Non-destructive testing methods and devices for ferromagnetic pipe defects

Abstract

This invention provides a non-destructive testing method and apparatus for defects in ferromagnetic pipes, belonging to the field of pipe inspection. The method includes: acquiring a voltage signal, which is obtained by converting the capacitance change signal continuously collected by the bipolar capacitor as the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitor move at a constant axial velocity relative to each other; extracting time-domain and frequency-domain features from the voltage signal; and determining the defect type and location based on the voltage signal and the extracted features. The extracted features include time-domain and frequency-domain features; the time-domain features include the signal standard deviation, coefficient of variation, and density of local extrema; and the frequency-domain features include the dominant frequency component and harmonic energy ratio. This method utilizes the physical property that the dielectric constant of a ferromagnetic pipe differs depending on whether it has defects or not, enabling the detection of defects deep within the component. It effectively avoids interference from various environmental electromagnetic noises, ensuring the accuracy of the detection results, and eliminates the need for point-by-point scanning, resulting in higher detection efficiency.

Description

Technical Field

[0001] This invention relates to the field of pipeline inspection, and in particular to a non-destructive testing method and apparatus for defects in ferromagnetic pipelines. Background Technology

[0002] Pipelines are widely used in the petroleum and chemical industries as important means of transporting media such as oil, gas, and water. However, with the increase in the service life of pipelines, they are susceptible to corrosion, cracks, and damage due to the harsh operating environment, which reduces their safety and reliability and creates safety hazards.

[0003] Currently, for non-destructive testing of ferromagnetic pipes, electromagnetic ultrasonic testing is used. This method applies excitation and receives the detection signal through electromagnetic coupling. However, because various environmental noises can be superimposed on the received acoustic signal, the received signal is noisy, and defect echo signals are easily submerged in the noise and difficult to observe, leading to low reliability of the test results. Another method, eddy current testing, can only detect surface and near-surface defects in conductive materials. When eddy currents flow in a conductor, their density rapidly decreases as they penetrate the material surface (skin effect). This means that eddy currents are primarily sensitive to surface and near-surface defects, and their detection capability for defects deeper than several millimeters typically drops sharply. They cannot be used to detect defects inside thick components. Furthermore, eddy current testing involves point-by-point scanning, resulting in relatively low detection efficiency, and large-area scanning is time-consuming. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a method and apparatus for non-destructive testing of defects in ferromagnetic pipes.

[0005] This invention provides a non-destructive testing method for defects in ferromagnetic pipes, comprising: acquiring a capacitance change signal continuously collected by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitors move relative to each other at a constant speed in the axial direction, wherein a constant external excitation voltage is applied to the bipolar capacitor; converting the capacitance change signal into a voltage signal, and extracting time-domain features and frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time; determining the defect category and defect location based on the voltage signal and the extracted features, wherein the extracted features include the time-domain features and the frequency-domain features; wherein the time-domain features include the signal standard deviation, coefficient of variation, and density of local extrema, and the frequency-domain features include the dominant frequency component and the harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the total energy of the voltage signal.

[0006] According to the present invention, a non-destructive testing method for defects in ferromagnetic pipes is provided. The step of determining the defect category and defect location based on the voltage signal and the extracted features includes: inputting the extracted features into a trained machine learning model to obtain the defect category; wherein the defect category includes corrosion, cracks, and holes; wherein the defect category includes corrosion, cracks, and holes, and the machine learning model is trained based on samples labeled with defect categories and the extracted features.

[0007] According to the present invention, a non-destructive testing method for defects in ferromagnetic pipes is provided, wherein determining the defect type and defect location based on the voltage signal and extracted features includes: based on... Determine the axial location of the defect Where v is the speed at which the pipe moves. The voltage signal is referred to here.

