A method and system for acquiring three-dimensional point clouds of film holes in turbine blades

Abstract

The present invention discloses a method and system for acquiring three-dimensional point clouds of film holes in turbine blades, which uses a device to obtain zoom microscopic sequence images of the film holes, and adopts an image defogging and edge retention method based on double filtering for all sequence images to remove image noise and enhance the brightness of the image area; uses a focusing evaluation method to perform focusing evaluation calculation on the zoom image sequence of the film holes, obtains a focusing evaluation curve for each pixel point of the film hole sequence image, and uses a maximum value screening method based on a flat area threshold to preliminarily determine the area where the pixel point focusing maximum value is located; according to the focusing evaluation curve of each pixel point, uses an adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain accurate pixel point focusing maximum value, and finally obtains the three-dimensional morphology of the film hole; the method of the present invention has high measurement accuracy and fast speed, and can realize the surface and inner wall measurement of special-shaped holes such as film holes.

Description

Technical Field

[0001] The present invention belongs to the technical field of aero-engine detection, and in particular relates to a method and system for acquiring three-dimensional point clouds of film holes in turbine blades. Background Art

[0002] Film holes are essential structures for improving aeroengine reliability and blade high-temperature performance. Their aperture size, axial orientation, spatial distribution, and shape must strictly meet design requirements. Zoom microscopy, a novel optical topography measurement method, is highly efficient, non-destructive, and can detect the internal features of micro-holes. Therefore, a film hole feature detection algorithm based on zoom microscopy image sequences enables high-precision quality inspection of film holes.

[0003] Zoom microscopy measurement technology is divided into image preprocessing, image sequence focus evaluation, and three-dimensional model reconstruction. Currently, some domestic scientific research institutions are committed to the research of this technology. Existing research work is mostly aimed at the focus evaluation and three-dimensional reconstruction of the microscopic surfaces of common components. However, there is no research on the optical path design and point cloud extraction methods for high-steepness tiny features such as air film pores.

[0004] The three-dimensional point cloud acquisition method is a key issue in air film hole measurement. The quantity and quality of the acquired point cloud will affect the accuracy of the evaluation of the geometric parameters of the air film holes, and the speed of acquiring the point cloud will affect the actual efficiency of batch detection of air film holes. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to address the deficiencies in the above-mentioned prior art and provide a method and system for acquiring three-dimensional point clouds of film holes in turbine blades, so as to solve the technical problem of point cloud extraction methods for complex and tiny features of film holes with high steepness.

[0006] The present invention adopts the following technical solutions:

[0007] A method for obtaining a three-dimensional point cloud of a turbine blade film hole comprises the following steps:

[0008] S1. Acquire zoom microscopic sequence images of air film holes, perform Gaussian blur defogging on the zoom microscopic sequence images of air film holes, use edge preservation method to remove noise from the zoom microscopic sequence images of air film holes and enhance the brightness of the image area;

[0009] S2. Performing focus evaluation calculation on the zoom image sequence of the air film hole obtained in step S1 using a gradient focus evaluation method, obtaining a focus evaluation curve for each pixel in the zoom image sequence of the air film hole, and preliminarily determining the region where the pixel focus maximum value is located using a maximum value screening method based on a flat region threshold;

[0010] S3. Based on the focus evaluation curve of each pixel point obtained in step S2 and the area where the pixel point focus maximum value is preliminarily determined, an adaptive truncation method based on the standard deviation of the Gaussian distribution is used to obtain the accurate pixel point focus maximum value, and finally a three-dimensional point cloud of the air film hole is obtained.

[0011] Specifically, step S1 is as follows:

[0012] S101, establishing a fog image formation model using a sequence of air film hole images and calculating the global atmospheric light component A;

[0013] S102, the dark color prior image I of the fog image obtained in step S101 is formed into a model d (x,y) performs Gaussian filtering to obtain the image after Gaussian filtering And make the difference to get the absolute value B(x,y);

[0014] S103. Consider the constraint 0≤G(x,y)≤I d (x,y), and calculate the atmospheric light curtain G(x,y);

[0015] S104, calculating J(x, y) based on G(x, y) obtained in step S103 to obtain a sequence of air film hole images after defogging;

[0016] S105 , applying a guided filtering operation with the guide image being the image itself to the air film hole image sequence after defogging in step S104 , and performing an edge-preserving filtering operation.

