External thread detection method and detection module based on dynamic cooperation of multiple optical devices

Abstract

The invention, which relates to the technical field of thread detection, discloses a multi-optical-equipment dynamic cooperative external thread detection method and detection module comprising the steps of performing edge detection on a visible light image of a target object, and extracting contour points of an external thread of the target object; if a first abnormal edge point exists in the contour points, determining an abnormal area where the first abnormal edge point is located; obtaining an infrared detection image of the abnormal area; identifying a second abnormal edge point in the infrared detection image; repairing the second abnormal edge point in the infrared detection image to obtain a repaired image; and judging whether the abnormal region in the repaired image has a thread defect or not. According to the embodiment of the invention, the accuracy of thread defect detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of thread detection, and in particular to an external thread detection method and a detection module for dynamic coordination of multiple optical devices. Background Art

[0002] In the process of oil and gas exploration and development, the oil well pipe string is made of tapered threads tightly connected. The quality of the threads has an important impact on the quality and life of the oil and gas wells. Therefore, in the production and processing of oil well pipes, it is necessary to strengthen the measurement and inspection of thread parameters to ensure that the quality of the oil well pipe threads meets the requirements and ensure the integrity and sealing of the oil well pipe string structure.

[0003] There are methods for detecting external threads in the prior art. A Chinese patent with the announcement number "CN109060836B" discloses a method for detecting external threads of high-pressure oil pipe joints based on machine vision. The method automatically identifies the features of the threaded area by collecting images of the high-pressure oil pipe joints, removes edge points of foreign matter adhered to the threaded area, calculates corresponding thread data, and determines whether the thread meets the standard.

[0004] However, in the above patent, when removing the edge points of the threaded area with foreign matter stuck to it, it is easy to misjudge the edge of the threaded area with the edge points of foreign matter stuck to it, for example, surface scratches or microcracks, but because foreign matter is stuck to the damaged area, the camera imaging causes the scratches or microcracks to be blocked by the foreign matter. The detection method disclosed in the above patent will regard the damaged area as a normal area, resulting in a misjudgment of defects.

[0005] Therefore, how to improve the accuracy of thread defect detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] The technical problem solved by the present invention is that in the related art, it is easy to make misjudgments at edge points where foreign matter is adhered, resulting in inaccurate detection of thread defects.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a method for detecting external threads by dynamic coordination of multiple optical devices, the detection method comprising: performing edge detection on a visible light image of a target object, and extracting contour points of the external threads of the target object; if there is a first abnormal edge point in the contour points, determining an abnormal area where the first abnormal edge point is located; acquiring an infrared detection image of the abnormal area; identifying a second abnormal edge point in the infrared detection image; repairing the second abnormal edge point in the infrared detection image to obtain a repaired image; and determining whether there is a thread defect in the abnormal area in the repaired image.

[0008] Preferably, the infrared detection image is generated by an infrared detection device; before obtaining the infrared detection image of the abnormal area, the detection method also includes: determining the central pixel coordinates of the abnormal area in the visible light image; converting the central pixel coordinates into spatial coordinates in the coordinate system of the infrared detection device; determining the target coordinates of the infrared detection device according to the spatial coordinates; controlling the infrared detection device to move to the target coordinates; and controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area.

[0009] Preferably, controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area includes: controlling the line between the thermal imaging optical axis of the infrared detection device and the center of the abnormal area to be perpendicular to the central axis of the target object in the world coordinate system.

[0010] Preferably, controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area includes: controlling the thermal imaging optical axis to radiate to the center of the abnormal area at a first angle, wherein the first angle is not less than 43 degrees and not more than 47 degrees.

[0011] Preferably, identifying the second abnormal edge point in the infrared detection image includes: interpolating the infrared detection image to obtain an infrared magnified image; identifying the second abnormal edge point in the infrared magnified image; and recognizing the second abnormal edge point in the infrared detection image to obtain a repaired image, including: repairing the second abnormal edge point in the infrared magnified image to obtain a repaired image.

[0012] Preferably, the infrared detection image is interpolated to obtain an infrared magnified image, including: determining the first adjacent area of ​​each target pixel in the infrared detection image along the spiral direction of the external thread; determining the maximum temperature difference between multiple pixel points in the first adjacent area; if the maximum temperature difference is less than a preset temperature difference threshold, performing bicubic interpolation processing on the target pixel points corresponding to the first adjacent area; if the maximum temperature difference is not less than the preset temperature difference threshold, performing nearest neighbor interpolation processing on the target pixel points corresponding to the first adjacent area.