[0008] According to the present invention, a non-destructive testing method for defects in ferromagnetic pipes is provided, wherein determining the defect category and defect location based on the voltage signal and extracted features includes determining the circumferential position based on the circumferential defect distribution matrix M(θ). ,in:

[0009] ;

[0010] ;

[0011] Where N is the number of sampling points in a single circumferential scan. For the Dirac sampling function, , The voltage signal is a discrete signal, and θ is the angular coordinate of the capacitor plates. The coordinates are the axial position coordinates of the defect.

[0012] According to the present invention, a non-destructive testing method for defects in ferromagnetic pipes is provided, wherein determining the defect type and defect location based on the voltage signal and extracted features includes:

[0013] according to Determine the depth of the defect;

[0014] Where k1 and k2 are nonlinear mapping coefficients, This is the reference value for the standard deviation of the voltage signal corresponding to a defect-free pipe of the same specification. The standard deviation of the voltage signal of the ferromagnetic pipe under inspection. Harmonic energy The voltage signal energy.

[0015] According to the present invention, a non-destructive testing method for defects in ferromagnetic pipes is provided. The defect location includes axial position, circumferential position, and depth position. Correspondingly, after determining the defect type and defect location based on the voltage signal and extracted features, the method further includes outputting a three-dimensional defect topology map G(z,θ,γ) containing the defect location, wherein:

[0016] ;

[0017] in, For axial error, For circumferential error, , , These represent the coordinates of axial position, circumferential position, and depth position, respectively. and Here are the axial and circumferential coordinates of the defect. These are the coordinates of the defect depth.

[0018] This invention also provides a non-destructive testing device for defects in ferromagnetic pipes, comprising: a data acquisition module for acquiring a voltage signal, wherein the voltage signal is obtained by converting the capacitance change signal continuously acquired by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitors move at a constant speed relative to each other in the axial direction, wherein a constant external excitation voltage is applied to the bipolar capacitor; an extraction module for converting the capacitance change signal into a voltage signal, and extracting time-domain features and frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time; and a processing module for determining the defect type and defect location based on the voltage signal and the extracted features, wherein the extracted features include the time-domain features and the frequency-domain features; wherein the time-domain features include the signal standard deviation, coefficient of variation, and density of local extrema, and the frequency-domain features include the dominant frequency component and the harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the total energy of the voltage signal.

[0019] The present invention also provides a non-destructive testing system for defects in ferromagnetic pipelines, comprising: upper and lower semi-circular arc-shaped capacitor plates, a signal converter, a signal amplifier, and the aforementioned non-destructive testing device for defects in ferromagnetic pipelines; the upper and lower semi-circular arc-shaped capacitor plates are divided into upper and lower parts, parallel to the ferromagnetic pipeline, and an external excitation voltage is applied; the signal converter is used to convert the capacitance change signal output by the upper and lower semi-circular arc-shaped capacitor plates into a voltage signal, which is then amplified by the signal amplifier and sent to the non-destructive testing device for defects in ferromagnetic pipelines.

[0020] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the non-destructive testing method for ferromagnetic pipe defects as described above.

[0021] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the non-destructive testing method for ferromagnetic pipe defects as described above.

[0022] The present invention provides a non-destructive testing method and apparatus for ferromagnetic pipeline defects. Utilizing the physical property that ferromagnetic pipelines have different dielectric constants in different states with and without defects, when the ferromagnetic pipeline to be tested moves parallel to the probe axis between bipolar plates, the capacitance value between the plates changes with the dielectric constant. By detecting the change in capacitance signal, the presence and location of defects in the ferromagnetic pipeline can be determined. This method can detect defects deep within the components and effectively avoids interference from various environmental electromagnetic noises, ensuring the accuracy of the test results. It eliminates the need for point-by-point scanning, resulting in higher testing efficiency. By extracting the time-domain characteristic standard deviation, coefficient of variation, local extremum density, dominant frequency components, harmonic energy ratio, and frequency domain characteristics, the location and type of defects can be accurately determined. Therefore, it can be widely applied to defect detection in various pipelines such as oil and gas pipelines, power pipelines, and water conservancy pipelines. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating the non-destructive testing method for ferromagnetic pipe defects provided by the present invention.