[0017] Furthermore, in step S101, the fog image formation model is as follows:

[0018] I(x,y)=J(x,y)t(x,y)+A(1-t(x,y))

[0019]

[0020] Among them, I(x,y) is the input image, J(x,y) is the fog-free image, A is the global atmospheric light component, t(x,y) is the transmittance, I d (x,y) is the dark color prior map, and Ω(x,y) is the local area centered at point (,y).

[0021] Furthermore, in step S102, the absolute value of the difference B(x, y) is calculated as follows:

[0022]

[0023] Among them, r is the coefficient factor and Gfilter is Gaussian filter.

[0024] Specifically, step S2 is as follows:

[0025] S201, using the focus evaluation function to calculate the focus function evaluation function value F of each pixel point in the image sequence M (x0,y0);

[0026] S202: Segment the focus evaluation sequence obtained in step S201 using a maximum value screening method based on a flat region threshold to obtain flat regions and non-flat regions, and preliminarily determine the region where the pixel focus maximum value is located;

[0027] S203, since it is inevitable that there will be erroneous maximum values in the actual focus evaluation sequence, it is assumed that k non-flat areas are segmented, each of which contains many pixel focus evaluation values, which are recorded as arrays array1, array2...array k ;

[0028] S204, calculate array1, array2, ... array by Max(len(array)) k The longest array in array i , as the non-flat area where the actual maximum value is located, the area where the pixel focus maximum value is located is preliminarily determined.

[0029] Furthermore, in step S201, the focus function evaluation function value F of each pixel in the image sequence is M (x0,y0) is calculated as follows:

[0030]

[0031] Among them, G x (x,y) is the gradient operator in the horizontal direction, G y (x,y) is the gradient operator in the vertical direction, and Ω(x,y) is the local area centered at point (x,y).

[0032] Furthermore, step S202 is specifically as follows:

[0033] S2021. Calculate the average of the focus evaluation values in the entire focus evaluation sequence as the flat area threshold. x,y ;

[0034] S2022, according to the flat area threshold Threshold x,y The focus evaluation sequence is divided. The same point should have only one maximum value position in the entire focus evaluation sequence. The area with a certain width extending to both sides with this position as the center is the non-flat area.

[0035] Specifically, step S3 is as follows:

[0036] S301, array array obtained according to step S2 i The length of Len(array i ) Calculate the estimated standard deviation σ i ;

[0037] S302, array i The maximum value is located at the center, and the standard deviation estimate σ is taken on both sides of it. i points, the extraction length is len(array i ), as the interception range for the final Gaussian fitting;

[0038] S303. Perform Gaussian fitting on the points in the intercepted range to obtain the maximum point Fm of the fitting curve, record the device movement step step, and the actual Z-axis coordinate Z of the pixel point is Z = Fm·step. Repeat the above steps S2 and S3 to obtain the actual Z-axis coordinates of all pixel points. The XY-axis coordinates of the pixel points are obtained after calibration of the pixel coordinates, and finally a complete three-dimensional point cloud of the measured area of the air film hole is obtained.

