Characteristic microstructure structure characterization method of ferromagnetic metal material

Abstract

The invention discloses a characterization method for a characteristic microstructure of a ferromagnetic metal material. The characterization method comprises the following steps: preparing a sample; based on an EBSD material characterization method, the microstructure of the ferromagnetic metal material is subjected to quantitative characterization, and the characteristic microstructure of the ferromagnetic metal material is obtained; the method comprises the following steps: based on multi-magnetic detection equipment, carrying out electromagnetic nondestructive detection on a ferromagnetic metal material to obtain electromagnetic signals representing reversible and irreversible motion of a magnetic domain, and defining and extracting corresponding electromagnetic characteristic parameters of the ferromagnetic metal material; the method comprises the following steps: taking electromagnetic characteristic parameters as input, modeling a characteristic microstructure on the basis of determining the characteristic microstructure, establishing a Light GBM model, and adjusting the parameters of the Light GBM model to obtain an optimal Light GBM model. According to the method, the recrystallization rate and the average grain size of the ferromagnetic metal material are taken as judgment standards, and the mode identification (classification) of the ferromagnetic metal material is realized through nondestructive testing.

Description

TECHNICAL FIELD

[0001] The present application relates to the electromagnetic nondestructive testing technology of ferromagnetic metal materials, and more particularly to a characterization method of characteristic microstructure of ferromagnetic metal materials. BACKGROUND

[0002] At present, steel plants at home and abroad mainly rely on optical microscopes, EBSD (Electron Back Scatter Diffraction, EBSD) and other equipment, supplemented by statistical analysis and the like to evaluate the microstructure of products. Such experimental methods cannot realize online detection, have long detection cycles, are not intelligent enough, and waste a lot of resources. Under the guidance of the concepts of carbon neutralization and green environmental protection, fast and nondestructive detection methods for microstructure are becoming more and more important.

[0003] In this field, the motion characteristics of magnetic domains have reversible motion of magnetic domains and irreversible motion of magnetic domains, and the incremental permeability technology based on reversible motion of magnetic domains and the magnetic Barkhausen technology based on irreversible motion of magnetic domains are feasible ways to realize detection of microstructure of materials. Under the excitation of an external magnetic field, different microstructures have different effects on the reversible and irreversible motion of magnetic domains, and also affect the structure of magnetic domains, so that electromagnetic nondestructive detection signals representing the reversible and irreversible motion of magnetic domains are extracted, analyzed and features are extracted, which can reflect the microstructure of the measured material.

[0004] Most of the current technologies focus on the detection method of mechanical properties of ferromagnetic metal materials, and the method for microstructure of ferromagnetic metal materials is also limited to destructive testing characterization technology, so there is no nondestructive testing technology that can directly characterize the microstructure of ferromagnetic metal materials. SUMMARY

[0005] In view of the defects in the prior art, the purpose of the present application is to provide a characterization method of characteristic microstructure of ferromagnetic metal materials, which realizes a nondestructive detection mode recognition (classification) method of ferromagnetic metal materials taking the recrystallization rate and average grain size of ferromagnetic metal materials as the judgment standard.

[0006] To achieve the above purpose, the present application adopts the following technical solutions:

[0007] A characterization method of characteristic microstructure of ferromagnetic metal materials comprises the following steps:

[0008] Preparation of a sample;

[0009] Based on the EBSD material characterization method, the microstructure of the ferromagnetic metal material is quantitatively characterized, and based on the correlation between the microstructure of the ferromagnetic metal material and the mechanical properties thereof, the characteristic microstructure of the ferromagnetic metal material is obtained.

[0010] Based on the multi-magnetic detection device, the electromagnetic nondestructive testing of the ferromagnetic metal material is performed to obtain the electromagnetic signal representing the reversible and irreversible motion of the magnetic domain, and the electromagnetic characteristic parameter of the ferromagnetic metal material is defined and extracted.

[0011] The electromagnetic characteristic parameter is taken as the input, and on the basis of determining the characteristic microstructure, the characteristic microstructure mode is established, the LightGBM model is established, and the LightGBM model parameter adjustment is performed to obtain the optimal LightGBM model.