[0025] Figure 2 This is a structural diagram of the upper and lower semi-circular bipolar plate capacitor provided by the present invention;

[0026] Figure 3 This is the electric field diagram of the pipeline structure provided by the present invention when there are no defects;

[0027] Figure 4 This is an electric field diagram of the pipeline structure provided by the present invention when there are defects;

[0028] Figure 5 This is a schematic diagram of the non-destructive testing device for ferromagnetic pipe defects provided by the present invention;

[0029] Figure 6 This is a schematic diagram of the non-destructive testing system for ferromagnetic pipe defects provided by the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention;

[0031] Explanation of reference numerals in the attached diagram: 1. Ferromagnetic pipe; 2. Upper and lower semi-circular bipolar capacitor; 3. Defect. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0033] The following is combined Figures 1-7 The present invention describes a non-destructive testing method and apparatus for defects in ferromagnetic pipes. Figure 1 This is a flowchart illustrating the non-destructive testing method for ferromagnetic pipe defects provided by the present invention, as shown below. Figure 1 As shown, the present invention provides a non-destructive testing method for defects in ferromagnetic pipes, comprising:

[0034] 101. Obtain a voltage signal, wherein the voltage signal is obtained by converting the capacitance change signal continuously collected by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitor move at a constant speed relative to each other in the axial direction, wherein a constant external excitation voltage is applied to the bipolar capacitor.

[0035] Bipolar capacitor with upper and lower semicircular arcs, such as Figure 2 As shown, the capacitor plates consist of two semi-circular arc-shaped metal conductor plates, separated by a dielectric material. The external excitation voltage can be AC ​​or DC. By applying an excitation AC / DC voltage to the outside of the semi-circular arc-shaped bipolar plate structure, an alternating / steady-state electric field is formed between the capacitor plates.

[0036] When an excitation voltage is applied to the two plates, the plates will carry different charges. Due to the presence of these charges, an electric field will be formed in the region between the plates, such as... Figure 3 As shown, due to the edge effect of the electric field, the electric field lines at the edges of the capacitor plates will be curved and diverge. When the pipe to be inspected moves between the plates, the dielectric constant between the plates will change due to defects such as cracks and corrosion, thus changing the capacitance value between the plates. Defects can be detected by detecting the capacitance change signal.

[0037] When there are defects in the pipeline structure, the electric field is as follows: Figure 4 As shown, the upper and lower semi-circular bipolar plate structure (1) can pass through the gap of the pipe (2) at a constant speed v≤0.5m / s to detect defects (3).

[0038] The capacitance change signal is converted into a voltage signal for detection and judgment, which facilitates signal processing.

[0039] 102. Extract time-domain features from the voltage signal and extract frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time. The time-domain features include the signal standard deviation, coefficient of variation, and density of local extrema; the frequency-domain features include the dominant frequency component and the harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the total energy of the voltage signal.

[0040] This includes operations such as filtering, amplification, and feature extraction of the voltage signal. In this invention, time-domain and frequency-domain features are extracted from the voltage signal separately to improve detection accuracy.

[0041] In the specific process, environmental electromagnetic interference (frequency range: 0.1-10 kHz) and power frequency noise can be eliminated by bandpass filtering. The gain of the capacitor-to-voltage conversion signal is adjusted by an instrumentation amplifier (gain coefficient: 40-60dB), and a standardized voltage signal V(t) is output, where t is the time series of the axial displacement of the pipeline.

[0042] Perform time-frequency domain joint analysis on V(t) to extract a vector containing the following features:

[0043] Time-domain characteristics: signal standard deviation σ v Coefficient of variation C v Local extreme point density ρ peak ;

[0044] Frequency domain characteristics: The dominant frequency component f is obtained through Fast Fourier Transform (FFT). dominant and harmonic energy ratio E harmonic / E.

