Ferromagnetic material recrystallization rate rapid characterization method based on magnetic Barkhausen electromagnetic nondestructive testing
By combining magnetic Barkhausen electromagnetic nondestructive testing with deep neural networks, the problem of nondestructive testing of recrystallization rate of microstructure in ferromagnetic materials was solved, achieving high-precision, low-cost, and rapid testing.
Patent Information
- Application Number
- CN202410750867.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-12
- Publication Date
- 2025-12-12
AI Technical Summary
Existing technologies lack non-destructive testing methods to rapidly and accurately characterize the recrystallization rate of the microstructure of ferromagnetic materials, especially in component inspection during service life, which cannot meet the needs of smart factories.
By combining magnetic Barkhausen electromagnetic nondestructive testing with deep neural networks, a correlation model between characteristic microstructure and recrystallization rate is established by acquiring the electromagnetic characteristic parameters of ferromagnetic materials, thereby achieving nondestructive testing.
It enables non-destructive testing of the recrystallization rate of ferromagnetic materials with an accuracy greater than 95%, an error of less than 10%, and a confidence rate of more than 80%, thereby improving testing efficiency and reducing costs.
Smart Images
Figure CN121114191A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the electromagnetic nondestructive testing technology of ferromagnetic materials, and more particularly to a method for quickly characterizing the recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing. BACKGROUND
[0002] Currently, the steel plants at home and abroad mainly use sampling detection methods such as optical metallography, EBSD (Electron Back Scatter Diffraction, EBSD for short) and the like for detecting the recrystallization rate of the microstructure of the ferromagnetic materials produced by the steel plants. Such a destructive detection method is time-consuming, relies on a laboratory and does not conform to the concept of smart factory. For the ferromagnetic materials and components during service, defect detection and maintenance and hidden danger management are increasingly concerned about the changes in the microstate, and efforts are made to intervene and manage the microstate before defects and failures occur, so as to eliminate hidden dangers in the embryonic state and ensure the intrinsic safety. Therefore, there is an urgent need for advanced nondestructive testing technology to detect the microstructure state and mechanical properties before failure. In this field, electromagnetic detection technology, including electromagnetic nondestructive testing methods such as Barkhausen based on electromagnetic principles, is a feasible way to detect the microstructure and mechanical properties of materials. Since the electromagnetic detection characteristic signal is a response generated based on the movement of magnetic domains under the action of an external magnetic field, and the magnetic domain structure and movement are affected by the microstructure, the analysis of the electromagnetic nondestructive testing signal can reflect the microstructure of the material being tested.
[0003] Most of the current technologies focus on the mechanical property detection method of ferromagnetic materials, and the method for the microstructure of ferromagnetic materials is also limited to destructive testing characterization technology. Therefore, no nondestructive testing technology for directly detecting the recrystallization rate of the microstructure of ferromagnetic materials has been found. SUMMARY
[0004] In view of the defects in the prior art, the purpose of the present application is to provide a method for quickly characterizing the recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing, so as to realize nondestructive testing of the recrystallization rate of ferromagnetic materials.
[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:
[0006] A method for quickly characterizing the recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing comprises the following steps:
[0007] determining the characteristic microstructure of the ferromagnetic material;
[0008] The electromagnetic nondestructive testing is performed on the ferromagnetic material based on the magnetic Barkhausen noise detection equipment to obtain electromagnetic characteristic parameters representing the magnetic characteristics of the ferromagnetic material.
[0009] The characteristic microstructure deep neural network representation model of the magnetic Barkhausen characteristic parameters is established by taking the electromagnetic characteristic parameters as inputs and the characteristic microstructure as outputs, so as to realize the nondestructive testing of the characteristic microstructure-recrystallization rate of the ferromagnetic material.