[0012] Preferably, the characteristic microstructure characterization method specifically comprises the following steps:

[0013] S1, a wire cutting method is used to prepare a sample for EBSD material characterization method and a sample for multi-magnetic detection;

[0014] S2, the microstructure of the ferromagnetic metal material is quantitatively characterized by the EBSD material characterization method;

[0015] S3, the steps S1 and S2 are repeated to obtain the quantitative characterization results of the microstructure of different ferromagnetic metal materials;

[0016] S4, on the basis of step S1, the electromagnetic nondestructive testing of different ferromagnetic metal materials is performed by using the multi-magnetic detection device, and the electromagnetic characteristic parameter of the reversible and irreversible motion of the magnetic domain of the ferromagnetic metal material is extracted;

[0017] S5, according to the quantitative characterization results in step S3, the characteristic microstructure of the ferromagnetic metal material is obtained, and the correlation between the electromagnetic characteristic parameter of the ferromagnetic metal material obtained in step S4 is established;

[0018] S6, the characteristic microstructure is patterned;

[0019] S7, a LightGBM model is established;

[0020] S8, according to the process of steps S6 and S7, the LightGBM model is repeatedly trained ten times, and the average value of the ten training results is taken as the final detection value.

[0021] Preferably, in step S1, the size of the sample for EBSD material characterization method is 10mm*10mm;

[0022] The size of the sample for the magnetic Barkhausen noise detection is 150mm*600mm.

[0023] Preferably, the multi-magnetic detection device is integrated with the magnetic Barkhausen noise method, the incremental permeability method, the tangential magnetic field harmonic analysis method and the multi-frequency eddy current detection method.

[0024] Preferably, the multi-magnetic detection device uses the magnetic Barkhausen noise method and the incremental permeability method, and analyzes 12 electromagnetic characteristic parameters in total.

[0025] Preferably, the step S6 of patterning the characteristic microstructure is specifically:

[0026] According to the characteristic microstructure of the sample, different samples are given different identification codes, and the identification code is called a patterning result.

[0027] Preferably, in the step S7, the algorithm process of the LightGBM model includes:

[0028] 1) initializing the LightGBM model parameters;

[0029] 2) obtaining the optimal parameters;

[0030] 3) improving the LightGBM model by using OVR-Jacobian regularization;

[0031] 4) using the LightGBM fusion model for diagnosis.

[0032] The characteristic microstructure characterization method of the ferromagnetic metal material provided by the application has the following advantages:

[0033] (1) to realize the nondestructive testing of the characteristic microstructure (recrystallization rate and average grain size) of the ferromagnetic metal material, the detection accuracy is greater than 90%, the error is less than 10%, and the confidence rate is higher than 90%;

[0034] (2) provides a digital and rapid evaluation method for the microstructure characterization of the ferromagnetic metal material, thereby improving the detection efficiency and reducing the detection cost;

[0035] (3) realizes the rapid characterization of the characteristic microstructure of the ferromagnetic metal material. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is a flowchart of the characteristic microstructure characterization method of the application;

[0037] Figure 2 is a schematic diagram of the microstructure EBSD characterization result of step S2 in the characteristic microstructure characterization method of the application;

[0038] Figure 3 This is a schematic diagram showing the relationship between recrystallization rate and yield strength in step S3 of the microstructure characterization method of the present invention.

[0039] Figure 4 This is a schematic diagram of the probe structure of the multimagnetic detection device in step S4 of the microstructure characterization method of the present invention.

[0040] Figure 5 This is a schematic diagram of the MBN (MIP) butterfly curve in step S4 of the microstructure characterization method of the present invention;

[0041] Figure 6 This is a schematic diagram showing the relationship between the electromagnetic characteristic parameters and characteristic microstructure of ferromagnetic metal materials MBN and MIP in step S5 of the microstructure characterization method of the present invention. (a) is MBN and (b) is MIP.

[0042] Figure 7 This is a schematic diagram of the LightGBM model algorithm flow in step S7 of the microstructure characterization method of the present invention;

[0043] Figure 8 This is a schematic diagram of the evaluation results in step S8 of the microstructure characterization method of the present invention.

