Pulse electromagnetic strengthening method and device for low-carbon martensitic stainless steel blade

Abstract

The invention discloses a low-carbon martensitic stainless steel blade pulse electromagnetic strengthening method and device. According to the method disclosed by the invention, the most potential target process parameters are efficiently determined for the to-be-tested low-carbon martensitic stainless steel blade by utilizing the pre-trained target machine learning model according to the special material attribute and stress distribution condition of the to-be-tested low-carbon martensitic stainless steel blade, and the strengthening process is easy to control. And pulse electromagnetic strengthening is carried out on the to-be-detected low-carbon martensitic stainless steel blade according to the target process parameters, so that a non-contact and non-pollution strengthening process is realized, uniform residual compressive stress distribution is introduced to the surface of the to-be-detected low-carbon martensitic stainless steel blade, and the surface of the to-be-detected low-carbon martensitic stainless steel blade is prevented from being damaged. Therefore, the overall strengthening result is guaranteed, the fatigue strength and corrosion resistance of the low-carbon martensitic stainless steel blade are enhanced, and the service life of the low-carbon martensitic stainless steel blade is prolonged.

Description

Technical Field

[0001] The present application relates to the technical field of material mechanics, and in particular to a pulse electromagnetic strengthening method and device for low-carbon martensitic stainless steel blades. Background Art

[0002] Low-carbon martensitic stainless steel, especially 05Cr17Ni4Cu4Nb martensitic stainless steel, is widely used in key components in high temperature and high pressure environments such as steam turbine blades due to its excellent high temperature strength and corrosion resistance. However, in actual applications, steam turbine blades are often subjected to frequent thermal and mechanical stress cycles, which are prone to fatigue cracks and stress corrosion cracking, seriously affecting their service life and reliability.

[0003] In the related technology, the residual compressive stress on the surface of low-carbon martensitic stainless steel is increased by surface shot peening, laser shock treatment and heat treatment, thereby improving the fatigue strength and corrosion resistance of low-carbon martensitic stainless steel. However, surface shot peening may introduce micro cracks on the surface of the material, and the compressive stress distribution is uneven, which is difficult to control. Laser shock treatment equipment is expensive, the process is complicated, and the scope of application is limited. Heat treatment takes a long time, consumes high energy, and has strict requirements on material composition and organizational structure. Therefore, the above-mentioned related technologies for increasing residual compressive stress are difficult to apply to the special hardness and toughness of low-carbon martensitic stainless steel blades, and cannot guarantee the surface strengthening results of low-carbon martensitic stainless steel. Summary of the invention

[0004] In view of this, the present application provides a pulse electromagnetic strengthening method and device for low-carbon martensitic stainless steel blades, which strengthens the surface of the low-carbon martensitic stainless steel blades through pulse magnetic field processing technology, and based on the specific conditions of the low-carbon martensitic stainless steel blades to be tested, determines a better pulse electromagnetic strengthening scheme for the low-carbon martensitic stainless steel blades to be tested, thereby achieving efficient, uniform, and contactless strengthening treatment of the surface of the low-carbon martensitic stainless steel blades, significantly improving the fatigue strength and corrosion resistance of the low-carbon martensitic stainless steel blades, and extending the service life of the low-carbon martensitic stainless steel blades.

[0005] According to one aspect of the present application, a pulse electromagnetic strengthening method for a low-carbon martensitic stainless steel blade is provided, comprising: determining stress distribution information of the blade to be tested under preset working conditions based on basic data of the blade to be tested, wherein the blade to be tested is a low-carbon martensitic stainless steel blade; sampling the blade to be tested based on the basic data and the stress distribution information to determine a test sample of the blade to be tested; inputting the basic data and the stress distribution information into a target machine learning model to determine candidate process parameters of the blade to be tested, wherein the target machine learning model is trained based on historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades; performing pulse electromagnetic strengthening on the sample to be tested based on the candidate process parameters; determining target process parameters from the candidate process parameters based on the strengthening result of the sample to be tested; performing pulse electromagnetic strengthening on the blade to be tested based on the target process parameters to obtain a target blade.

[0006] According to another aspect of the present application, a pulse electromagnetic strengthening device for low-carbon martensitic stainless steel blades is provided, comprising: a determination module, used to determine the stress distribution information of the blade to be tested under preset working conditions based on basic data of the blade to be tested, wherein the blade to be tested is a low-carbon martensitic stainless steel blade; and, sampling the blade to be tested based on the basic data and the stress distribution information to determine the test sample of the blade to be tested; and, inputting the basic data and the stress distribution information into a target machine learning model to determine candidate process parameters of the blade to be tested, wherein the target machine learning model is trained based on historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades; and, performing pulse electromagnetic strengthening on the sample to be tested based on the candidate process parameters; and, determining target process parameters from the candidate process parameters based on the strengthening result of the sample to be tested; a strengthening module, used to perform pulse electromagnetic strengthening on the blade to be tested based on the target process parameters to obtain a target blade.