[0039] Furthermore, the estimated standard deviation σ i Specifically:

[0040]

[0041] In a second aspect, an embodiment of the present invention provides a system for acquiring a three-dimensional point cloud of film holes in a turbine blade, comprising:

[0042] A processing module acquires a zoom microscopic sequence of air film holes, performs a Gaussian blur defogging operation on the zoom microscopic sequence of air film holes, and uses an edge preservation method to remove noise from the zoom microscopic sequence of air film holes and enhance the brightness of the image area;

[0043] An evaluation module uses a gradient focus evaluation method to perform focus evaluation calculations on the air film hole zoom image sequence obtained by the processing module, obtains a focus evaluation curve for each pixel in the air film hole zoom image sequence, and uses a maximum value screening method based on a flat area threshold to preliminarily determine the area where the pixel point focus maximum value is located;

[0044] The point cloud module obtains the focus evaluation curve of each pixel point obtained by the evaluation module and preliminarily determines the area where the pixel point focus maximum value is located. It uses the adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain the accurate pixel point focus maximum value, and finally obtains the three-dimensional point cloud of the air film hole.

[0045] Compared with the prior art, the present invention has at least the following beneficial effects:

[0046] A method for acquiring three-dimensional point clouds of film holes on turbine blades was proposed. To improve the acquisition quality of film hole image sequences and reduce image noise, a Gaussian blur dehazing operation was performed on the zoom microscopic sequence images of film holes. An edge-preserving method was used to remove noise from the zoom microscopic sequence images of film holes and enhance the brightness of the image area.

[0047] Furthermore, the focus evaluation algorithm can calculate and extract clear areas for the air film hole image sequence.

[0048] Furthermore, the sub-step of step S202 can clearly distinguish the curve intervals, thereby facilitating efficient search for the extreme value points of the focusing curve.

[0049] Furthermore, step S3 can accurately obtain the actual depth of the point cloud.

[0050] Furthermore, since the focus evaluation sequence is Gaussian distributed, and the probability of the Gaussian probability distribution within the range of six times the standard deviation on both sides of the mean is close to 1, it can be considered that the width of the non-flat area where the actual maximum value is located is about six times the standard deviation, so the array i The length of the standard deviation is calculated as σ i .

[0051] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0052] In summary, the method of the present invention has high precision and high speed, will not scratch the surface of the object being measured, and can realize the surface and inner wall measurement of special-shaped holes such as air film holes.

[0053] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is an overall flow chart of the method of the present invention;

[0055] Figure 2 This is a sequence of images of some air film holes;

[0056] Figure 3 The comparison diagram of the preprocessing of a certain air film hole image, where (a) is before preprocessing and (b) is after preprocessing;

[0057] Figure 4 is the focusing evaluation curve of the focusing operator;

[0058] Figure 5 It is the adaptive Gaussian fitting curve in the maximum search method. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0060] In the description of the present invention, it is to be understood that the terms “include” and “comprise” indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0061] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0062] It should be further understood that the term "and / or" as used in the present specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. For example, A and / or B may represent: A alone, A and B simultaneously, or B alone. In addition, the character " / " herein generally indicates that the associated items are in an "or" relationship.

[0063] It should be understood that although the terms "first," "second," and "third" may be used to describe preset ranges in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are merely used to distinguish one preset range from another. For example, without departing from the scope of embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0064] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0065] The accompanying drawings illustrate various schematic diagrams of structures according to embodiments disclosed herein. These figures are not drawn to scale; for clarity, some details are exaggerated and some details may be omitted. The shapes of the various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions as needed.

[0066] The present invention provides a method for acquiring three-dimensional point clouds of film holes in turbine blades. The method is based on a zoom microscopic image sequence and combines a focus evaluation method and a maximum value search method applicable to the film hole image sequence to achieve three-dimensional point cloud acquisition of film holes.

[0067] See also Figure 1 The present invention provides a method for obtaining a three-dimensional point cloud of a turbine blade film hole, comprising the following steps:

[0068] S1. Use the device to obtain zoom microscopic sequence images of air film holes, and use the double-filtering based image defogging and edge preservation method to remove noise from the zoom microscopic sequence images and improve the brightness of the image area;

[0069] S101. Based on the dark channel image prior theory and the atmospheric scattering model, the air film hole sequence image is established as a fog image formation model and A is calculated;

[0070] The fog map formation model is as follows:

[0071] I(x,y)=J(x,y)t(x,y)+A(1-t(x,y))

[0072]

[0073] Among them, I(x,y) is the input image, J(x,y) is the fog-free image, A is the global atmospheric light component, t(x,y) is the transmittance, I d (x,y) is the dark color prior map, Ω(x,y) is the local area centered at point (x,y), and G(x,y) = A(1-t(x,y)) is defined.

