Method and system for measuring component inner cavity dimensions based on DR detection and reconstruction of three-dimensional imaging

Abstract

The present application belongs to the field of quality inspection technology, and discloses a method and system for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging. The method includes: establishing a position angle relationship model of the component, the ray source, and the imaging plate, and using the position angle relationship model to obtain a complex inner cavity multi-morphology flaw detection image of the component; adjusting the position relationship of the ray source, the imaging plate, and the inner cavity-free twin of the component to be the same as the position angle relationship model, and obtaining a multi-morphology flaw detection image of the inner cavity-free twin; performing difference processing on the multi-morphology flaw detection image of the component and the inner cavity-free twin, performing adaptive threshold processing on the difference result and performing pixel conversion to obtain the complex inner cavity contour coordinates; using the complex inner cavity contour coordinates and the position angle relationship model to reconstruct the inner cavity three-dimensional entity, and obtaining the inner cavity characteristic size to be measured from the inner cavity three-dimensional entity. The present application can break through the limitations of image clarity and detection area, and realize the measurement of the complex inner cavity size of the component based on DR detection.

Description

Technical Field

[0001] The present application belongs to the field of quality inspection, and more specifically, relates to a method and system for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging. Background Art

[0002] Complex internal components, such as hollow turbine blades, integral casings, and turbopumps, are widely used in advanced core equipment, which is experiencing surging demand in the aerospace sector. Measuring their internal dimensions is a key technology for ensuring equipment reliability and safety, and a core element in promoting high-quality, low-cost, and short-cycle intelligent manufacturing. Existing methods for measuring complex internal dimensions include 3D optical imaging and full-scale industrial CT (industrial computed tomography) inspection (ICT). 3D optical imaging relies on a manually operated endoscope to direct a low-coherence beam onto the component's internal surface and transmit the reflected light signal to the inspection instrument via optical fiber. This method suffers from limitations such as low precision on complex surfaces, numerous inspection space limitations, and low manual operation efficiency. This results in fluctuating and inefficient internal dimension measurement, making it difficult to meet the current demand for intelligent and efficient inspection of advanced core equipment. Industrial CT inspection utilizes the attenuation characteristics of radiation to obtain a large number of 2D tomographic images and generates 3D images based on image reconstruction algorithms. However, this method suffers from limitations such as low data processing efficiency and high equipment operating costs, making it difficult to implement in engineering applications. This makes it impossible to measure the dimensions of some complex internal cavities, seriously impacting the performance, lifespan, and safety of critical equipment such as casings. Summary of the Invention

[0003] In response to the defects of the existing technology, the purpose of this application is to provide a method and system for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging, aiming to solve the problems of low data processing efficiency, low accuracy in scanning complex surfaces and many detection space limitations of the existing measurement methods.

[0004] To achieve the above objectives, the present application provides a method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging, comprising the following steps:

[0005] S1 establishes a position angle relationship model of a component, a radiation source, and an imaging plate, and uses the position angle relationship model to obtain a multi-topography flaw detection image of a complex inner cavity of the component;

[0006] S2: adjusting the positional relationship among the ray source, the imaging plate, and the cavity-free twin of the component to be the same as the position angle relationship model, and obtaining a multi-morphological flaw detection image of the cavity-free twin using DR detection technology;

[0007] S3 performs a subtraction between the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image of the twin without the inner cavity, and obtains a complex inner cavity image after performing adaptive threshold processing on the subtraction result; performs pixel conversion on the complex inner cavity image to obtain the coordinates of the complex inner cavity contour;

[0008] S4 reconstructs the three-dimensional entity of the inner cavity using the complex inner cavity contour coordinates and the position angle relationship model, and obtains the inner cavity characteristic size to be measured from the three-dimensional entity of the inner cavity.