[0044] Figure 4 In the middle, 1-shell, 2-electronic board (preamplifier), 3-magnetic yoke, 4-electromagnetic coil, 5-connecting cable, 6-Hall sensor, 7-transmitter coil, 8-receiver coil, 9-electromagnetic non-destructive testing sample. Detailed Implementation

[0045] To better understand the above-mentioned technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0046] This invention provides a method for characterizing the characteristic microstructure of ferromagnetic metallic materials. Based on the EBSD material characterization method, it quantitatively characterizes the microstructure of ferromagnetic metallic materials. Based on the analysis of the intrinsic physical relationship between microstructure and mechanical properties, it determines the characteristic microstructure parameters that significantly influence the mechanical properties of ferromagnetic metallic materials. Simultaneously, using multi-magnetic detection equipment, it performs electromagnetic non-destructive testing on the ferromagnetic metallic materials to obtain electromagnetic characteristic parameters characterizing the magnetic properties of the material. Based on the determined characteristic microstructure, it patterns the characteristic microstructure. Using the electromagnetic characteristic parameters of the ferromagnetic metallic material as input and the patterned result of the characteristic microstructure as output, a LightGBM model of the characteristic microstructure based on the electromagnetic characteristic parameters of reversible and irreversible magnetic domain motion is established, thereby achieving non-destructive recognition of the material's characteristic microstructure pattern.

[0047] Ferromagnetic steel materials are cut into small sizes of 10mm*10mm (for material characterization using EBSD technology) and large sizes of 150mm*600mm (for detection by multi-magnetic detection equipment) using wire cutting.

[0048] Based on the EBSD material characterization method, the microstructure of ferromagnetic metal materials is quantitatively characterized. Furthermore, based on the correlation between the microstructure and mechanical properties of ferromagnetic metal materials, the characteristic microstructure of ferromagnetic metal materials is derived.

[0049] Based on multi-magnetic detection equipment, electromagnetic non-destructive testing is performed on ferromagnetic metallic materials to obtain electromagnetic signals characterizing the reversible and irreversible motion of magnetic domains, while defining and extracting the corresponding electromagnetic characteristic parameters of ferromagnetic metallic materials.

[0050] By analyzing the correlation between the electromagnetic characteristic parameters of the reversible and irreversible motion of magnetic domains in ferromagnetic metal materials and the characteristic microstructure of ferromagnetic metal materials, electromagnetic characteristic parameters that can be used as input are selected. At the same time, based on the determination of the characteristic microstructure, the characteristic microstructure is patterned and a LightGBM model is established. The parameters of the LightGBM model are adjusted to obtain the optimal LightGBM model, and finally the characteristic microstructure pattern recognition of ferromagnetic metal materials is achieved non-destructively.

[0051] The method for characterizing the feature microstructure of this invention specifically includes the following steps:

[0052] S1 uses wire cutting to process ferromagnetic steel materials into small sizes of 10mm*10mm (for material characterization in EBSD technology) and large sizes of 150mm*600mm (for detection by multi-magnetic detection equipment).

[0053] S2, The microstructure of ferromagnetic metallic materials was quantitatively characterized using the EBSD material characterization method. The quantitative characterization results are as follows: Figure 2 As shown.

[0054] S3. Repeat steps S1 and S2 to obtain the quantitative characterization results of the microstructure of different ferromagnetic metal materials. Simultaneously, based on the correlation analysis between the microstructure and mechanical properties of different ferromagnetic metal materials, it was found that as the recrystallization rate increases, the yield strength gradually decreases, and the grain size becomes more concentrated, leading to an increase in yield strength (e.g., ...). Figure 3 (As shown). From the overall trend analysis, it can be concluded that the characteristic microstructure of ferromagnetic metallic materials is the recrystallization rate.

[0055] S4, based on step S1, uses a multi-magnetic detection device to perform electromagnetic non-destructive testing on different ferromagnetic metal materials, and extracts electromagnetic characteristic parameters of the reversible and irreversible motion of magnetic domains in the ferromagnetic metal materials. The multi-magnetic detection device integrates multiple electromagnetic detection methods, applying different excitation magnetic fields to stimulate different electromagnetic principles, such as the magnetic Barkhausen noise method, incremental permeability method, tangential magnetic field harmonic analysis method, and multi-frequency eddy current detection method. During testing, different alternating magnetic field excitations are applied to the ferromagnetic material, from zero magnetic field excitation to positive saturation and back to zero magnetic field excitation, then increasing to negative saturation and back to zero magnetic field excitation. Throughout the entire repeated magnetization cycle, the magnetization process of different microstructures is different. The cumulative effect of magnetic domain motion leads to changes in the material's permeability, deepening the magnetization, and ultimately causing changes in the entire magnetization curve. The signals obtained in this process can reflect the magnetic properties and microstructural characteristics of different ferromagnetic materials.