[0074] S102, image I d (x,y) is Gaussian filtered And calculate B(x,y);

[0075] The absolute value of the difference B(x,y) is calculated as follows:

[0076]

[0077] Among them, r is the coefficient factor, Gfilter is Gaussian filter, is the image after Gaussian filtering.

[0078] S103. Consider the constraint 0≤G(x,y)≤I d (x,y), and calculate G(x,y);

[0079] The atmospheric light curtain G(x,y) is calculated as follows:

[0080] G(x,y)=max(min(μB(x,y),I d (x,y)),0)

[0081] Among them, μ is a factor that controls the amount of dehazing to ensure the natural effect of the dehazed image, and its value range is [0,1].

[0082] S104. Finally, calculate J(x,y)=[I(x,y)-G(x,y)] / (1-G(x,y) / A) to obtain a sequence of air film hole images after defogging.

[0083] S105 , applying a guided filtering operation with the guide image being the original image to the air film hole image sequence after the Gaussian blurring and defogging, and performing an edge-preserving filtering operation.

[0084] S2. Performing focus evaluation calculations on the zoom image sequence of the air film hole obtained by defogging and edge preservation in step S1 using a focus evaluation method, obtaining a focus evaluation curve for each pixel in the air film hole sequence image, and preliminarily determining the region where the pixel focus maximum value is located using a maximum value screening method based on a flat region threshold;

[0085] S201, using the focus evaluation function to calculate the focus function evaluation function value F of each pixel point in the image sequence M (x0,y0);

[0086] The calculation is done using the following formula:

[0087]

[0088] in

[0089] G x (x,y)=f(x+2,y)-f(x,y)

[0090] G y (x,y)=f(x,y+2)-f(x,y).

[0091] S202: Based on the focus evaluation sequence obtained in step S201, the focus evaluation sequence is segmented using a maximum value screening method based on a flat region threshold to obtain flat regions and non-flat regions, and the region where the pixel focus maximum value is located is preliminarily determined. The specific steps are as follows:

[0092] S2021. Calculate the average of the focus evaluation values over the entire focus evaluation sequence as the flat zone threshold;

[0093] Flat zone threshold x,y for:

[0094]

[0095] S2022, according to the flat area threshold Threshold x,y The focus evaluation sequence is divided. The same point should have only one maximum value position in the entire focus evaluation sequence. The area with a certain width extending to both sides with this position as the center is the non-flat area.

[0096] S203, since it is inevitable that there will be erroneous maximum values in the actual focus evaluation sequence, it is assumed that k non-flat areas are segmented, each of which contains many pixel focus evaluation values, which are recorded as arrays array1, array2...array k ;

[0097] S204, calculate array1, array2, ... array by Max(len(array)) k The longest array in array i , as the non-flat area where the actual maximum value is located, the area where the pixel focus maximum value is located is preliminarily determined.

[0098] S3. Based on the focus evaluation curve of each pixel point obtained in step S2 and the area where the pixel point focus maximum value is preliminarily determined, an adaptive truncation method based on the standard deviation of the Gaussian distribution is used to obtain the accurate pixel point focus maximum value, and finally a three-dimensional point cloud of the air film hole is obtained.

