Nondestructive testing method, system and equipment for mechanical properties of steel plate based on magnetic anisotropy and medium

Through the magnetic anisotropy method, the mechanical properties of steel plates are detected using the BP neural network model, which solves the problems of irreversible damage, time and error of traditional detection methods, realizes the lossless intelligent detection of steel plates, and improves the detection accuracy and speed.

CN119089278AInactive Publication Date: 2024-12-06上海能辛智能科技有限公司

Patent Information

Application Number
CN202411570145.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-06
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional steel plate mechanical properties detection methods have problems such as irreversible damage to the material, long detection time, large subjectivity and error, inability to online detection, and incomplete data collection of electromagnetic non-destructive testing technology and complex operation.

Method used

Using a method based on magnetic anisotropy, electromagnetic signal data is obtained through preset sampling frequency, preprocessing and 3MA analysis is performed, characteristic parameters are calculated using the BP neural network model to realize non-destructive detection, and the detection is carried out in combination with adaptive signal control cutting equipment.

Benefits of technology

It realizes lossless intelligent detection of the mechanical properties of steel plates, avoids waste of resources and environmental radiation pollution, and improves the accuracy and calculation speed of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089278A_ABST
    Figure CN119089278A_ABST
Patent Text Reader

Abstract

The invention relates to a nondestructive testing method, system and equipment for mechanical properties of a steel plate based on magnetic anisotropy and a medium, and belongs to the technical field of nondestructive testing. The method comprises the following steps: presetting a sampling frequency, setting a sampling point according to the sampling frequency, acquiring electromagnetic signal data of a magnetized steel plate through acquisition equipment according to the sampling point, and performing preprocessing according to the electromagnetic signal data to obtain preprocessed signal data; obtaining a characteristic parameter set of the preprocessed signal data, and obtaining related parameters through principal component analysis and calculation according to the characteristic parameter set; constructing a feature vector according to the related parameters, and calculating to obtain a detection result through a BP neural network model according to the feature vector; and marking the sampling points according to a detection result to obtain a marking point sequence, calculating through a diagnosis model according to the marking point sequence to obtain cutting points, and cutting the steel plate according to the cutting points. Nondestructive testing of the mechanical property of the steel plate and automatic cutting of the abnormal steel plate are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of nondestructive testing, and in particular relates to a method, system, equipment and medium for nondestructive testing of mechanical properties of steel plates based on magnetic anisotropy. Background Art

[0002] The mechanical properties of steel plates refer to their performance under external forces, including multiple important indicators, such as yield strength, tensile strength, hardness, elongation, and toughness. The mechanical properties of steel plates are crucial to structural design and material selection.

[0003] Traditionally, the mechanical properties of steel plates are tested mainly through sampling and tensile testing. This method has the following defects: (1) it causes irreversible damage to the material, rendering it unusable; (2) it takes a long time to test; and (3) it relies on manual observation and experimental analysis, which has certain subjectivity and errors, resulting in insufficient accuracy and sensitivity of the test results, and it is impossible to conduct online testing.

[0004] Existing online nondestructive testing methods for steel plates include X-ray testing, ultrasonic testing, magnetic particle testing, and penetration testing. These nondestructive testing methods have specific requirements for testing materials and environmental radiation pollution problems. The existing electromagnetic nondestructive testing technology uses one of the following methods for testing: magnetic Barkhausen noise, magnetic incremental permeability, multi-frequency eddy current, and tangential magnetic field harmonic analysis. These methods require specialized technicians to operate, and incomplete data collection results in low accuracy of test results. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a method, system, equipment and medium for nondestructive testing of mechanical properties of steel plates based on magnetic anisotropy; The purpose of the present invention can be achieved through the following technical solutions: S1: preset a sampling frequency, set up sampling points according to the sampling frequency, obtain electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; S2: Acquire a characteristic parameter set of the preprocessed signal data by 3MA analysis technology, and calculate relevant parameters by principal component analysis based on the characteristic parameter set; S3: constructing a feature vector according to the relevant parameters, and obtaining a detection result by calculating the feature vector through a BP neural network model; S4: Marking the sampling points according to the detection results to obtain a marked point sequence, calculating the cutting points through a diagnostic model according to the marked point sequence, and generating an adaptive signal according to the cutting points to control the cutting equipment to cut the steel plate.