[0056] The probe structure of multi-magnetic detection equipment is as follows Figure 4 As shown, the probe incorporates four micro-electromagnetic non-destructive testing techniques and selects 41 micro-electromagnetic properties to characterize the magnetic parameters of automotive sheet steel. However, in the micro-electromagnetic testing experiments, the characteristic parameters extracted by the tangential magnetic field strength detection technique showed poor stability, thus excluding this technique. The magnetic Barkhausen noise method (MBN) and incremental permeability method (MIP) were used in the experimental analysis, involving a total of 12 micro-electromagnetic properties.

[0057] In MBN technology, a high-amplitude, low-frequency sinusoidal current is fed into a yoke coil 4 wound around a U-shaped yoke 3. In order to ensure that the signal of irreversible magnetic domain motion is detected by the receiver coil 8, the applied magnetization amplitude is sufficient to excite the detected ferromagnetic material to reach a saturation level.

[0058] The detected MBN signal undergoes a combination of bandpass and low-pass / high-pass filters, followed by amplification, post-amplification, and signal smoothing rectification. The MBN butterfly curve is shown below. Figure 5As shown, it uses the digitally transformed and smoothed MBN amplitude timing signal as the vertical axis and the excitation magnetic field strength corresponding to the MBN amplitude signal as the horizontal axis, resulting in a butterfly diagram of the MBN signal (the curve shape resembles a butterfly with outstretched wings). From this, the maximum amplitude (the maximum value of the MBN signal, MMAX) can be derived as a test statistic. Correspondingly, the magnetic field strength at MMAX is assigned to the test statistic (the horizontal axis value corresponding to the maximum value, HCM). The expansion of the profile curve is evaluated at 25%, 50%, and 75% of MMAX (referred to as the width, defined as "the distance (width) between the two intersections of the vertical axis value at the 25%, 50%, and 75% positions of the maximum value with the two points of the butterfly diagram," DH25M, DH50M, and DH75M). An additional test statistic is MMEAN, which is the average value of the profile curve over a certain period (the average value of the MBN signal amplitude over one butterfly period).

[0059] During the reorganization of magnetic domains, displacement of the Bloch walls occurs, happening in a discrete, hopping manner. Bloch domain walls are influenced by different microstructures, thus exhibiting different motion characteristics. These microstructural variations can be reflected by the properties of the MBN. MMAX test statistics can be used to quantitatively obtain finishing conditions such as depth hardness and surface hardness. When grain boundaries represent the main barrier to Bloch wall displacement, HCM can be quantitatively correlated with grain size. Relationships between the expansion of profile curves (DH25M, DH50M, and DH75M) and internal stress or plastic deformation have been observed.

[0060] Unlike the MBN detection method, in the MIP technique, high- and low-frequency sinusoidal currents are necessary for obtaining reversible motion information. Similar to the MBN method, the high-amplitude, low-frequency (10–1000 Hz) excitation of the U-shaped yoke 3 generates hysteresis loops in the material. Simultaneously, a low-amplitude (milliampere level), high-frequency (10 kHz–1 MHz) sinusoidal current is required to be fed into the transmitter coil, similar to the MFEC method, to generate small asymmetric hysteresis loops that superimpose on the main hysteresis curve.

[0061] Similar to MBN, the maximum amplitude of the MIP (the maximum value of the signal, UMAX) is extracted as an important feature. The magnetic field strength at UMAX (the abscissa value at its maximum, HCU) is also derived as a statistical parameter. Furthermore, the curve extensions at 25%, 50%, and 75% (defined as above, DH25U, DH50U, and DH75U) and the average UMEAN over the time period are also used as MIP features. MIP can be used to characterize near-surface (surface hardened) material properties. Shell depth information is derived from the amplitude of the UMAX signal received from the core structure, and hardness information can be obtained from the associated forced field strength HCU. Stress state information is quantitatively described using curve extensions (DH25U, DH50U, and DH75U).

[0062] Electromagnetic nondestructive testing experiments were conducted on ferromagnetic metal material samples using a multi-magnetic detection device. This yielded 12 electromagnetic characteristic parameters, including MBN and MIP, as shown above. Each sample was tested for 120 seconds, resulting in more than 100 sets of electromagnetic characteristic data. After outlier cleaning, 100 sets of data were retained for subsequent analysis.