[0007] By means of the above technical scheme, the present application provides a pulse electromagnetic strengthening method and device for low-carbon martensitic stainless steel blades. According to the special material properties and stress distribution of the low-carbon martensitic stainless steel blades to be tested, the pre-trained target machine learning model is used to efficiently determine the most potential target process parameters for the low-carbon martensitic stainless steel blades to be tested, which is easy to control the strengthening process. Then, pulse electromagnetic strengthening is performed on the low-carbon martensitic stainless steel blades to be tested according to the target process parameters to achieve a contactless and pollution-free strengthening process, introduce a uniform residual compressive stress distribution to the surface of the low-carbon martensitic stainless steel blades to be tested, and prevent damage to the surface of the low-carbon martensitic stainless steel blades to be tested, thereby ensuring the overall strengthening result, enhancing the fatigue strength and corrosion resistance of the low-carbon martensitic stainless steel blades, and extending the service life of the low-carbon martensitic stainless steel blades.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0010] Figure 1 A schematic diagram of the process of pulse electromagnetic strengthening of low-carbon martensitic stainless steel blades provided in an embodiment of the present application is shown;

[0011] Figure 2 A structural block diagram of a pulse electromagnetic strengthening device for low-carbon martensitic stainless steel blades provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0012] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0013] The embodiments of the present application are described in detail below, and 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 cannot be interpreted as limiting the present application.

[0014] Those skilled in the art will appreciate that, unless expressly stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, or there may be intermediate elements. In addition, the "connection" or "connection" used herein may include wireless connection or wireless fusion. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0015] Now, exemplary embodiments according to the present application will be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in a variety of different forms and should not be interpreted as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided to make the disclosure of the present application thorough and complete, and to fully convey the concepts of these exemplary embodiments to those of ordinary skill in the art.

[0016] Low-carbon martensitic stainless steel, especially 05Cr17Ni4Cu4Nb martensitic stainless steel, is widely used in key components in high temperature and high pressure environments such as steam turbine blades due to its excellent high temperature strength and corrosion resistance. However, in actual applications, steam turbine blades are often subjected to frequent thermal and mechanical stress cycles, which are prone to fatigue cracks and stress corrosion cracking, seriously affecting their service life and reliability.

[0017] The introduction of residual compressive stress is one of the effective methods to improve the fatigue strength and corrosion resistance of materials. In the related art, the residual compressive stress on the surface of low-carbon martensitic stainless steel blades is increased by surface shot peening, laser shock treatment and heat treatment. Among them, surface shot peening is to impact the surface of low-carbon martensitic stainless steel blades by high-speed spraying of small spherical objects to form a residual compressive stress layer. During the impact process of high-speed small spherical objects, the compressive stress is unevenly distributed, which will produce local stress concentration and cause surface micro cracks. These cracks will become the initiation source of fatigue cracks, affecting the fatigue life of low-carbon martensitic stainless steel blades and reducing the strengthening effect. In addition, the process parameters of surface shot peening (such as spray speed, angle, sphere size, etc.) are difficult to control accurately, which further leads to uneven distribution of compressive stress. Laser shock treatment uses high-energy laser pulses to impact the surface of low-carbon martensitic stainless steel blades to form a deep compressive stress zone. However, the laser shock treatment equipment is costly, the operation process is difficult, and the process parameters need to be precisely controlled. It is suitable for parts with high added value and high precision requirements, but not suitable for industrial production of low-carbon martensitic stainless steel blades. The heat treatment process requires a long heating and cooling time, which affects production efficiency. In addition, heat treatment requires a high temperature environment, consumes a lot of energy, and is difficult to accurately control temperature and time parameters, which increases the difficulty of processing.

[0018] In view of this, a pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades is provided in this embodiment. According to the target process parameters, the surface of the low-carbon martensitic stainless steel blades is pulse electromagnetic strengthened to introduce uniform high-level residual compressive stress, simplify the process flow, improve the versatility and applicability of the process, and significantly improve the fatigue strength and corrosion resistance of the low-carbon martensitic stainless steel blades. Figure 1 As shown, the method includes:

[0019] Step 101, determining stress distribution information of the blade to be tested under preset working conditions according to basic data of the blade to be tested.

[0020] Among them, the blade to be tested is a low-carbon martensitic stainless steel blade.

[0021] In this embodiment, a preliminary measurement is performed on the low-carbon martensitic stainless steel blade to be tested to obtain basic data such as the size of the blade to be tested, the characteristics of the base material, the original residual compressive stress value on the surface, etc., so as to analyze the residual stress distribution on the surface of the blade to be tested based on the basic data, and determine a more accurate residual compressive stress distribution on the surface of the blade to be tested, thereby providing accurate basic information and reference basis for pulse electromagnetic strengthening.

[0022] It is worth mentioning that the low carbon martensitic stainless steel may be 05Cr17Ni4Cu4Nb martensitic stainless steel.

[0023] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the steps of determining the stress distribution information of the blade to be tested under preset working conditions based on the basic data of the blade to be tested specifically include: establishing a three-dimensional model of the blade to be tested based on the basic data of the blade to be tested; performing finite element meshing on the three-dimensional model; and calculating the stress distribution information based on the simulation data of the divided three-dimensional model under preset working conditions.

[0024] In this embodiment, a three-dimensional model of the blade to be measured is established based on the basic data of the blade to be measured to simulate the actual situation of the blade to be measured. Then, according to the simulation data in the three-dimensional model, a suitable mesh size and type are selected, and the finite element analysis method is used to perform finite element mesh division on the three-dimensional model of the blade to be measured, and it is discretized into multiple small units to improve the analysis accuracy and efficiency. For example, in stress concentration areas, key parts and places with large geometric changes, finer meshes are used to improve the analysis accuracy; relatively coarse meshes can be used in other areas to reduce calculation time.

