Pinhole through-blind state judgment method and device, electronic equipment and storage medium

Abstract

The invention relates to a small hole through-blind state judgment method and device, electronic equipment and a storage medium. The method for judging the through-blind state of the small hole comprises the steps that a focusing image sequence of the small hole to be detected is obtained, and the focusing image sequence is a two-dimensional image set based on visible light and obtained by scanning the small hole to be detected in the axial direction at equal intervals; generating a full-clear image of the to-be-detected small hole according to the focusing image sequence, wherein the full-clear image is an image in which each part of the to-be-detected small hole is clear; and determining the through-blind state of the to-be-detected small hole according to the average gray value of the full-clear image in the sub-region of the preset range in the to-be-detected small hole and a preset threshold value. According to the method, the through-blind state of the small hole in the mass production process can be rapidly and accurately judged.

Description

Technical Field

[0001] The present application relates to the field of machine vision detection technology, and in particular to a method, device, electronic device and storage medium for determining the through-blind state of a small hole. Background Art

[0002] In major national technical equipment such as aircraft engines and gas turbines, many key components are designed with tiny through-hole features, such as cooling holes on turbine blades and spray holes on fuel nozzles. Due to the difficulty of hole making, special hole making processes such as electric spark, electro-hydraulic beam and femtosecond laser are usually used. In the process of hole making, it is inevitable that internal defects such as blind holes will occur due to inadequate through-hole processing. If the hole is not in good condition, or even in a blind hole state, it will reduce or block the flow of the working medium, affecting the normal and stable operation of the entire technical equipment. Therefore, the through (through) and blind (not through) state of the small hole has become one of the important geometric technical state parameters of related components and has received widespread attention.

[0003] In the prior art, due to the complexity of the geometry and inner cavity structure of turbine blades, fuel nozzles, etc., the product inspection and quality control issues such as the blindness and blockage status of the small holes on them are usually carried out by using the stop-through needle gauge method and the water injection test method. The former is that the operator inserts a needle gauge of a selected size into the hole to check the actual state of the hole; the latter is to inject a certain pressure of water into the inner cavity of the component, and then visually observe the water flow injection status of each small hole to complete the penetration inspection of the small hole. The above manual inspection and judgment methods have a large workload, low efficiency, and are easily affected by subjective factors, resulting in missed inspections and misjudgments. It is difficult to cope with the task of quickly and accurately judging the blindness and blockage status of small holes in mass production. Summary of the invention

[0004] (1) Technical issues to be solved

[0005] The present application provides a method, device, electronic device and storage medium for determining the through-and-blind state of a small hole, which solves the problem that the prior art is difficult to cope with in rapidly and accurately determining the through-and-blind state of a small hole in a mass production process.

[0006] (2) Technical solution

[0007] In a first aspect, the present application provides a method for determining a blind hole state, comprising:

[0008] Acquire a focused image sequence of the pinhole to be tested, wherein the focused image sequence is a set of two-dimensional images based on visible light obtained by scanning the pinhole to be tested at equal intervals along the axial direction;

[0009] Generate a full-clear image of the pinhole to be tested according to the focused image sequence, wherein the full-clear image is an image in which all parts of the pinhole to be tested are clear;

[0010] The blind state of the small hole to be tested is determined according to the average grayscale value of the sub-area of ​​the full-resolution image within the preset range inside the small hole to be tested and a preset threshold.

[0011] Furthermore, before acquiring the focused image sequence of the pinhole to be tested, the method further includes:

[0012] The step length, moving range and starting position of the axially evenly spaced scanning of the small hole to be measured are determined.

[0013] Further, generating a full-definition image of the pinhole to be tested according to the focused image sequence includes:

[0014] Extracting pixels of the clearest part of each image in the focused image sequence using a set pixel clarity evaluation algorithm and a prescribed focus measurement;

[0015] By using the set overlapping and splicing rules, the pixels of the clearest part of each image are fused according to the original image position to generate a full clear image of the pinhole to be tested.