[0045] 103. Based on the voltage signal and the extracted features, determine the defect category and defect location. The extracted features include the time-domain features and the frequency-domain features.

[0046] By using computational methods such as inversion models, the defect type and location are finally determined based on the extracted features.

[0047] A machine learning inversion model based on physical constraints can be established, where the results... Defect parameter vector These correspond to defect type, defect depth, and defect location, respectively, and feature vectors. include These correspond to the signal standard deviation, coefficient of variation, density of local extrema, and dominant frequency component, respectively. Furthermore, in some embodiments, the extracted features also include constitutive parameters of the pipe material. , Including the initial dielectric constant of the pipe And the pipe wall thickness, such an inversion model can be used for The inversion model F can employ a transfer learning framework, through parameter... It can adaptively match pipes of different specifications.

[0048] Defect type detection can be achieved using a support vector machine classifier and a transfer learning framework, when the pipe material parameter P... m When changes occur, the weight matrix can be automatically adjusted.

[0049] The main theoretical basis for detecting pipeline defects through voltage changes is as follows:

[0050] The formula for calculating a semi-circular arc capacitor can be derived from the formula:

[0051]

[0052] Where C represents capacitance, denoted by , h represents the relative permittivity of the dielectric, r represents the height of the capacitor plates, and k represents the electrostatic constant.

[0053] The formula for calculating the voltage across the plates of a semi-circular capacitor is:

[0054]

[0055] Where Q represents the charge on the capacitor plates, and U represents the voltage across the capacitor plates. The relative permittivity can be obtained by measurement, specifically by detecting the capacitance of a semi-circular capacitor plate under vacuum conditions. The undamaged ferromagnetic pipe to be tested is placed between the plates of a semi-circular capacitor, and the capacitance value is measured. The relative permittivity of the pipe under test was calculated. .

[0056] The ferromagnetic pipe under test moves in a direction parallel to the probe axis; pipes with defects... Compared to defect-free pipelines The differences will cause the capacitance value of the capacitor plates to change.

[0057] This invention provides a non-destructive testing method for ferromagnetic pipeline defects. It utilizes the physical property that the dielectric constant of a ferromagnetic pipeline varies depending on whether it has defects or not. When the ferromagnetic pipeline under test moves parallel to the probe axis between bipolar plates, the capacitance between the plates changes with the dielectric constant. By detecting the change in capacitance signal, the presence and location of defects in the ferromagnetic pipeline can be determined. This method can detect defects deep within the structure and effectively avoids interference from various environmental electromagnetic noises, ensuring the accuracy of the test results. It eliminates the need for point-by-point scanning, resulting in higher testing efficiency. By extracting the time-domain characteristic standard deviation, coefficient of variation, local extremum density, dominant frequency components, harmonic energy ratio, and frequency domain characteristics, the location and type of defects can be accurately determined. Therefore, it can be widely applied to defect detection in various pipelines such as oil and gas pipelines, power pipelines, and water conservancy pipelines.

[0058] This method has strong engineering applicability, with a processing time complexity of O(nlogn), which meets the requirements for real-time detection (delay <50 ms when sampling rate ≥1 kHz).

[0059] In some embodiments, determining the defect category and defect location based on the voltage signal and extracted features includes: inputting the extracted features into a trained machine learning model to obtain a defect category; wherein the defect category includes corrosion, cracks, and holes; wherein the defect category includes corrosion, cracks, and holes, and the machine learning model is trained by obtaining the extracted features from samples labeled with defect categories. The machine learning model can employ the support vector machine classifier mentioned above and be implemented through a transfer learning framework.

[0060] In some embodiments, determining the defect category and defect location based on the voltage signal and extracted features includes: based on Determine the axial location of the defect Where v is the speed at which the pipe moves. The voltage signal is referred to here.

[0061] In some embodiments, determining the defect category and defect location based on the voltage signal and the extracted features includes determining the circumferential location based on the circumferential defect distribution matrix M(θ). ,in:

[0062] ;

[0063] ;

[0064] Where N is the number of sampling points in a single circumferential scan. For the Dirac sampling function, , The voltage signal is a discrete signal, and θ is the angular coordinate of the capacitor plates. Let θ be the axial position coordinates of the defect. In this embodiment of the invention, a circumferential defect distribution matrix M(θ,z) is constructed based on the bipolar differential signal ΔV(t).

[0065] In some embodiments, determining the defect category and defect location based on the voltage signal and the extracted features includes:

[0066] according to Determine the depth of the defect ;

[0067] Where k1 and k2 are nonlinear mapping coefficients, which can be determined through calibration experiments. This is the reference value for the standard deviation of the voltage signal corresponding to a defect-free pipe of the same specification. The standard deviation of the voltage signal of the ferromagnetic pipe under inspection. Harmonic energy The voltage signal energy.

[0068] In some embodiments, the defect location includes axial location, circumferential location, and depth location. Accordingly, after determining the defect category and defect location based on the voltage signal and extracted features, the method further includes outputting a three-dimensional defect topology map G(z,θ,γ) containing the defect location, wherein:

[0069] ;

[0070] in, For axial error, For circumferential error, , , These represent the coordinates of axial position, circumferential position, and depth position, respectively. and Here are the axial and circumferential coordinates of the defect. These are the coordinates of the defect depth.

[0071] Among them, when taking values, it is possible to , This ensures that the defect positioning accuracy meets the requirements of ±2mm for axial error and ±3° for circumferential error. A defect topology map G(z,θ,γ) can be dynamically generated via a real-time display terminal.

[0072] The non-destructive testing device for ferromagnetic pipe defects provided by the present invention is described below. The non-destructive testing device for ferromagnetic pipe defects described below can be referred to in correspondence with the non-destructive testing method for ferromagnetic pipe defects described above.

[0073] Figure 5This is a schematic diagram of the non-destructive testing device for ferromagnetic pipe defects provided by the present invention, as shown below. Figure 5 As shown, the non-destructive testing device for defects in ferromagnetic pipes includes: an acquisition module 501, an extraction module 502, and a processing module 503. The acquisition module 501 acquires a voltage signal, which is obtained by converting the capacitance change signal continuously acquired by the bipolar capacitor as the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitors move at a constant axial velocity relative to each other. A constant external excitation voltage is applied to the bipolar capacitor. The extraction module 502 extracts time-domain features and frequency-domain features from the voltage signal, where time is the independent variable. The processing module 503 determines the defect type and location based on the voltage signal and the extracted features. The extracted features include the time-domain features and the frequency-domain features. The time-domain features include the signal standard deviation, coefficient of variation, and local extremum density. The frequency-domain features include the dominant frequency component and the harmonic energy ratio, where the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the total voltage signal energy.

[0074] Figure 6 This is a schematic diagram of the non-destructive testing system for ferromagnetic pipe defects provided by the present invention, as shown below. Figure 6 As shown, the non-destructive testing system for ferromagnetic pipe defects includes:

[0075] The device comprises upper and lower semi-circular arc-shaped capacitor plates, a signal converter, a signal amplifier, and the non-destructive testing device for ferromagnetic pipe defects described in the above embodiment. The upper and lower semi-circular arc-shaped capacitor plates are divided into upper and lower parts, parallel to the ferromagnetic pipe, and an external excitation voltage is applied. The signal converter is used to convert the capacitance change signal output by the upper and lower semi-circular arc-shaped capacitor plates into a voltage signal, which is then amplified by the signal amplifier and sent to the non-destructive testing device for ferromagnetic pipe defects.