[0025] Furthermore, the boundary conditions are determined according to the actual installation and working conditions of the blade to be tested. For example, if the blade to be tested is fixed on the hub, a fixed constraint can be set at the installation location to limit the displacement and rotation in certain directions, or the interaction between the blade to be tested and the surrounding environment can be considered, such as the friction between the blade to be tested and the air can be simulated by setting an appropriate boundary friction coefficient.

[0026] At the same time, determine the various loads that the blade to be tested bears during normal operation. For example, the centrifugal force is calculated based on the rotation speed and mass of the blade to be tested, and is applied to the blade to be tested as a body load. Alternatively, the pressure distribution on the surface of the blade to be tested is determined through aerodynamic analysis or empirical formulas, and is applied to the blade to be tested as a surface load. If the blade to be tested has temperature changes during operation, the thermal stress is calculated based on the thermal expansion coefficient of the material and the temperature difference, and is considered as an additional load.

[0027] Therefore, according to the simulation data of the divided three-dimensional model under the above-mentioned preset working conditions, the thermal stress and mechanical stress of the blade to be tested are accurately analyzed, the residual compressive stress distribution of the blade to be tested under normal working conditions is calculated, and the stress distribution information of the blade to be tested is determined, so that the target process parameters obtained in the subsequent steps can be applicable to the stress state of the blade to be tested under actual working conditions, thereby improving the effectiveness of surface strengthening of the blade to be tested.

[0028] Step 102 : sampling the blade to be tested according to the basic data and the stress distribution information to determine the sample to be tested of the blade to be tested.

[0029] In this embodiment, based on the special properties of the blade to be tested as reflected by the basic data and stress distribution information, the blade to be tested is sampled to ensure the typicality of the sample, thereby making the subsequent pulse electromagnetic strengthening results more reliable and representative.

[0030] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the steps of sampling the blade to be tested according to the basic data and stress distribution information and determining the test sample of the blade to be tested specifically include: determining multiple stress areas of the blade to be tested according to the stress distribution information; determining the stratification conditions of the stress area according to the basic data, and determining multiple sampling layers of the stress area according to the stratification conditions; sampling the preset position of the sampling layer to determine the sample to be tested.

[0031] In this embodiment, compared with simple random sampling or selection based on existing experience in conventional methods, this embodiment adopts a quantitative sampling method to improve the accuracy and reliability of the pulse electromagnetic strengthening process and avoid damage to the surface of the blade to be tested during actual pulse electromagnetic strengthening.

[0032] Specifically, the residual stress difference on the surface of the blade to be tested is determined based on the stress distribution information, and the blade to be tested is divided into multiple stress areas, for example, the blade to be tested is divided into a high stress area, a medium stress area and a low stress area. Usually, the high stress area of ​​the blade is located at the root of the blade, while the low stress area is at the tip of the blade. Then, based on the basic data of the blade to be tested or the simulation data of the three-dimensional model, the stratification conditions of each stress area are determined, so as to perform stratified sampling in combination with the special properties of the surface and interior of the blade to be tested (composition uniformity, grain size, surface residual stress state, etc.), so that the samples can reflect the strengthening effects of different areas of the blade to be tested.

[0033] Exemplarily, each stress region can be divided into multiple sampling layers according to the change in grain size or the difference in surface residual stress in each stress region. For example, if the grain size of the blade material to be tested varies significantly in different parts of the stress region, the sampling layers can be divided according to the change in grain size. For example, the part with smaller grain size is divided into one layer, and the part with larger grain size is divided into another layer, so as to better understand the influence of grain size on material properties and stress distribution. Alternatively, the stress region is further divided into multiple sampling layers according to the difference in surface residual stress in different parts of the stress region. For example, the stress region can be divided into different levels at a certain stress interval, such as 100MPa and 200MPa as the basis for division, and the stress region can be further divided into high stress layer, medium stress layer and low stress layer to ensure that material properties at different stress levels can be sampled and analyzed.

[0034] Samples are then extracted at specific locations in each sampling layer to ensure that the material properties of each layer are representatively covered. For example, in a high-stress layer, locations with the most obvious stress concentrations can be selected, such as the blade edge, root, or around holes. In medium-stress and low-stress layers, relatively uniform locations can be selected to represent the average material properties of the layer.

[0035] In one embodiment, the pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades also includes: obtaining sampling conditions; determining a sampling area that meets the sampling conditions on the blade to be tested based on stress distribution information; and sampling a preset position in the sampling area to determine a sample to be tested.

[0036] In this embodiment, the sampling conditions are determined according to the actual needs of the user. For example, if sampling is performed in a high stress area of ​​the blade to be tested, an area with higher stress is determined on the blade to be tested based on the stress distribution information, which is usually located at the blade root, and sampling is performed at a specific position in the high stress area to obtain a sample with more concentrated stress, so that the stress state of the blade to be tested can be represented by the sample with concentrated stress.

[0037] Step 103, input the basic data and stress distribution information into the target machine learning model to determine the candidate process parameters of the blade to be tested.

[0038] Among them, the target machine learning model is trained based on the historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades.