[0013] Preferably, repairing the second abnormal edge point in the infrared magnified image to obtain a repaired image includes: determining the thread edge point in the infrared magnified image; determining the non-threaded area and the threaded area in the infrared magnified image based on the thread edge point; if the second abnormal point is located in the threaded area, repairing the second abnormal edge point based on the threaded area to obtain a repaired image; if the second abnormal point is located in the non-threaded area, repairing the second abnormal edge point based on the non-threaded area to obtain a repaired image.

[0014] Preferably, judging whether there is a thread defect in the abnormal area in the repaired image includes: matching a thread infrared image consistent with the target object from a pre-stored thread infrared template library according to the infrared detection image; aligning the thread infrared image according to the infrared detection image to obtain an aligned sub-image of the thread infrared image; and judging whether there is a thread defect in the repaired image according to the aligned sub-image.

[0015] Preferably, matching a thread infrared image consistent with the target object from a pre-stored thread infrared template library according to the infrared detection image includes: determining the geometric parameters of the target object according to the visible light image, and determining the material thermal conductivity parameters of the target object according to the infrared detection image; matching a thread infrared image consistent with the target object from the thread infrared template library according to the geometric parameters and the material thermal conductivity, wherein the thread infrared image includes a preset thread, the geometric parameter tolerance of the preset thread and the target object is less than a preset tolerance threshold, and the material thermal conductivity deviation of the preset thread and the target object is less than a preset deviation threshold; aligning the thread infrared image according to the infrared detection image to obtain an aligned sub-image of the thread infrared image, including: performing thermal expansion compensation alignment on the thread infrared image according to a thermal compensation formula to obtain an aligned sub-image of the thread infrared image; the thermal compensation formula is: ;in, is the pixel coordinate of the thread infrared image, is the pixel coordinate after compensation in the thread infrared image, α is the material linear expansion coefficient of the target object, is the temperature of the target object during detection, It is the reference temperature when collecting the thread infrared template library.

[0016] In a second aspect, the present invention provides an external thread detection module that dynamically coordinates multiple optical devices, and the detection module includes: a camera module for capturing a visible light image of a target object; a processing module for performing edge detection on the visible light image, extracting contour points of the external thread of the target object, and if there is a first abnormal edge point in the contour point, determining the abnormal area where the first abnormal edge point is located; an infrared detection module for determining an infrared detection image of the abnormal area; the processing module is also used to identify a second abnormal edge point in the infrared detection image, repair the second abnormal edge point in the infrared detection image, obtain a repaired image, and determine whether there is a thread defect in the abnormal area in the repaired image.

[0017] The beneficial effects of the present invention are as follows: by performing edge detection on a visible light image of a target object, contour points of the external thread of the target object are extracted, and a first abnormal edge point is identified in the contour points, and the first abnormal edge point is used to characterize the edge point with foreign matter adhered to it, so as to locate the edge point with foreign matter adhered to it; by acquiring an infrared detection image of an abnormal area corresponding to the first abnormal edge point, a second abnormal edge point in the infrared detection image is identified, so as to identify the coordinates of the edge point with foreign matter adhered to it in the infrared detection image, and the foreign matter adhered to the edge point in the infrared detection image is repaired to obtain a repaired image after the foreign matter is removed, and based on the repaired image, it is judged whether there is a thread defect at the edge point with foreign matter adhered to it, thereby improving the accuracy of thread defect detection at the edge point. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the basic flow of a method for detecting external threads by dynamic coordination of multiple optical devices provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0020] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a method for detecting external threads in dynamic coordination of multiple optical devices, the detection method comprising S110~S160: S110, performing edge detection on the visible light image of the target object to extract contour points of the external thread of the target object.

[0021] S120: If there is a first abnormal edge point among the contour points, determine an abnormal region where the first abnormal edge point is located.

[0022] The first abnormal edge point is used to characterize an edge point where foreign matter is adhered.

[0023] S130, acquiring an infrared detection image of the abnormal area.

[0024] The infrared detection image is generated by an infrared detection device; before S130, the detection method further includes S121 to S129: S121, determining the central pixel coordinates of the abnormal area in the visible light image.

[0025] is the pixel coordinate of the center of the abnormal area in the visible light image.

[0026] S123, converting the central pixel coordinates into space coordinates in the coordinate system of the infrared detection device.