[0063] S5, based on the characteristic microstructure of the ferromagnetic metal material obtained in step S3, establish a correlation with the electromagnetic characteristic parameters of the ferromagnetic metal material obtained in step S4. Plot the MBN and MIP electromagnetic characteristic parameters of the ferromagnetic metal material on the ordinate and the characteristic microstructure of the ferromagnetic metal material on the abscissa, such as... Figure 6 As shown.

[0064] It can be observed that the electromagnetic characteristics and microstructures characterizing the reversible and irreversible motion of magnetic domains exhibit a monotonic trend. Therefore, the electromagnetic characteristics characterizing the reversible and irreversible motion of magnetic domains can be used to characterize the microstructures of ferromagnetic steel materials.

[0065] S6. As shown in step 5, there is a correlation between electromagnetic characteristics and characteristic microstructures, and electromagnetic characteristics can be used to characterize characteristic microstructures. Based on this, the characteristic microstructures are patterned, that is, different samples are assigned different identification codes (patterns) according to their characteristic microstructures (recrystallization rate and average grain size). This process is called patterning, and the identification codes are called patterning results. The results are shown in Table 1 below:

[0066] Table 1 Sample patterning results

[0067] Sample No. Recrystallization rate (%) Average grain size (pm 2 )]]> Pattern 6921 18.8 561.2 1 9632 23.1 340.9 2 0115 27.7 165.0 3 2305 33.3 577.7 4 0114 39.2 228.4 5 4396 51.0 362.1 6 0098 55.2 301.2 7 3290 67.1 305.8 8 3328 78.7 206.7 9 4681 78.8 141.3 10

[0068] S7, build the LightGBM model.

[0069] LightGBM is an improved model based on Gradient Boosting Decision Tree (GBDT), a machine learning algorithm developed by Microsoft in 2017. LightGBM is widely used in atmospheric science, such as early warning and forest convective weather, wind forecasting, and weather visibility prediction. These studies demonstrate that LightGBM can handle large-scale, multi-dimensional machine learning tasks.

[0070] LG is also based on GBDT and XB. Compared to the pre-sorted traversal algorithm used in Extreme Gradient Boost (XGBoost), the histogram splitting algorithm has higher training efficiency and effectively avoids overfitting. The basic idea is to discretize continuous floating-point feature values ​​into k integers and construct a histogram of width k. During data traversal, statistical information is accumulated in the histogram based on the discrete values ​​as indices. After one data traversal, the histogram accumulates the necessary statistical information. Then, the optimal split point is found by traversing the discrete values ​​of the histogram. LightGBM further optimizes the histogram algorithm. First, it abandons the level-wise decision tree growth strategy and adopts a depth-constrained leaf-by-leaf algorithm, ensuring high efficiency while preventing overfitting. Another optimization of LightGBM is the histogram of differential acceleration.

[0071] In pattern recognition, LightGBM directly supports categorical features (without requiring one-time encoding). In fact, most machine learning tools cannot directly support categorical features, generally requiring them to be converted into multi-dimensional one-hot encoded features, reducing space and time efficiency. LightGBM optimizes support for categorical features, allowing direct input of categorical features without the need for additional one-hot encoding extensions. Furthermore, it incorporates decision rules for categorical features into the decision tree algorithm, such as... Figure 7 As shown.

[0072] S8. Following steps S6 and S7, repeat the training process for the LightGBM model ten times, and take the average of the ten training results as the final detection value. The pattern recognition accuracy is greater than 95% (e.g., Figure 8 (As shown).

[0073] Example

[0074] This embodiment takes pickled steel from a cold-rolling production line in a steel plant as an example and proposes a method for characterizing the characteristic microstructure of ferromagnetic metallic materials. The specific flowchart is as follows: Figure 1 As shown. The quantitative characterization results of the microstructure are as follows. Figure 2 As shown. The relationship between microstructure and mechanical properties is as follows. Figure 3 As shown, the recrystallization rate of pickled steel can be determined based on its characteristic microstructure, and the pattern recognition results are shown in Table 1. Multi-magnetic detection equipment such as... Figure 4As shown. The signals characterizing reversible and irreversible magnetic domain motion are as follows: Figure 5 As shown. The relationship between the reversible and irreversible electromagnetic eigenvalues ​​of magnetic domains and the characteristic microstructure of pickled steel is as follows. Figure 6 As shown. Specifically, it includes the following steps:

[0075] LightGBM was established, using the MIP and MBN electromagnetic feature parameters, based on the theory of reversible and irreversible magnetic domain motion in pickled steel, as input, and the patterned results of the microstructure of pickled steel as output. The training set consisted of 296 data points, and the validation set consisted of 90 data points. Training was repeated ten times, and the average of the ten training results was used as the final detection value. The pattern recognition evaluation accuracy was greater than 95% (e.g., ...). Figure 8 (As shown).