[0039] In this embodiment, a pre-trained target machine learning model is used to select multiple most suitable candidate process parameters for the blade to be tested. Compared with the traditional method of traversing various historical parameter combinations, this embodiment analyzes large data sets to find the most potential parameter combination, thereby avoiding excessive experimental attempts and improving efficiency.

[0040] In one embodiment, the pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades also includes: determining an initial machine learning model in a preset machine learning model based on basic data of the blade to be tested; training the initial machine learning model based on historical pulse electromagnetic strengthening data to determine a target machine learning model so that the target machine learning model can determine predicted process parameters that match the basic data and stress distribution information, and determining candidate process parameters in the predicted process parameters based on the predicted strengthening results of the blade to be tested by the predicted process parameters.

[0041] Among them, the historical pulse electromagnetic strengthening data includes historical basic data, historical stress distribution information, historical process parameters and historical strengthening results corresponding to the historical process parameters.

[0042] Specifically, the initial machine learning model for training is selected based on the amount and complexity of the historical pulse electromagnetic enhancement data related to the basic data. For example, when the amount of historical pulse electromagnetic enhancement data is relatively small and relatively simple, models such as random forest and support vector machine are selected as the initial machine learning model. When the amount of historical pulse electromagnetic enhancement data is relatively large and relatively complex, a neural network model is used.

[0043] Furthermore, the historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades are used as the training set of the initial machine learning model, and the initial machine learning model is trained so that the initial machine learning model can analyze and learn the relationship between various types of data in the historical pulse electromagnetic strengthening data, so as to predict the strengthening effects of different parameter combinations on different blades, and then obtain the target machine learning model.

[0044] In actual application scenarios, the basic data or simulation data and stress distribution information of the blade to be tested are input into the target machine learning model. The target machine learning model can predict the strengthening effect of the blade to be tested under different process parameters based on the input data, and thus sort the different predicted process parameters according to the predicted strengthening effect, determine the parameter order, and output the predicted process parameters that are before the preset position in the parameter order as candidate process parameters.

[0045] Exemplarily, the candidate process parameters may include pulse electromagnetic frequency, magnetic field strength, and number of enhancement times.

[0046] In this embodiment, by adopting a machine learning method, candidate process parameters matching the blade to be tested are quickly found, thereby saving a lot of time and resources while ensuring that the strengthening effect on the blade to be tested is maximized.

[0047] Step 104: performing pulse electromagnetic strengthening on the sample to be tested according to the candidate process parameters.

[0048] In this embodiment, the candidate process parameters are verified by the sample to be tested, so as to determine more optimal target process parameters in subsequent steps.

[0049] Furthermore, as a refinement and expansion of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, the steps of performing pulse electromagnetic strengthening on the sample to be tested according to the candidate process parameters specifically include: according to the basic data of the sample to be tested, associating the candidate process parameters with the sample to be tested according to preset association rules; performing pulse electromagnetic strengthening on the sample to be tested associated with the candidate process parameters according to the candidate process parameters.

[0050] In this embodiment, the candidate process parameters are associated with the samples to be tested, so that each sample to be tested corresponds to one candidate process parameter, thereby preventing repeated pulse electromagnetic strengthening of the samples and improving the reliability of the strengthening results.

[0051] Exemplarily, if the blade to be tested is sampled in layers to obtain samples to be tested, different sampling layers in the stress area can be sampled according to the number of candidate process parameters, so that the number of samples to be tested in each sampling layer is the same as the number of candidate process parameters, thereby randomly associating the candidate process parameters with different samples to be tested in each sampling layer, so that each candidate process parameter is associated with a sample to be tested in different sampling layers in different stress areas of the blade to be tested, thereby determining the strengthening effect of the candidate process parameter on the entire blade to be tested based on the strengthening result of the candidate process parameter on the associated sample to be tested.

[0052] If stratification is not performed when sampling the blade to be tested, but sampling conditions are obtained, the number of all samples to be tested is determined according to the number of candidate process parameters, so that the number of candidate process parameters is the same as the number of samples to be tested, and the samples to be tested are randomly associated with the candidate process parameters, so that each candidate process parameter is associated with only one sample to be tested. Similarly, the strengthening effect of the candidate process parameters on the entire blade to be tested is determined based on the strengthening results of the candidate process parameters on the associated samples to be tested.

[0053] Step 105: determining target process parameters from candidate process parameters according to the strengthening result of the sample to be tested.

[0054] In this embodiment, based on the strengthening results of the candidate process parameters on the sample to be tested, more optimal target process parameters are determined from the candidate process parameters to improve the reliability and effectiveness of the pulse electromagnetic strengthening of the blade to be tested.

[0055] Further, as a refinement and extension of the specific implementation methods of the above-mentioned embodiment, in order to fully illustrate the specific implementation process of this embodiment, according to the strengthening results of the sample to be tested, the target process parameters are determined in the candidate process parameters, including: determining the sample to be tested associated with the candidate process parameters as the target sample; determining the detection area in the target sample; determining the strengthening results of the detection area by the candidate process parameters according to the initial stress data of the detection area before pulse electromagnetic strengthening and the target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters; determining the strengthening results of the target sample by the candidate process parameters according to the strengthening results of the detection area; according to the strengthening results of the target sample by the candidate process parameters, determining the overall strengthening results of the blade to be tested by the candidate process parameters according to preset calculation rules, and determining the target process parameters among the candidate process parameters according to the overall strengthening results.

