Insulation pull rod defect detection platform based on image recognition

Abstract

The invention relates to an insulating pull rod defect detection platform based on image recognition, which comprises an image acquisition unit and an upper computer, the image acquisition unit is used for acquiring an image of the surface of an insulating pull rod and uploading the image to the upper computer, and the upper computer performs defect detection on the insulating pull rod based on the image of the surface of the insulating pull rod; the device further comprises a lamp stand and a plurality of rolling shafts, the axes of all the rolling shafts are parallel to one another, all the rolling shafts are arranged on the lamp stand and rotate in the same direction, a pull rod installation position is formed between every two adjacent rolling shafts, and the to-be-tested insulation pull rod installed on any pull rod installation position rotates under driving of the two rolling shafts. The axis of an optical signal receiving port of the image acquisition unit is perpendicular to the upper surface of the lamp stand, and the insulating pull rod is located between the lamp stand and the image acquisition unit. Compared with the prior art, the method has the advantages of improving the efficiency and accuracy of defect detection of the insulating pull rod and the like.

Description

Technical Field

[0001] The invention relates to the field of insulating pull rod detection, and in particular to an insulating pull rod defect detection platform based on image recognition. Background Art

[0002] The insulating rod is one of the core insulating parts in GIS (gas insulated switchgear), and its product quality is of great significance to the high-reliability operation of GIS. Once the insulating rod with latent defects is put into service, it will greatly reduce the reliability of GIS operation and threaten the safe operation of the power grid. At present, there are two main types of insulating rod defect detection: visual inspection and mechanical inspection. Insulating rods are often placed inside to illuminate and directly observe by human eyes due to their good permeability and hollow interior for easy observation. In addition to the visual inspection method, mechanical methods such as X-ray imaging inspection, industrial CT imaging inspection and ultrasonic flaw detection are also commonly used methods for insulating rod defect detection. X-ray imaging inspection uses the principle that normal areas and defective areas and different defects have different absorption effects on radiation. By measuring different radiation intensities on the other side of the object to be tested, it is determined whether there are defects inside the rod. Compared with X-ray imaging inspection, the image detected by industrial CT is 3D. In addition, ultrasonic testing can also be used as a method for detecting defects in insulating pull rods. When ultrasonic waves encounter tiny defects such as cracks and impurities during propagation, they will be reflected at the sample-defect interface, and the location and type of the defect can be determined based on the characteristics of the reflected wave.

[0003] In recent years, with the development of machine vision technology, some existing technologies have also adopted machine vision technology to detect defects of insulating pull rods. For example, Chinese patent CN118603993A discloses an insulating pull rod defect detection device, including a fixed platform and a lamp tube arranged in the center of the fixed platform, three groups of camera adjustment brackets are evenly arranged at the edge of the fixed platform, three camera stages are arranged on the three groups of camera adjustment brackets, each camera stage is provided with a camera, the camera is connected to a camera control device, a closed outer cover is fixedly connected to the top of the fixed platform, a circular opening is opened on the top of the closed outer cover, and a cover is arranged on the circular opening.

[0004] However, when the above-mentioned prior art is used, the insulating rod needs to be put on the lamp tube each time, and only one insulating rod can be detected at a time. On the one hand, the efficiency is not high, and on the other hand, the camera array arranged around it may not be able to detect the entire insulating railing at all angles. Summary of the invention

[0005] The purpose of the present invention is to provide an insulating pull rod defect detection platform based on image recognition.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] An insulating pull rod defect detection platform based on image recognition, comprising:

[0008] An image acquisition unit and a host computer, wherein the image acquisition unit is used to acquire an image of the surface of the insulating rod and upload it to the host computer, and the host computer performs defect detection on the insulating rod based on the image of the surface of the insulating rod;

[0009] It also includes a lamp stand and multiple rollers, the axes of all the rollers are parallel to each other, and all the rollers are placed on the lamp stand and rotate in the same direction, a pull rod installation position is formed between every two adjacent rollers, and the insulating pull rod to be tested installed on any pull rod installation position rotates driven by the two rollers, the axis of the optical signal receiving port of the image acquisition unit is perpendicular to the upper surface of the lamp stand, and the insulating pull rod is located between the lamp stand and the image acquisition unit.

[0010] The image acquisition unit comprises:

[0011] Industrial camera, used to capture images of the insulating rod surface;

[0012] The camera fixing bracket comprises a slide rail and a camera seat arranged on the slide rail and sliding along the slide rail. The industrial camera is fixed in the camera seat, and the visual axis of the industrial camera is perpendicular to the upper surface of the lamp stand. The slide rail is parallel to the axis of the roller.