[0027] , is the scaling factor from the visible light camera pixel to the actual space (obtained through calibration), , It is the compensation value of the installation position deviation between the visible light camera and the infrared device.

[0028] The spatial coordinates of the center pixel coordinates in the coordinate system of the infrared detection device are: ( ), z is the default value.

[0029] S125, determining the target coordinates of the infrared detection device according to the spatial coordinates.

[0030] The target coordinates are:

[0031] S127, controlling the infrared detection device to move to the target coordinates.

[0032] S129, controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area.

[0033] Specifically, S129 also includes: S129a, controlling the line between the thermal imaging optical axis of the infrared detection device and the center of the abnormal area to be perpendicular to the central axis of the target object in the world coordinate system to avoid the infrared rays being unable to penetrate the threads of the external thread.

[0034] Preferably, S129 may also include: S129b, controlling the thermal imaging optical axis to irradiate the center of the abnormal area at a first angle, wherein the first angle is not less than 43 degrees and not greater than 47 degrees; when the foreign matter is an emulsion, setting the infrared ray to be incident at 45° can improve the penetration effect of the infrared ray on the emulsion.

[0035] First angle calculation: the first incident angle of the infrared light axis , through the following constraints:

[0036] is the standard pitch of the external thread of the target object; is the nominal diameter of the external thread of the target object; is the angle correction value, the value range is , used to compensate for the penetration requirements of emulsion / foreign matter; the final constraint .

[0037] S140, identifying a second abnormal edge point in the infrared detection image.

[0038] The second abnormal edge point is used to characterize the foreign matter area, such as emulsion, iron filings, etc.

[0039] S150, repairing the second abnormal edge point in the infrared detection image to obtain a repaired image.

[0040] The foreign matter is repaired in the infrared detection image, the repaired image is restored, and the repaired image is detected, so as to avoid mistaking the foreign matter for a defect and causing the foreign matter to interfere with the detection.

[0041] To improve the restoration effect of the restored image, S140 includes sub-steps S141 to S143: S141, performing interpolation processing on the infrared detection image to obtain an infrared magnified image.

[0042] Specifically, S141 includes sub-steps S141a to S141d: S141a, determining a first adjacent region of each target pixel in the infrared detection image along the spiral direction of the external thread.

[0043] S141b, determining the maximum temperature difference between multiple pixel points in the first adjacent area.

[0044] S141c: If the maximum temperature difference is less than the preset temperature difference threshold, bicubic interpolation processing is performed on the target pixel point corresponding to the first adjacent area.

[0045] S141d: If the maximum temperature difference is not less than the preset temperature difference threshold, perform nearest neighbor interpolation processing on the target pixel point corresponding to the first adjacent area.

[0046] Traditional methods lead to misjudgment in areas with sudden temperature changes (such as scratch edges), such as magnifying small scratches into larger artifacts. Therefore, bicubic interpolation is used to maintain details in areas with smooth temperature changes, and nearest neighbors are used to avoid artifacts in areas with sudden temperature changes. The adjacent areas are determined along the spiral direction, which is related to the structure of the thread, to ensure that the analysis window conforms to the physical characteristics of the thread and avoid mistaking artifacts between the protruding and non-protruding parts of the thread for cracks.

[0047] S143, identifying a second abnormal edge point in the infrared amplified image.

[0048] S150 includes sub-step S151: S151, repairing the second abnormal edge point in the infrared magnified image to obtain a repaired image.

[0049] S151 includes sub-steps S151a to S151d: S151a, determining the thread edge point in the infrared magnified image.

[0050] S151b, determining the non-threaded area and the threaded area in the infrared magnified image according to the thread edge points.

[0051] S151c: If the second abnormal point is located in the thread area, the second abnormal edge point is repaired according to the thread area to obtain a repaired image.

[0052] S151d, if the second abnormal point is located in the non-threaded area, the second abnormal edge point is repaired according to the non-threaded area to obtain a repaired image.

[0053] S160, determining whether there is a thread defect in the abnormal area in the repaired image.

[0054] S161, matching a thread infrared image consistent with the target object from a pre-stored thread infrared template library according to the infrared detection image.

[0055] S162, aligning the thread infrared image according to the infrared detection image to obtain an aligned sub-image of the thread infrared image.

[0056] S163, judging whether there is a thread defect in the repaired image according to the aligned sub-image.