[0010] Preferably, the ferromagnetic material recrystallization rate rapid representation method specifically comprises the following steps:
[0011] S1, preparing a sample for the EBSD material representation method and a sample for the magnetic Barkhausen noise detection;
[0012] S2, quantitatively representing the microstructure recrystallization rate of the ferromagnetic material by using the EBSD material representation method;
[0013] S3, repeating the step S1 and the step S2 to obtain the quantitative representation results of different ferromagnetic materials;
[0014] S4, on the basis of the step S1, performing electromagnetic nondestructive testing on the different ferromagnetic materials by using the magnetic Barkhausen noise detection equipment, and extracting electromagnetic characteristic parameters of the ferromagnetic materials;
[0015] S5, establishing a correlation between the characteristic microstructure of the ferromagnetic material obtained according to the quantitative representation results in the step S3 and the electromagnetic characteristic parameters of the ferromagnetic material obtained in the step S4;
[0016] S6, establishing a characteristic microstructure deep neural network representation model of the magnetic Barkhausen characteristic parameters;
[0017] S7, evaluating the accuracy of the characteristic microstructure deep neural network representation model by using the confidence degree;
[0018] S8, repeating the training of the characteristic microstructure deep neural network representation model ten times according to the process of the step S6 and the step S7, and taking the average of the ten training results as the final detection value.
[0019] Preferably, the size of the sample for the EBSD material representation method is 10mm*10mm.
[0020] The size of the sample for the magnetic Barkhausen noise detection is 150mm*600mm.
[0021] Preferably, the step S4 specifically comprises:
[0022] The test direction of the magnetic Barkhausen noise detection device is parallel to the rolling direction of the sample. During the test, the program-controlled chip AD9833 outputs a sinusoidal voltage with a frequency of 10 Hz and an amplitude of 600 mV, which is amplified by an isolation capacitor to a sinusoidal voltage with a frequency of 10 Hz and an amplitude of 6 V.
[0023] Then, the sinusoidal voltage is applied to the u-shaped yoke around the coil.
[0024] During the magnetization process, the MBN sensor is used to collect the MBN pulse signal.
[0025] Preferably, the acquisition card of the MBN sensor has an acquisition frequency of 15-40 kHz, and then is subjected to band-pass filtering and amplification processing.
[0026] Preferably, the MBN sensor uses an equal-interval sampling and smoothing filtering algorithm to preliminarily process the MBN pulse signal, and then uses a Hilbert-Huang transform algorithm to extract the intercepted MBN pulse signal and the smooth envelope signal of the MBN pulse signal, and further extracts electromagnetic characteristic parameters from the MBN pulse signal and the smooth envelope signal.
[0027] Preferably, the electromagnetic characteristic parameters include root mean square, ringing number, half-width, peak value, peak time and mean value.
[0028] Preferably, the root mean square is the root mean square value of the MBN pulse signal in one period, and the calculation formula is as follows:
[0029]
[0030] In the formula, x is the amplitude of the MBN pulse signal, and n is the number of the MBN pulse signal.
[0031] The ringing number is the number of pulses whose amplitudes exceed a certain threshold value from bottom to top in the MBN pulse signal, and the threshold value is 30% of the peak value.
[0032] The peak time is the difference between the time corresponding to the minimum of the smooth envelope signal and the time corresponding to the maximum of the smooth envelope signal.
[0033] The half-width is the distance between the intersection points of the smooth envelope signal when the vertical coordinate value is 50% of the maximum value, which is calculated based on the maximum value of the smooth envelope signal.
[0034] Preferably, in the training process of the characteristic microstructure depth neural network representation model of the magnetic Barkhausen characteristic parameter in step S6, logsig, tansig, purelin activation functions and trainlm training functions are used, the error threshold is set to 0.000001, the initial learning rate is set to 0.01, and the iteration number is set to 1000.