[0009] The twin-driven inner cavity contour extraction method provided in this application obtains the inner cavity contour based on the same group of flaw detection images and flaw detection parameter information, breaking through the limitations of image clarity and detection area, and solving the problems of low precision and multiple detection space restrictions in three-dimensional optical imaging scanning of complex surfaces.

[0010] Furthermore, in step S3, the step of performing adaptive threshold processing on the subtraction result includes:

[0011] S301 divides the difference result into a plurality of rectangular areas of W*W pixels in size, and calculates a local threshold value for each of the rectangular areas;

[0012] S302 compares each pixel value with the local threshold of its corresponding rectangular area: if the pixel value is greater than the corresponding local threshold, the pixel is retained; if the pixel value is less than the local threshold, the pixel is removed.

[0013] Furthermore, in step S302, the expression for calculating the local threshold is:

[0014]

[0015] Where T(x,y) represents the local threshold at position (x,y), N represents the total number of pixels in the neighborhood, (i,j) represents the neighborhood pixels around (x,y); I(i,j) represents the pixel value, and C represents a constant used to avoid over-thresholding.

[0016] Furthermore, in step S3, the complex inner cavity contour coordinates are expressed as:

[0017] {P i |P i =(x i ,y i ),i=1,2,…,n}

[0018] Among them, P i Represents the coordinates of the i-th contour point, x i Indicates the horizontal coordinate of the i-th contour point, y i It represents the vertical coordinate of the i-th contour point, and n represents the number of contour points.

[0019] Furthermore, in step S3, the complex inner cavity contour coordinates obtained after pixel conversion of the complex inner cavity image are expressed as:

[0020]

[0021] Among them, X i Y is the horizontal coordinate of the complex inner cavity contour point after pixel conversion, i is the vertical coordinate of the complex inner cavity contour point after pixel conversion, ray d is the detection distance from the ray source to the component, img d is the imaging distance from the imaging plate to the center of the component, m is the height of the imaging plate, n is the width of the imaging plate, M represents the number of pixels in the horizontal direction of the image, and N represents the number of pixels in the vertical direction of the image.

[0022] Furthermore, in step S4, the step of reconstructing the inner cavity three-dimensional entity includes:

[0023] S401: arranging a virtual ray source and a virtual imaging plate on both sides of a component model, with the centers of the virtual ray source and the virtual imaging plate being arranged relative to each other;

[0024] S402: establishing an image coordinate system with the upper left corner of the virtual imaging plate as the origin, and establishing a world coordinate system with the center of the virtual turntable as the origin;

[0025] S403: acquiring the center coordinates of the virtual imaging plate based on the coordinates of the virtual ray source in the world coordinate system; calculating the three-dimensional world coordinates of the defect contour point based on the two-dimensional image coordinates of the defect contour point and the center coordinates of the virtual imaging plate;

[0026] In step S404, a ray is drawn with the virtual ray source as the starting point and all defect contour points as the end points, the ray is rotated in sequence and intersected with the component model, the coordinates of the intersections at different rotation angles are counted, and a polyhedron containing all the intersections is obtained to obtain a three-dimensional solid of the inner cavity.

[0027] Furthermore, in step S403, the formula for calculating the three-dimensional world coordinates of the defect contour point is:

[0028]

[0029] Wherein, (X2, Y2, Z2) are the center coordinates of the virtual imaging plate, (X3, Y3) are the two-dimensional image coordinates of the defect contour point, (X4, Y4, Z4) are the three-dimensional world coordinates of the defect contour point, m is the height of the virtual imaging plate, n is the width of the virtual imaging plate, and θ is the imaging angle formed by the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system.

[0030] Furthermore, the center coordinates of the virtual imaging plate are expressed as:

[0031]

[0032] Among them, (X2, Y2, Z2) is the center coordinate of the virtual imaging plate, (X1, Y1, Z1) is the coordinate of the virtual ray source in the world coordinate system, D is the detection distance from the virtual ray source to the component model, img D is the imaging distance from the virtual imaging plate to the center of the component model, and θ is the imaging angle formed by the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system.