[0057] Specifically, S161 includes sub-steps S161a-S161b: S161a, determining geometric parameters of the target object according to the visible light image, and determining material thermal conductivity parameters of the target object according to the infrared detection image.

[0058] S161b, matching a thread infrared image consistent with the target object from a thread infrared template library according to geometric parameters and material thermal conductivity, wherein the thread infrared image includes a preset thread, a geometric parameter tolerance between the preset thread and the target object is less than a preset tolerance threshold, and a material thermal conductivity deviation between the preset thread and the target object is less than a preset deviation threshold.

[0059] S162 includes sub-step S162a: S162a, performing thermal expansion compensation alignment on the thread infrared image according to a thermal compensation formula to obtain an aligned sub-image of the thread infrared image, wherein the thermal compensation formula is:

[0060] in, is the pixel coordinate of the thread infrared image, is the pixel coordinate after compensation in the thread infrared image, α is the material linear expansion coefficient of the target object, is the temperature of the target object during detection, It is the reference temperature when collecting the thread infrared template library.

[0061] If thermal expansion is not compensated, temperature changes will cause pixel-level displacement of the thread in the image. For example, after turning, the thread surface temperature is above 80°C, causing the thread to expand by about 0.058mm per 10mm length. If the imaging resolution is 0.02mm / pixel, the deformation is equivalent to a 2.9-pixel displacement, causing image registration failure. The role of the thermal compensation formula: dynamically correct the coordinate mapping relationship based on the temperature difference, so that the detection image is aligned with the template on a physical scale.

[0062] For example, the pitch of a threaded joint is P=5.08mm at 20℃, and the temperature is maintained at 70℃ during summer inspection: P′=5.08·[1+11.7×10-6·(70-20)]=5.082967mm. Therefore, thermal compensation and subsequent comparison can avoid misjudgment of pitch deviation due to thermal expansion.

[0063] The embodiment of the present application performs edge detection on a visible light image of a target object, extracts contour points of the external thread of the target object, and identifies the existence of a first abnormal edge point in the contour points. The first abnormal edge point is used to characterize the edge point with foreign matter adhered to it, so as to locate the edge point with foreign matter adhered to it; an infrared detection image of an abnormal area corresponding to the first abnormal edge point is acquired, a second abnormal edge point in the infrared detection image is identified, and the coordinates of the edge point with foreign matter adhered to it in the infrared detection image are identified; the foreign matter adhered to the edge point in the infrared detection image is repaired to obtain a repaired image after the foreign matter is removed; and based on the repaired image, it is determined whether there is a thread defect at the edge point with foreign matter adhered to it, thereby improving the accuracy of thread defect detection at the edge point.

[0064] Furthermore, experimental data are provided in the embodiments of the present application to illustrate the technical effects of the embodiments of the present application. Specifically, please refer to Table 1.

[0065] Table 1: Data effect of this solution

[0066] According to another aspect of an embodiment of the present application, there is also provided an external thread detection module for dynamic coordination of multiple optical devices, the detection module comprising: a camera module for capturing a visible light image of a target object; a processing module for performing edge detection on the visible light image, extracting contour points of the external thread of the target object, and if there is a first abnormal edge point in the contour points, determining an abnormal area where the first abnormal edge point is located; an infrared detection module for determining an infrared detection image of the abnormal area; the processing module is also used to identify a second abnormal edge point in the infrared detection image, repair the second abnormal edge point in the infrared detection image, obtain a repaired image, and determine whether there is a thread defect in the abnormal area in the repaired image.

[0067] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting external threads by dynamic coordination of multiple optical devices, characterized in that: The detection method comprises: Performing edge detection on the visible light image of the target object to extract contour points of the external threads of the target object; If there is a first abnormal edge point among the contour points, determining an abnormal region where the first abnormal edge point is located; Acquire an infrared detection image of the abnormal area; Identifying a second abnormal edge point in the infrared detection image; Repairing the second abnormal edge point in the infrared detection image to obtain a repaired image; It is determined whether there is a thread defect in the abnormal area in the repaired image.

2. The detection method according to claim 1, characterized in that: The infrared detection image is generated by an infrared detection device; Before acquiring the infrared detection image of the abnormal area, the detection method further includes: Determine the center pixel coordinates of the abnormal area in the visible light image; Converting the center pixel coordinates into spatial coordinates in the coordinate system of the infrared detection device; Determining the target coordinates of the infrared detection device according to the spatial coordinates; Controlling the infrared detection device to move to the target coordinates; The thermal imaging optical axis of the infrared detection device is controlled to align with the center of the abnormal area.