[0076] Among them, the capacitor plate type defect detection structure is a semi-circular capacitor plate structure that can completely surround the ferromagnetic pipe to be inspected, so as to achieve comprehensive inspection.

[0077] The sensor detects the capacitance change of the upper and lower semi-circular arc-shaped capacitor plates, and the capacitance signal is converted into a voltage signal by a signal converter. The resulting voltage signal is relatively weak and needs to be amplified by a signal amplifier. After amplification, the voltage signal is sent to the non-destructive testing device for ferromagnetic pipeline defects. The device filters the signal to remove interference, and performs amplification, feature extraction, and inversion model calculation. Through this series of signal processing steps, the location and type of pipeline defects are determined.

[0078] The apparatus (system) embodiments provided in this invention are for implementing the above-described method embodiments. For specific processes and details, please refer to the above-described method embodiments, which will not be repeated here.

[0079] The non-destructive testing device (system) for ferromagnetic pipeline defects provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned embodiment of the non-destructive testing method for ferromagnetic pipeline defects. For the sake of brevity, any parts not mentioned in the embodiment of the non-destructive testing device (system) for ferromagnetic pipeline defects can be referred to the corresponding content in the aforementioned embodiment of the non-destructive testing method for ferromagnetic pipeline defects.

[0080] Figure 7 As shown in Figure 7, the electronic device provided by the present invention may include: a processor 701, a communication interface 702, a memory 703, and a communication bus 704. The processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704. The processor 701 can call logic instructions in the memory 703 to execute a non-destructive testing method for defects in ferromagnetic pipes. This method includes: acquiring a capacitance change signal continuously collected by the bipolar capacitor as the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitors move relative to each other at a constant axial velocity, wherein a constant external excitation voltage is applied to the bipolar capacitor; converting the capacitance change signal into a voltage signal, and extracting time-domain features and frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time; determining the defect category and defect location based on the voltage signal and the extracted features, wherein the extracted features include the time-domain features and the frequency-domain features; wherein the time-domain features include the signal standard deviation, coefficient of variation, and local extremum density, and the frequency-domain features include the dominant frequency component and harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the total energy of the voltage signal.

[0081] Furthermore, the logical instructions in the aforementioned memory 703 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a non-destructive testing method for ferromagnetic pipe defects provided by the methods described above. This method includes: acquiring a capacitance change signal continuously collected by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitor move relative to each other at a uniform axial velocity, wherein a constant external excitation voltage is applied to the bipolar capacitor; converting the capacitance change signal into a voltage signal, and extracting time-domain features and frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time; determining the defect category and defect location based on the voltage signal and the extracted features, wherein the extracted features include the time-domain features and the frequency-domain features; wherein the time-domain features include the signal standard deviation, coefficient of variation, and local extremum density, and the frequency-domain features include the dominant frequency component and the harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the energy of the voltage signal.

[0083] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of non-destructive testing of ferromagnetic pipeline defects, characterized in that, include: A voltage signal is acquired, which is obtained by converting the capacitance change signal continuously collected by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular bipolar capacitor move at a constant speed relative to each other in the axial direction. A constant external excitation voltage is applied to the bipolar capacitor. Time-domain features are extracted from the voltage signal, and frequency-domain features are extracted from the voltage signal, wherein the independent variable of the voltage signal is time; Based on the voltage signal and the extracted features, the defect category and defect location are determined. The extracted features include the time-domain features and the frequency-domain features. The step of determining the defect category and defect location based on the voltage signal and extracted features includes: according to Determine the depth of the defect ; Where k1 and k2 are nonlinear mapping coefficients, This is the reference value for the standard deviation of the voltage signal corresponding to a defect-free pipe of the same specification. The standard deviation of the voltage signal of the ferromagnetic pipe under inspection. Harmonic energy The voltage signal energy; The time-domain features include signal standard deviation, coefficient of variation, and local extremum density; the frequency-domain features include dominant frequency components and harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the voltage signal energy.

2. The non-destructive testing method for ferromagnetic pipe defects according to claim 1, characterized in that, The step of determining the defect category and defect location based on the voltage signal and extracted features includes: The extracted features are input into the trained machine learning model to obtain the defect category; The defect categories include corrosion, cracks, and holes. The machine learning model is trained by obtaining the extracted features from samples labeled with defect categories.

3. The non-destructive testing method for ferromagnetic pipe defects according to claim 1, characterized in that, The step of determining the defect category and defect location based on the voltage signal and extracted features includes: according to Determine the axial location of the defect ; Where v is the speed at which the pipe moves. The voltage signal is referred to here.

4. The non-destructive testing method for ferromagnetic pipe defects according to claim 1, characterized in that, The step of determining the defect category and defect location based on the voltage signal and extracted features includes determining the circumferential location based on the circumferential defect distribution matrix M(θ). ,in: ； ； Where N is the number of sampling points in a single circumferential scan. For the Dirac sampling function, , The voltage signal is a discrete signal, and θ is the angular coordinate of the capacitor plates. Let be the axial position coordinates of the defect. Indicates axial position place .

5. The non-destructive testing method for ferromagnetic pipe defects according to claim 1, characterized in that, The defect location includes axial position, circumferential position, and depth position. Accordingly, after determining the defect type and defect location based on the voltage signal and extracted features, the method further includes outputting a three-dimensional defect topology map G(z,θ,γ) containing the defect location, where: ； in, For axial error, For circumferential error, , , These represent the coordinates of axial position, circumferential position, and depth position, respectively. and Here are the axial and circumferential coordinates of the defect. These are the coordinates of the defect depth.

6. A non-destructive testing device for defects in ferromagnetic pipes, characterized in that, include: The acquisition module is used to acquire voltage signals. The voltage signals are obtained by converting the capacitance change signals continuously acquired by the bipolar capacitor when the ferromagnetic pipe and the upper and lower semi-circular arc bipolar capacitor move at a constant speed relative to each other in the axial direction. The bipolar capacitor is subjected to a constant external excitation voltage. An extraction module is used to extract time-domain features from the voltage signal and to extract frequency-domain features from the voltage signal, wherein the independent variable of the voltage signal is time. The processing module is used to determine the defect category and defect location based on the voltage signal and the extracted features, wherein the extracted features include the time-domain features and the frequency-domain features; The step of determining the defect category and defect location based on the voltage signal and extracted features includes: according to Determine the depth of the defect ; Where k1 and k2 are nonlinear mapping coefficients, This is the reference value for the standard deviation of the voltage signal corresponding to a defect-free pipe of the same specification. The standard deviation of the voltage signal of the ferromagnetic pipe under inspection. Harmonic energy, The voltage signal energy; The time-domain features include signal standard deviation, coefficient of variation, and local extremum density; the frequency-domain features include dominant frequency components and harmonic energy ratio, wherein the harmonic energy ratio is the ratio of the harmonic energy of the voltage signal to the voltage signal energy.

7. A non-destructive testing system for ferromagnetic pipe defects, characterized in that, include: The device comprises upper and lower semi-circular arc-shaped capacitor plates, a signal converter, a signal amplifier, and the non-destructive testing device for ferromagnetic pipe defects as described in claim 6. The upper and lower semi-circular arc-shaped capacitor plates are divided into upper and lower parts, parallel to the ferromagnetic pipe, and an external excitation voltage is applied. The signal converter is used to convert the capacitance change signal output by the upper and lower semi-circular arc capacitor plates into a voltage signal, which is then amplified by the signal amplifier and sent to the non-destructive testing device for ferromagnetic pipe defects.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the non-destructive testing method for ferromagnetic pipe defects as described in any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the non-destructive testing method for ferromagnetic pipe defects as described in any one of claims 1 to 5.

Images