[0099] Based on the focus evaluation sequence of each pixel point obtained in step S2, a Gaussian function is used to fit the non-flat area where the actual maximum value selected on the focus evaluation sequence is located. However, due to the large number of points on both sides of the maximum value, in order to improve the calculation processing speed, an adaptive truncation method based on the standard deviation of the Gaussian distribution is used to select some points for fitting, and finally a three-dimensional point cloud of the air film hole is obtained. The specific steps are as follows:

[0100] S301, since the focus evaluation sequence is Gaussian distributed, and the probability of the Gaussian probability distribution within the range of six times the standard deviation on both sides of the mean is close to 1, it can be considered that the width of the non-flat area where the actual maximum value is located is about six times the standard deviation. According to the array array obtained in step S204 i The length of Len(array i ) can calculate the estimated standard deviation σ i ;

[0101] Standard deviation estimate σ i Specifically:

[0102]

[0103] S302, array i The maximum value is located at the center, and the standard deviation estimate σ is taken on both sides of it. i (round) points, extract length len(array i ), as the interception range for the final Gaussian fitting;

[0104] S303: Perform Gaussian fitting on the points within the intercepted range to obtain the maximum point Fm of the fitting curve. Record the device movement step, step, and then the actual Z-axis coordinate of the pixel point Z = Fm·step. Repeat steps S2 and S3 to obtain the actual Z-axis coordinates of all pixels. The XY-axis coordinates of the pixel points can be obtained after calibration of the pixel coordinates, and finally a complete 3D point cloud of the film hole area is obtained.

[0105] In another embodiment of the present invention, a three-dimensional point cloud acquisition system for turbine blade film holes is provided. The system can be used to implement the above-mentioned three-dimensional point cloud acquisition method for turbine blade film holes. Specifically, the three-dimensional point cloud acquisition system for turbine blade film holes includes a processing module, an evaluation module and a point cloud module.

[0106] Among them, the processing module obtains the zoom microscopic sequence images of the air film holes, performs Gaussian blur defogging operation on the zoom microscopic sequence images of the air film holes, uses the edge preservation method to remove the noise of the zoom microscopic sequence images of the air film holes and improves the brightness of the image area;

[0107] An evaluation module uses a gradient focus evaluation method to perform focus evaluation calculations on the air film hole zoom image sequence obtained by the processing module, obtains a focus evaluation curve for each pixel in the air film hole zoom image sequence, and uses a maximum value screening method based on a flat area threshold to preliminarily determine the area where the pixel point focus maximum value is located;

[0108] The point cloud module obtains the focus evaluation curve of each pixel point obtained by the evaluation module and preliminarily determines the area where the pixel point focus maximum value is located. It uses the adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain the accurate pixel point focus maximum value, and finally obtains the three-dimensional point cloud of the air film hole.

[0109] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor 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, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the method for acquiring three-dimensional point clouds of air film holes of turbine blades, including:

[0110] Acquire the zoom microscopic sequence images of the film hole, perform Gaussian blur dehazing operation on the zoom microscopic sequence images of the film hole, use the edge preservation method to remove the noise of the zoom microscopic sequence images of the film hole and enhance the brightness of the image area; use the gradient focus evaluation method to perform focus evaluation calculation on the zoom image sequence of the film hole, obtain the focus evaluation curve of each pixel in the zoom image sequence of the film hole, and use the maximum value screening method based on the flat area threshold to preliminarily determine the area where the pixel focus maximum value is located; according to the focus evaluation curve of each pixel point and the preliminarily determined area where the pixel focus maximum value is located, use the adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain the accurate pixel focus maximum value, and finally obtain the three-dimensional point cloud of the film hole.

[0111] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory (Non-Volatile Memory), such as at least one disk memory.

[0112] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for acquiring a three-dimensional point cloud of a turbine blade film hole in the above embodiment. The processor may load and execute the following steps:

[0113] Acquire the zoom microscopic sequence images of the film hole, perform Gaussian blur dehazing operation on the zoom microscopic sequence images of the film hole, use the edge preservation method to remove the noise of the zoom microscopic sequence images of the film hole and enhance the brightness of the image area; use the gradient focus evaluation method to perform focus evaluation calculation on the zoom image sequence of the film hole, obtain the focus evaluation curve of each pixel in the zoom image sequence of the film hole, and use the maximum value screening method based on the flat area threshold to preliminarily determine the area where the pixel focus maximum value is located; according to the focus evaluation curve of each pixel point and the preliminarily determined area where the pixel focus maximum value is located, use the adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain the accurate pixel focus maximum value, and finally obtain the three-dimensional point cloud of the film hole.