[0013] The axes of all rollers are equidistant from the upper surface of the lamp stand.

[0014] The relationship between the distance between the axes of any two adjacent rollers and the radius of the rollers is:

[0015] 2≤d(g i, g i+1 ) / (r i +r i+1 )≤10

[0016] Where: d(g i, g i+1 ) is the horizontal distance between the axes of the i-th roller and the i+1-th roller, r i is the radius of the i-th roller, r i+1 is the radius of the i+1th roller.

[0017] All rollers have the same diameter and the distances between the axes of all adjacent rollers are equal.

[0018] The detection platform also includes a stepper motor and a transmission mechanism, and the output end of the stepper motor is respectively connected to and synchronously drives all rollers through the transmission mechanism;

[0019] The stepper motor drives the roller to rotate by a first set angle every t seconds through a transmission mechanism, wherein the first set angle is:

[0020] θ=2arcsin[(d-2r) / 2R]

[0021] Wherein: θ is the first set angle, d is the distance between the axes of two adjacent rollers, r is the radius of the roller, and R is the radius of the insulating pull rod.

[0022] The lamp stand comprises an outer shell without a top cover, a light source arranged in the outer shell, and a light scattering plate arranged on the top surface of the outer shell.

[0023] The light source is a linear light source, and the axis of the linear light source is parallel to the axis of the roller.

[0024] The roller comprises an axial rod and a plurality of rollers sleeved on the axial rod. The diameters of all rollers of the same roller are equal, and the radius of the roller is the radius of the roller.

[0025] The roller has a rough surface.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. Based on the multiple tie rod installation positions formed by the roller array, combined with the light stand and the image acquisition unit perpendicular to the upper surface of the light stand, it is possible to perform a full range of 60-degree surface acquisition of multiple insulating tie rods at one time based on machine vision. On the one hand, the efficiency of image sampling is improved, and on the other hand, no surface of any insulating tie rod is missed, thereby improving efficiency.

[0028] 2. The axis of the slide rail is parallel to the roller, ensuring that the field of view does not shift during the movement of the industrial camera, thereby ensuring sampling accuracy without the need for repeated calibration and color calibration.

[0029] 3. By limiting the relationship between the distance between the axes of any two adjacent rollers and the radius of the rollers, it is possible to ensure that the light provided by the lamp stand can have a sufficiently small error in different horizontal radial phases after passing through the insulating pull rod, thereby improving the accuracy of detection and reducing the requirements for machine vision technology.

[0030] 4. By limiting the angle of each rotation, it is possible to ensure that every surface is captured.

[0031] 5. The light source is a linear light source, which, combined with a diffuser, can ensure that the imaging of defect-free insulating rods is consistent at latitudes parallel to the axis, thereby reducing the requirements of machine vision algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1It is a structural schematic diagram of the present invention;

[0033] Figure 2 Schematic diagram of roller arrangement;

[0034] Figure 3 It is a schematic diagram of the structure of the camera fixing bracket;

[0035] Figure 4 is a schematic diagram of the light source part of the lamp stand;

[0036] Figure 5 is a schematic diagram of a roller in a certain embodiment;

[0037] Among them: 1. lamp stand, 2. roller, 3. pull rod installation position, 4. insulating pull rod, 5. industrial camera, 6. camera fixing bracket, 7. host computer, 1-1. light source, 1-2. light scattering plate, 2-1. axis rod, 2-2, roller, 6-1. slide rail, 6-2. camera holder. DETAILED DESCRIPTION

[0038] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0039] It should be noted that similar numbers and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further defined and explained in the subsequent figures. In the description of the present invention, it should be noted that the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "proximal", "distal", and "third" are used only for descriptive purposes and cannot be understood as indicating or implying relative importance. The physical quantities in the formula, if not separately marked, should be understood as basic quantities of the basic units of the International System of Units, or derived quantities derived from the basic quantities through mathematical operations such as multiplication, division, differentiation or integration.

[0040] In addition, the terms "horizontal", "vertical", "overhanging" and the like do not mean that the components are required to be absolutely horizontal or overhanging, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0041] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In conjunction with the accompanying drawings, some embodiments of the present invention are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0043] An insulating rod defect detection platform based on image recognition, such as Figure 1 As shown, including:

[0044] An image acquisition unit and a host computer 7, wherein the image acquisition unit is used to acquire an image of the surface of the insulating rod and upload it to the host computer 7, and the host computer 7 performs defect detection on the insulating rod based on the image of the surface of the insulating rod;

[0045] The lamp stand 1 and a plurality of rollers 2 are also included. The axes of all the rollers 2 are parallel to each other, and all the rollers 2 are placed on the lamp stand 1 and rotate in the same direction. Figure 2 As shown, a pull rod installation position 3 is formed between every two adjacent rollers 2, and the insulating pull rod 4 to be tested installed on any pull rod installation position 3 rotates driven by the two rollers 2, the axis of the optical signal receiving port of the image acquisition unit is perpendicular to the upper surface of the lamp stand 1, and the insulating pull rod 4 is located between the lamp stand 1 and the image acquisition unit.

[0046] Based on the multiple tie rod installation positions 3 formed by the roller array, combined with the lamp stand 1 and the image acquisition unit perpendicular to the upper surface of the lamp stand 1, it is possible to perform all-round 60-degree surface acquisition of multiple insulating tie rods at one time based on machine vision. On the one hand, the efficiency of image sampling is improved, and on the other hand, no surface of any insulating tie rod 4 is missed, thereby improving efficiency.

[0047] like Figure 3 As shown, in this embodiment, the image acquisition unit includes:

[0048] Industrial camera 5, used for collecting images of the surface of the insulating pull rod;

[0049] The camera fixing bracket 6 includes a slide rail 6-1, a camera seat 6-2 arranged on the slide rail 6-1 and sliding along the slide rail 6-1, the industrial camera 5 is fixed in the camera seat 6-2, and the visual axis of the industrial camera 5 is perpendicular to the upper surface of the lamp stand 1, and the slide rail 6-1 is parallel to the axis of the roller 2, thereby ensuring that the field of view does not shift during the movement of the industrial camera, thereby ensuring that the sampling accuracy does not need to be repeated. Calibration and color calibration.

[0050] In almost all embodiments, the distances between the axes of all rollers 2 and the upper surface of the lamp stand 1 are equal. In addition, the relationship between the distance between the axes of any two adjacent rollers 2 and the radius of the roller 2 is:

[0051] 2≤d(g i, g i+1 ) / (r i +r i+1 )≤10

[0052] Where: d(g i, g i+1 ) is the horizontal distance between the axes of the i-th roller 2 and the i+1-th roller 2, r i is the radius of the i-th roller 2, r i+1 is the radius of the i+1th roller 2.

[0053] In this way, by limiting the relationship between the distance between the axes of any two adjacent rollers 2 and the radius of the roller 2, it is possible to ensure that the light provided by the lamp stand 1 can have a sufficiently small error in different horizontal radial phases after passing through the insulating pull rod, thereby improving the accuracy of detection and reducing the requirements for machine vision technology.

[0054] In addition, in this embodiment, the diameters of all rollers 2 are the same, and the distances between the axes of all adjacent rollers 2 are equal. In addition, the detection platform further includes a stepper motor and a transmission mechanism. The output ends of the stepper motor are respectively connected to and synchronously drive all rollers 2 through the transmission mechanism. The stepper motor drives the roller 2 to rotate by a first set angle every t seconds through the transmission mechanism, wherein the first set angle is:

[0055] θ=2arcsin[(d-2r) / 2R]

[0056] Wherein: θ is the first set angle, d is the distance between the axes of two adjacent rollers 2 , r is the radius of the roller 2 , and R is the radius of the insulating pull rod 4 .

[0057] Based on this, in this embodiment, by limiting the angle of each rotation, it is possible to ensure that each surface is photographed and can be effectively photographed, thereby avoiding poor light imaging effects in individual areas due to being blocked by the roller in the sampled image. In addition, through the driving method of the stepper motor, each angle has sufficient exposure time, thereby magnifying the pixel error between the defective part and the normal part.

[0058] like Figure 4 As shown, the lamp stand 1 includes a housing 1-1 without a top cover, a light source 1-2 disposed in the housing, and a light diffuser 1-2 disposed on the top surface of the housing 1-1. Generally, the light source 1-2 is a linear light source, and the axis of the linear light source is parallel to the axis of the roller 2. The light source 1-1 is a linear light source, and combined with the light diffuser 1-2, it can ensure that the imaging of the defect-free insulating rod 4 is consistent at the latitude parallel to the axis, thereby reducing the requirements of the machine vision algorithm.

[0059] like Figure 5 As shown, in some embodiments, the roller 2 includes an axial rod 2-1 and a plurality of rollers 2-2 sleeved on the axial rod 2-1. The diameters of all rollers 2-2 of the same roller 2 are equal, and the radius of the roller 2 is the radius of the roller 2-2, so that material can be saved. Of course, in this embodiment, the roller 2 as a whole is a cylindrical device.

[0060] In some embodiments, the roller 2 should have a rough surface so as to have a certain friction coefficient. Of course, in this embodiment, the roller 2 should be soft enough, should not have sharp objects on the surface, and should have a large enough friction coefficient to avoid damaging the insulating pull rod 4.

[0061] In this embodiment, the industrial camera 5 is set to rotate 90° every 0.5s, the distance between the industrial camera 5 and the lamp stand 1 is 3 cm, and the roller 2 is set to perform a time-lapse shooting every 0.5s. In addition, it moves a fixed distance every 2.5s, and the distance can be set according to the needs. Within this time, the 360° image acquisition of a certain section of the rod can be completed. Then move the position of the industrial camera 5, and shoot the next section of the insulating rod 4 according to the above process until the image acquisition of the entire outer surface of the insulating rod 4 is completed.

[0062] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

Claims

1. An insulating rod defect detection platform based on image recognition, comprising: An image acquisition unit and a host computer (7), wherein the image acquisition unit is used to acquire an image of the surface of the insulating rod and upload the image to the host computer (7), and the host computer (7) performs defect detection on the insulating rod based on the image of the surface of the insulating rod; The invention is characterized in that it also includes a lamp stand (1) and a plurality of rollers (2), the axes of all the rollers (2) are parallel to each other, and all the rollers (2) are placed on the lamp stand (1) and rotate in the same direction, a pull rod installation position (3) is formed between every two adjacent rollers (2), and the insulating pull rod (4) to be tested installed on any pull rod installation position (3) rotates driven by the two rollers (2), the axis of the optical signal receiving port of the image acquisition unit is perpendicular to the upper surface of the lamp stand (1), and the insulating pull rod (4) is located between the lamp stand (1) and the image acquisition unit.

2. The insulating pull rod defect detection platform based on image recognition according to claim 1 is characterized in that: The image acquisition unit comprises: An industrial camera (5) for collecting images of the surface of the insulating rod; The camera fixing bracket (6) comprises a slide rail (6-1), a camera seat (6-2) arranged on the slide rail (6-1) and sliding along the slide rail (6-1), the industrial camera (5) is fixed in the camera seat (6-2), and the visual axis of the industrial camera (5) is perpendicular to the upper surface of the lamp stand (1), and the slide rail (6-1) is parallel to the axis of the roller (2).

3. The insulating pull rod defect detection platform based on image recognition according to claim 1 is characterized in that: The distances between the axes of all rollers (2) and the upper surface of the lamp stand (1) are equal.

4. The insulating pull rod defect detection platform based on image recognition according to claim 3 is characterized in that: The relationship between the distance between the axes of any two adjacent rollers (2) and the radius of the rollers (2) is: 2≤d(g i, g i+1 ) / (r i +r i+1 )≤10 Where: d(g i, g i+1 ) is the horizontal distance between the axes of the i-th roller (2) and the i+1-th roller (2), r i is the radius of the i-th roller (2), r i+1 is the radius of the i+1th roller (2).

5. The insulating pull rod defect detection platform based on image recognition according to claim 3 is characterized in that: The diameters of all rollers (2) are the same, and the distances between the axes of all adjacent rollers (2) are equal.

6. The insulating pull rod defect detection platform based on image recognition according to claim 5 is characterized in that: The detection platform also includes a stepping motor and a transmission mechanism, wherein the output end of the stepping motor is respectively connected to and synchronously drives all rollers (2) through the transmission mechanism; The stepper motor drives the roller (2) to rotate by a first set angle every t seconds through a transmission mechanism, wherein the first set angle is: θ=2arcsin[(d-2r) / 2R] Wherein: θ is a first set angle, d is the distance between the axes of two adjacent rollers (2), r is the radius of the roller (2), and R is the radius of the insulating pull rod (4).

7. The insulating pull rod defect detection platform based on image recognition according to claim 1 is characterized in that: The lamp stand (1) comprises an outer shell (1-1) lacking a top cover, a light source (1-2) arranged in the outer shell, and a light-distributing plate (1-2) arranged on the top surface of the outer shell (1-1).

8. The insulating pull rod defect detection platform based on image recognition according to claim 7 is characterized in that: The light source (1-1) is a linear light source, and the axis of the linear light source is parallel to the axis of the roller (2).

9. The insulating pull rod defect detection platform based on image recognition according to claim 1 is characterized in that: The roller (2) comprises an axial rod (2-1) and a plurality of rollers (2-2) sleeved on the axial rod (2-1); the diameters of all rollers (2-2) of the same roller (2) are equal, and the radius of the roller (2) is the same as the radius of the roller (2-2).

10. The insulating pull rod defect detection platform based on image recognition according to claim 1, characterized in that: The surface of the roller (2) is rough.

Images