[0033] According to another aspect of the present application, a system for implementing a method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging is provided, comprising:

[0034] The first image acquisition module is used to establish a position angle relationship model of the component, the radiation source and the imaging plate, and to obtain a complex inner cavity multi-morphology flaw detection image of the component using the position angle relationship model;

[0035] a second image acquisition module, configured to adjust the positional relationship among the ray source, the imaging plate, and the cavity-free twin of the component to be identical to the position angle relationship model, and to acquire a multi-morphological flaw detection image of the cavity-free twin using DR detection technology;

[0036] a contour parameter acquisition module, configured to perform a subtraction between the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image of the twin without an inner cavity, and to obtain a complex inner cavity image after performing adaptive threshold processing on the subtraction result; and further configured to perform pixel conversion on the complex inner cavity image to obtain the coordinates of the complex inner cavity contour;

[0037] The inner cavity characteristic dimension acquisition module is used to reconstruct the inner cavity three-dimensional entity by using the complex inner cavity contour coordinates and the position angle relationship model, and obtain the inner cavity characteristic dimension to be measured from the inner cavity three-dimensional entity.

[0038] According to yet another aspect of the present application, a computer program product is provided. When the computer program product is run on a processor, the processor is enabled to execute any of the above methods.

[0039] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0040] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the existing technologies:

[0041] (1) This application proposes a twin-driven inner cavity contour extraction algorithm for the component to be measured. Based on the same set of flaw detection images and flaw detection parameter information, the complex inner cavity contour of the component is obtained, breaking through the limitations of image clarity and detection area, achieving high-precision and unlimited spatial detection, and solving the pain points of low precision and many spatial limitations in three-dimensional optical imaging scanning of complex surfaces.

[0042] (2) This application creates a multi-angle inner cavity entity reconstruction model and proposes a coordinate dimension upgrade method from a two-dimensional image to a three-dimensional entity, breaking through the limitations of machine automatic fitting and two-dimensional to three-dimensional, improving the efficiency of component inner cavity detection, and solving the pain point of low efficiency of three-dimensional optical imaging scanning and industrial CT full-size detection.

[0043] (3) This application develops a system for measuring the dimensions of complex internal cavities of components, providing an integrated solution from component reconstruction to dimension measurement, filling the technical gap in the existing technology of dimension measurement based on DR detection, namely digital radiography (DR) detection technology, and further reducing the pain point of high operating costs of component internal cavity detection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a component inner cavity size measurement method based on DR detection and reconstruction of three-dimensional imaging provided in an embodiment of the present application;

[0045] Figure 2 This is a schematic diagram of the process flow of the twin-driven lumen contour extraction algorithm provided in an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the process of multi-angle inner cavity entity reconstruction and measurement model provided in an embodiment of the present application;

[0047] Figure 4 This is a schematic diagram of the coordinate dimensionality-increasing model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] The term "and / or" as used herein describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. The symbol " / " as used herein indicates that the related objects are in an "or" relationship, for example, A / B means either A or B.

[0050] The terms "first" and "second" in this specification and claims are used to distinguish different objects rather than to describe a specific order of objects. For example, "first response message" and "second response message" are used to distinguish different response messages rather than to describe a specific order of response messages.

[0051] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units means two or more processing units, etc.; multiple elements means two or more elements, etc.

[0053] Next, the technical solutions provided in the embodiments of this application are introduced.

[0054] This embodiment provides a method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging, such as Figure 1 As shown, the following steps are included:

[0055] S1 establishes a position-angle relationship model among the component, the radiation source, and the imaging plate, and uses the position-angle relationship model to obtain multi-morphological flaw detection images of the complex inner cavity of the component.