[0016] Further, the determining of the blind state of the small hole to be tested according to the average grayscale value of the sub-region of the full-resolution image within the preset range inside the small hole to be tested and a preset threshold value includes:

[0017] Determine a circular sub-region inside the pinhole to be tested, the sub-region having its center located at the center of the image and a pixel diameter smaller than the theoretical pixel diameter of the pinhole to be tested;

[0018] If the average grayscale value of the full-resolution image in the circular sub-area is less than the preset threshold, the small hole to be tested is determined to be a through hole, otherwise it is a blind hole.

[0019] Furthermore, after determining the blind state of the small hole to be tested according to the average grayscale value of the sub-region of the preset range within the small hole to be tested of the full-resolution image and the preset threshold, the method further includes:

[0020] The physical aperture of the through hole is determined according to the pixel diameter of the through hole and the calibrated pixel size equivalent.

[0021] Furthermore, the method for determining the blind state of the small hole further includes:

[0022] Determine the detection path of the part to be detected according to all the small holes to be detected on the part to be detected;

[0023] According to the detection path, the through-hole and blind-hole status determination of all the small holes to be tested on the tested part and the through-hole diameter detection are completed to determine the number of through holes and the number of blind holes.

[0024] In a second aspect, the present application provides a small hole blind state determination device, including a five-axis machine vision detection platform and a host computer; the five-axis machine vision detection platform includes a base assembly, a three-axis linear motion assembly, a two-axis rotary motion assembly, an image acquisition assembly and a fixture assembly;

[0025] The three-axis linear motion component is installed on the base component, and the image acquisition component is installed on the three-axis linear motion component; the two-axis rotary motion component is installed on the base component, and the fixture component is installed on the two-axis rotary motion component;

[0026] The fixture assembly is used to clamp the measured part, the two-axis rotary motion assembly is used to drive the measured part to rotate, the three-axis linear motion assembly is used to drive the image acquisition assembly to move linearly, and the image acquisition assembly works within the visible light spectrum range and is used to scan the small holes to be measured on the measured part at equal intervals along the axial direction;

[0027] The host computer is connected to the five-axis machine vision inspection platform; the host computer is used to implement the small hole blind state determination method as described above.

[0028] Furthermore, the image acquisition component includes an industrial camera, a telecentric lens and an LED ring light source; the telecentric lens is mounted on the industrial camera, and the LED ring light source is mounted on the telecentric lens.

[0029] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for determining the blind state of a small hole as described above when executing the computer program.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for determining the blind state of a small hole as described above is implemented.

[0031] (3) Beneficial effects

[0032] The above technical solution of the present application has the following advantages:

[0033] The method for determining the blind state of a small hole provided in the first aspect of the present application obtains a set of two-dimensional images based on visible light obtained by scanning the small hole to be tested at equal intervals along the axial direction. Compared with imaging detection methods such as X-ray, infrared and fluorescence, the method has the advantages of low cost, simple principle and strong versatility. By using a full-clear image in which all parts of the small hole to be tested are clear, the blind state of the small hole is analyzed. It has the advantages of high reliability, strong robustness and anti-interference ability, low misjudgment rate and high aperture detection accuracy, and can cope with the rapid and accurate determination of the blind state of the small hole in the mass production process.

[0034] It can be understood that the beneficial effects of the second, third and fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A schematic diagram of the flow chart of the method for determining the blind state of a small hole provided in this application;

[0037] Figure 2 A schematic diagram of the structure of the five-axis machine vision inspection platform provided for this application;

[0038] Figure 3 A schematic diagram of the structure of the image acquisition component provided for this application;

[0039] Figure 4 A schematic diagram of the acquisition process of the focus image sequence provided in this application;

[0040] Figure 5 The overall flow chart of the method for determining the blind state of a small hole provided in this application;

[0041] Figure 6 A full clear image of a turbine blade cooling hole and a schematic diagram of a circular sub-area provided in this application;

[0042] Figure 7 A full clear image of a turbine blade cooling hole and a schematic diagram of a circular sub-area provided in this application;

[0043] Figure 8 The edge extraction and least squares circle fitting result diagram of a turbine blade cooling hole provided in this application;

[0044] Fig. 9A schematic diagram of the structure of the electronic device provided in this application.