3. The detection method according to claim 2, characterized in that: The step of controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area comprises: The line between the thermal imaging optical axis of the infrared detection device and the center of the abnormal area is controlled to be perpendicular to the central axis of the target object in the world coordinate system.

4. The detection method according to claim 3, characterized in that: The step of controlling the thermal imaging optical axis of the infrared detection device to align with the center of the abnormal area comprises: The thermal imaging optical axis is controlled to irradiate the center of the abnormal area at a first angle, wherein the first angle is not less than 43 degrees and not more than 47 degrees.

5. The detection method according to claim 1, characterized in that: The identifying a second abnormal edge point in the infrared detection image includes: Performing interpolation processing on the infrared detection image to obtain an infrared magnified image; identifying a second abnormal edge point in the infrared amplified image; The step of repairing the second abnormal edge point in the infrared detection image to obtain a repaired image includes: The second abnormal edge point in the infrared magnified image is repaired to obtain a repaired image.

6. The detection method according to claim 5, characterized in that: The interpolation processing is performed on the infrared detection image to obtain the infrared magnified image, including: Determining a first adjacent area of ​​each target pixel point in the infrared detection image along the spiral direction of the external thread; Determining a maximum temperature difference between a plurality of pixels in the first adjacent region; If the maximum temperature difference is less than a preset temperature difference threshold, performing bicubic interpolation processing on the target pixel point corresponding to the first adjacent area; If the maximum temperature difference is not less than a preset temperature difference threshold, a nearest neighbor interpolation process is performed on the target pixel point corresponding to the first adjacent area.

7. The detection method according to claim 6, characterized in that: The step of repairing the second abnormal edge point in the infrared magnified image to obtain a repaired image includes: Determining thread edge points in the infrared magnified image; Determine the non-threaded area and the threaded area in the infrared magnified image according to the threaded edge points; If the second abnormal point is located in the thread region, repairing the second abnormal edge point according to the thread region to obtain the repaired image; If the second abnormal point is located in the non-threaded area, the second abnormal edge point is repaired according to the non-threaded area to obtain the repaired image.

8. The detection method according to claim 7, characterized in that: The determining whether there is a thread defect in the abnormal area in the repaired image includes: Matching a thread infrared image consistent with the target object from a pre-stored thread infrared template library according to the infrared detection image; Performing alignment processing on the thread infrared image according to the infrared detection image to obtain an aligned sub-image of the thread infrared image; It is determined whether the repaired image has a thread defect according to the aligned sub-image.

9. The detection method according to claim 8, characterized in that: The step of matching a thread infrared image consistent with the target object from a pre-stored thread infrared template library according to the infrared detection image includes: Determine the geometric parameters of the target object according to the visible light image, and determine the material thermal conductivity parameters of the target object according to the infrared detection image; Matching a thread infrared image consistent with the target object from the thread infrared template library according to the geometric parameters and the material thermal conductivity, wherein the thread infrared image includes a preset thread, a geometric parameter tolerance between the preset thread and the target object is less than a preset tolerance threshold, and a material thermal conductivity deviation between the preset thread and the target object is less than a preset deviation threshold; The step of performing alignment processing on the thread infrared image according to the infrared detection image to obtain an aligned sub-image of the thread infrared image includes: Performing thermal expansion compensation alignment on the thread infrared image according to a thermal compensation formula to obtain an aligned sub-image of the thread infrared image; The thermal compensation formula is: ;in, is the pixel coordinate of the thread infrared image, is the pixel coordinate after compensation in the thread infrared image, α is the material linear expansion coefficient of the target object, is the temperature of the target object during detection, It is the reference temperature when the thread infrared template library is collected.

10. An external thread detection module with dynamic coordination of multiple optical devices, characterized in that: The detection module comprises: A camera module, used for taking visible light images of the target object; a processing module, configured to perform edge detection on the visible light image, extract contour points of the external thread of the target object, and if a first abnormal edge point exists in the contour points, determine an abnormal region where the first abnormal edge point is located; An infrared detection module, used to determine an infrared detection image of the abnormal area; The processing module is also used to identify the second abnormal edge point in the infrared detection image, repair the second abnormal edge point in the infrared detection image to obtain a repaired image, and determine whether there is a thread defect in the abnormal area in the repaired image.

Images