Eddy current magnetic flux leakage deformation integrated composite detection method and system
By combining eddy current and magnetic leakage technology in pipeline detection, using magnetic field and detection plate to obtain signals, and through detection network analysis, the problem of sensitivity to vibration interference in the prior art is solved, and more accurate detection of defects in the inner and outer walls of the pipeline is achieved.
Patent Information
- Application Number
- CN202311425482.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-30
- Publication Date
- 2025-05-02
AI Technical Summary
The existing pipeline detection methods are too sensitive to interference factors such as vibration, and have a high error detection rate, making it difficult to accurately distinguish the defects in the inner and outer walls of the pipeline.
The composite detection method integrated with eddy current leakage magnetic deformation is adopted. By applying a magnetic field parallel to the pipe axis to the target pipeline, the eddy current signal detection sensor and Hall sensor in the detection plate are used to obtain the detection signal, and the pipe corrosion situation is analyzed through the trained detection network.
It improves the accuracy of defect detection in the inner and outer walls of the pipeline, reduces the sensitivity to interference such as vibration, and has a low error detection rate, which is suitable for detection in various environments.
Smart Images
Figure CN119915894A_ABST
Abstract
Description
Background Art
[0002] As a special equipment, pressure pipelines are prone to failure and accidents due to corrosion and other reasons during use. There are two types of inspection technologies for pressure pipelines: internal and external inspection. The integrity evaluation is a quantitative evaluation of the remaining strength and remaining life of the pipeline based on the data of internal and external inspections. The evaluation results can provide data support for the subsequent maintenance and replacement of pipelines, as well as the formulation of re-inspection cycles, to avoid unnecessary and unplanned pipeline maintenance work and ensure that the pipeline is always in a safe and reliable operating state. Due to the different environments of the inner and outer walls of the pipeline, the causes and speeds of defect formation are also different. Therefore, distinguishing between the damage of the inner and outer walls of the pipeline is crucial for pipeline inspection.
[0003] The conventional pipeline inspection technology currently used is magnetic flux leakage detection technology, which can directly detect defects on the inner and outer walls of the pipeline, but cannot directly distinguish the inner and outer wall locations of metal loss. The traditional technology used to distinguish defects on the inner and outer walls is weak magnetic detection, which requires additional equipment structure, resulting in bulky equipment and increasing the risk of pipeline inspection operations. This technology for distinguishing between inner and outer walls uses only one detection method and then conducts a comprehensive analysis to distinguish between inner and outer wall damage. It is also sensitive to interference factors such as vibration of the detector during the actual inspection process, and has a high false detection rate. Summary of the invention
[0004] In order to solve the above-mentioned problem in the prior art, that is, the existing pipeline detection method is too sensitive to interference factors such as vibration and has a high false detection rate, the present invention provides a composite detection method integrating eddy current leakage magnetic deformation, the method comprising:
[0005] A magnetic field parallel to the pipeline axis is applied to the target pipeline, and the target pipeline is scanned by a detection board to obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor;
[0006] Based on the detection signal, the corrosion condition of the target pipeline is obtained through a trained detection network.
[0007] In some preferred embodiments, the magnetic field parallel to the axial direction of the pipeline is applied into the target pipeline by a permanent magnet or an electromagnet.
[0008] In some preferred embodiments, after the target pipeline is scanned by the detection board, a step of preprocessing the scanned signal is further included, specifically:
[0009] The eddy current signal obtained by scanning the target pipeline is amplified and Schottky detection is performed to obtain the pre-processed eddy current signal;
[0010] The preprocessed eddy current signal and the signal collected by the Hall sensor are used as detection signals.
[0011] In some preferred embodiments, the trained detection network obtains the magnetic flux leakage data and eddy current data of the test pipes and adds defect labels as training data by setting multiple eddy current magnetic flux leakage composite probes in multiple test pipes with prefabricated inner and outer wall standard defects.