[0056] In this embodiment, the sample to be tested associated with the candidate process parameters is determined as the target sample, and the target sample is subjected to actual pulse electromagnetic treatment according to the candidate process parameters. Thus, according to the strengthening result of the target sample by the candidate process parameters, the overall strengthening effect of the candidate process parameters on the blade to be tested is evaluated, and then the target process parameters are determined to ensure that after the pulse electromagnetic strengthening of the blade to be tested according to the target process parameters, a uniform high level of residual compressive stress can be introduced into the blade to be tested, and the fatigue strength and corrosion resistance of the blade to be tested can be significantly improved.

[0057] Exemplarily, if a candidate process parameter is associated with multiple target samples, pulse electromagnetic enhancement is performed on each target sample associated with the candidate process parameter, and enhancement results of each target sample associated with the candidate process parameter are determined respectively.

[0058] It is worth mentioning that if the strengthening results of the candidate process parameters for each target sample associated with it are relatively close, the overall strengthening result of the candidate process parameters on the blade to be tested can be determined based on the average value of the strengthening results of each target sample associated with the candidate process parameters. If the strengthening results of the candidate process parameters for each target sample associated with it are relatively discrete, the variance or standard deviation of the strengthening results of the candidate process parameters for each target sample associated with it is calculated, and the variance or standard deviation is used to reflect the degree of discreteness of the strengthening results, so as to more comprehensively understand the strengthening effect of the candidate process parameters on the blade to be tested as a whole. If different target samples differ in importance during sampling, different weights can be assigned to the strengthening results of each target sample, and then the overall strengthening result can be calculated by weighted average. For example, higher weights are assigned to samples in key areas, and lower weights are assigned to samples in non-key areas.

[0059] If the candidate process parameter is associated with only one target sample, the strengthening result of the candidate process parameter on the associated target sample is used as the overall strengthening result of the candidate process parameter on the blade to be tested.

[0060] Furthermore, the candidate process parameters are sorted according to the overall strengthening result, the candidate parameter sequence is determined, and the candidate process parameter at the first position in the candidate parameter sequence is used as the target process parameter.

[0061] It is worth mentioning that in this embodiment, multiple detection areas are randomly determined on the target sample, and the residual compressive stress of the detection area before and after pulse electromagnetic strengthening is measured by a residual stress tester or a high-precision X-ray diffraction device, and the strengthening result of each detection area is determined according to the difference in residual compressive stress before and after pulse electromagnetic strengthening. Thus, the strengthening result of the target sample is determined according to the average value of the strengthening results of multiple detection areas to avoid errors caused by measurement.

[0062] In this embodiment, microstructural observations (such as scanning electron microscopy (SEM), electron backscatter diffraction (EBSD), etc.) can also be combined to obtain the structural stability and performance improvement of the strengthened target sample, thereby jointly determining the strengthening result of the target sample with the change in residual compressive stress, comprehensively and accurately evaluating the effect of pulsed electromagnetic treatment, providing strong experimental data support, and providing an accurate basis for determining the target process parameters.

[0063] In one embodiment, the pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades also includes: collecting first stress data of the detection area before pulse electromagnetic strengthening according to a preset number of times; collecting second stress data of the detection area after pulse electromagnetic strengthening according to candidate process parameters according to a preset number of times; determining initial stress data of the detection area before pulse electromagnetic strengthening according to an average value of the first stress data; and determining target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters according to an average value of the second stress data.

[0064] In this embodiment, each detection area is measured multiple times, which further reduces measurement errors and improves the accuracy and reliability of the enhancement.

[0065] Exemplarily, a portable residual stress tester is used to measure the type II residual stress by measuring the change in the half-width FWHM. At this time, the stress balance range reflected is at the grain size level. Generally, type II residual stress will cause the diffraction peak to broaden. In order to further standardize the measurement data and strictly require the measurement direction, the measurement positioning method is designed as follows: the height and angle are fixed by a fixture to determine the measurement position, and the X-ray incident angle is specified to ensure that the data is stable each time and eliminate instrument and system errors. Furthermore, the residual compressive stress value of each detection area before and after pulse electromagnetic strengthening is measured multiple times using the set device, and the initial stress data and target stress data are determined by taking the average value of multiple measurements to reduce measurement errors.

[0066] In one embodiment, the blade to be tested is a 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blade, which is specially designed for high temperature and high pressure turbine environment. The number of candidate process parameters is 2, namely the first process parameter and the second process parameter, the number of samples to be tested is also 2, the samples to be tested are randomly associated one-to-one with the candidate process parameters, each sample to be tested has 3 detection areas, each detection area is measured three times and the average value is taken, and the residual compressive stress measurement data of each detection area of ​​the sample to be tested before and after pulse electromagnetic strengthening are shown in Table 1. Among them, for the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blade, the first process parameter can be specifically: the high-frequency pulse electromagnetic frequency is fixed at 0.865Hz, the magnetic field strength is fixed at 0.6T, and the number of processing times is 4 times, and the second process parameter is specifically: the high-frequency pulse electromagnetic frequency is fixed at 0.865Hz, the magnetic field strength is fixed at 0.6T, and the number of processing times is 8 times.

[0067] Table 1

[0068]

[0069] It can be seen from Table 1 that after the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blade is treated according to the second process parameters, the residual compressive stress on the surface of the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blade is greatly increased. Therefore, for the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blade, the second process parameters are used as the target process parameters.

[0070] Step 106, performing pulse electromagnetic strengthening on the blade to be tested according to the target process parameters to obtain a target blade.

[0071] In this embodiment, in view of the special hardness and toughness of the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blades, a better pulse electromagnetic treatment scheme is determined based on the target process parameters, so that the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blades are pulse electromagnetic strengthened according to the pulse electromagnetic treatment scheme that is more suitable for the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blades, so as to prevent surface damage or uneven strengthening during the pulse electromagnetic treatment process, enhance the overall performance of the surface of the 05Cr17Ni4Cu4Nb martensitic stainless steel candidate blades, and improve fatigue strength and corrosion resistance.

[0072] In one embodiment, the pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades also includes: in the process of pulse electromagnetic strengthening of the sample to be tested according to the candidate process parameters, the magnetic field intensity distribution data and surface stress data of the sample to be tested are collected in real time by a sensor located at a preset position; if the magnetic field intensity distribution data or the surface stress data does not meet the preset conditions, the device associated with the magnetic field intensity distribution data or the surface stress data that does not meet the preset conditions is controlled to be adjusted, so as to adjust the candidate process parameters in real time so that the magnetic field intensity distribution data and the surface stress data both meet the preset conditions.

[0073] In this embodiment, during the actual pulse electromagnetic strengthening process of the sample to be tested, a real-time sensor is used to feedback the stress changes and magnetic field intensity distribution on the surface of the sample to be tested. According to the real-time electromagnetic field distribution and the stress state of the surface of the sample to be tested, the candidate process parameters are adaptively controlled and dynamically adjusted to prevent stronger candidate process parameters from damaging smaller samples to be tested, thereby ensuring the strengthening effect of the candidate process parameters on the sample to be tested, providing an accurate basis for the subsequent determination of the target process parameters, and improving the reliability of the strengthening.

[0074] Exemplarily, in the process of pulse electromagnetic strengthening of the sample to be tested according to the candidate process parameters, the stress changes on the surface of the sample to be tested are monitored in real time. Once the stress concentration area is detected, the pulse power supply device is controlled to increase the pulse frequency to a higher frequency to increase the processing intensity. At the same time, the electromagnetic field distribution on the surface of the sample to be tested is monitored in real time. When it is detected that the electromagnetic field distribution on the surface of the sample to be tested is uneven, such as when the magnetic field strength in some areas is weak, the magnetic field generator is controlled to adjust the position and angle so that the electromagnetic field can cover the surface of the sample to be tested more evenly. For example, the magnetic field generator is moved a certain distance to one side of the sample to be tested, and the angle is adjusted to 30 degrees to improve the electromagnetic field distribution.

[0075] Similarly, in the process of pulse electromagnetic strengthening of the blade to be tested according to the target process parameters, the surface of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade is first cleaned and fixed in a specific blade fixture with a clamp, the magnetic field processing parameters are set according to the target process parameters, the pulse magnetic field power supply is started, the steam inlet edge of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade is processed, and the magnetic field intensity distribution data and surface stress data of the blade to be tested are collected in real time. According to the magnetic field intensity distribution data and surface stress data of the blade to be tested, the device that does not meet the association of the magnetic field intensity distribution data and the surface stress data of the preset conditions is controlled, so that the magnetic field intensity distribution data and the surface stress data of the blade to be tested meet the preset conditions, thereby accurately controlling the processing process according to the changes in the surface and internal materials of the blade to be tested, achieving a more uniform and in-depth residual compressive stress distribution, and overcoming the uneven effect caused by inaccurate process parameters in related technologies.

[0076] The present application provides a pulse electromagnetic strengthening method and device for low-carbon martensitic stainless steel blades, which adopts non-contact pulse magnetic field processing technology, and through the action of electromagnetic field, will not produce mechanical impact on the surface of 05Cr17Ni4Cu4Nb martensitic stainless steel blades, and will not cause mechanical damage or pollution to the surface of 05Cr17Ni4Cu4Nb martensitic stainless steel blades. When determining the target process parameters, not only the optimization on the micro scale (such as grain size and surface stress) is considered, but also the macro scale (such as shape, stress distribution, and use environment) is combined for comprehensive optimization. Through a multi-scale optimization method, a high level of residual compressive stress is introduced into the surface of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade, and a uniform compressive stress distribution is formed on the surface of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade, so as to achieve the maximum improvement of the overall performance of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade, improve the fatigue life and fatigue crack resistance of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade, and enhance the service life of the 05Cr17Ni4Cu4Nb martensitic stainless steel blade. In addition, the present application is easy to control, has a uniform treatment effect, is easy to operate, has a short treatment time, has low energy consumption, reduces equipment cost and energy consumption cost, is more economical, improves economic benefits and environmental friendliness, and is suitable for large-scale industrial production.

[0077] Furthermore, if Figure 2 As shown, as a specific implementation of the above-mentioned pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades, an embodiment of the present application provides a pulse electromagnetic strengthening device 200 for low-carbon martensitic stainless steel blades, and the pulse electromagnetic strengthening device 200 for low-carbon martensitic stainless steel blades includes: a determination module 201 and a strengthening module 202.