[0006] Specifically, the electromagnetic signal data includes tangential magnetic field harmonic signals, Barkhausen noise signals, incremental magnetic permeability signals, and multi-frequency eddy current signals.

[0007] Specifically, the preprocessing includes filtering, removing DC bias, normalizing, and denoising.

[0008] Specifically, the characteristic parameter set includes electromagnetic characteristic parameters of tangential magnetic field harmonic analysis, Barkhausen noise detection characteristic parameters, incremental magnetic permeability detection characteristic parameters, and multi-frequency eddy current detection characteristic parameters.

[0009] Specifically, the specific calculation steps of the BP neural network model are: Transmitting the feature vector to the transmission layer, and calculating a hidden layer output vector according to the feature vector; Constructing a mapping relationship according to the hidden layer output vector to obtain a prediction result; A comparison threshold interval is preset, and the detection result is obtained by judging based on the comparison threshold interval and the prediction result. If the prediction result is within the comparison threshold interval, the detection result is normal; if the prediction result is not within the comparison threshold interval, the detection result is abnormal.

[0010] Specifically, the BP neural network model training process is: S201: Preset an initial BP neural network model, and initialize parameters and thresholds of the initial BP neural network model; S202: Acquire a training set, and calculate the prediction result by using the initial BP neural network model according to the training set; S203: Obtaining an expected output, and calculating a loss value through a loss function according to the prediction result and the expected output; S204: Obtain a new threshold and a new parameter by back propagation calculation according to the loss value, and replace the parameter and the threshold with the new parameter and the new threshold; S205: preset the stop iteration number, obtain the iteration number, and make a judgment based on the iteration number and the stop iteration number. If the iteration number is equal to the stop iteration number, exit the iteration; if the iteration number is less than the stop iteration number, repeat steps S202~S205.

[0011] Specifically, the diagnostic model includes: S301: judging the target point according to the target point sequence. If the detection result of the target point is normal, traverse the target point sequence in sequence and repeat step S301; if the detection result of the target point is abnormal, set the target point as point number one and execute step S302; S302: Determine point No. 2 according to point No. 1, sequentially traverse the target point sequence from point No. 1 and perform target point determination. If the detection result of the target point is abnormal, sequentially traverse the target point sequence and repeat step S302; if the detection result of the target point is normal, set the target point as point No. 3 and execute step S303; S303: Setting the second point and the third point as the cutting points.

[0012] Specifically, the related parameters include yield strength related parameters, tensile strength related parameters, hardness related parameters, toughness related parameters, and elongation related parameters, and the feature vector includes yield strength feature vector, tensile strength feature vector, hardness feature vector, toughness feature vector, and elongation feature vector.

[0013] A nondestructive testing system for mechanical properties of steel plates based on magnetic anisotropy, comprising: a data acquisition module, an analysis module, a detection module, and a control module; The data acquisition module is used to preset a sampling frequency, set up sampling points according to the sampling frequency, acquire electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; The analysis module is used to obtain a characteristic parameter set of the preprocessed signal data through a 3MA analysis technique, and calculate relevant parameters through principal component analysis based on the characteristic parameter set; The detection module is used to construct a feature vector according to the relevant parameters, and obtain a detection result by calculating the feature vector through a BP neural network model; The control module is used to mark the sampling points according to the detection results to obtain a mark point sequence, calculate the cutting points through the diagnostic model according to the mark point sequence, and generate an adaptive signal according to the cutting point to control the cutting equipment to cut the steel plate.

[0014] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy as described above is implemented.

[0015] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned non-destructive testing method for mechanical properties of steel plates based on magnetic anisotropy when executed by a computer processor.

[0016] The beneficial effects of the present invention are: (1) By setting up a collection device, the tangent magnetic field harmonic signal, Barkhausen noise signal, incremental permeability signal and multi-frequency eddy current signal of the magnetized steel plate are obtained through the collection device, thereby realizing the collection of multiple electromagnetic signal data, avoiding the incomplete data collection of the single electromagnetic non-destructive testing technology resulting in low accuracy of the test results, solving the problem of waste of resources caused by the loss of steel by traditional testing methods, and avoiding the specific requirements for the test materials and environmental radiation pollution of the existing online non-destructive testing methods for steel plates.