[0076] Those skilled in the art should recognize that the above embodiments are merely illustrative of the present invention and are not intended to limit the present invention. Any variations or modifications to the above embodiments that are within the spirit and essence of the present invention will fall within the scope of the claims of the present invention.

Claims

1. A method for characterizing the characteristic microstructure of ferromagnetic metallic materials, characterized in that: Sample preparation; Based on the EBSD material characterization method, the microstructure of ferromagnetic metal materials is quantitatively characterized. At the same time, based on the correlation between the microstructure and mechanical properties of ferromagnetic metal materials, the characteristic microstructure of ferromagnetic metal materials is obtained. Based on multi-magnetic detection equipment, electromagnetic non-destructive testing is performed on ferromagnetic metal materials to obtain electromagnetic signals characterizing the reversible and irreversible motion of magnetic domains, while defining and extracting electromagnetic characteristic parameters of ferromagnetic metal materials. Using electromagnetic characteristic parameters as input, and based on the determination of the characteristic microstructure, the characteristic microstructure is patterned to establish a LightGBM model. The LightGBM model parameters are then adjusted to obtain the optimal LightGBM model.

2. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 1, characterized in that, The specific method for characterizing the feature microstructure is as follows. Includes the following steps: S1, using wire cutting, prepares samples for EBSD material characterization methods and samples for multimagnetic detection; S2, The microstructure of ferromagnetic metallic materials was quantitatively characterized using the EBSD material characterization method; S3. Repeat steps S1 and S2 to obtain the quantitative characterization results of the microstructure of different ferromagnetic metal materials. S4. Based on step S1, use a multi-magnetic detection device to perform electromagnetic non-destructive testing on different ferromagnetic metal materials, and extract the electromagnetic characteristic parameters of the reversible and irreversible motion of the magnetic domains of the ferromagnetic metal materials. S5. Based on the quantitative characterization results in step S3, the characteristic microstructure of the ferromagnetic metal material is obtained, and a correlation is established with the electromagnetic characteristic parameters of the ferromagnetic metal material obtained in step S4. S6, patterning the characteristic microstructure; S7, build the LightGBM model; S8. Following the process of steps S6 and S7, repeat the training of the LightGBM model ten times, and take the average of the ten training results as the final detection value.

3. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 2, characterized in that: In step S1, the sample size used for the EBSD material characterization method is 10mm*10mm. The sample size used for magnetic Barkhausen noise detection is 150mm*600mm.

4. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 3, characterized in that: The multi-magnetic detection device integrates the magnetic Barkhausen noise method, incremental permeability method, tangential magnetic field harmonic analysis method, and multi-frequency eddy current detection method.

5. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 4, characterized in that: The multi-magnetic detection device uses the magnetic Barkhausen noise method and the incremental permeability method to analyze a total of 12 electromagnetic characteristic parameters.

6. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 5, characterized in that, The 12 electromagnetic characteristic parameters are as follows: MBN includes MMAX, MMEAN, HCM, DH25M, DH50M, and DH75M; The MIP series includes UMAX, UMEAN, HCU, DH25U, DH50U, and DH75U.

7. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 6, characterized in that, The specific steps in step S6 of patterning the characteristic microstructure are as follows: Based on the characteristic microstructure of the sample, different samples are assigned different identification codes, which are called patterned results.

8. The method for characterizing the characteristic microstructure of ferromagnetic metallic materials according to claim 6, characterized in that, In step S7, the algorithm flow of the LightGBM model includes: 1) Initialize the LightGBM model parameters; 2) Obtain the optimal parameters; 3) The LightGBM model is improved using OVR-Jacobian regularization; 4) Use the LightGBM fusion model for diagnosis.

Images