[0078] Among them, the determination module 201 is used to determine the stress distribution information of the blade to be tested under preset working conditions according to the basic data of the blade to be tested, wherein the blade to be tested is a low-carbon martensitic stainless steel blade; and, sampling the blade to be tested according to the basic data and the stress distribution information to determine the sample to be tested of the blade to be tested; and, inputting the basic data and the stress distribution information into the target machine learning model to determine the candidate process parameters of the blade to be tested, wherein the target machine learning model is trained based on the historical pulse electromagnetic strengthening data of the low-carbon martensitic stainless steel blade; and, pulse electromagnetic strengthening is performed on the sample to be tested according to the candidate process parameters; and, according to the strengthening result of the sample to be tested, the target process parameters are determined from the candidate process parameters;

[0079] The strengthening module 202 is used to perform pulse electromagnetic strengthening on the blade to be tested according to target process parameters to obtain a target blade.

[0080] In one embodiment, the determination module 201 is specifically used to establish a three-dimensional model of the blade to be measured based on the basic data of the blade to be measured; perform finite element meshing on the three-dimensional model; and calculate stress distribution information based on simulation data of the divided three-dimensional model under preset working conditions.

[0081] In one embodiment, the determination module 201 is specifically used to determine multiple stress areas of the blade to be tested based on stress distribution information; determine the stratification conditions of the stress area based on basic data, and determine multiple sampling layers of the stress area based on the stratification conditions; sample the preset positions of the sampling layers to determine the samples to be tested.

[0082] In one embodiment, the pulse electromagnetic strengthening device for low carbon martensitic stainless steel blades further comprises:

[0083] A training module is used to determine an initial machine learning model in a preset machine learning model based on basic data of the blade to be tested; train the initial machine learning model based on historical pulse electromagnetic strengthening data to determine a target machine learning model so that the target machine learning model can determine predicted process parameters that match the basic data and stress distribution information, and determine candidate process parameters in the predicted process parameters based on the predicted strengthening results of the blade to be tested using the predicted process parameters; wherein the historical pulse electromagnetic strengthening data includes historical basic data, historical stress distribution information, historical process parameters and historical strengthening results corresponding to the historical process parameters.

[0084] In one embodiment, the strengthening module 202 is specifically used to associate candidate process parameters with the sample to be tested according to the basic data of the sample to be tested and according to preset association rules; and perform pulse electromagnetic strengthening on the sample to be tested associated with the candidate process parameters according to the candidate process parameters.

[0085] In one embodiment, the determination module 201 is specifically used to determine the sample to be tested associated with the candidate process parameters as the target sample; determine the detection area in the target sample; determine the strengthening result of the detection area by the candidate process parameters based on the initial stress data of the detection area before pulse electromagnetic strengthening and the target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters; determine the strengthening result of the target sample by the candidate process parameters based on the strengthening result of the detection area; determine the overall strengthening result of the blade to be tested by the candidate process parameters according to the preset calculation rules based on the strengthening result of the target sample by the candidate process parameters, and determine the target process parameters among the candidate process parameters based on the overall strengthening result.

[0086] In one embodiment, the pulse electromagnetic strengthening device for low carbon martensitic stainless steel blades further comprises:

[0087] The acquisition module is used to acquire the first stress data of the detection area before pulse electromagnetic strengthening according to a preset number of times; to acquire the second stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters according to the preset number of times; to determine the initial stress data of the detection area before pulse electromagnetic strengthening according to the average value of the first stress data; and to determine the target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters according to the average value of the second stress data.

[0088] In one embodiment, the pulse electromagnetic strengthening device for low carbon martensitic stainless steel blades further comprises:

[0089] A process module, for candidate process parameters including a first process parameter and a second process parameter;

[0090] Among them, the first process parameters include a pulse electromagnetic frequency of 0.810-0.890 Hz, a magnetic field strength of 0.3-0.7 T, and a strengthening number of 4-6 times; the second process parameters include a pulse electromagnetic frequency of 0.810-0.890 Hz, a magnetic field strength of 0.3-0.7 T, and a strengthening number of 7-9 times.

[0091] In one embodiment, the pulse electromagnetic strengthening device for low carbon martensitic stainless steel blades further comprises:

[0092] The adjustment module is used to collect the magnetic field intensity distribution data and surface stress data of the sample to be tested in real time through a sensor located at a preset position during the process of pulse electromagnetic strengthening of the sample to be tested according to the candidate process parameters; if the magnetic field intensity distribution data or the surface stress data does not meet the preset conditions, the device associated with the magnetic field intensity distribution data or the surface stress data that does not meet the preset conditions is controlled to be adjusted, so as to adjust the candidate process parameters in real time so that the magnetic field intensity distribution data and the surface stress data both meet the preset conditions.

[0093] For the specific definition of the pulse electromagnetic strengthening device for low-carbon martensitic stainless steel blades, please refer to the definition of the pulse electromagnetic strengthening method for low-carbon martensitic stainless steel blades mentioned above, which will not be repeated here. Each module in the above-mentioned pulse electromagnetic strengthening device for low-carbon martensitic stainless steel blades can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or the embodiments of the present application can be implemented by hardware.

[0095] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0096] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades, characterized in that: The method comprises: Determine stress distribution information of the blade to be tested under preset working conditions according to basic data of the blade to be tested, wherein the blade to be tested is a low-carbon martensitic stainless steel blade; Sampling the blade to be tested according to the basic data and the stress distribution information to determine the sample to be tested of the blade to be tested; Inputting the basic data and the stress distribution information into a target machine learning model to determine candidate process parameters of the blade to be tested, wherein the target machine learning model is trained based on historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades; Performing pulse electromagnetic strengthening on the sample to be tested according to the candidate process parameters; Determining target process parameters from the candidate process parameters according to the strengthening result of the sample to be tested; The blade to be tested is pulsed electromagnetically strengthened according to the target process parameters to obtain a target blade.

2. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: Determining the stress distribution information of the blade to be measured under preset working conditions according to the basic data of the blade to be measured includes: Establishing a three-dimensional model of the blade to be measured according to the basic data of the blade to be measured; Performing finite element meshing on the three-dimensional model; The stress distribution information is calculated based on the simulation data of the divided three-dimensional model under the preset working conditions.

3. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: The step of sampling the blade to be tested according to the basic data and the stress distribution information to determine the sample to be tested of the blade to be tested includes: Determine a plurality of stress regions of the blade to be tested according to the stress distribution information; Determining a stratification condition of the stress region according to the basic data, and determining a plurality of sampling layers of the stress region according to the stratification condition; Sampling is performed on a preset position of the sampling layer to determine the sample to be tested.

4. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: The method further comprises: Determining an initial machine learning model in a preset machine learning model according to the basic data of the blade to be tested; Training the initial machine learning model according to the historical pulse electromagnetic strengthening data, determining the target machine learning model, so that the target machine learning model can determine the predicted process parameters that match the basic data and the stress distribution information, and determining the candidate process parameters in the predicted process parameters according to the predicted strengthening result of the blade to be tested by the predicted process parameters; The historical pulse electromagnetic strengthening data include historical basic data, historical stress distribution information, historical process parameters and historical strengthening results corresponding to the historical process parameters.

5. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: The step of performing pulse electromagnetic enhancement on the sample to be tested according to the candidate process parameters comprises: According to the basic data of the sample to be tested, the candidate process parameters are associated with the sample to be tested according to a preset association rule; According to the candidate process parameters, pulse electromagnetic enhancement is performed on the sample to be tested associated with the candidate process parameters.

6. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 5, characterized in that: Determining a target process parameter from the candidate process parameters according to the strengthening result of the sample to be tested includes: Determine the sample to be tested associated with the candidate process parameter as a target sample; determining a detection region in the target sample; Determine the strengthening result of the detection area by the candidate process parameters according to the initial stress data of the detection area before pulse electromagnetic strengthening and the target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameters; Determining, according to the strengthening result of the detection area, the strengthening result of the candidate process parameters on the target sample; According to the strengthening result of the target sample by the candidate process parameters, the overall strengthening result of the candidate process parameters on the blade to be tested is determined according to a preset calculation rule, and the target process parameters are determined from the candidate process parameters according to the overall strengthening result.

7. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 6, characterized in that: The method further comprises: Collecting the first stress data of the detection area before pulse electromagnetic enhancement according to a preset number of times; Collecting second stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameter according to the preset number of times; Determining initial stress data of the detection area before pulse electromagnetic enhancement according to the average value of the first stress data; According to the average value of the second stress data, target stress data of the detection area after pulse electromagnetic strengthening according to the candidate process parameter is determined.

8. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: The method further comprises: The candidate process parameters include a first process parameter and a second process parameter; Among them, the first process parameters include a pulse electromagnetic frequency of 0.810-0.890 Hz, a magnetic field strength of 0.3-0.7 T, and a strengthening number of 4-6 times; the second process parameters include a pulse electromagnetic frequency of 0.810-0.890 Hz, a magnetic field strength of 0.3-0.7 T, and a strengthening number of 7-9 times.

9. The pulse electromagnetic strengthening method for low carbon martensitic stainless steel blades according to claim 1, characterized in that: The method further comprises: In the process of pulse electromagnetic strengthening the sample to be tested according to the candidate process parameters, the magnetic field intensity distribution data and surface stress data of the sample to be tested are collected in real time by a sensor located at a preset position; If the magnetic field intensity distribution data or the surface stress data do not meet the preset conditions, the device associated with the magnetic field intensity distribution data or the surface stress data that do not meet the preset conditions is controlled to be adjusted, so as to adjust the candidate process parameters in real time so that both the magnetic field intensity distribution data and the surface stress data meet the preset conditions.

10. A device for pulse electromagnetic strengthening of low-carbon martensitic stainless steel blades, characterized in that: The device comprises: a determination module, configured to determine stress distribution information of the blade to be tested under preset working conditions according to basic data of the blade to be tested, wherein the blade to be tested is a low-carbon martensitic stainless steel blade; and Sampling the blade to be tested according to the basic data and the stress distribution information to determine the sample to be tested of the blade to be tested; and Inputting the basic data and the stress distribution information into a target machine learning model to determine candidate process parameters of the blade to be tested, wherein the target machine learning model is trained based on historical pulse electromagnetic strengthening data of low-carbon martensitic stainless steel blades; and Performing pulse electromagnetic strengthening on the sample to be tested according to the candidate process parameters; and Determining target process parameters from the candidate process parameters according to the strengthening result of the sample to be tested; The strengthening module is used to perform pulse electromagnetic strengthening on the blade to be tested according to the target process parameters to obtain a target blade.

Images