[0017] (2) By setting up a BP neural network, preprocessing and feature extraction are performed according to the acquired electromagnetic signal to obtain feature data, and the detection results are obtained by calculating the feature data through the BP neural network, thereby realizing non-destructive intelligent detection of steel plates and solving the problem of complex operation of traditional electromagnetic detection technology.

[0018] (3) The BP neural network has one input layer, one output layer, and three hidden layers. This improves the calculation speed while avoiding the problem of slowing down the calculation speed due to too many hidden layers. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0020] Figure 1 The present invention is a schematic flow chart of a method for nondestructive testing of mechanical properties of steel plates based on magnetic anisotropy. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments; See also Figure 1 , a nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy; S1: preset a sampling frequency, set up sampling points according to the sampling frequency, obtain electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; S2: Acquire a characteristic parameter set of the preprocessed signal data by 3MA analysis technology, and calculate relevant parameters by principal component analysis based on the characteristic parameter set; S3: constructing a feature vector according to the relevant parameters, and obtaining a detection result by calculating the feature vector through a BP neural network model; S4: Marking the sampling points according to the detection results to obtain a marked point sequence, calculating the cutting points through a diagnostic model according to the marked point sequence, and generating an adaptive signal according to the cutting points to control the cutting equipment to cut the steel plate.

[0022] Specifically, the electromagnetic signal data includes tangential magnetic field harmonic signals, Barkhausen noise signals, incremental magnetic permeability signals, and multi-frequency eddy current signals.

[0023] In this embodiment, the acquisition equipment consists of three parts: a 3MA electromagnetic detection device, a probe, and a computer. The 3MA electromagnetic detection device integrates four electromagnetic detection methods: Barkhausen noise detection, incremental magnetic permeability detection, multi-frequency eddy current detection, and tangential magnetic field harmonic analysis. The detection angle is controlled by rotating the probe through a computer. When the detection in one direction is completed, the probe rotates a certain angle to ensure that the detection equipment performs detection at the same position.

[0024] Specifically, the preprocessing includes filtering, removing DC bias, normalizing, and denoising.

[0025] Specifically, the characteristic parameter set includes electromagnetic characteristic parameters of tangential magnetic field harmonic analysis, Barkhausen noise detection characteristic parameters, incremental magnetic permeability detection characteristic parameters, and multi-frequency eddy current detection characteristic parameters.

[0026] Specifically, the electromagnetic characteristic parameters of the tangential magnetic field harmonic analysis include the third harmonic phase size, the fifth harmonic phase size, the seventh harmonic phase size, the third harmonic amplitude size, the fifth harmonic amplitude size, the seventh harmonic amplitude size, the deformation coefficient, the third harmonic phase amplitude sum, the fifth harmonic phase amplitude sum, the seventh harmonic phase amplitude sum, the harmonic amplitude at the zero point of the hysteresis loop, the coercive force size, and the stable voltage of the sensor coil; the Barkhausen noise detection characteristic parameters include the maximum amplitude, the amplitude within an excitation cycle, Mean, coercive magnetic field strength, residual magnetism point amplitude, 25% Barkhausen butterfly diagram width, 50% Barkhausen butterfly diagram width, 75% Barkhausen butterfly diagram width; the incremental permeability detection characteristic parameters include the maximum amplitude, the mean amplitude within an excitation cycle, the coercive magnetic field strength, the residual magnetism point amplitude, 25% permeability butterfly diagram width, 50% permeability butterfly diagram width, 75% permeability butterfly diagram width; the multi-frequency eddy current detection characteristic parameters include the imaginary part, real part, phase and amplitude of the coil impedance.

[0027] Specifically, the related parameters include yield strength related parameters, tensile strength related parameters, hardness related parameters, toughness related parameters, and elongation related parameters, and the feature vector includes yield strength feature vector, tensile strength feature vector, hardness feature vector, toughness feature vector, and elongation feature vector.