[0012] In some preferred embodiments, the training method of the trained detection network includes:
[0013] Input the training data into the initial detection network;
[0014] The initial detection network outputs the prediction results of the defect type of the training set;
[0015] Based on the comparison between the defect type prediction results of the training set and the defect labels of the training data, the parameters of the initial detection network are adjusted;
[0016] Repeatedly input training data and output the defect type prediction results of the training set until the set loss function is less than the preset threshold, and obtain the trained detection network.
[0017] In some preferred embodiments, the detection board specifically includes one eddy current signal detection sensor and twelve Hall sensors.
[0018] In some preferred embodiments, the detection board is implemented by a circuit arranged on a PCB.
[0019] In some preferred embodiments, the eddy current signal detection sensor includes a sinusoidal signal excitation circuit, a differential amplifier circuit, an envelope signal acquisition circuit and a secondary amplifier circuit.
[0020] In some preferred embodiments, the Hall sensor includes a sensor array circuit and a multiplex switch preferred circuit.
[0021] Another aspect of the present invention provides a composite detection system integrating eddy current leakage magnetic field and deformation, the system comprising:
[0022] A signal acquisition module is configured to apply a magnetic field parallel to the pipeline axis direction into the target pipeline, scan the target pipeline through a detection board, and obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor;
[0023] The signal analysis module is configured to obtain the corrosion status of the target pipeline based on the detection signal through a trained detection network.
[0024] Beneficial effects of the present invention: (1) Based on the experience that the leakage magnetic signal obtained in actual detection is insensitive to the distinction between inner and outer wall defects, while the eddy current signal is more sensitive to inner and outer wall signals, the present invention proposes a method of integrating the leakage magnetic detection and eddy current detection technology to improve the accuracy of pipeline inner and outer wall defect detection. (2) The present invention closely combines the characteristics of magnetic flux leakage detection and eddy current detection, which generate very different signals for defects on the inner and outer walls of the pipeline, thereby achieving effective distinction between defects on the inner and outer walls of the pipeline. (3) After training the neural network, this method is insensitive to interference such as vibration generated during pipeline detection, has a low false detection rate, and has low environmental requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0026] Figure 1 1 is a schematic flow chart of a composite detection method integrating eddy current leakage magnetic field and deformation according to an embodiment of the present invention;
[0027] Figure 2 is a physical picture of a detection board in an embodiment of the present invention;
[0028] Figure 3 Schematic diagram of a PCB board of a detection board in an embodiment of the present invention;
[0029] Figure 4 is a circuit schematic diagram of a detection board in an embodiment of the present invention;
[0030] Figure 5 It is a schematic diagram of the effect of the deformation defect design in the embodiment of the present invention. DETAILED DESCRIPTION
[0031] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.
[0032] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0033] In order to more clearly explain the composite detection method of eddy current leakage magnetic deformation integration of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.
[0034] This embodiment adopts a composite detector structure to combine eddy current, corrosion and geometric deformation, that is, the eddy current corrosion probe and the deformation probe are placed on one detector at the same time, and the data acquisition and storage system simultaneously acquires and stores the detection data of both.
[0035] This embodiment adopts a method of detecting the inner and outer wall signals of the pipeline based on leakage magnetic detection and eddy current detection according to the different properties of the defect signals of the inner and outer walls of the pipeline, designs a detection probe (detection board) that combines leakage magnetic detection and eddy current detection, collects the detection signal through a data acquisition system, and outputs the detection result through a neural network algorithm.
[0036] The eddy current magnetic leakage deformation integrated composite detection method of the first embodiment of the present invention includes steps S100 to S200, and each step is described in detail as follows:
[0037] Step S100, applying a magnetic field parallel to the axial direction of the pipeline into the target pipeline, scanning the target pipeline through a detection board to obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor; this embodiment can synchronously obtain leakage magnetic data and eddy current data through the eddy current signal sensor and the Hall sensor.