[0035] Preferably, in step S7, the confidence is defined as:
[0036]
[0037] In the formula, N 10 is the number of errors ρ between the model prediction value Y ci and the true value Y i in the verification set less than 10%, and N is the total number of the verification set, that is:
[0038]
[0039] The ferromagnetic material recrystallization rate fast characterization method provided by the application has the following beneficial effects:
[0040] (1) To realize the nondestructive testing of the characteristic microstructure-recrystallization rate of the ferromagnetic material, the detection accuracy is greater than 95%, the error is less than 10%, and the confidence rate is higher than 80%;
[0041] (2) A digital and fast evaluation method is provided for the microstructure characterization of the ferromagnetic material, thereby improving the detection efficiency and reducing the detection cost. BRIEF DESCRIPTION OF DRAWINGS
[0042] Figure 1 is a flowchart of the ferromagnetic material recrystallization rate fast characterization method of the application;
[0043] Figure 2 is a microstructure EBSD characterization result schematic diagram of step S2 in the ferromagnetic material recrystallization rate fast characterization method of the application;
[0044] Figure 3 is a schematic diagram of the relationship between the recrystallization rate and the yield strength in step S3 of the ferromagnetic material recrystallization rate fast characterization method of the application;
[0045] Figure 4 is a schematic diagram of the magnetic Barkhausen noise detection equipment in step S4 of the ferromagnetic material recrystallization rate fast characterization method of the application;
[0046] Figure 5These are typical MBN pulse signals in step S4 of the rapid characterization method for recrystallization rate of ferromagnetic materials in this invention. (a) is the MBN pulse signal waveform, and (b) is the MBN envelope signal waveform.
[0047] Figure 6 This is a schematic diagram showing the relationship between the electromagnetic characteristics of the ferromagnetic material MBN and the recrystallization rate of its characteristic microstructure in step S5 of the rapid characterization method for recrystallization rate of ferromagnetic materials in this invention.
[0048] Figure 7 This is a schematic diagram of the evaluation results in step S8 of the rapid characterization method for recrystallization rate of ferromagnetic materials in this invention. Detailed Implementation
[0049] 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.
[0050] The present invention provides a rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing. Based on material characterization techniques such as EBSD, the microstructure of ferromagnetic materials is quantitatively characterized. At the same time, based on the analysis of the intrinsic physical relationship between microstructure and mechanical properties, the characteristic parameters of microstructure that have a great influence on the mechanical properties of ferromagnetic materials are determined. This process is called determining the characteristic microstructure of ferromagnetic materials.
[0051] Electromagnetic nondestructive testing is performed on ferromagnetic materials using a magnetic Barkhausen noise (MBN) instrument to obtain electromagnetic parameters characterizing the magnetic properties of the ferromagnetic materials. At the same time, MBN electromagnetic characteristic parameters of ferromagnetic steel materials are defined and extracted.
[0052] Using electromagnetic characteristic parameters as input and characteristic microstructure as output, a deep neural network (DNN) representation model of the characteristic microstructure of magnetic Barkhausen characteristic parameters is established, thereby realizing non-destructive testing of the characteristic microstructure and recrystallization rate of ferromagnetic materials.
[0053] Combination Figure 1 As shown, the rapid characterization method for recrystallization rate of ferromagnetic materials of the present invention specifically includes the following steps:
[0054] S1 uses wire cutting technology to process ferromagnetic materials into small samples of 10mm*10mm (for EBSD material characterization methods) and large samples of 150mm*600mm (for magnetic Barkhausen noise detection).
[0055] S2, The recrystallization rate of the microstructure of ferromagnetic materials was quantitatively characterized using the EBSD material characterization method. The quantitative characterization results are as follows: Figure 2 As shown.
[0056] S3. Repeat steps S1 and S2 to obtain the quantitative characterization results of different ferromagnetic materials. Simultaneously, based on the correlation analysis between the microstructure and mechanical properties of different ferromagnetic 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). Analysis of the overall trend reveals that the characteristic microstructure of ferromagnetic materials is the recrystallization rate.