[0114] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0115] See also Figure 2 , which is a partial sequence of air film hole images collected. The air film holes were scanned at a step interval of 0.01 mm, and a total of 150 air film hole image sequence photos were obtained.

[0116] See also Figure 3 The comparison chart of a certain air film hole image preprocessed by the image preprocessing method combining blur defogging and edge preservation shows that the image is clearly focused and the position is prominent after processing, and the overall image quality is high.

[0117] See also Figure 4 , the focusing evaluation function diagram of pixel (1670, 200) shows that the maximum value of the curve obtained by using the focusing operator is prominent, the noise influence is small, and the stability is good. Therefore, this operator is suitable for evaluating the focusing degree of the air film hole image sequence.

[0118] See also Figure 5 , which is a schematic diagram of the adaptive truncation method based on the standard deviation of the Gaussian distribution. This method can efficiently complete the Gaussian fitting and accurately obtain the focus maximum point of the pixel point.

[0119] In summary, the present invention provides a method and system for acquiring three-dimensional point clouds of air film holes in turbine blades, explores a focusing evaluation method and a maximum value search method suitable for sequence images of air film holes, expands the application scenarios of zoom microscopy measurement technology, has high precision and fast speed, will not cause scratches on the surface of the object being measured, and can realize the surface and inner wall measurement of special-shaped holes such as air film holes; in addition, by adopting an image preprocessing algorithm based on the combination of double-filtering defogging and edge retention, an improved gradient operator is used to calculate the focusing degree of image pixel points, and an adaptive truncation method based on the standard deviation of the Gaussian distribution is used to find the focusing extreme value for the focusing curve, and finally a high-precision three-dimensional point cloud of the air film hole is obtained, which is convenient for the subsequent quality evaluation of the geometric parameters of the air film hole.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0121] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0122] Those skilled in the art will appreciate that the units 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0123] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0124] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0126] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. 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 include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0130] The above content is only for explaining the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for acquiring a three-dimensional point cloud of a turbine blade film hole, characterized in that: The following steps are involved: S1. Acquire zoom microscopic sequence images of air film holes, perform Gaussian blur defogging on the zoom microscopic sequence images of air film holes, use edge preservation method to remove noise from the zoom microscopic sequence images of air film holes and enhance the brightness of the image area; S2. Perform focus evaluation calculation on the sequence of zoom microscopic images of the air film hole obtained in step S1 using a gradient focus evaluation method, obtain a focus evaluation curve for each pixel in the sequence of zoom microscopic images of the air film hole, and preliminarily determine the region where the pixel focus maximum value is located using a maximum value screening method based on a flat region threshold, specifically: S201, using the focus evaluation function to calculate the focus function evaluation function value of each pixel point of the sequence image ; S202: Segment the focus evaluation sequence obtained in step S201 using a maximum value screening method based on a flat region threshold to obtain flat regions and non-flat regions, and preliminarily determine the region where the pixel focus maximum value is located; S203, since it is inevitable that there will be erroneous maximum values in the actual focus evaluation sequence, it is assumed that k non-flat areas are segmented, and each non-flat area contains many pixel focus evaluation values, which are recorded as arrays. 、 … ; S204, by Get array 、 … The longest array , as the non-flat area where the actual maximum value is located, the area where the pixel focus maximum value is located is preliminarily determined; S3. Based on the focusing evaluation curve of each pixel point obtained in step S2 and the area where the pixel point focusing maximum value is located, an adaptive truncation method based on the standard deviation of the Gaussian distribution is used to obtain the accurate pixel point focusing maximum value, and finally obtain the three-dimensional point cloud of the air film hole.

2. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 1, characterized in that: Step S1 is specifically as follows: S101, establishing a fog image formation model using a sequence of air film hole images and calculating the global atmospheric light component A; S102: Dark color prior image of the fog image obtained in step S101 forming a model Perform Gaussian filtering to obtain the image after Gaussian filtering , and take the difference to get the absolute value ; S103. Considering Constraints , and calculate the atmospheric light curtain ; S104, according to step S103 calculate , obtain the sequence images of air film holes after defogging; S105 , applying a guided filtering operation with the guide image being the image itself to the air film hole sequence image after defogging in step S104 , and performing an edge-preserving filtering operation.

3. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 2, characterized in that: In step S101, the fog image formation model is as follows: in, is the input image, is a fog-free image, A is the global atmospheric light component, is the transmittance, is the dark color prior map, It is a point The local area centered.

4. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 2, characterized in that: In step S102, the absolute value of the difference The calculation is as follows: in, is the coefficient factor, is a Gaussian filter.

5. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 1, characterized in that: In step S201, the focus function evaluation function value of each pixel point in the sequence image is The calculation is as follows: in, is the gradient operator in the horizontal direction, is the gradient operator in the vertical direction, For point The local area centered.

6. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 1, characterized in that: Step S202 is specifically as follows: S2021. Calculate the average of the focus evaluation values in the entire focus evaluation sequence as the flat zone threshold. ; S2022, based on the flat zone threshold The focus evaluation sequence is divided. The same point should have only one maximum value position in the entire focus evaluation sequence. The area with a certain width extending to both sides with this position as the center is the non-flat area.

7. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 1, characterized in that: Step S3 is specifically as follows: S301, the array obtained according to step S2 Length Calculate the standard deviation estimate ; S302, The maximum value is located at the center, and the standard deviation estimates are taken on both sides of it. points, the extraction length is , as the interception range for the final Gaussian fitting; S303, perform Gaussian fitting on the points in the intercepted range to obtain the maximum point of the fitting curve , record the device movement step step, then the actual Z-axis coordinate of the pixel point Z=Fm·step, repeat the above steps S2 and S3 to obtain the actual Z-axis coordinates of all pixel points, and the XY-axis coordinates of the pixel point are obtained after calibration of the pixel coordinates. Finally, a complete three-dimensional point cloud of the measured area of the air film hole is obtained.

8. The method for acquiring a three-dimensional point cloud of a turbine blade film hole according to claim 7, characterized in that: Standard deviation estimate Specifically: 。 9. A three-dimensional point cloud acquisition system for film holes in turbine blades, characterized in that: include: A processing module acquires a zoom microscopic sequence of air film holes, performs a Gaussian blur defogging operation on the zoom microscopic sequence of air film holes, and uses an edge preservation method to remove noise from the zoom microscopic sequence of air film holes and enhance the brightness of the image area; The evaluation module uses the gradient focus evaluation method to perform focus evaluation calculation on the air film hole zoom microscopic image sequence obtained by the processing module, obtains the focus evaluation curve of each pixel in the air film hole zoom microscopic image sequence, and uses the maximum value screening method based on the flat area threshold to preliminarily determine the area where the pixel point focus maximum value is located. Specifically: Use the focus evaluation function to calculate the focus function evaluation function value of each pixel in the sequence image According to the obtained focus evaluation sequence, the maximum value screening method based on the flat area threshold is used to segment the focus evaluation sequence to obtain the flat area and non-flat area parts, and preliminarily determine the area where the pixel focus maximum value is located; since the actual focus evaluation sequence inevitably has incorrect maximum values, it is assumed that k non-flat areas are segmented, and each non-flat area contains many pixel focus evaluation values, which are recorded as arrays 、 … ;Depend on Get array 、 … The longest array , as the non-flat area where the actual maximum value is located, the area where the pixel focus maximum value is located is preliminarily determined; The point cloud module uses an adaptive truncation method based on the standard deviation of the Gaussian distribution to obtain the accurate pixel focus maximum value based on the focus evaluation curve of each pixel point obtained by the evaluation module and the area where the pixel focus maximum value is preliminarily determined, and finally obtains the three-dimensional point cloud of the air film hole.

Images