[0045] Figure numerals: 1. Five-axis machine vision inspection platform; 11. Base assembly; 12. Three-axis linear motion assembly; 13. Two-axis rotary motion assembly; 14. Image acquisition assembly; 141. Industrial camera; 142. Telecentric lens; 143. LED ring light source; 144. Imaging optical axis; 15. Fixture assembly; 2. Part to be tested; 21. Small hole to be tested; 3. Focus image sequence; 4. Circular sub-area. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0047] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0048] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0049] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. "Multiple" means "two or more".

[0050] In order to solve the problems existing in the prior art, the present application provides a method for determining the through-and-blind status of small holes. Based on a five-axis machine vision inspection platform, the method adopts digital image processing and analysis methods to realize rapid and accurate determination of the through-and-blind status of small holes such as turbine blade cooling holes and fuel nozzle spray holes within the visible light spectrum range, and can further realize the counting of through holes and blind holes and the calculation of through hole apertures.

[0051] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0052] like Figure 1 As shown, the embodiment of the present application provides a method for determining a small hole blind state, comprising:

[0053] Acquire a focused image sequence of the pinhole to be tested, wherein the focused image sequence is a set of two-dimensional images based on visible light obtained by scanning the pinhole to be tested at equal intervals along the axial direction;

[0054] Generate a full-clear image of the pinhole to be tested according to the focused image sequence, wherein the full-clear image is an image in which all parts of the pinhole to be tested are clear;

[0055] The blind state of the small hole to be tested is determined according to the average grayscale value of the sub-area of ​​the full-resolution image within the preset range inside the small hole to be tested and a preset threshold.

[0056] The present application first obtains a focused image sequence of the pinhole to be tested, and then reconstructs and synthesizes a full-clear image to determine the blind state of the pinhole to be tested. A sub-area of ​​a preset range is set inside the pinhole to be tested on the full-clear image and the average grayscale of the pixels inside is calculated, which is used as a criterion and compared with the set threshold to determine the blind state of the pinhole.

[0057] The image acquisition component working in the visible light spectrum can be used as the front-end sensor to scan the small hole to be tested. Compared with X-ray, infrared and fluorescence imaging detection methods, it has the advantages of low cost, simple principle and strong versatility. Since a full-clear image that can truly reflect the entire surface of the small hole to be tested is used to analyze the blind state of the small hole, it has the advantages of high reliability, strong robustness and anti-interference ability, low misjudgment rate and high aperture detection accuracy.

[0058] In some embodiments, before acquiring the focused image sequence of the pinhole to be tested, the method further includes:

[0059] The step length, moving range and starting position of the axially evenly spaced scanning of the small hole to be measured are determined.

[0060] In some embodiments, generating a full-resolution image of the pinhole to be tested according to the focused image sequence includes:

[0061] Extracting pixels of the clearest part of each image in the focused image sequence using a set pixel clarity evaluation algorithm and a prescribed focus measurement;

[0062] By using the set overlapping and splicing rules, the pixels of the clearest part of each image are fused according to the original image position to generate a full clear image of the pinhole to be tested.

[0063] In some embodiments, determining the blind state of the small hole to be tested according to the average grayscale value of the sub-region of the full-resolution image within a preset range inside the small hole to be tested and a preset threshold value includes:

[0064] Determine a circular sub-region inside the pinhole to be tested, the sub-region having its center located at the center of the image and a pixel diameter smaller than the theoretical pixel diameter of the pinhole to be tested;

[0065] If the average grayscale value of the full-resolution image in the circular sub-area is less than the preset threshold, the small hole to be tested is determined to be a through hole, otherwise it is a blind hole.

[0066] In some embodiments, after determining the blind state of the small hole to be tested according to the average grayscale value of the sub-region of the preset range within the small hole to be tested of the full-resolution image and the preset threshold, the method further includes:

[0067] The physical aperture of the through hole is determined according to the pixel diameter of the through hole and the calibrated pixel size equivalent.

[0068] In some embodiments, the method for determining the blind state of a small hole further includes:

[0069] Determine the detection path of the part to be detected according to all the small holes to be detected on the part to be detected;

[0070] According to the detection path, the through-hole and blind-hole status determination of all the small holes to be tested on the tested part and the through-hole diameter detection are completed to determine the number of through holes and the number of blind holes.

