower, which may lead to their enrichment in local areas; while a higher grain boundary diffusion coefficient indicates that vanadium elements can diffuse more rapidly at the grain boundary, which is beneficial to their uniform distribution in steel. By calculating the grain boundary diffusion coefficient at different stages, the diffusion behavior of vanadium elements at the grain boundary can be deeply understood, providing a reference for optimizing the alloying process.

[0093] Example 5:

[0094] When constructing a comprehensive evaluation model of alloying effect, the segregation index of vanadium elements, grain boundary diffusion coefficient, phase composition ratio and retained austenite content at each stage are input into a pre-trained multi-layer neural network model, and the comprehensive score of alloying effect is output.

[0095] The multi-layer neural network model includes an input layer, at least three hidden layers and an output layer. The number of nodes in the input layer is the same as the number of feature parameters. Since the feature parameters input into this model include the segregation index of vanadium elements, grain boundary diffusion coefficient, phase composition ratio and retained austenite content, a total of 4 parameters, the number of nodes in the input layer is 4. The number of nodes in the output layer is 1, and the output result is the comprehensive score of alloying effect.

[0096] The training steps of the multi-layer neural network model are as follows:

[0097] Obtain the segregation index of vanadium elements, grain boundary diffusion coefficient, phase composition ratio, retained austenite content and the manually marked alloying effect score corresponding to each heat treatment stage in the historical dataset. The historical dataset can be obtained through a large number of experimental accumulations. During the experiment, the heat treatment process parameters are strictly controlled, various characteristic parameters are accurately measured, and the alloying effect score is given by professionals according to the performance of the steel.

[0098] Divide the historical data into a training set and a validation set according to a ratio of 7:3. Use the training set to train the multi-layer neural network model, and adopt the backpropagation algorithm to optimize the network weights. During the training process, continuously adjust the weights and thresholds of the network to make the output result of the model as close as possible to the manually marked score in the training set. During the training process, use the mean square error (MSE) on the validation set as the evaluation index. When the mean square error on the validation set is less than the preset threshold (for example, 0.01), it is considered that the model training has achieved a good effect and the training is stopped.

[0099] In addition, after the heat treatment is completed, the specimen is immersed in the corrosion medium, and the corrosion rate of the specimen is recorded. The corrosion medium is 3.5% sodium chloride solution, and the immersion time is 48 hours. The calculation formula for the corrosion rate is:

[0100]

[0101] wherein, R c is the corrosion rate, ΔW is the mass loss of the specimen, A is the surface area, and t is the immersion time.

[0102] Based on the comprehensive score of the corrosion rate and the alloying effect, the weight parameters in the comprehensive evaluation model are corrected. If a certain correlation is found between the corrosion rate and the comprehensive score of the alloying effect, for example, the specimen with a lower corrosion rate has a higher comprehensive score of the alloying effect, then the weight parameters of the model can be adjusted according to this correlation to make the model more accurately reflect the relationship between the alloying effect and the actual performance.

[0103] The comprehensive evaluation model of the alloying effect constructed and optimized through the above steps can comprehensively consider the influence of multiple factors on the alloying effect of high-vanadium steel, providing important technical support for the research and development, production and quality control of high-vanadium steel. In practical applications, according to the comprehensive score of the alloying effect output by the model, the influence of different heat treatment processes and composition designs on the alloying effect of high-vanadium steel can be quickly evaluated, so as to optimize the process parameters and composition design and improve the performance and quality of high-vanadium steel.

[0104] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0105] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating the alloying effect of high-vanadium steel, characterized in that, The method includes: Controlling the high-vanadium steel specimen to be tested to undergo multi-stage heat treatment within a preset temperature range, and performing rapid cooling after each stage of heat treatment; Collecting the microstructure data and composition distribution data of the specimen after each stage of heat treatment; Calculating the segregation index of vanadium element and the grain boundary diffusion coefficient corresponding to each stage based on the microstructure data and composition distribution data; Constructing a comprehensive evaluation model for alloying effect based on the segregation index of vanadium element and the grain boundary diffusion coefficient; The step of controlling the high-vanadium steel specimen to be tested to undergo multi-stage heat treatment within a preset temperature range includes: Controlling the specimen to be held at a first preset temperature for a first preset duration and then cooled to room temperature at a first cooling rate; Controlling the cooled specimen to be held at a second preset temperature for a second preset duration and then cooled to room temperature at a second cooling rate, where the second preset temperature is higher than the first preset temperature; Controlling the specimen after secondary cooling to be held at a third preset temperature for a third preset duration and then cooled to room temperature at a third cooling rate, where the third preset temperature is lower than the first preset temperature; Controlling the specimen after three-stage cooling to be held at a fourth preset temperature for a fourth preset duration and then cooled to room temperature at a fourth cooling rate, where the fourth preset temperature is between the first preset temperature and the second preset temperature.