[0056] Place the component on the turntable of the industrial X-ray detection device, set the initial position of the component and the turntable, adjust the position of the radiation source and the imaging plate to form a position angle relationship model of the component, radiation source and imaging plate. Use the automatic positioning system and software auxiliary tools in the detection device to record the distance from the radiation source to the casting (ray d ), the distance from the casting to the imaging plate (img d ), the turntable's rotation angle (θ). Set the turntable's rotation step size and continuously adjust the turntable's rotation angle during the inspection process. Each generated flaw detection image has corresponding position and angle parameters. These position and angle parameters are then saved in an XML file, with the file name consistent with the image name, for easy access in subsequent steps.

[0057] S2 adjusts the positional relationship between the ray source, imaging plate and the cavity-free twin of the component to be the same as the position angle relationship model, and uses DR detection technology to obtain multi-morphological flaw detection images of the cavity-free twin.

[0058] Before the component is produced, the corresponding three-dimensional model is generated, so the twin component without inner cavity can be produced based on the three-dimensional model of the component in step 1. Figure 2 As shown in FIG, a flow chart of the twin-driven inner cavity contour extraction algorithm provided in this embodiment is shown in FIG. Figure 2 As shown in a, the obtained twin component is placed on the turntable of the industrial X-ray detection device, and the initial positions of the twin component and the turntable are set. Read the XML file parameters saved in step 1, adjust the positions of the ray source, imaging plate and turntable to make them consistent with the parameters of the position angle relationship model in step S1. Then follow Figure 2 As shown in Figure (b), the twin component is inspected from multiple angles, generating multiple topographical flaw detection images of the cavity-free twin component. Each flaw detection image has position and angle parameters corresponding to the image in step 1. The position and angle parameters are saved in an XML file named the same as the image.

[0059] S3 performs subtraction on the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image, obtains the complex inner cavity image after adaptive threshold processing of the subtraction result; performs pixel conversion on the complex inner cavity image to obtain the complex inner cavity contour coordinates.

[0060] The specific steps of subtracting the complex inner cavity multi-morphology flaw detection image from the multi-morphology flaw detection image are as follows: subtracting the grayscale values ​​of the two images corresponding to the position angle parameter items of the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image without the inner cavity twin to obtain the complex inner cavity image; specifically, reading the XML format files generated by steps S1 and S2, subtracting the grayscale values ​​of the two images with the same corresponding position angle parameters to obtain a preliminary complex inner cavity image.

[0061] The specific steps of obtaining a complex intracavity image after adaptive threshold processing of the difference result are as follows:

[0062] S301 divides the difference result (i.e., the preliminary complex lumen image) into multiple rectangular areas of W*W pixels in size, and calculates the local threshold of each rectangular area. Specifically, for each local window, the mean of all pixels in the window is calculated, and then the mean is used as the local threshold. The expression for calculating the local threshold is:

[0063]

[0064] Where T(x,y) represents the local threshold at position (x,y), N represents the total number of pixels in the neighborhood; (i,j)∈N(x,y) represents the neighborhood pixels around (x,y); I(i,j) represents the pixel value, and C represents a constant used to avoid over-thresholding.

[0065] S302 compares each pixel value with the local threshold of its corresponding rectangular area: if the pixel value is greater than the local threshold of the corresponding rectangular area, the pixel is retained; if the pixel value is less than the local threshold of the corresponding rectangular area, the pixel is removed.

[0066] A complex inner cavity image is acquired based on the retained pixel values, and the coordinates of the contour points of the complex inner cavity image are pixel-converted to acquire the coordinates of the complex inner cavity contour.

[0067] Specifically, the contour extraction function in the OpenCV library is used to obtain the coordinates of the complex inner cavity contour and expressed as:

[0068] {P i |P i =(x i ,y i ),i=1,2,…,n}(2)

[0069] Among them, P i Represents the coordinates of the i-th contour point, x i Indicates the horizontal coordinate of the i-th contour point, y i It represents the vertical coordinate of the i-th contour point, and n represents the number of contour points.