[0071] The method for determining the through and blind status of small holes provided in the present application aims to provide a method for quickly and accurately determining the through and blind status of batch small holes using visible light machine vision and digital image processing and analysis technology, targeting the small hole features on key components such as turbine blade cooling holes and fuel nozzle spray holes, and can further count through holes and blind holes and detect the aperture size of through holes.

[0072] This method is based on Figure 2The five-axis machine vision inspection platform 1 shown is implemented as follows. The five-axis machine vision inspection platform 1 comprises a base assembly 11 , a three-axis linear motion assembly 12 , a two-axis rotary motion assembly 13 , an image acquisition assembly 14 and a fixture assembly 15 .

[0073] The five-axis machine vision inspection platform 1 has three linear motion axes X, Y, and Z and two rotary motion axes B and C, which can realize single-axis motion and multi-axis linkage; the three linear motion axes X, Y, and Z are perpendicular to each other and integrated together, which are realized by a three-axis linear motion component 12; the two rotary motion axes B and C are perpendicular to each other and integrated together, the direction of the B axis is parallel to the direction of the Y axis, and the direction of the C axis is parallel to the direction of the Z axis, which are realized by a two-axis rotary motion component 13, the angle rotation range of the B axis is -90° to +90°, and the angle rotation range of the C axis is 0° to 360°.

[0074] The three-axis linear motion assembly 12 is mounted on the base assembly 11, and each linear axis is equipped with an air-floating guide rail and a high-precision linear grating ruler to ensure the motion stability and linear displacement accuracy of each linear axis. The image acquisition assembly 14 is mounted on the moving end of the Z axis of the three-axis linear motion assembly 12, and the imaging optical axis 144 of the image acquisition assembly 14 is parallel to the Z axis of the three-axis linear motion assembly 12 through mechanical adjustment.

[0075] The two-axis rotary motion assembly 13 is fixed on the base assembly 11, and the two-axis rotary motion assembly 13 is located in the middle of the Y-axis travel of the three-axis linear motion assembly 12. Each rotary axis is equipped with a high-precision circular grating scale to ensure the motion stability and angular displacement accuracy of each rotary axis. The fixture assembly 15 is fixed on the table of the two-axis rotary motion assembly 13, and the measured part 2 is clamped in the fixture assembly 15.

[0076] like Figure 3 and Figure 4 As shown, the image acquisition component 14 includes an industrial camera 141, a telecentric lens 142, and an LED ring light source 143, all of which work within the visible light spectrum. The telecentric lens 142 is installed in the lens interface at the front end of the industrial camera 141, and the LED ring light source 143 is installed at the front end of the telecentric lens 142 through a fixture, and is used for bright field forward illumination of the small hole 21 to be measured.

[0077] like Figure 5 As shown, the method is specifically implemented through the following steps:

[0078] Step 1: Clamp the part to be tested. After cleaning, put the part to be tested 2 into the fixture assembly 15 , and then use a micrometer or the like to mechanically adjust and align the part to be tested 2 and then clamp it, so that the part to be tested 2 is correctly positioned in the fixture assembly 15 .

[0079] Step 2: Plan the detection path. Import the digital model of the tested part 2 into the host computer software, pick up all the small holes 21 to be tested in turn, and plan the detection path. Then, according to the axial depth of the small hole 21 to be tested and the depth of field of the telecentric lens 142, set the step length, moving range and starting position along the Z axis direction when the image acquisition component 14 is used to obtain the focused image sequence 3 in the host computer software, so that the moving range is larger than the axial depth of the small hole 21 to be tested, and the step length is smaller than the depth of field of the telecentric lens 142. At the same time, the number of through holes N T and the number of blind holes is N B Both are set to 0.

[0080] Step three, collect the focused image sequence. According to the planned detection path, on the one hand, the two-axis rotary motion component 13 is controlled to drive the measured part 2 to rotate, so that the opening of the small hole 21 to be measured faces the positive direction of the Z axis, and further the axial direction of the small hole 21 to be measured is parallel to the Z axis direction; on the other hand, the three-axis linear motion component 12 is controlled to drive the image acquisition component 14 to move, so that it is aligned with the small hole 21 to be measured and moves to the starting position. At this time, the small hole 21 to be measured completely enters the field of view of the image acquisition component 14 and is in the central position of the field of view. Then the three-axis linear motion component 12 is controlled to drive the image acquisition component 14 to move at equal intervals from the starting position along the Z axis direction according to the set step size and moving range, and synchronously collect the two-dimensional image of the small hole 21 to be measured, thereby completing the axial equal-interval scanning of the small hole 21 to be measured and obtaining a series of two-dimensional images. The collection of these two-dimensional images is called the focused image sequence 3.

[0081] Step 4: Synthesize a fully clear image. Each image in the focused image sequence 3 is processed by the digital image processing and analysis module in the upper computer software, and the set pixel clarity evaluation algorithm and the specified focus measurement are used to extract the pixels of each image that are clearly imaged. Then, through the set superposition and splicing rules, the clear pixels in each image are all merged into a new image according to their positions in the original image, thereby reconstructing and synthesizing a new image of the small hole 21 to be tested with all parts being very clear and sharp, that is, a fully clear image.

[0082] Step 5: Calculate the blind state criterion. In the hole internal area of ​​the synthesized full-resolution image, a circular sub-area 4 is set with the center located at the center of the image and the pixel diameter smaller than the theoretical pixel diameter of the small hole 21 to be tested. The pixel diameter d R (Unit: pixel) can be calculated by the following formula:

[0083]

[0084] Wherein, D0 is the theoretical physical diameter of the small hole 21 to be measured, unit: mm; K is the pixel size equivalent of the calibrated image acquisition component 14, unit: mm / pixel; a is the proportional coefficient, 0 <a≤1。

[0085] Step 6: Determine the through-hole or blind-hole state. The average grayscale value L (0≤L≤255) of all pixels in the circular sub-area 4 is set as the through-hole or blind-hole state criterion of the small hole 21 to be tested. The small hole 21 to be tested is determined to be a through hole or a blind hole according to its size. The calculation formula of the average grayscale value L is as follows:

[0086]

[0087] Where N is the number of pixels in the circular sub-area 4; L i is the gray value of the i-th pixel in the circular sub-area 4, i=1, 2, ..., N. Then the calculated average gray value L is compared with the set threshold value L0, and the result is used to judge the blind state of the small hole 21 to be tested, that is,

[0088]

[0089] If the small hole 21 to be tested is determined to be a through hole, then the number of through holes N T The value of is added by 1, and the judgment result is recorded; if the small hole 21 to be tested is judged to be a blind hole, the number of blind holes N B Add 1 to the value and record the judgment result.

[0090] Step 7: Detect the aperture of the through hole. For the small hole 21 to be detected that is determined to be a through hole, its pixel diameter d can be further calculated through steps such as median filtering, threshold segmentation, region selection, edge extraction and least squares circle fitting. H (unit: pixel), and then multiplied by the calibrated pixel size equivalent K of the image acquisition component 14 (unit: mm / pixel), the physical aperture D of the through hole can be obtained. H (Unit: mm), that is

[0091] D H =d H ·K (3)

[0092] Repeat steps 3 to 7 according to the planned detection path to complete the blind state determination and through-hole diameter detection tasks of all the small holes 21 to be tested on the tested part 2 in sequence, and output the through-hole number N T and the number of blind holes N B .

[0093] The present application also provides a device for determining the blind state of a small hole, including a five-axis machine vision detection platform and a host computer; Figure 2As shown, the five-axis machine vision inspection platform 1 includes a base assembly 11, a three-axis linear motion assembly 12, a two-axis rotary motion assembly 13, an image acquisition assembly 14 and a fixture assembly 15;

[0094] The three-axis linear motion component 12 is installed on the base component 11, and the image acquisition component 14 is installed on the three-axis linear motion component 12; the two-axis rotary motion component 13 is installed on the base component 11, and the fixture component 15 is installed on the two-axis rotary motion component 13;

[0095] The fixture assembly 15 is used to clamp the measured part 2, the two-axis rotary motion assembly 13 is used to drive the measured part 2 to rotate, and the three-axis linear motion assembly 12 is used to drive the image acquisition assembly 14 to move linearly. The image acquisition assembly 14 works within the visible light spectrum and is used to scan the small holes to be measured on the measured part 2 at equal intervals along the axial direction;

[0096] The host computer is connected to the five-axis machine vision inspection platform 1; the host computer is used to implement the small hole blind state determination method as described above.

[0097] In some embodiments, Figure 3 and Figure 4 As shown, the image acquisition component includes an industrial camera 141 , a telecentric lens 142 and an LED ring light source 143 ; the telecentric lens 142 is mounted on the industrial camera 141 , and the LED ring light source 143 is mounted on the telecentric lens 142 .

[0098] The five-axis machine vision inspection platform of this embodiment, its base assembly and three-axis linear motion assembly can be realized by the FUTURE755 three-coordinate measuring machine; the two-axis rotary motion assembly can be realized by the 902E-1 two-axis position turntable; the image acquisition assembly can be composed of a Grasshopper3 series industrial camera, an MML-ST series telecentric lens and a P-RL series LED ring light source.

[0099] A certain type of turbine blade is selected as the part to be tested, and the cooling holes distributed on it are selected as the small holes to be tested, whose theoretical physical diameter D0 = 0.5mm. Figure 6 and Figure 7 The following are the reconstructed and synthesized full-resolution images of two cooling holes. In the five-axis machine vision inspection platform, the threshold L0 is set to 128, the proportional coefficient a is set to 0.8, and the calibrated pixel size equivalent K is set to 0.0005 mm / pixel. According to formula (1), the pixel diameter d of the circular sub-area 4 is set to R for:

[0100]

[0101] In Figure 6 it, the average gray value L of all pixels within the circular sub-region thereon is calculated according to Equation (2) as L = 18.5, which is within the range of 0 ≤ L < L0, so it is determined that this hole is a through-hole; in Figure 7 it, the average gray value L of all pixels within the circular sub-region thereon is calculated according to Equation (2) as L = 236.4, which is within the range of L0 ≤ L ≤ 255, so it is determined that this hole is a blind hole.

[0102] As Figure 8 shown, for the cooling holes determined to be through-holes, their pixel diameters d are calculated through steps such as median filtering, threshold segmentation, region selection, edge extraction, and least squares circle fitting H = 1042 pixel, and according to Equation (3), the physical diameter D of this cooling hole can be obtained H , that is

[0103] D H = d H ·K = 1042·0.0005 = 0.521

[0104] The method and device for determining the through / blind state of small holes provided by the embodiments of the present application can quickly and accurately determine the through / blind state of a batch of small holes by applying visible light machine vision and digital image processing and analysis technologies. This method is implemented relying on a non-contact five-axis machine vision detection platform, and its steps include clamping the part to be measured, planning the detection path, collecting a sequence of focused images, synthesizing a fully clear image, calculating the through / blind state criterion, determining the through / blind state, and detecting the aperture of the through-hole. The present application provides a reference solution for the geometric technical state evaluation and quality inspection of small hole features such as turbine blade cooling holes and fuel nozzle spray holes, which helps to improve the manufacturing quality of such key components, and has the advantages of low cost, high efficiency, simple principle, strong versatility, and easy automation, and has great practical application value.

[0105] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application.

[0106] The embodiments of the present application also provide an electronic device 900, such as Fig. 9 As shown, it includes a memory 901, a processor 902, and a computer program 903 stored in the memory 901 and executable on the processor 902. When the processor 902 executes the computer program 903, the steps of the method for determining the blind state of the small hole provided in the first aspect are implemented.

[0107] In applications, the electronic device may include, but is not limited to, a processor and a memory. Fig. 9 This is only an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input and output devices, network access devices, etc. Input and output devices may include cameras, audio acquisition / playback devices, display screens, etc. Network access devices may include a network module for wirelessly communicating with external devices.

[0108] In applications, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0109] In application, the memory may be an internal storage unit of an electronic device in some embodiments, such as a hard disk or memory of the electronic device. The memory may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. The memory may also include both an internal storage unit of the electronic device and an external storage device. The memory is used to store operating systems, applications, boot loaders (BootLoader), data, and other programs, such as program codes of computer programs, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0110] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0111] The present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0112] Those of ordinary skill in the art will appreciate that the devices and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0113] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices, which can be electrical, mechanical or other forms.

[0114] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for determining the blind state of a small hole, characterized in that: include: Acquire a focused image sequence of the pinhole to be tested, wherein the focused image sequence is a set of two-dimensional images based on visible light obtained by scanning the pinhole to be tested at equal intervals along the axial direction; Generate a full-clear image of the pinhole to be tested according to the focused image sequence, wherein the full-clear image is an image in which all parts of the pinhole to be tested are clear; The blind state of the small hole to be tested is determined according to the average grayscale value of the sub-area of ​​the full-resolution image within the preset range inside the small hole to be tested and a preset threshold.

2. The method for determining the blind state of a small hole according to claim 1, characterized in that: Before acquiring the focused image sequence of the pinhole to be tested, the method further includes: The step length, moving range and starting position of the axially evenly spaced scanning of the small hole to be measured are determined.

3. The method for determining the blind state of a small hole according to claim 1, characterized in that: The step of generating a full-resolution image of the pinhole to be tested according to the focused image sequence comprises: Extracting pixels of the clearest part of each image in the focused image sequence using a set pixel clarity evaluation algorithm and a prescribed focus measurement; By using the set overlapping and splicing rules, the pixels of the clearest part of each image are fused according to the original image position to generate a full clear image of the pinhole to be tested.

4. The method for determining the blind state of a small hole according to claim 1, characterized in that: The step of determining the blind state of the small hole to be tested according to the average grayscale value of a sub-region of a preset range within the small hole to be tested of the full-resolution image and a preset threshold value comprises: Determine a circular sub-region inside the pinhole to be tested, the sub-region having its center located at the center of the image and a pixel diameter smaller than the theoretical pixel diameter of the pinhole to be tested; If the average grayscale value of the full-resolution image in the circular sub-area is less than the preset threshold, the small hole to be tested is determined to be a through hole, otherwise it is a blind hole.

5. The method for determining the blind state of a small hole according to claim 1, characterized in that: After determining the blind state of the small hole to be tested according to the average grayscale value of the sub-area of ​​the full clear image within the preset range inside the small hole to be tested and the preset threshold, the method further includes: The physical aperture of the through hole is determined according to the pixel diameter of the through hole and the calibrated pixel size equivalent.

6. The method for determining the blind state of a small hole according to claim 1, characterized in that: The method for determining the blind state of the small hole further includes: Determine the detection path of the part to be detected according to all the small holes to be detected on the part to be detected; According to the detection path, the through-hole and blind-hole status determination of all the small holes to be tested on the tested part and the through-hole diameter detection are completed to determine the number of through holes and the number of blind holes.

7. A device for determining the blind state of a small hole, characterized in that: It includes a five-axis machine vision inspection platform and a host computer; the five-axis machine vision inspection platform includes a base assembly, a three-axis linear motion assembly, a two-axis rotary motion assembly, an image acquisition assembly and a fixture assembly; The three-axis linear motion component is installed on the base component, and the image acquisition component is installed on the three-axis linear motion component; the two-axis rotary motion component is installed on the base component, and the fixture component is installed on the two-axis rotary motion component; The fixture assembly is used to clamp the measured part, the two-axis rotary motion assembly is used to drive the measured part to rotate, the three-axis linear motion assembly is used to drive the image acquisition assembly to move linearly, and the image acquisition assembly works within the visible light spectrum range and is used to scan the small holes to be measured on the measured part at equal intervals along the axial direction; The host computer is connected to the five-axis machine vision inspection platform; the host computer is used to implement the method for determining the blind state of a small hole as described in any one of claims 1 to 6.

8. The device for determining the blind state of a small hole according to claim 7, characterized in that: The image acquisition component includes an industrial camera, a telecentric lens and an LED ring light source; the telecentric lens is installed on the industrial camera, and the LED ring light source is installed on the telecentric lens.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for determining the blind state of a small hole according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for determining the blind state of a small hole according to any one of claims 1 to 6 is implemented.

Images