2. The method for evaluating the alloying effect of high-vanadium steel according to claim 1, wherein: The first preset temperature is 500°C to 600°C, and the first cooling rate is 10°C / s to 20°C / s; The second preset temperature is 800°C to 900°C, and the second cooling rate is 5°C / s to 15°C / s; The third preset temperature is 300°C to 400°C, and the third cooling rate is 20°C / s to 30°C / s; The fourth preset temperature is 650°C to 750°C, and the fourth cooling rate is 8°C / s to 12°C / s.

3. The method for evaluating the alloying effect of high-vanadium steel according to claim 1, characterized in that, The step of collecting the microstructure data and composition distribution data of the specimen after each stage of heat treatment includes: Using a scanning electron microscope to obtain the grain size and grain boundary morphology data of the specimen at each stage; Measuring the concentration distribution data of vanadium element at the grain boundary and in the grain through an electron probe microanalyzer; Using an X-ray diffractometer to determine the phase composition ratio and retained austenite content of the specimen at each stage.

4. The method for evaluating the alloying effect of high-vanadium steel according to claim 3, characterized in that, The step of calculating the segregation index of vanadium element corresponding to each stage includes: Inputting the ratio of the vanadium element concentration at the grain boundary to the vanadium element concentration in the grain into a first formula to calculate the segregation index of vanadium element, where the first formula is: Among them, I v is the segregation index of vanadium element, C gb is the vanadium element concentration at the grain boundary, C bulk is the vanadium element concentration within the grain.

5. The method for evaluating the alloying effect of high-vanadium steel according to claim 3, characterized in that The step of calculating the grain boundary diffusion coefficient corresponding to each stage includes: Calculating the grain boundary diffusion coefficient through a second formula based on the grain size, holding temperature, and holding duration of the specimen at each stage, where the second formula is: Among them, D gb is the grain boundary diffusion coefficient, D0 is the diffusion constant, Q is the activation energy, R is the gas constant, T is the absolute temperature, δ is the grain boundary width, and d is the grain size.

6. The method for evaluating the alloying effect of high-vanadium steel according to claim 1, characterized in that The step of constructing a comprehensive evaluation model for alloying effect includes: Inputting the segregation index of vanadium element, grain boundary diffusion coefficient, phase composition ratio, and retained austenite content at each stage into a pre-trained multi-layer neural network model to output a comprehensive score for alloying effect; The multi-layer neural network model includes an input layer, at least three hidden layers, and an output layer, where the number of nodes in the input layer is the same as the number of characteristic parameters, and the number of nodes in the output layer is 1.

7. The method for evaluating the alloying effect of high-vanadium steel according to claim 6, characterized in that The training steps of the multi-layer neural network model include: Obtaining the segregation index of vanadium element, grain boundary diffusion coefficient, phase composition ratio, retained austenite content and manually labeled alloying effect score corresponding to each heat treatment stage in the historical dataset; Dividing the historical data into a training set and a validation set according to a ratio of 7:3; Using the backpropagation algorithm to optimize the network weights until the mean square error on the validation set is less than a preset threshold.

8. The method for evaluating the alloying effect of high-vanadium steel according to claim 1, wherein The method further includes: after completing the heat treatment, immersing the specimen in a corrosion medium and recording the corrosion rate of the specimen; correcting the weight parameters in the comprehensive evaluation model based on the corrosion rate and the comprehensive score of the alloying effect.

9. The method for evaluating the alloying effect of high vanadium steel according to claim 8, characterized in that, The corrosion medium is a 3.5% sodium chloride solution, and the immersion time is 24 to 72 hours. The calculation formula for the corrosion rate is: Among them, R c is the corrosion rate, ΔW is the mass loss of the specimen, A is the surface area, and t is the immersion time.

10. A high-vanadium steel alloying effect evaluation system, characterized in that, Including: Heat treatment control module: used to control the multi-stage heat treatment of the high-vanadium steel specimen to be tested within a preset temperature range. Specifically, it controls the specimen to be held at the first preset temperature for the first preset duration and then cooled to room temperature at the first cooling rate. It controls the cooled specimen to be held at the second preset temperature for the second preset duration and then cooled to room temperature at the second cooling rate, where the second preset temperature is higher than the first preset temperature. It controls the specimen after the second cooling to be held at the third preset temperature for the third preset duration and then cooled to room temperature at the third cooling rate, where the third preset temperature is lower than the first preset temperature. It controls the specimen after the third cooling to be held at the fourth preset temperature for the fourth preset duration and then cooled to room temperature at the fourth cooling rate, where the fourth preset temperature is between the first preset temperature and the second preset temperature, and rapid cooling is performed after each stage of heat treatment; Data acquisition module: used to collect the microstructure data and composition distribution data of the specimen after each stage of heat treatment; Calculation module: calculating the segregation index of vanadium element and the grain boundary diffusion coefficient corresponding to each stage based on the microstructure data and composition distribution data; Model construction module: constructing a comprehensive evaluation model of alloying effect based on the segregation index of vanadium element and the grain boundary diffusion coefficient.

Images