[0070] After pixel conversion, the coordinates of the aforementioned complex intracavity image are expressed as:

[0071]

[0072] Among them, X i Y is the horizontal coordinate of the complex inner cavity contour point after pixel conversion, i is the vertical coordinate of the complex inner cavity contour point after pixel conversion, ray d is the detection distance from the ray source to the component, img d is the imaging distance from the imaging plate to the center of the component, m is the height of the imaging plate, n is the width of the imaging plate, M represents the number of pixels in the horizontal direction of the image, and N represents the number of pixels in the vertical direction of the image.

[0073] S4 uses the contour parameters and position angle relationship model of the complex inner cavity to reconstruct the inner cavity three-dimensional entity and obtain the inner cavity characteristic dimensions to be measured from the inner cavity three-dimensional entity.

[0074] Specifically, such as Figure 3 The figure shows a flow chart of multi-angle inner cavity entity reconstruction and measurement model. The steps of reconstructing the inner cavity three-dimensional entity include:

[0075] S401 Figure 3As shown in a, the virtual ray source and the virtual imaging plate are placed on both sides of the component model, and the centers of the virtual ray source and the virtual imaging plate are set relative to each other. The distance from the virtual ray source to the component model is defined as the detection distance (ray D ), the distance from the virtual imaging plate to the center of the component model is defined as the imaging distance (img D The height of the virtual imaging plate is m, and its width is n. The angle between the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system is defined as the imaging angle θ. Adjust the aforementioned parameters based on the XML file generated in steps S1 and S2.

[0076] S402 Figure 3 As shown in b, the image coordinate system is established with the upper left corner of the imaging plate as the origin, and the world coordinate system is established with the center of the virtual turntable as the origin;

[0077] S403 Figure 4 As shown, the center coordinates of the virtual imaging plate are obtained based on the coordinates of the virtual ray source in the world coordinate system; the three-dimensional world coordinates of the defect contour point are calculated based on the two-dimensional image coordinates of the defect contour point and the center coordinates of the virtual imaging plate to achieve coordinate dimensionality upgrade.

[0078] Specifically, the formula for calculating the three-dimensional world coordinates of the defect contour point is:

[0079]

[0080] Wherein, (X2, Y2, Z2) are the center coordinates of the virtual imaging plate, (X3, Y3) are the two-dimensional image coordinates of the defect contour point, (X4, Y4, Z4) are the three-dimensional world coordinates of the defect contour point, m is the height of the virtual imaging plate, n is the width of the virtual imaging plate, and θ is the imaging angle formed by the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system.

[0081] The center coordinates of the virtual imaging plate in the above formula (4) are expressed as:

[0082]

[0083] Among them, (X2, Y2, Z2) is the center coordinate of the virtual imaging plate, (X1, Y1, Z1) is the coordinate of the virtual ray source in the world coordinate system, D is the detection distance from the virtual ray source to the component model, img D is the imaging distance from the virtual imaging plate to the center of the component model.

[0084] S404 uses the ray source as the starting point and all defect contour points as the end points to draw rays, rotate the rays in sequence and intersect the components, count the coordinates of the intersections at different rotation angles, and obtain a polyhedron containing all the intersections to obtain the following: Figure 3 The three-dimensional solid of the inner cavity shown in c.

[0085] Specifically, after converting the two-dimensional points of the defect contour in the image into three-dimensional points in the world coordinate system using the above formulas (4)-(5), the virtual ray source is used as the starting point and the numerous defect contour points as the end points, and the intersection with the component model is calculated in sequence. The coordinates of the intersection points at each angle are counted, and the Delaunay triangulation method is used to generate a polyhedron containing all the intersection points. Each flaw detection angle can generate a polyhedron generated by the intersection. By intersecting these polyhedrons, a characteristic polyhedron representing the inner cavity entity can be obtained, completing the reconstruction process.