[0057] S4, based on step S1, electromagnetic non-destructive testing is performed on different ferromagnetic materials using a magnetic Barkhausen noise detector (MBN), and the MBN electromagnetic characteristic parameters of the ferromagnetic materials are extracted. An MBN system is used, which consists of an excitation circuit, a magnetic sensor, a signal conditioning circuit, an MBN signal acquisition circuit, and a scanning mechanism drive section, as shown below. Figure 4 As shown. The excitation section consists of a signal generator (AD9833 chip), a power amplifier, an excitation coil, and a magnetic yoke. It is used to drive the coil to generate a suitable alternating magnetic field to excite the Barkhausen effect and produce an external excitation magnetic field of a certain magnitude. The signal conditioning circuit is composed of a multi-stage amplifier circuit, including an RC filter circuit. The amplifier chip used is the instrumentation amplifier INA111 chip. The acquisition circuit inputs to the acquisition card through a voltage follower circuit and uses a DAQ-2010(G) acquisition card.
[0058] The test direction (the direction in which the probe generates the magnetic field) is parallel to the rolling direction of the sample. During testing, the AD9833 programmable chip outputs a sinusoidal voltage with a frequency of 10Hz and an amplitude of 600mV, which is amplified to a sinusoidal voltage with a frequency of 10Hz and an amplitude of 6V through an isolation capacitor. This sinusoidal voltage is then applied to a U-shaped yoke (800 turns of 1.5mm wire) around the coil. During magnetization, an MBN sensor (a receiving coil with a wire diameter of 0.1mm, approximately 2500 turns) is used to collect MBN pulse signals. A data acquisition card (DAQ-2010(G), sampling frequency 200kHz) acquires MBN pulse signals with a frequency of 15–40kHz, which are then amplified after bandpass filtering.
[0059] like Figure 5 As shown, the typical MBN pulse signal waveform is obtained. The MBN pulse signal is initially processed using an equal-interval sampling and smoothing filtering algorithm. Then, the Hilbert-Huang transform algorithm is used to extract the captured MBN pulse signal (e.g., ...). Figure 5 (a) The smooth envelope signal of the MBN pulse signal (as shown in blue in the image) Figure 5 (b) As shown in blue, electromagnetic characteristic parameters are then extracted from the MBN pulse signal and the smooth envelope signal, as shown in Table 1 below.
[0060] Table 1 MBN Feature Table
[0061]
[0062] Wherein, the root mean square (RMS) is the root mean square value of the MBN pulse signal within one period, and the calculation formula is as follows:
[0063]
[0064] In the formula, x is the amplitude of the MBN pulse signal, and n is the number of MBN pulse signals.
[0065] The ring count is determined by analyzing the MBN pulse signal, specifically the number of pulses whose amplitude exceeds a certain threshold from bottom to top. This threshold is 30% of the maximum value YMAX.
[0066] Peak time is the difference between the time corresponding to the minimum point of the smooth envelope signal and the time corresponding to the maximum point of the smooth envelope signal, obtained by analyzing the smooth envelope signal.
[0067] The half-width is the distance between the intersection points of the smooth envelope signal when the vertical coordinate value is 50% of the maximum value of the smooth envelope signal, calculated by analyzing the smooth envelope signal.
[0068] By using a magnetic Barkhausen noise detector (MBN) to perform electromagnetic nondestructive testing on ferromagnetic material samples, the six electromagnetic characteristic parameters of the MBN shown above can be obtained. Each sample is tested for 60 seconds, and more than 100 sets of electromagnetic characteristic data are obtained. After outlier cleaning, 100 sets of data are retained for subsequent analysis.