[0038] In this embodiment, a magnetic field is applied to the target pipeline by a permanent magnet or an electromagnet. When a magnetic field parallel to the pipeline axis is applied to the pipeline, if the pipeline is intact and has no defects, the magnetic field passing through the pipeline will not change. If there is damage or defect on the surface of the pipeline, the magnetic field will be distorted and deformed at the damaged or defective part, that is, the leakage magnetic signal here can be detected after being processed by a filter and an amplifier to detect leakage magnetic data that can reflect the defect condition. An electromagnetic coil is set on the inner wall, and the electromagnetic coil is close to the metal surface of the pipeline. Eddy currents will be generated in the pipe wall. The eddy currents will change when encountering pipeline damage. The eddy current data is obtained by measuring the change in the impedance of the electromagnetic coil.
[0039] In this embodiment, the detection board is as follows Figure 2 As shown, the PCB board is as follows Figure 2 , Figure 3 As shown, the white part is the eddy current sensor and the black part is the Hall sensor. The electromagnetic field generated and detected by the eddy current sensor is perpendicular to the surface of the circuit board, and the leakage magnetic field signal detected by the Hall sensor is parallel to the surface of the circuit board. Therefore, the two detection mechanisms will not interfere with each other and can be combined. The circuit principle is as follows Figure 4 As shown, the eddy current circuit and the leakage magnetic circuit adopt a modular layout and work independently.
[0040] In this embodiment, the detection board is implemented by a circuit arranged on a PCB.
[0041] In this embodiment, the eddy current signal detection sensor includes a sinusoidal signal excitation circuit, a differential amplifier circuit, an envelope signal acquisition circuit and a secondary amplifier circuit.
[0042] In this embodiment, the Hall sensor includes a sensor array circuit and a multiplex switch optimization circuit.
[0043] In this embodiment, after the target pipeline is scanned by the detection board, a step of preprocessing the scanned signal is also included, specifically:
[0044] The eddy current signal obtained by scanning the target pipeline is amplified and Schottky detection is performed to obtain the pre-processed eddy current signal;
[0045] The preprocessed eddy current signal and the signal collected by the Hall sensor are used as detection signals.
[0046] Step S200: Based on the detection signal, the corrosion condition of the target pipeline is obtained through a trained detection network.
[0047] The composite detection technology adopted in this embodiment can accurately detect corrosion conditions on small deformations and improve the recognition rate of corrosion defects. At the same time, the equipment also has the function of measuring changes in the wall thickness of the pipeline. The identifiable metal loss characteristics include metal growth and metal loss, complex corrosion conditions, extended axial defects, mechanical defects, pipeline supervision defects, weld cracks, dents, wrinkles, gouges, circumferential cracks, etc.
[0048] Compared with the method in the prior art that divides coils into two types, namely, measuring coils and reference coils, the two coils in this embodiment are not divided into measuring coils and reference coils. The prior art requires using the information of eddy current signals and the information of leakage magnetic signals as the basis for identifying inner wall defects. Both have the same detection function and reduce the impact of vibration through the form of two sets of coils.
[0049] The trained detection network obtains magnetic flux leakage data and eddy current data of the test pipes and adds defect labels as training data by setting multiple eddy current magnetic flux leakage composite probes in multiple test pipes with prefabricated inner and outer wall standard defects.
[0050] In this embodiment, the eddy current composite probe is installed on the detection device and moves in the pipeline together with the detection device to obtain pipeline information. The probe evenly covers the inner wall of the pipeline along the circumference of the pipeline, and needs to meet the full coverage of the inner wall of the pipeline.
[0051] Before training, it is necessary to build an experimental sample library in advance, prefabricate standard defects of various degrees, types, and multiple types on the test piece pipeline through mechanical processing or artificial simulation, and obtain eddy current signals and magnetic flux leakage signals corresponding to various defects through eddy current magnetic flux leakage probes, and add them to the experimental sample library as training data. Figure 5 As shown, taking a 40" pipe as an example, it is connected with a flange. The wall thickness of the 40" pipe is 14.6mm, 17.5mm, and 21mm respectively. Artificial metal loss points are prefabricated on the pipe, and deformation depressions are set on the defective prefabricated pipe sections. The pipe deformation defect in this embodiment is verified by calibration. There are 6 levels of calibration, and the radial compression amount of each level is fixed to 15mm. The corresponding angle sensor also has a fixed calibration value inside the electronic package. 100 sets of deformation probes are calibrated to finally obtain 600 sets of calibration data, which serve as a "ruler" for quantifying deformation depressions.
[0052] In this embodiment, the training method of the trained detection network includes:
[0053] Input the training data into the initial detection network;
[0054] The initial detection network outputs the prediction results of the defect type of the training set;
[0055] Based on the comparison between the defect type prediction results of the training set and the defect labels of the training data, the parameters of the initial detection network are adjusted;
[0056] Repeatedly input training data and output the defect type prediction results of the training set until the set loss function is less than the preset threshold, and obtain the trained detection network.
[0057] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.
[0058] The present invention combines magnetic flux leakage data and eddy current data, which improves the detection accuracy and the range of defect types detected without affecting the detection speed and does not require a strict detection environment. The training neural network is trained by a plurality of the training data, and a detection neural network is obtained after the training is completed; the pipeline damage is detected by the detection neural network, and the pipeline damage prediction is more accurate and convenient.
[0059] The eddy current magnetic leakage deformation integrated composite detection system of the second embodiment of the present invention comprises:
[0060] A signal acquisition module is configured to apply a magnetic field parallel to the pipeline axis direction into the target pipeline, scan the target pipeline through a detection board, and obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor;
[0061] The signal analysis module is configured to obtain the corrosion status of the target pipeline based on the detection signal through a trained detection network.
[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0063] It should be noted that the eddy current leakage magnetic deformation integrated composite detection system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.
[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.
[0065] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
[0066] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.
[0067] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.
[0068] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. A composite detection method integrating eddy current leakage magnetic field and deformation, characterized in that: The method comprises: A magnetic field parallel to the pipeline axis is applied to the target pipeline, and the target pipeline is scanned by a detection board to obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor; Based on the detection signal, the corrosion condition of the target pipeline is obtained through a trained detection network.
2. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The magnetic field parallel to the axial direction of the pipeline is applied to the target pipeline by a permanent magnet or an electromagnet.
3. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: After the target pipeline is scanned by the detection board, the step of preprocessing the scanned signal is also included, specifically: The eddy current signal obtained by scanning the target pipeline is amplified and Schottky detection is performed to obtain the pre-processed eddy current signal; The preprocessed eddy current signal and the signal collected by the Hall sensor are used as detection signals.
4. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The trained detection network obtains magnetic flux leakage data and eddy current data of the test pipes and adds defect labels as training data by setting multiple eddy current magnetic flux leakage composite probes in multiple test pipes with prefabricated inner and outer wall standard defects.
5. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The training method of the trained detection network includes: Input the training data into the initial detection network; The initial detection network outputs the prediction results of the defect type of the training set; Based on the comparison between the defect type prediction results of the training set and the defect labels of the training data, the parameters of the initial detection network are adjusted; Repeatedly input training data and output the defect type prediction results of the training set until the set loss function is less than the preset threshold, and obtain the trained detection network.
6. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The detection board specifically includes one eddy current signal detection sensor and twelve Hall sensors.
7. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The detection board is realized by a circuit arranged on a PCB.
8. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The eddy current signal detection sensor comprises a sinusoidal signal excitation circuit, a differential amplifier circuit, an envelope signal acquisition circuit and a secondary amplifier circuit.
9. The eddy current leakage magnetic field deformation integrated composite detection method according to claim 1 is characterized in that: The Hall sensor comprises a sensor array circuit and a multiplex switch optimization circuit.
10. A composite detection system integrating eddy current leakage magnetic field and deformation, characterized in that: The system comprises: A signal acquisition module is configured to apply a magnetic field parallel to the pipeline axis direction into the target pipeline, scan the target pipeline through a detection board, and obtain a detection signal; the detection board includes an eddy current signal detection sensor and a Hall sensor; The signal analysis module is configured to obtain the corrosion status of the target pipeline based on the detection signal through a trained detection network.