[0028] Specifically, the BP neural network model consists of an input layer, an output layer, and three hidden layers. The specific calculation steps are: Transmitting the feature vector to the transmission layer, and calculating a hidden layer output vector according to the feature vector; The hidden layer output vector calculation formula is: ; in, H j is the hidden layer output vector, f j () is the activation function between the input layer and the hidden layer, n is the dimension of the feature vector, w ij is the weight from the input layer to the hidden layer, X i is the i-th eigenvector, b is the neuron threshold, j is the number of hidden layer nodes, i is a variable parameter;

[0029] Constructing a mapping relationship according to the hidden layer output vector to obtain a prediction result; The prediction result calculation formula is: ; in, Y m To predict the results, f m () is the activation function of the hidden layer and the output layer, H i is the output vector of the i-th hidden layer, c is the output layer threshold, w im is the weight value between the hidden layer and the output layer, m is the output vector dimension, i is a variable parameter;

[0030] A comparison threshold interval is preset, and the detection result is obtained by judging based on the comparison threshold interval and the prediction result. If the prediction result is within the comparison threshold interval, the detection result is normal; if the prediction result is not within the comparison threshold interval, the detection result is abnormal.

[0031] In this embodiment, the activation function between the input layer and the hidden layer and the activation function between the hidden layer and the output layer both use the sigmoid function, and the activation function between the hidden layers is the tanh function.

[0032] Specifically, the BP neural network model training process is: S201: Preset an initial BP neural network model, and initialize parameters and thresholds of the initial BP neural network model; S202: Acquire a training set, and calculate the prediction result by using the initial BP neural network model according to the training set; S203: Obtaining an expected output, and calculating a loss value through a loss function according to the prediction result and the expected output; The loss function calculation formula is: ; in, E is the loss value, m is the output vector dimension, k is the independent variable, X To predict the results, Y is the expected output;

[0033] S204: Obtain a new threshold and a new parameter by back propagation calculation according to the loss value, and replace the parameter and the threshold with the new parameter and the new threshold; S205: preset the stop iteration number, obtain the iteration number, and make a judgment based on the iteration number and the stop iteration number. If the iteration number is equal to the stop iteration number, exit the iteration; if the iteration number is less than the stop iteration number, repeat steps S202~S205.

[0034] Specifically, the diagnostic model includes: S301: judging the target point according to the target point sequence. If the detection result of the target point is normal, traverse the target point sequence in sequence and repeat step S301; if the detection result of the target point is abnormal, set the target point as point number one and execute step S302; S302: Determine point No. 2 according to point No. 1, sequentially traverse the target point sequence from point No. 1 and perform target point determination. If the detection result of the target point is abnormal, sequentially traverse the target point sequence and repeat step S302; if the detection result of the target point is normal, set the target point as point No. 3 and execute step S303; It should be noted that the second point is the previous sampling point of the first point in the target point sequence; S303: Setting the second point and the third point as the cutting points.

[0035] A nondestructive testing system for mechanical properties of steel plates based on magnetic anisotropy, comprising: a data acquisition module, an analysis module, a detection module, and a control module; The data acquisition module is used to preset a sampling frequency, set up sampling points according to the sampling frequency, acquire electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; The analysis module is used to obtain a characteristic parameter set of the preprocessed signal data through a 3MA analysis technique, and calculate relevant parameters through principal component analysis based on the characteristic parameter set; The detection module is used to construct a feature vector according to the relevant parameters, and obtain a detection result by calculating the feature vector through a BP neural network model; The control module is used to mark the sampling points according to the detection results to obtain a mark point sequence, calculate the cutting points through the diagnostic model according to the mark point sequence, and generate an adaptive signal according to the cutting point to control the cutting equipment to cut the steel plate.

[0036] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy as described above is implemented.

[0037] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the above-mentioned non-destructive testing method for mechanical properties of steel plates based on magnetic anisotropy when executed by a computer processor.

[0038] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0039] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0040] The program code contained on the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language-such as Java, Smalltalk, C++, and also includes a conventional procedural programming language-such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0041] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy. It is characterized in that include: S1: preset a sampling frequency, set up sampling points according to the sampling frequency, collect electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; S2: Acquire a characteristic parameter set of the preprocessed signal data by 3MA analysis technology, and calculate relevant parameters by principal component analysis based on the characteristic parameter set; S3: constructing a feature vector according to the relevant parameters, and obtaining a detection result by calculating the feature vector through a BP neural network model; S4: Marking the sampling points according to the detection results to obtain a marked point sequence, calculating the cutting points through a diagnostic model according to the marked point sequence, and generating an adaptive signal according to the cutting points to control the cutting equipment to cut the steel plate.

2. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that The electromagnetic signal data includes tangential magnetic field harmonic signals, Barkhausen noise signals, incremental magnetic permeability signals, and multi-frequency eddy current signals.

3. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that The preprocessing includes filtering, removing DC bias, normalization and denoising.

4. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that The characteristic parameter set includes electromagnetic characteristic parameters of tangential magnetic field harmonic analysis, Barkhausen noise detection characteristic parameters, incremental magnetic permeability detection characteristic parameters, and multi-frequency eddy current detection characteristic parameters.

5. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that Specifically, the specific calculation steps of the BP neural network model are: Transmitting the feature vector to a transmission layer, and calculating a hidden layer output vector according to the feature vector; Constructing a mapping relationship according to the hidden layer output vector to obtain a prediction result; Preset a comparison threshold interval, and obtain the detection result by judging according to the comparison threshold interval and the prediction result, if the prediction result is within the comparison threshold interval, the detection result is normal; If the prediction result is not within the comparison threshold range, the detection result is abnormal.

6. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that The BP neural network model training process is: S201: Preset an initial BP neural network model, and initialize parameters and thresholds of the initial BP neural network model; S202: Acquire a training set, and calculate the prediction result by using the initial BP neural network model according to the training set; S203: Obtaining an expected output, and calculating a loss value through a loss function according to the prediction result and the expected output; S204: Obtain a new threshold and a new parameter by back propagation calculation according to the loss value, and replace the parameter and the threshold with the new parameter and the new threshold; S205: Preset the stop iteration number, obtain the iteration number, and make a judgment based on the iteration number and the stop iteration number. If the iteration number is equal to the stop iteration number, exit the iteration; If the number of iterations is less than the stop number of iterations, steps S202 to S205 are repeated.

7. The nondestructive testing method for mechanical properties of steel plates based on magnetic anisotropy according to claim 1, It is characterized in that The diagnostic model includes: S301: judging the target point according to the target point sequence. If the detection result of the target point is normal, traverse the target point sequence in sequence and repeat step S301; if the detection result of the target point is abnormal, set the target point as point number one and execute step S302; S302: Determine point No. 2 according to point No. 1, sequentially traverse the target point sequence from point No. 1 and perform target point determination. If the detection result of the target point is abnormal, sequentially traverse the target point sequence and repeat step S302; if the detection result of the target point is normal, set the target point as point No. 3 and execute step S303; S303: Setting the second point and the third point as the cutting points.

8. A non-destructive testing system for mechanical properties of steel plates based on magnetic anisotropy. It is characterized in that include: Data acquisition module, analysis module, detection module, control module; The data acquisition module is used to preset a sampling frequency, set up sampling points according to the sampling frequency, acquire electromagnetic signal data of the magnetized steel plate through a collection device according to the sampling points, and preprocess the electromagnetic signal data to obtain preprocessed signal data; The analysis module is used to obtain a characteristic parameter set of the preprocessed signal data through a 3MA analysis technique, and calculate relevant parameters through principal component analysis based on the characteristic parameter set; The detection module is used to construct a feature vector according to the relevant parameters, and obtain a detection result by calculating the feature vector through a BP neural network model; The control module is used to mark the sampling points according to the detection results to obtain a mark point sequence, calculate the cutting points through the diagnostic model according to the mark point sequence, and generate an adaptive signal according to the cutting point to control the cutting equipment to cut the steel plate.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method for nondestructive testing of mechanical properties of steel plates based on magnetic anisotropy as described in any one of claims 1 to 7 is implemented.

10. A storage medium containing computer executable instructions, It is characterized in that The computer executable instructions are used to execute the non-destructive testing method for mechanical properties of steel plates based on magnetic anisotropy as described in any one of claims 1 to 7 when executed by a computer processor.

Citation Information

Patent Citations

  • Silicon steel magnetic performance online detection method, device and equipment and storage medium

    CN114820224A

  • Silicon steel performance nondestructive testing method based on deep learning

    CN115186748A

  • Method for detecting mechanical property of steel plate

    CN116106402A

  • Method for measuring mechanical property of cold-rolled steel plate by non-destructive inspection

    JP1994308090A

Cited By

  • Material damage intelligent diagnosis method and system based on magnetic characteristic data fusion

    CN120195261A