[0069] S5. Based on the characteristic microstructure of the ferromagnetic material obtained in step S3, establish a correlation between it and the MBN electromagnetic characteristic parameters of the ferromagnetic material obtained in step S4. Plot the MBN electromagnetic characteristic parameters of the ferromagnetic material on the ordinate and the recrystallization rate of the characteristic microstructure of the ferromagnetic material on the abscissa, such as... Figure 6 As shown, it can be found that the electromagnetic characteristic parameters and recrystallization rate of MBN exhibit a monotonic trend. Therefore, the electromagnetic characteristics extracted by MBN nondestructive testing technology can be used to characterize the characteristic microstructure of ferromagnetic materials - recrystallization rate.
[0070] S6. A deep neural network representation model of the microstructure of magnetic Barkhausen features was established, using a 3-hidden-layer DNN model (9, 10, and 21 nodes per layer). The MBN electromagnetic feature parameters of ferromagnetic materials were used as input, and the recrystallization rate (true value) of the microstructure of ferromagnetic materials was used as output. During the training of the deep neural network representation model, the logsig, tansig, and purelin activation functions and the trainlm training function were used. The error threshold was set to 0.000001, the initial learning rate was set to 0.01, and the number of iterations was set to 1000.
[0071] S7 uses confidence scores to evaluate the accuracy of the deep neural network representation model of the characteristic microstructure of the magnetic Barkhausen feature parameters. The confidence score is defined as:
[0072]
[0073] In the formula, N 10 To verify the predicted value Y of the ensemble model ci Compared with the true value Y i The number of validation sets with an error ρ less than 10%, where N is the total number of validation sets, i.e.:
[0074]
[0075] S8. Following steps S6 and S7, the deep neural network representation model of the characteristic microstructure of the magnetic Barkhausen feature parameters is trained ten times, and the average of the ten training results is taken as the final detection value. The evaluation accuracy of recrystallization rate is: under the condition that the error ρ is less than 10%, the confidence rate is greater than 80% (e.g., ...). Figure 7 (As shown).
[0076] Example
[0077] This embodiment takes pickled steel from a cold-rolling production line in a steel plant as an example and proposes a rapid characterization method for the recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing. 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. MBN testing equipment and systems include... Figure 4 As shown. The MBN signal is as follows. Figure 5 As shown in Table 1, the extracted eigenvalues are also shown. The relationship between the electromagnetic eigenvalues and characteristic microstructure of pickled steel MBN is as follows: Figure 6 As shown, it specifically includes:
[0078] A three-layer DNN model (with 9, 10, and 21 nodes per layer) was established, using the MBN electromagnetic characteristic parameters of pickled steel as input and the microstructure of pickled steel as output. The training set consisted of 145 data points, and the validation set consisted of 44 data points. During the training of the DNN model, activation functions "logsig", "tansig", and "purelin" and the training function "trainlm" were used. The error threshold was set to 0.000001, the initial learning rate was set to 0.01, and the number of iterations was set to 1000. Following the above modeling and training process, the training was repeated ten times, and the average of the ten training results was taken as the final detection value. The accuracy of the recrystallization rate assessment was greater than 95%: the confidence rate was greater than 80% while maintaining an error of less than 10% (e.g., ...). Figure 7 (As shown).
[0079] 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 rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing, characterized in that: Determine the characteristic microstructure of ferromagnetic materials; Electromagnetic nondestructive testing was performed on ferromagnetic materials using a magnetic Barkhausen noise detection device to obtain electromagnetic characteristic parameters characterizing the magnetism of the ferromagnetic material. Using electromagnetic property parameters as input and characteristic microstructure as output, a deep neural network representation model of the characteristic microstructure of magnetic Barkhausen characteristic parameters is established to achieve non-destructive testing of the characteristic microstructure-recrystallization rate of ferromagnetic materials.
2. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 1, characterized in that, The rapid characterization method for recrystallization rate of ferromagnetic materials specifically includes the following steps: S1, Prepare samples for EBSD material characterization methods and samples for magnetic Barkhausen noise detection; S2, The recrystallization rate of the microstructure of ferromagnetic materials was quantitatively characterized using the EBSD material characterization method; S3. Repeat steps S1 and S2 to obtain the quantitative characterization results of different ferromagnetic materials. S4. Based on step S1, electromagnetic non-destructive testing is performed on different ferromagnetic materials using a magnetic Barkhausen noise detection device, and the electromagnetic characteristic parameters of the ferromagnetic materials are extracted. S5. Based on the quantitative characterization results in step S3, establish a correlation between the characteristic microstructure of the ferromagnetic material obtained and the electromagnetic characteristic parameters of the ferromagnetic material obtained in step S4. S6. Establish a deep neural network representation model of the characteristic microstructure of magnetic Barkhausen feature parameters; S7 uses confidence level to evaluate the accuracy of the deep neural network representation model of the feature microstructure. S8. Following the process of steps S6 and S7, the deep neural network representation model of the feature microstructure is trained ten times, and the average of the ten training results is taken as the final detection value.
3. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 2, characterized in that: The sample size used for EBSD material characterization methods is 10mm*10mm; The sample size used for magnetic Barkhausen noise detection is 150mm*600mm.
4. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 3, characterized in that, Step S4 specifically includes: The test direction of the magnetic Barkhausen noise detection equipment is parallel to the rolling direction of the sample. During the test, the programmable chip AD9833 outputs a sinusoidal voltage with a frequency of 10Hz and an amplitude of 600mV, which is amplified into a sinusoidal voltage with a frequency of 10Hz and an amplitude of 6V through the isolation capacitor. Then, a sinusoidal voltage is applied to the U-shaped yoke around the coil; During the magnetization process, an MBN sensor is used to collect MBN pulse signals.
5. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 4, characterized in that: The MBN sensor's acquisition card has a acquisition frequency of 15–40 kHz, which is then amplified by bandpass filtering.
6. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 5, characterized in that: The MBN sensor uses an equal-interval sampling and smoothing filtering algorithm to perform preliminary processing on the MBN pulse signal. Then, the Hilbert-Huang transform algorithm is used to extract the intercepted MBN pulse signal and the smoothed envelope signal of the MBN pulse signal. Finally, electromagnetic feature parameters are extracted from the MBN pulse signal and the smoothed envelope signal.
7. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 6, characterized in that: The electromagnetic characteristic parameters include root mean square, number of rings, half-width at half-maximum, peak value, peak time, and mean value.
8. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 7, characterized in that: The root mean square (RMS) is the root mean square value of the MBN pulse signal within one period, and the calculation formula is as follows: In the formula, x is the amplitude of the MBN pulse signal, and n is the number of MBN pulse signals; The ring count is the number of pulses whose amplitude of the MBN pulse signal exceeds a certain threshold from bottom to top, determined by analyzing the MBN pulse signal. This threshold is 30% of the peak value. The peak time is the difference between the time corresponding to the minimum point of the smooth envelope signal and the time corresponding to the maximum point of the smooth envelope signal, obtained by analyzing the smooth envelope signal. The half-height width is the distance between the intersection points of the smooth envelope signal when the vertical coordinate value is 50% of the maximum value of the smooth envelope signal, calculated by analyzing the smooth envelope signal.
9. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 2, characterized in that: In step S6, during the training process of the deep neural network representation model of the feature microstructure of the magnetic Barkhausen feature parameters, the logsig, tansig, purelin activation functions and trainlm training function are used, the error threshold is set to 0.000001, the initial learning rate is set to 0.01, and the number of iterations is set to 1000.
10. The rapid characterization method for recrystallization rate of ferromagnetic materials based on magnetic Barkhausen electromagnetic nondestructive testing according to claim 9, characterized in that, In step S7, the confidence level is defined as: In the formula, N 10 To verify the predicted value Y of the ensemble model ci Compared with the true value Y i The number of validation sets with an error ρ less than 10%, where N is the total number of validation sets, i.e.: