Magnetic nondestructive testing system for welding seam and control method of magnetic nondestructive testing system
Through the magnetic non-destructive detection system and control method, the accuracy of the weld detection of pressure vessels and bridge U ribs is solved, and automated and accurate defect identification and detection are achieved.
Patent Information
- Application Number
- CN202510698591.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-28
- Publication Date
- 2025-07-18
- Estimated Expiration
- 2045-05-28
AI Technical Summary
In the prior art, it is difficult to achieve accurate non-destructive testing of internal welds of pressure vessels and bridge U ribs, especially because there are contaminants inside the welds and the detection results require manual evaluation, resulting in inaccurate testing results.
A magnetic non-destructive detection system is designed, including a moving module, a cleaning module, a spraying module, a magnetization module, a detection module and a lighting module. The magnetic powder distribution change stage is identified through system parameter setting, image recognition and optical flow method. The control system conducts detection at the critical moving speed and extracts timing image features to obtain weld defect information.
Through the cleaning and uniform lighting of the system, the accuracy of magnetic powder detection is improved, and the weld defects are automatically identified, which avoids the inaccurate detection results caused by manual evaluation, and achieves efficient and accurate detection of internal welds.
Smart Images

Figure CN120334345A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of weld detection equipment, and particularly to a magnetic non-destructive testing system for welds and its control method. Background Art
[0002] Welding is an important connection process in the manufacturing of pressure vessels and bridge U ribs. Good welding quality helps improve the stability and durability of pressure vessels and bridge U ribs. However, in production, there are often subtle defects, such as cracks and pores, on the weld surfaces of both, leading to potential safety hazards. Since some welds of pressure vessels and bridge U ribs are inside the workpieces, it is difficult to detect the defects of these internal welds manually.
[0003] In the technology of defect detection, magnetic particle testing attracts magnetic particles through the leakage magnetic field generated at subtle defects to display the position and size of weld surface defects, and can achieve non-destructive testing of welds. Integrating the magnetic particle testing device into an automated testing system can enter the inside of the workpiece to be tested and detect the surface defects of the welds inside the workpiece.
[0004] Currently, although there are non-destructive testing systems with magnetic particle testing functions that have been put into the weld detection of complex workpieces with a large number of internal welds such as bridge U ribs, due to the presence of contaminants on the surface of the internal welds of the workpieces and the fact that the test results still need to be manually evaluated, there are still problems with inaccurate test results. Summary of the Invention
[0005] In order to solve the problems existing in the above-mentioned prior art, the purpose of this application is to provide a magnetic non-destructive testing system for welds and its control method.
[0006] In a first aspect, this application provides a magnetic non-destructive testing system for welds, including:
[0007] A moving module for performing horizontal linear motion inside the workpiece to be tested;
[0008] A cleaning module for cleaning the welds of the workpiece to be tested;
[0009] A spraying module for spraying magnetic powder liquid onto the welds of the workpiece to be tested;
[0010] A magnetization module for magnetizing the welds;
[0011] A detection module for collecting the magnetic powder distribution images on the welds;
[0012] An illumination module for providing uniform light to the welds;
[0013] A control module, and the moving module, cleaning module, spraying module, magnetization module, detection module, and illumination module are all signal-connected to the control module.
[0014] In a second aspect, the present application provides a method for controlling magnetic non-destructive testing of welds, which is applied to the magnetic non-destructive testing system for welds provided in the first aspect of the present application. The steps of the control method include:
[0015] S1. In response to the workpiece parameters of the workpiece to be tested, set the working parameters of magnetic particle testing; the workpiece parameters include the workpiece length and magnetic permeability; the working parameters include the spraying amount of the spraying module and the magnetic field strength of the magnetization module;
[0016] S2. Calibrate the weld of the workpiece to be tested according to the working parameters, and obtain the change stage of the magnetic particle distribution by image recognition of the images during the calibration operation; the change stages include magnetic particle accumulation, stable magnetic marks, and magnetic mark diffusion;
[0017] S3. Obtain the critical detection time based on the change stage of the magnetic particle distribution, and obtain the critical moving speed according to the critical detection time and the preset module spacing; the critical detection time is the time from spraying the magnetic particle liquid to the magnetic particle distribution entering the stable magnetic mark stage;
[0018] S4. Control the magnetic non-destructive testing system to move within the workpiece to be tested at the critical moving speed, and simultaneously perform magnetic particle testing on the weld of the workpiece to be tested to obtain the magnetic particle distribution image on the weld surface;
[0019] S5. Extract the images of each position of the weld in the magnetic particle distribution image to obtain the sequential images of the weld at each spraying time; the spraying time is the time from spraying the magnetic particle liquid to collecting the magnetic particle distribution image;
[0020] S6. Extract the magnetic mark features in the sequential images, and obtain the defect information of the weld according to the magnetic mark features; the magnetic mark features include the magnetic mark shape, the generation speed of the magnetic marks, and the diffusion speed of the magnetic marks; the defect information includes the defect type, defect distribution, and defect depth.
[0021] In one of the embodiments, step S2 includes:
[0022] S21. Control the magnetic non-destructive testing system to enter the workpiece to be tested and move to a preset position; the preset position is set according to the detection range of the detection module;
[0023] S22. During the movement of the magnetic non-destructive testing system, spray the magnetic particle liquid onto the weld within the preset position according to the spraying amount and magnetize the weld within the preset position according to the magnetic field strength;
[0024] S23. When the magnetic non-destructive testing system moves to the preset position, continuously collect the magnetic particle distribution calibration images on the weld within the preset position;
[0025] S24. Based on the magnetic particle distribution calibration images, identify the change stage of the magnetic particle distribution by the optical flow method.
[0026] In one embodiment, step S24 includes:
[0027] S241, performing a preprocessing operation on the magnetic particle distribution calibration image; the preprocessing operation includes region alignment and grayscale conversion;
[0028] S242, based on the preprocessed magnetic particle distribution calibration image, calculating the average movement speed of the magnetic particles by means of the dense optical flow method;
[0029] S243, judging the change stage of the magnetic particle distribution according to the average movement speed; if the average movement speed is greater than the preset value, it is in the magnetic particle accumulation stage; if the average speed is not greater than the preset value, it is in the stable magnetic trace stage; if the movement direction reverses, it is in the magnetic trace diffusion stage.
[0030] In one embodiment, step S3 includes:
[0031] Obtaining the magnetic particle distribution image on the weld at the preset position, and determining the critical detection time according to the change time of the magnetic particle distribution; the critical detection time is the time from spraying the magnetic particle liquid to the magnetic particle distribution entering the stable magnetic trace stage;
[0032] Obtaining the critical moving speed according to the critical detection time and the preset module spacing; the preset module spacing is the distance between the spraying module and the detection module.
[0033] In one embodiment, step S5 includes:
[0034] Obtaining the sequential pixel length according to the critical moving speed and the preset acquisition interval;
[0035] Starting from the middle of the magnetic particle distribution image, segmenting the magnetic particle distribution image with the sequential pixel length to obtain the magnetic particle distribution fragment images at each position of the weld at each spraying time;
[0036] Stitching the magnetic particle distribution fragment images at different weld positions with the same spraying time to obtain the sequential image.
[0037] In one embodiment, step S6 includes:
[0038] Obtaining each magnetic trace region through edge detection, and determining the size and position of each magnetic trace region;
[0039] Calculating the aspect ratio of each magnetic trace region in the magnetic trace stable stage to obtain the shape of the magnetic trace, and judging the type of defect shown by the magnetic trace; the types of defects include linear defects and punctiform defects;
[0040] Calculating the magnetic trace growth speed and diffusion speed of each magnetic trace region according to the optical flow method, and combining the growth speed and diffusion speed to obtain the defect depth shown by each magnetic trace region.
[0041] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of the second aspects of the present application are implemented.
[0042] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method according to any one of the second aspects of the present application are implemented.
[0043] The magnetic non-destructive testing system and its control method for welds according to the present application have the following advantages:
[0044] 1. Before detection, the system uses the cleaning module to clean the contaminants on the internal weld of the workpiece to be detected, improving the uniformity of the magnetic powder liquid spraying by the spraying module and the adsorption of defects in the weld. The lighting module provides sufficient and uniform light to the weld, which can improve the image quality collected by the detection module, thereby improving the accuracy of image recognition. The above system reduces the interference of contaminants during magnetic powder detection by cleaning weld contaminants and providing uniform light, improving the accuracy of magnetic powder detection.
[0045] 2. The control method sets the working parameters during magnetic powder detection of the system according to the parameters of the workpiece to be detected, ensuring that the uniformity of magnetic powder liquid spraying and the magnetic field strength during magnetic powder detection meet the requirements. By performing a magnetic powder detection calibration operation at the beginning of magnetic powder detection to obtain the time required for different stages from magnetic powder liquid spraying on the weld to magnetic powder distribution, and then calibrating the critical detection time and further determining the critical moving speed of the system, the detection module can reach the weld to be detected at an appropriate time and collect a clear and accurate magnetic powder distribution image. By segmenting the images of different positions of the weld at different spraying times and stitching them to obtain a time-series image, and then extracting the defect information existing at each position by feature extraction of the time-series image, the accuracy of image recognition can be improved. The above method automatically obtains the magnetic powder detection result of the weld by adjusting the critical moving speed and identifying the time-series images at different times, effectively avoiding the problem of inaccurate detection results caused by manual evaluation. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.
[0047] Figure 1 It is a schematic structural diagram of a magnetic non-destructive testing system for welds provided by the present application;
[0048] Figure 2 is a flowchart of the steps of a magnetic non-destructive testing control method for weld seams provided by this application;
[0049] Figure 3 is a flowchart of the steps of identifying different change stages of magnetic particle distribution provided by this application;
[0050] Figure 4 is a flowchart of the steps of judging the change stage of magnetic particle distribution according to the movement speed of magnetic particles provided by this application.
[0051] Explanation of reference numerals:
[0052] 1 - Moving module; 2 - Cleaning module; 3 - Spraying module; 4 - Magnetizing module; 5 - Detecting module; 6 - Control module; 7 - Cleaning liquid container; 8 - Magnetic particle liquid container; 9 - Magnetic field generator. Detailed implementation manners
[0053] To facilitate the understanding of this application, the following will describe this application more comprehensively with reference to the relevant drawings. Embodiments of this application are shown in the drawings. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of this application more thorough and comprehensive.
[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used in the specification of this application herein are only for the purpose of describing specific embodiments and are not intended to limit this application. It should be noted that when an element is considered to be "connected" to another element, it can be directly connected to the other element or connected to the other element through an intermediate element. In addition, "connection" in the following embodiments should be understood as "electrical connection", "communication connection", etc. if there is transmission of electrical signals or data between the connected objects.
[0055] As used herein, the singular forms "a", "an" and "the" may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms "comprising / including" or "having" etc. specify the presence of the stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the related listed items.
[0056] In one embodiment, this application provides a magnetic non-destructive testing system for weld seams, as Figure 1 shown, including:
[0057] The moving module 1 is used for linear movement in the horizontal direction inside the workpiece to be measured;
[0058] The cleaning module 2 is arranged at both ends of the moving module 1 and is used for cleaning the weld seam of the workpiece to be measured;
[0059] The spraying module 3 is arranged on both sides of the moving module 1 and is used for spraying magnetic powder liquid onto the weld seam of the workpiece to be measured;
[0060] The magnetization module 4 is arranged on both sides of the moving module 1 and is adjacent to the spraying module 3, and is used for magnetizing the weld seam;
[0061] The detection module 5 is arranged on both sides of the moving module 1 and is adjacent to the magnetization module 4, and is used for collecting the magnetic powder distribution image on the weld seam;
[0062] The lighting module, not shown in the figure, installs LED light sources on the moving module 1 using the prior art, and can be arranged on both sides of the moving module 1, and is used for providing uniform light to the weld seam;
[0063] The control module 6 is arranged on the moving module 1 and close to one end thereof. The moving module 1, the cleaning module 2, the spraying module 3, the magnetization module 4, the detection module 5 and the lighting module are all signal-connected to the control module 1;
[0064] The cleaning liquid containers 7 are respectively arranged at both ends of the moving module 1. The cleaning liquid containers 7 at the same end are communicated with the cleaning module 2. The cleaning liquid containers 7 are filled with cleaning liquid and are used for providing cleaning liquid to the cleaning module 2;
[0065] The magnetic powder liquid container 8 is arranged on the moving module 1 and at the end far from the control module 6, and is communicated with the spraying module 3. The magnetic powder liquid container 8 is filled with magnetic powder liquid and is used for providing magnetic powder liquid to the spraying module 3;
[0066] The magnetic field generator 9 is arranged on the moving module 1 and is electrically connected to the magnetization module 4, and is used for generating and providing a magnetic field to the magnetization module 4; The magnetic field is used for magnetizing the workpiece to be measured.
[0067] A magnetic force non-destructive testing system for weld seams described in this application cleans the pollutants on the internal weld seam of the workpiece to be measured by the cleaning module before detection, improving the uniformity of the magnetic powder liquid spraying of the spraying module and the adsorption of defects in the weld seam; The lighting module provides sufficient and uniform light to the weld seam, which can improve the image quality collected by the detection module, and further improve the accuracy of image recognition; The above system improves the quality of the magnetic particle flaw detection image through weld contamination cleaning and uniform lighting, effectively avoiding the problem of inaccurate detection results.
[0068] In one embodiment, the present application provides a method for controlling magnetic non-destructive testing of welds, which is applied to the magnetic non-destructive testing system for welds provided in the first aspect of the present application, as Figure 2 shown, the control method includes the following steps S1 to S6:
[0069] S1, in response to the workpiece parameters of the workpiece to be tested, set the working parameters of magnetic particle testing; the workpiece parameters include the workpiece length and magnetic permeability; the working parameters include the spraying amount of the spraying module and the magnetic field strength of the magnetization module.
[0070] It should be noted that the magnetic yoke method is used in this system to apply a magnetic field, that is, by contacting the surface to be tested with the two magnetic yokes of the magnetization module 4, a closed magnetic field can be formed between the magnetization module 4 and the surface to be tested, and the defects on the surface to be tested will cause the magnetic field to distort and generate a leakage magnetic field; the wet method in magnetic particle testing is also used in this system, that is, a suspension containing magnetic powder is sprayed onto the part to be tested through the spraying module 3, and the magnetic powder in the suspension will be attracted by the leakage magnetic field at the defect and accumulate on the defect, visually displaying the originally invisible fine defects.
[0071] Specifically, the staff measures and inputs the parameters of the workpiece to be tested, such as the magnetic permeability of the workpiece of the bridge U-rib and the workpiece length of the whole U-rib; in response to the input parameters of the workpiece to be tested, according to the basic parameters of the modules required for magnetic particle testing, calculate the working parameters of the required modules; the basic parameters of the required modules may include the magnetic powder liquid capacity of the spraying module 3 and the pole pitch of the magnetization module 4; the working parameters of the required modules may include the magnetic powder liquid spraying amount of the spraying module 3, the magnetic field strength of the magnetization module 4 and the critical moving speed of the moving module 1.
[0072] S2, perform a calibration operation on the weld of the workpiece to be tested according to the working parameters, and obtain the change stage of the magnetic powder distribution by performing image recognition on the images during the calibration operation process; the change stages include magnetic powder accumulation, stable magnetic marks and magnetic mark diffusion.
[0073] It should be noted that since it is difficult to grind the internal weld, the surface of the internal weld is usually not flat, and the concave areas on it may also affect the magnetic field distribution on the weld surface and form false magnetic marks; due to the differences between the materials used for welding and the workpiece materials, there may also be false magnetic marks at the weld toes due to the differences in the magnetic permeability of the materials; performing a magnetic particle testing calibration operation on a small range of welds before detection can not only judge the accumulation time and demagnetization time of the magnetic powder under the current magnetization detection parameters through the formation time, stable time and disappearance time of the false magnetic marks, but also obtain the image characteristics of some false magnetic marks, which helps to reduce the interference of false magnetic marks in subsequent image processing.
[0074] Specifically, the magnetic particle testing calibration operation includes cleaning the weld, spraying magnetic particle liquid, and magnetizing the weld area while entering the workpiece to be tested at an initial speed; in the case of reaching the end of a small-range weld, stopping the movement, spraying, and magnetizing, and recording the image of the small-range weld for a period of time; identifying false magnetic marks and possible defect magnetic marks through the magnetic particle distribution in the image, and judging the change stage of the magnetic particle distribution according to the accumulation and diffusion of the magnetic marks and false magnetic marks, and calculating the magnetic particle accumulation time and the stable time; the accumulation time is the time from magnetization to the stable stage of the magnetic marks; the stable time is the time from magnetization to the diffusion of the magnetic marks.
[0075] S3. Obtain the critical detection time based on the change stage of the magnetic particle distribution, and obtain the critical moving speed according to the critical detection time and the preset module spacing; the critical detection time is the time from spraying the magnetic particle liquid to the magnetic particle distribution entering the stable magnetic mark stage.
[0076] Specifically, based on the time for the magnetic particles to migrate to form stable magnetic marks, obtain the magnetic particle testing operation duration for any point on the weld, and combine the distance from the spraying module 3 to the detection module 5 to obtain the critical moving speed; the magnetic particle testing operation duration can take values within the stable time range.
[0077] S4. Control the magnetic force non-destructive testing system to move within the workpiece to be tested at the critical moving speed, and simultaneously perform magnetic particle testing operations on the weld of the workpiece to be tested to obtain the magnetic particle distribution image on the weld surface.
[0078] Specifically, control the moving module 1 to move forward inside the workpiece based on the critical moving speed, and simultaneously control the cleaning module 2, the spraying module 3, the magnetizing module 4, and the detection module 5 to jointly perform magnetic particle testing operations on the internal weld, and obtain the magnetic particle distribution image on the weld surface.
[0079] S5. Extract the images of each position of the weld in the magnetic particle distribution image to obtain the time-sequence images of the weld at each spraying time; the spraying time is the time from spraying the magnetic particle liquid to collecting the magnetic particle distribution image.
[0080] It can be understood that since the magnetic particle testing of the workpiece to be tested by the system is continuous, the images collected by the detection module will simultaneously include the images of the stable magnetic mark stage at this position, the images of the magnetic mark diffusion stage at the previous position, and the images of the accumulation stage at the subsequent position; and because the moving module 1 moves at a constant speed, the continuously collected magnetic particle distribution images should contain the images of each position of the weld at each spraying time; by segmenting the magnetic particle distribution image and splicing the images in time series, the time-sequence images of the workpiece to be tested at each spraying time can be obtained.
[0081] Specifically, perform preprocessing operations on a number of collected magnetic powder distribution images. The preprocessing operations may include segmentation, denoising, alignment, and contrast enhancement. Obtain the segmentation length of the magnetic powder distribution image according to the critical movement speed and the acquisition interval, and segment the magnetic powder distribution image into several images according to the segmentation length. Each image contains the magnetic powder distribution of the image within a certain spraying time. Stitch the images at different positions corresponding to the same spraying time into one or more images according to the position order, and then multiple sequential images of the workpiece to be tested from the spraying of magnetic powder to the magnetic trace diffusion stage can be obtained.
[0082] S6. Extract the magnetic trace features in the sequential images, and obtain the defect information of the weld according to the magnetic trace features. The magnetic trace features include the magnetic trace shape, the generation speed of the magnetic trace, and the diffusion speed of the magnetic trace. The defect information includes the defect type, defect distribution, and defect depth.
[0083] Specifically, extract the magnetic trace area and its features, and obtain the defect type and its distribution shown by the magnetic trace based on the magnetic trace area features.
[0084] Furthermore, through an algorithm, the sequential images of the magnetic trace area at any position of the weld can be used to obtain the speed at which magnetic powder migrates and accumulates on the defect to generate a magnetic trace, and the speed at which the magnetic trace diffuses at the defect during the demagnetization process. According to the magnetic trace generation speed and diffusion speed, the depth of the defect can be judged.
[0085] In this embodiment, a magnetic force non-destructive testing control method for welds provided by the present application ensures that the uniformity of the magnetic powder liquid spraying and the magnetic field strength during the magnetic powder testing meet the requirements by setting the working parameters during the magnetic powder testing of the system according to the parameters of the workpiece to be tested. By performing a magnetic powder testing calibration operation at the beginning of the magnetic powder testing to obtain the time required for different stages of the magnetic powder distribution after the weld is magnetized, and then calibrating the critical detection time and further determining the critical movement speed of the system, the detection module can reach the weld part to be detected at an appropriate time and collect clear and accurate magnetic powder distribution images. By segmenting and stitching the images at different positions of the weld at different spraying times to obtain sequential images, and then extracting the feature information of the defects existing at each position from the sequential images, the accuracy of image recognition can be improved. The above method automatically obtains the magnetic powder testing results of the weld by adjusting the critical movement speed and identifying the sequential images at different times, effectively avoiding the problem of inaccurate detection results caused by manual evaluation.
[0086] In an exemplary embodiment, step S1 specifically includes:
[0087] S11. Obtain the magnetic field strength of the magnetization module according to the magnetic permeability of the workpiece.
[0088] S12. Obtain the spraying amount of the spraying module according to the length of the workpiece.
[0089] Specifically, during magnetic particle testing, the magnetic flux density on the surface of the workpiece determines the efficiency of magnetic particle adsorption by defects, and the magnetic flux density depends on the applied magnetic field strength and the magnetic permeability of the workpiece; the magnetic field strength at which the magnetization module operates corresponds to the magnetic flux density sufficient to magnetize the workpiece to produce clear magnetic marks on its surface, generally not less than 1 T; on the other hand, due to the limitation of the magnetic particle liquid container in the spraying module 3, the magnetic particle liquid for each magnetic particle testing is limited, so the maximum spraying amount for each section of the weld needs to be obtained according to the length of the workpiece to be tested; the spraying amount should be sufficient to show the defective magnetic marks on the weld, but not too large, otherwise the probability of false magnetic marks will increase.
[0090] Further, the formula for calculating the magnetic field strength according to the magnetic permeability is as follows:
[0091]
[0092] Among them, H is the magnetic field strength; B is the magnetic flux density; μ0 is the magnetic permeability of vacuum, taking 4π×10 -7 H / m; μ r is the relative magnetic permeability of the workpiece.
[0093] Exemplarily, taking the minimum value of the magnetic flux density on the workpiece surface as 1 T, the common bridge U-rib uses low-carbon steel, and the relative magnetic permeability is taken as 2000, the minimum magnetic field strength can be obtained as 398 A / m; the working current of the magnetization module 4 can be further obtained according to the minimum magnetic field strength of the magnetization module 4 and the pole pitch of the magnetic yoke in the magnetization module 4.
[0094] Exemplarily, taking the length of the workpiece to be tested as 20 m and the capacity of the magnetic particle liquid container as 200 mL; if both sides of the weld are detected simultaneously, the total length is 40 m, then the maximum spraying amount per 1 m is 50 mL; if the initial moving speed of the system is 1 m / min, the maximum initial spraying flow rate is about 0.83 mL / s.
[0095] In an exemplary embodiment, as Figure 2 shown, step S2 specifically includes the following steps S21 to S24:
[0096] S21, control the magnetic non-destructive testing system to enter the workpiece to be tested and move to a preset position; the preset position is set according to the detection range of the detection module.
[0097] Specifically, under the condition that the limiter of the moving module is adjusted to be closely attached to the inner wall of the workpiece to be tested, the moving module 1 drives into the workpiece to be tested according to the initial moving speed, and starts the front-end cleaning module 2 to clean the weld until there is only the image of the weld within the detectable range of the detection module 5.
[0098] S22. During the movement of the magnetic nondestructive testing system, spray magnetic powder liquid onto the weld seam within the preset position according to the spraying amount and magnetize the weld seam within the preset position according to the magnetic field strength.
[0099] Specifically, during the process of driving into the workpiece to be tested, if the spraying port has reached the workpiece, control the spraying module 3 to spray magnetic powder liquid onto the weld seam according to the initial spraying flow rate, and then start the magnetization module 4 and the detection module 5 to perform magnetic powder detection.
[0100] S23. When the magnetic nondestructive testing system moves to the preset position, continuously collect the magnetic powder distribution calibration images on the weld seam within the preset position.
[0101] Specifically, the preset position is set according to the detectable range of the detection module; when there is only an image of the workpiece to be tested within the detectable range of the detection module 5, control the moving module 1, the cleaning module 2, the spraying module 3, and the magnetization module 4 to stop working, and control the detection module 5 to collect the continuous magnetic powder distribution calibration images of the preset position of the weld seam within the workpiece to be tested at intervals within the preset time period.
[0102] Preferably, the preset time period is set to 15 s, including the time for magnetic powder to accumulate on defects to form magnetic marks and the time for magnetic powder to diffuse after magnetization weakens.
[0103] S24. Based on the magnetic powder distribution calibration images, identify the change stage of the magnetic powder distribution by the optical flow method.
[0104] Among them, step S24 includes the following steps S241 to S243:
[0105] S241. Perform preprocessing operations on the magnetic powder distribution calibration images; the preprocessing operations include region alignment and grayscale conversion.
[0106] Specifically, eliminate camera jitter through SIFT or ORB feature matching to ensure that the optical flow is dominated by magnetic powder; enhance the contrast of magnetic powder through grayscale conversion or RGB channel separation.
[0107] S242. Based on the preprocessed magnetic powder distribution calibration images, calculate the average movement speed of the magnetic powder by the dense optical flow method.
[0108] Specifically, calculate the motion vectors of the magnetic powder in the weld seam area based on the change of the magnetic powder position in the calibration image by the dense optical flow method, and calculate the velocity amplitude map and the motion direction map according to the motion vectors; divide the calibration image into regions according to different directions in the motion direction map, and calculate the average velocity of each region in combination with the velocity amplitude map.
[0109] S243. Determine the change stage of the magnetic powder distribution according to the average movement speed. If the average movement speed is greater than the preset value, it is in the magnetic powder accumulation stage. If the average speed is not greater than the preset value, it is in the stable magnetic trace stage. If the movement direction reverses, it is in the magnetic trace diffusion stage.
[0110] Specifically, since the mass of the magnetic powder is very small and its migration speed under the magnetic field is very fast, the completion of magnetic powder migration can be judged by its movement speed. When the average movement speed of the magnetic powder in each area is greater than the preset speed value, the magnetic powder migration is in the accumulation stage. When the average movement speed of the magnetic powder in each area is not greater than the preset value, the magnetic powder migration is in the stable stage. When the movement direction of the magnetic powder in any area is opposite to the initial direction, the magnetic powder migration is in the diffusion stage. At this time, the surface magnetic field at this position starts to demagnetize, and the gravitational force of the magnetic field on the magnetic powder is insufficient. Under the action of gravity, the magnetic powder diffuses from the magnetic trace.
[0111] The method in this embodiment judges the change stage of magnetic powder migration in the calibration operation by the optical flow method, obtains the time when the magnetic powder migration reaches the stable stage under the current working parameters, and provides a basis for determining the critical detection time of the detection module 5 and the critical movement speed of the movement module 1.
[0112] In an exemplary embodiment, step S3 includes the following steps S31 to S32:
[0113] S31. Obtain the magnetic powder distribution image on the weld at the preset position, and determine the critical detection time according to the change time of the magnetic powder distribution. The critical detection time is the time from spraying the magnetic powder liquid to the magnetic powder distribution entering the stable magnetic trace stage.
[0114] Specifically, by extracting the image features of the magnetic powder distribution image, identify the process of magnetic powder migration, and select the best critical detection time within the time range of forming a stable magnetic trace.
[0115] It can be understood that during the process of magnetic powder accumulation, due to the accumulation of magnetic powder, the gray level gradient of the image continuously rises, and the contrast also rises. When the magnetic powder accumulates to form a stable magnetic trace, the contrast reaches the maximum and the edge of the magnetic trace is clear. During the demagnetization process, due to gravity, the magnetic powder diffuses, the contrast decreases and the gray level distribution changes.
[0116] S32. Obtain the critical movement speed according to the critical detection time and the preset module spacing. The preset module spacing is the distance between the spraying module and the detection module.
[0117] Specifically, the preset module spacing is the distance between the magnetization module and the detection module. By adjusting the movement speed to the critical movement speed, the detection module can just reach the weld at the critical detection time after spraying the magnetic powder liquid on the weld, and clear and stable magnetic traces can be collected.
[0118] Optionally, the moving speed can also be set according to the time when the magnetic particle fluid is sprayed until it enters the magnetic trace diffusion stage, because the magnetic trace stable stage has a certain duration.
[0119] The method in this embodiment obtains the critical moving speed through the critical detection time, ensuring that the detection module 5 can collect a stable and clear magnetic trace image at the critical detection time.
[0120] In an exemplary embodiment, step S4 includes the following steps S41 to S45:
[0121] S41, control the magnetic nondestructive testing system to move forward at the critical moving speed inside the workpiece to be tested, and at the same time control the front-end cleaning module to clean the weld in front.
[0122] Specifically, after the magnetic particle testing calibration operation, control the moving module 1 to advance inside the workpiece to be tested according to the obtained critical moving speed, and at the same time start the front-end cleaning module 2, spraying module 3, magnetization module 4 and lighting module.
[0123] S42, control the spraying module to spray magnetic particle fluid on the cleaned weld.
[0124] Specifically, the spraying flow rate of the spraying module 3 is reset according to the obtained critical moving speed. During the movement, the spraying module 3 evenly sprays magnetic particle fluid on the internal weld of the workpiece to be tested.
[0125] S43, control the magnetization module to magnetize the sprayed weld.
[0126] Specifically, the magnetic yoke of the magnetization module 4 is closely attached to both sides of the weld, and magnetizes the weld area during the movement.
[0127] S44, control the detection module to collect the magnetic particle distribution image on the magnetized weld.
[0128] Specifically, during the movement, the lighting module uses uniform white light to illuminate the weld; the detection module 5 collects the magnetic particle distribution image of the current weld according to the preset acquisition interval; the acquisition interval should not be too long, and continuous images should be able to clearly record the change process of the magnetic particle distribution at any weld.
[0129] S45, when the rear-end cleaning module reaches the sprayed weld, clean the magnetic particle fluid on the weld.
[0130] Specifically, when the rear-end cleaning module 2 set at the rear end of the moving module 1 enters the workpiece to be tested, start the rear-end cleaning module 2 to clean the weld that has completed magnetic particle testing.
[0131] In an exemplary embodiment, step S5 includes the following steps S51 to S53:
[0132] S51, obtaining the timing pixel length according to the critical moving speed and the preset acquisition interval.
[0133] Specifically, the physical length of the segmentation is obtained by multiplying the critical moving speed and the preset acquisition interval, and then the timing pixel length is obtained according to the calibration coefficient.
[0134] Exemplarily, if the critical moving speed is 1 m / min and the preset acquisition interval is 1 s, the physical length to be segmented is about 16.7 mm. If there is a difference of 100 pixel points between the same positions in two adjacent acquired images, the calibration coefficient is 16.7 mm divided by 100 pixel points, that is, 1 pixel point corresponds to 0.167 mm; the calibration coefficient is used to associate the physical length and the pixel length, and is also applied in the process of determining the position of the defect on the workpiece.
[0135] S52, starting from the middle of the magnetic particle distribution image, segmenting the magnetic particle distribution image with the timing pixel length to obtain the magnetic particle distribution fragment images of each position of the weld at each spraying time.
[0136] Specifically, since the middle of the magnetic particle distribution image is a clear and stable magnetic trace image, several magnetic particle distribution fragment images of different positions and different spraying times are segmented from the middle of each magnetic particle distribution image with the timing pixel length.
[0137] Exemplarily, if a magnetic particle distribution image is 1600×1200 in size, starting from the abscissa 750 - 850 and with the timing pixel length of 100 pixel points, then the image with the abscissa in the range of 50 - 1550 can be segmented into 15 fragment images of 100×1200 in size.
[0138] S53, splicing the magnetic particle distribution fragment images of different weld positions at the same spraying time to obtain the timing image.
[0139] Specifically, after the magnetic particle distribution image is segmented into several fragment images, the fragment images at the same position in each image are images of different positions at the same spraying time; the fragment images at the same position of each magnetic particle distribution image are spliced in position order into several timing images of a preset length; the preset length corresponds to the input image length allowed by the image recognition algorithm.
[0140] Exemplarily, the fragmented images divided into 15 pieces are sequentially numbered, with the numbers being 1 - 15 in sequence, and the corresponding spraying times being 1 - 15 s respectively; if a total of 200 magnetic powder distribution images are collected and the image length is 1600; splicing the images numbered 1 in the 200 magnetic powder distribution images can obtain 12 images with a length of 1600 and 1 time - series image with a length of 800. These time - series images show the magnetic powder distribution of the weld of the workpiece to be measured at the spraying time of 1 s.
[0141] The method in this embodiment obtains the time - series image of the weld by segmenting the magnetic powder distribution images at different positions and splicing the images with the same spraying time, providing data for identifying the defect information corresponding to the magnetic marks.
[0142] In an exemplary embodiment, step S6 includes the following steps S61 to S63:
[0143] S61, obtain each magnetic mark area through edge detection, and determine the size and position of each magnetic mark area.
[0144] Specifically, perform alignment and denoising pre - processing on the time - series image, and delete the pseudo - magnetic marks as noise; then obtain the magnetic mark areas in the time - series image corresponding to the clear stage of the magnetic marks through edge detection, and at the same time obtain the area of the magnetic mark areas; establish a rectangular coordinate system in the time - series image, and combine the calibration coefficient to obtain the position of each defect area in the weld.
[0145] S62, calculate the aspect ratio of each magnetic mark area in the stable stage of the magnetic marks to obtain the shape of the magnetic marks, and judge the type of defect indicated by the magnetic marks; the defect types include linear defects and point - like defects.
[0146] Specifically, by calculating the aspect ratio of the defect, that is, the ratio of the long side length to the short side length of the magnetic powder aggregation area, it is obtained whether the defect at this place is a linear crack or a point - like defect; multiply the number of pixels in the magnetic powder aggregation area by the calibration coefficient to obtain the size of the area occupied by the defect.
[0147] S63, calculate the growth rate and diffusion rate of the magnetic marks in each magnetic mark area according to the optical flow method, and combine the growth rate and diffusion rate to obtain the defect depth shown by each magnetic mark area.
[0148] It can be understood that due to the large leakage magnetic field of surface defects, magnetic powder will migrate and accumulate on the surface defects faster, and the magnetic marks can still remain for a long time after the magnetic yoke leaves; while the near - surface defects are buried within 2 mm below the workpiece surface, so the leakage magnetic field on the workpiece surface is small, and the ability to attract magnetic powder is weak. Therefore, magnetic powder cannot migrate to the near - surface defects quickly, and the magnetic marks are prone to diffusion after the magnetic yoke leaves.
[0149] Specifically, the optical flow field during the magnetic powder migration in adjacent sequential images can be calculated by the optical flow method, and then the migration speed can be statistically analyzed. If the magnetic powder migration speed is greater than the first preset value, it indicates that there is a surface defect in the defect area. If the magnetic powder migration speed is not greater than the first preset value, it indicates that there is a near-surface defect in the defect area. The first preset value is the maximum migration speed at which the magnetic powder is attracted by the near-surface defect.
[0150] On the other hand, the optical flow field during the magnetic powder diffusion process after the yoke leaves in adjacent sequential images is calculated by the optical flow method, and the diffusion speed is further obtained. If the diffusion speed is not greater than the second preset value, it indicates that there is a surface defect in the defect area, and vice versa, there is a near-surface defect. The second preset value is the maximum diffusion speed of the magnetic powder on the surface defect after the yoke leaves. The first preset value and the second preset value can be obtained through defect coupon tests.
[0151] The method in this embodiment extracts and identifies various features of the magnetic trace area, obtains the defect information of the defects existing in each magnetic trace area, improves the speed and accuracy of obtaining defect information, and reduces the errors caused by manual evaluation.
[0152] It should be understood that although Figure 2-4 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 2-4 at least a part of the steps in
[0153] may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.
[0154] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of any one of the methods provided by the present application for magnetic non-destructive testing control of welds.
[0155] In the description of the present application, it should be understood that the orientation or positional relationship indicated by orientation words such as "front, rear, upper, lower, left, right", "horizontal, vertical, level" and "top, bottom", etc. is usually based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description. Without contrary explanation, these orientation words do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation on the protection scope of the present application.
[0156] For those skilled in the art, according to the technical solutions and concepts described above, various corresponding changes and deformations can be made, and all these changes and deformations should fall within the protection scope of the claims of the present application.
Claims
1. A magnetic non-destructive testing system for welds, characterized in that, Including: A moving module (1), a cleaning module (2), a spraying module (3), a magnetization module (4), a detection module (5), a lighting module, and a control module (6); The moving module (1), the cleaning module (2), the spraying module (3), the magnetization module (4), the detection module (5), and the lighting module are all signal-connected to the control module (6).
2. A magnetic non-destructive testing control method for welds, applied to the magnetic non-destructive testing system for welds as described in claim 1, characterized in that, The steps of the control method include: S1. In response to the workpiece parameters of the workpiece to be tested, set the working parameters of magnetic particle testing; the workpiece parameters include workpiece length and magnetic permeability; the working parameters include the spraying amount of the spraying module and the magnetic field strength of the magnetization module; S2. Calibrate the weld of the workpiece to be tested according to the working parameters, and obtain the change stage of the magnetic particle distribution by image recognition of the images during the calibration operation process; the change stages include magnetic particle accumulation, stable magnetic marks, and magnetic mark diffusion; S3. Obtain the critical detection time based on the change stage of the magnetic particle distribution, and obtain the critical moving speed according to the critical detection time and the preset module spacing; the critical detection time is the time from spraying the magnetic particle liquid to the magnetic particle distribution entering the stable magnetic mark stage; S4. Control the magnetic force non-destructive testing system to move in the workpiece to be tested at the critical moving speed, and at the same time perform magnetic particle testing operations on the weld of the workpiece to be tested to obtain the magnetic particle distribution image on the weld surface; S5. Extract the images of each position of the weld in the magnetic particle distribution image to obtain the sequential images of the weld at each spraying time; the spraying time is the time from spraying the magnetic particle liquid to collecting the magnetic particle distribution image; S6. Extract the magnetic mark features in the sequential images, and obtain the defect information of the weld according to the magnetic mark features; the magnetic mark features include magnetic mark shape, magnetic mark generation speed, and magnetic mark diffusion speed; the defect information includes defect type, defect distribution, and defect depth.
3. The magnetic non-destructive testing control method for weld seams according to claim 2, characterized in that, The step S2 includes: S21. Control the magnetic force non-destructive testing system to enter the workpiece to be tested and move to a preset position; the preset position is set according to the detection range of the detection module; S22. During the movement of the magnetic force non-destructive testing system, spray the magnetic particle liquid on the weld within the preset position according to the spraying amount and magnetize the weld within the preset position according to the magnetic field strength; S23. When the magnetic force non-destructive testing system moves to the preset position, continuously collect the magnetic particle distribution calibration images on the weld within the preset position; S24. Based on the magnetic particle distribution calibration images, identify the change stage of the magnetic particle distribution by the optical flow method.
4. The magnetic non-destructive testing control method for weld seams according to claim 3, characterized in that, The step S24 includes: S241. Perform preprocessing operations on the magnetic particle distribution calibration images; the preprocessing operations include region alignment and grayscale conversion; S242. Based on the preprocessed magnetic particle distribution calibration images, calculate the average movement speed of the magnetic particles by the dense optical flow method; S243. Determine the change stage of the magnetic powder distribution according to the average movement speed. If the average movement speed is greater than the preset value, it is in the magnetic powder accumulation stage. If the average speed is not greater than the preset value, it is in the stable magnetic trace stage. If the movement direction reverses, it is in the magnetic trace diffusion stage.
5. The magnetic non-destructive testing control method for weld seams according to claim 2, wherein The step S5 includes: Obtain the time-series pixel length according to the critical movement speed and the preset acquisition interval. Starting from the middle of the magnetic powder distribution image, divide the magnetic powder distribution image with the time-series pixel length to obtain the magnetic powder distribution fragment images of each position of the weld at each spraying time. Stitch the magnetic powder distribution fragment images of different weld positions at the same spraying time to obtain the time-series image.
6. The magnetic non-destructive testing control method for weld seams according to claim 2, characterized in that, The step S6 includes: Obtain each magnetic trace region through edge detection, and determine the size and position of each magnetic trace region. Calculate the aspect ratio of each magnetic trace region in the magnetic trace stable stage to obtain the shape of the magnetic trace, and judge the defect type shown by the magnetic trace. The defect types include linear defects and punctiform defects. Calculate the magnetic trace growth speed and diffusion speed of each magnetic trace region according to the optical flow method, and combine the growth speed and the diffusion speed to obtain the defect depth shown by each magnetic trace region.
7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 2 to 6.
8. A 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 steps of the method according to any one of claims 2 to 6.
Citation Information
Patent Citations
Intelligent nondestructive detecting system
CN110026962A
Magnetic powder automatic detection system
CN111398411A
Assembly type steel structure weld joint detection device
CN111693599A
Workpiece visual detection analysis method and device based on magnetic powder
CN114518404A
Defect magnetic particle detection system and method based on deep learning
CN116416236A
Cited By
Steel structure welding seam intelligent magnetic powder inspection system and method thereof
CN121186184A