[0086] Create a complex internal cavity dimension measurement system. The measurement system offers a range of functions, including creating a new project, saving, configuring, and loading data. After creating a project, input the measurement system to components' internal cavity flaw detection images, flaw detection images of twin components without a cavity, and XML files. The system then outputs a reconstructed internal cavity entity. After selecting the measurement range, the PyVista and NumPy library functions are used to measure the characteristic dimensions of the internal cavity and generate the measurement results.

[0087] The twin-driven inner cavity contour extraction method provided in this application obtains the inner cavity contour based on the same group of flaw detection images and flaw detection parameter information, breaking through the limitations of image clarity and detection area, and solving the problems of low precision and multiple detection space restrictions in three-dimensional optical imaging scanning of complex surfaces.

[0088] In another embodiment, a system for implementing a method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging is provided, comprising:

[0089] The first image acquisition module is used to establish a position angle relationship model of the component, the radiation source and the imaging plate, and to obtain a complex inner cavity multi-morphology flaw detection image of the component using the position angle relationship model;

[0090] The second image acquisition module is used to adjust the positional relationship between the ray source, the imaging plate and the component's twin without inner cavity to be the same as the position angle relationship model, and to obtain multi-morphological flaw detection images of the twin without inner cavity using DR detection technology;

[0091] The contour parameter acquisition module is used to perform subtraction between the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image to obtain the contour parameters of the complex inner cavity in the image;

[0092] The inner cavity characteristic dimension acquisition module is used to reconstruct the inner cavity three-dimensional entity by using the contour parameters and position angle relationship model of the complex inner cavity, and obtain the inner cavity characteristic dimension to be measured from the inner cavity three-dimensional entity.

[0093] It is understandable that the detailed functional implementation of each of the above units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0094] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method and will not be repeated here.

[0095] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0096] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0097] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0098] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0099] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0100] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

[0101] It is easy for those skilled in the art to understand that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging, characterized in that: The following steps are involved: S1 establishes a position angle relationship model of a component, a radiation source, and an imaging plate, and uses the position angle relationship model to obtain a multi-topography flaw detection image of a complex inner cavity of the component; S2: adjusting the positional relationship among the ray source, the imaging plate, and the cavity-free twin of the component to be the same as the position angle relationship model, and obtaining a multi-morphological flaw detection image of the cavity-free twin using DR detection technology; S3: subtracting the complex inner cavity multi-morphology flaw detection image from the multi-morphology flaw detection image of the twin without inner cavity, and performing adaptive threshold processing on the subtraction result to obtain a complex inner cavity image; performing pixel conversion on the complex inner cavity image to obtain complex inner cavity contour coordinates; S4 reconstructs the three-dimensional entity of the inner cavity using the complex inner cavity contour coordinates and the position angle relationship model, and obtains the inner cavity characteristic size to be measured from the three-dimensional entity of the inner cavity.

2. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 1, characterized in that: In step S3, the step of performing adaptive threshold processing on the subtraction result includes: S301 divides the difference result into a plurality of rectangular areas of W*W pixels in size, and calculates a local threshold value for each of the rectangular areas; S302 compares each pixel value with the local threshold of its corresponding rectangular area: if the pixel value is greater than the corresponding local threshold, the pixel is retained; if the pixel value is less than the local threshold, the pixel is removed.

3. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 2, characterized in that: In step S302, the expression for calculating the local threshold is: Where T(x,y) represents the local threshold at position (x,y), N represents the total number of pixels in the neighborhood, (i,j) represents the neighborhood pixels around (x,y); I(i,j) represents the pixel value, and C represents a constant used to avoid over-thresholding.

4. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 1, characterized in that: In step S3, the coordinates of the complex lumen image are expressed as: {P i |P i =(x i ,y i ),i=1,2,…,n} Among them, P i Represents the coordinates of the i-th contour point, x i Indicates the horizontal coordinate of the i-th contour point, y i It represents the vertical coordinate of the i-th contour point, and n represents the number of contour points.

5. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 4, characterized in that: In step S3, the complex inner cavity contour coordinates obtained after pixel conversion of the complex inner cavity image are expressed as: Among them, X i Y is the horizontal coordinate of the complex inner cavity contour point after pixel conversion, i is the vertical coordinate of the complex inner cavity contour point after pixel conversion, ray d is the detection distance from the ray source to the component, img d is the imaging distance from the imaging plate to the center of the component, m is the height of the imaging plate, n is the width of the imaging plate, M represents the number of pixels in the horizontal direction of the image, and N represents the number of pixels in the vertical direction of the image.

6. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 1, characterized in that: In step S4, the step of reconstructing the inner cavity three-dimensional entity includes: S401: arranging a virtual ray source and a virtual imaging plate on both sides of a component model, with the centers of the virtual ray source and the virtual imaging plate being arranged relative to each other; S402: establishing an image coordinate system with the upper left corner of the virtual imaging plate as the origin, and establishing a world coordinate system with the center of the virtual turntable as the origin; S403: acquiring the center coordinates of the virtual imaging plate based on the coordinates of the virtual ray source in the world coordinate system; calculating the three-dimensional world coordinates of the defect contour point based on the two-dimensional image coordinates of the defect contour point and the center coordinates of the virtual imaging plate; In step S404, a ray is drawn with the virtual ray source as the starting point and all defect contour points as the end points, the ray is rotated in sequence and intersected with the component model, the coordinates of the intersections at different rotation angles are counted, and a polyhedron containing all the intersections is obtained to obtain a three-dimensional solid of the inner cavity.

7. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 6, characterized in that: In step S403, the formula for calculating the three-dimensional world coordinates of the defect contour point is: Wherein, (X2, Y2, Z2) are the center coordinates of the virtual imaging plate, (X3, Y3) are the two-dimensional image coordinates of the defect contour point, (X4, Y4, Z4) are the three-dimensional world coordinates of the defect contour point, m is the height of the virtual imaging plate, n is the width of the virtual imaging plate, and θ is the imaging angle formed by the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system.

8. The method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging according to claim 6, characterized in that: The center coordinates of the virtual imaging plate are expressed as: Among them, (X2, Y2, Z2) is the center coordinate of the virtual imaging plate, (X1, Y1, Z1) is the coordinate of the virtual ray source in the world coordinate system, D is the detection distance from the virtual ray source to the component model, img D is the imaging distance from the virtual imaging plate to the center of the component model, and θ is the imaging angle formed by the line connecting the virtual ray source and the center of the virtual imaging plate and the X-axis in the world coordinate system.

9. A system for realizing a method for measuring the inner cavity size of a component based on DR detection and reconstruction of three-dimensional imaging, characterized in that: include: The first image acquisition module is used to establish a position angle relationship model of the component, the radiation source and the imaging plate, and to obtain a complex inner cavity multi-morphology flaw detection image of the component using the position angle relationship model; a second image acquisition module, configured to adjust the positional relationship among the ray source, the imaging plate, and the cavity-free twin of the component to be identical to the position angle relationship model, and to acquire a multi-morphological flaw detection image of the cavity-free twin using DR detection technology; a contour parameter acquisition module, configured to perform a subtraction between the complex inner cavity multi-morphology flaw detection image and the multi-morphology flaw detection image of the twin without an inner cavity, and to obtain a complex inner cavity image after performing adaptive threshold processing on the subtraction result; and further configured to perform pixel conversion on the complex inner cavity image to obtain the coordinates of the complex inner cavity contour; The inner cavity characteristic dimension acquisition module is used to reconstruct the inner cavity three-dimensional entity by using the complex inner cavity contour coordinates and the position angle relationship model, and obtain the inner cavity characteristic dimension to be measured from the inner cavity three-dimensional entity.

10. A computer program product, characterized in that When the computer program product is run on a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

Images