Method and device for predicting aerodynamic stability of a compressor

Abstract

The application provides a compressor aerodynamic stability prediction method and device, the method comprising color space conversion on an initial flow field cloud image of the compressor to obtain a target flow field cloud image, wherein the target flow field cloud image comprises at least two color channels; for any pixel point in the target flow field cloud image, the gradient amplitude of the pixel point on different color channels is calculated, and a color gradient map is generated according to the gradient amplitudes of multiple pixel points; based on a preset threshold and the gradient amplitudes, the color attribute of each pixel point in the color gradient map is adjusted to obtain a color mask image; the connected region of a target color in the color mask image is determined as a target region of a shock wave, a main flow and a leakage flow interface; based on the distance between the target interface region and the blade leading edge of the compressor, a stability prediction result is generated, wherein the stability prediction result represents that the compressor is in an unstable or stable state.

Description

Technical Field

[0001] This application relates to the field of compressor technology, and more specifically, to a method and device for predicting the aerodynamic stability of a compressor. Background Technology

[0002] With the continuous pursuit of high thrust-to-weight ratio and high efficiency in aero-engines, the load on modern compressor stages has increased significantly, and the internal flow has become increasingly complex. Aerodynamic stability has become a key bottleneck restricting further performance improvement. The existence and interaction of transient and unsteady flow structures such as shock waves and tip leakage vortices are the main causes of instability phenomena such as flow separation and even rotating stall / surge. Traditional aerodynamic stability assessments rely heavily on overall performance parameters (such as abrupt changes in pressure rise and efficiency) or limited steady-state measurement data. This "black box" or "retrospective" monitoring method is difficult to capture the subtle and local structural evolution before flow field instability, and it is difficult to provide advanced and effective guidance information for accurate prediction of stability boundaries and active control. Summary of the Invention

[0003] In view of this, this application provides a method and apparatus for predicting the aerodynamic stability of a compressor.

[0004] One aspect of this application provides a method for predicting the aerodynamic stability of a compressor, comprising: performing color space conversion on an initial flow field cloud map of the compressor to obtain a target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels; calculating the gradient magnitude of any pixel in the target flow field cloud map on different chromaticity channels, and generating a color gradient map based on the gradient magnitudes of multiple pixels; adjusting the color attributes of each pixel in the color gradient map based on a preset threshold and gradient magnitudes to obtain a color mask image; determining the connected regions of the target colors in the color mask image as the target region at the interface of shock wave, mainstream, and leakage flow; and generating a stability prediction result based on the distance between the target region and the leading edge of the compressor blades, wherein the stability prediction result characterizes whether the compressor is in an unstable or stable state.

[0005] According to an embodiment of this application, the initial flow field cloud map is generated in the following manner: using a probe to collect fluid flow characteristics from the casing wall of the compressor; generating an initial flow field cloud map based on the fluid flow characteristics, wherein the initial flow field cloud map represents the surface static pressure cloud map at the blade tips of the rotor of the compressor; or performing numerical simulation on the compressor to obtain numerical simulation data of the fluid flow inside the compressor; generating the initial flow field cloud map based on the numerical simulation data, wherein the initial flow field cloud map includes surface static pressure cloud maps or static entropy cloud maps representing different blade heights of the blade row.

[0006] According to an embodiment of this application, calculating the gradient magnitude of the aforementioned pixel in different chroma channels and generating a color gradient map based on the gradient magnitude of multiple pixels includes: for any direction, generating the gradient magnitude of the aforementioned direction based on the chroma channel values ​​of at least two chroma channels of the aforementioned pixel in the aforementioned direction using the Sobel operator; and generating the aforementioned color gradient map based on the gradient magnitude of multiple pixels in different directions.

[0007] According to an embodiment of this application, the method further includes: determining a brightness threshold based on the brightness of different pixels in the color gradient map; and performing binarization processing on the color gradient map based on the brightness threshold to obtain a binarized color gradient map.

[0008] According to an embodiment of this application, the color attributes of each pixel in the color gradient map are adjusted based on a preset threshold and gradient magnitude to obtain a color mask image, including: determining the preset threshold from the color gradient map using the Otsu adaptive thresholding method; and performing a discrete binary mask on the color attributes of each pixel in the color gradient map based on the preset threshold to obtain the color mask image.

[0009] According to an embodiment of this application, a discrete binary mask is applied to the color attribute of each pixel in the color gradient map based on the preset threshold to obtain the color mask image, including: for any pixel, if the gradient magnitude of the pixel is greater than the preset threshold, adjusting the color attribute of the pixel to the target color; if the gradient magnitude of the pixel is not greater than the preset threshold, adjusting the color attribute of the pixel to a reference color different from the target color.

[0010] According to an embodiment of this application, determining the connected regions of the target color in the aforementioned color mask image as the target region between the interface of the shock wave, the main stream, and the leakage flow includes: performing morphological operations on the aforementioned color mask image to obtain a target mask image, wherein the aforementioned morphological operations include at least one of the following: opening operation, dilation, and closing operation based on pixel distance; identifying the connected regions of the target color from the aforementioned target mask image, and determining the aforementioned connected regions as the aforementioned target region.

[0011] According to an embodiment of this application, a stability prediction result is generated based on the distance between the target region and the leading edge of the compressor blade, including: determining the centroid of the pixels in the target region as the feature center; calculating the distance between the feature center and the leading edge of the blade, and calculating the ratio of the distance to the blade length; when the ratio is a first value, the stability prediction result indicates that the compressor is in an unstable state; when the ratio is greater than a second value, the stability prediction result indicates that the compressor is in a stable state; when the ratio is between the first value and the second value, the stability prediction result indicates that the compressor is in a near-unstable state.

[0012] According to an embodiment of this application, the method further includes: for any connected region, calculating an average gradient magnitude based on the center of the connected region and the gradient magnitude of each pixel in the connected region in different directions; and comparing the average gradient magnitude with a magnitude threshold to correct the stability prediction result of the compressor.

[0013] Another aspect of this application provides a compressor aerodynamic stability prediction device, comprising: a conversion module for performing color space conversion on an initial flow field cloud map of the compressor to obtain a target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels; a generation module for calculating the gradient magnitude of any pixel in the target flow field cloud map on different chromaticity channels, and generating a color gradient map based on the gradient magnitudes of multiple pixels; an adjustment module for adjusting the color attributes of each pixel in the color gradient map based on a preset threshold and gradient magnitude to obtain a color mask image; a determination module for determining the connected regions of the target colors in the color mask image as target regions at the interface of shock waves, mainstream flows, and leakage flows; and a prediction module for generating a stability prediction result based on the distance between the target region and the leading edge of the compressor blades, wherein the stability prediction result characterizes whether the compressor is in an unstable or stable state.

[0014] Another aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method as described above.

[0015] Another aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0016] Another aspect of this application provides a computer program product comprising computer-executable instructions which, when executed, are used to implement the method described above.

[0017] According to embodiments of this application, a target flow field cloud map is obtained by color space conversion of the initial flow field cloud map. The gradient magnitude of each pixel in the target flow field cloud map on different chromaticity channels is calculated, thereby adjusting the color gradient map to determine the target region of the interface between the shock wave, the main flow, and the leakage flow from the obtained color mask image. The distance between the target region and the leading edge of the compressor blades determines whether the compressor is in an unstable or stable state. Through the above-described flow field cloud map processing method, the aerodynamic stability of the compressor can be predicted automatically, in batches, and quickly, improving the efficiency of flow field analysis and aerodynamic stability prediction. Attached Figure Description

[0018] The above and other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0019] Figure 1 An exemplary system architecture for applying a compressor aerodynamic stability prediction method according to an embodiment of this application is shown.

[0020] Figure 2 A flowchart of a compressor aerodynamic stability prediction method according to an embodiment of this application is shown.

[0021] Figure 3A The static entropy cloud diagrams under different operating conditions according to embodiments of this application are shown.

[0022] Figure 3B The static pressure cloud diagrams of the flow surface under different operating conditions according to embodiments of this application are shown.

[0023] Figure 4 The color gradient diagrams under different operating conditions according to embodiments of this application are shown.

[0024] Figure 5 The binary color gradient maps under different operating conditions according to embodiments of this application are shown.

[0025] Figure 6 The color mask images under different conditions after noise and artifact removal according to another embodiment of this application are shown.

[0026] Figure 7 The diagram shows flow field cloud maps under different operating conditions with added identifiers according to embodiments of this application.

[0027] Figure 8The diagram illustrates the location of shock waves and leakage flow in the blade passage under different operating conditions according to embodiments of this application.

[0028] Figure 9 A block diagram of a compressor aerodynamic stability prediction device according to an embodiment of this application is shown.

[0029] Figure 10 A block diagram of an electronic device suitable for implementing the methods described above, according to an embodiment of this application, is shown. Detailed Implementation

[0030] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0031] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0032] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0033] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0034] In the embodiments of this application, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security and network security.

[0035] The maturity of computational fluid dynamics and advanced flow visualization technologies (such as particle image velocimetry and schlieren) has made it possible to capture high-resolution transient flow fields inside compressors, but it has also generated massive amounts of images and flow field data rich in physical information. Traditional methods relying on manual interpretation are not only inefficient but also highly subjective, making it difficult to quantitatively and consistently extract key features. Therefore, developing a technology capable of automatically and accurately identifying and quantifying key flow structures from complex flow field data, achieving a leap from "qualitative observation" to "quantitative characterization," and establishing a quantitative correlation between flow structure and stability, has become an urgent technical requirement in the field of high-stability compressor design.

[0036] In view of this, embodiments of this application provide a method and apparatus for predicting the aerodynamic stability of a compressor. The method includes performing color space conversion on an initial flow field cloud map of the compressor to obtain a target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels; for any pixel in the target flow field cloud map, calculating the gradient magnitude of the pixel in different chromaticity channels, and generating a color gradient map based on the gradient magnitudes of multiple pixels; adjusting the color attributes of each pixel in the color gradient map based on a preset threshold and gradient magnitudes to obtain a color mask image; determining the connected regions of the target colors in the color mask image as the target regions at the interface of shock waves, mainstream flows, and leakage flows; and generating a stability prediction result based on the distance between the target region and the leading edge of the compressor blades, wherein the stability prediction result characterizes whether the compressor is in an unstable or stable state.

[0037] Figure 1 An exemplary system architecture for applying a compressor aerodynamic stability prediction method according to embodiments of this application is shown. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this application, in order to help those skilled in the art understand the technical content of this application, but do not mean that the embodiments of this application cannot be used in other devices, systems, environments or scenarios.

[0038] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0039] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software, etc. (for example only).

[0040] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0041] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0042] It should be noted that the compressor aerodynamic stability prediction method provided in this application embodiment can generally be executed by server 105. Correspondingly, the compressor aerodynamic stability prediction device provided in this application embodiment can generally be installed in server 105. The compressor aerodynamic stability prediction method provided in this application embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the compressor aerodynamic stability prediction device provided in this application embodiment can also be installed in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Alternatively, the compressor aerodynamic stability prediction method provided in this application embodiment can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the compressor aerodynamic stability prediction device provided in this application embodiment can also be installed in the first terminal device 101, the second terminal device 102 or the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0043] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0044] Figure 2 A flowchart of a compressor aerodynamic stability prediction method according to an embodiment of this application is shown.

[0045] like Figure 2 As shown, the compressor aerodynamic stability prediction method includes operations S201~S205.

[0046] In operation S201, the initial flow field cloud map of the compressor is converted to color space to obtain the target flow field cloud map, which includes at least two chromaticity channels.

[0047] In operation S202, for any pixel in the target flow field cloud map, the gradient magnitude of the pixel in different chromaticity channels is calculated, and a color gradient map is generated based on the gradient magnitudes of multiple pixels.

[0048] In operation S203, based on a preset threshold and gradient magnitude, the color attributes of each pixel in the color gradient map are adjusted to obtain a color mask image.

[0049] In operation S204, the connected regions of the target colors in the color mask image are identified as the target regions at the interface of the shock wave, the main flow, and the leakage flow.

[0050] In operation S205, stability prediction results are generated based on the distance between the target area and the leading edge of the compressor blades. The stability prediction results characterize whether the compressor is in an unstable or stable state.

[0051] According to the embodiments of this application, the flow field cloud map of the compressor refers to the result of visually presenting the complex three-dimensional flow state inside the compressor through a visual color image using computational fluid dynamics or experimental fluid dynamics. In essence, it is to "draw" the invisible airflow inside the compressor with color.

[0052] According to embodiments of this application, the initial flow field cloud map of the compressor is converted from the RGB color space to a target flow field cloud map with only two chromaticity channels, such as a target flow field cloud map in the CIE-Lab color space. CIE L*a*b* (CIE-Lab) is a device-independent color space. Its core objective is to uniformly describe all visible colors in a manner perceptible to the human eye.

[0053] According to an embodiment of this application, for any pixel in the target flow field cloud map, the gradient magnitude of the pixel in different chromaticity channels is calculated, thereby generating a color gradient map based on the gradient magnitudes of multiple pixels.

[0054] According to an embodiment of this application, for each pixel in the color gradient map, the color of each pixel can be adjusted by comparing the gradient magnitude of the pixel with a preset threshold, for example, by adjusting it to black or white, thereby obtaining a color mask image. The size of the preset threshold can be set according to actual needs, for example, it can be set according to the gradient magnitude in the color gradient map.

[0055] According to embodiments of this application, in a color mask image, pixels of a target color (such as white) are connected to form a connected region, thereby identifying the target region at the interface between the shock wave, the main flow, and the leakage flow. The distance between the target region and the leading edge of the compressor blades is calculated, and based on this distance, a stability prediction result determining whether the compressor is in an unstable or stable state can be generated.

[0056] According to embodiments of this application, a target flow field cloud map is obtained by color space conversion of the initial flow field cloud map. The gradient magnitude of each pixel in the target flow field cloud map on different chromaticity channels is calculated, thereby adjusting the color gradient map to determine the target region of the interface between the shock wave, the main flow, and the leakage flow from the obtained color mask image. The distance between the target region and the leading edge of the compressor blades determines whether the compressor is in an unstable or stable state. Through the above-described flow field cloud map processing method, the aerodynamic stability of the compressor can be predicted automatically, in batches, and quickly, improving the efficiency of flow field analysis and aerodynamic stability prediction.

[0057] According to an embodiment of this application, the initial flow field cloud map is generated as follows: fluid flow characteristics are collected from the casing wall of the compressor using a probe; the initial flow field cloud map is generated based on the fluid flow characteristics, wherein the initial flow field cloud map characterizes the S1 flow surface static pressure cloud map at the blade tip of the compressor rotor.

[0058] According to the embodiments of this application, the test data obtained by the compressor casing wall probe, including but not limited to fluid flow characteristics, can be used to draw the S1 flow surface static pressure cloud map of the compressor rotor blade tip.

[0059] Figure 3A The static entropy cloud diagrams under different operating conditions according to embodiments of this application are shown. Figure 3B The static pressure cloud diagrams of the S1 flow surface under different operating conditions according to embodiments of this application are shown.

[0060] According to an embodiment of this application, the initial flow field cloud map is generated in the following manner: numerical simulation of the compressor is performed to obtain numerical simulation data of the fluid flow inside the compressor; the initial flow field cloud map is generated based on the numerical simulation data, wherein the initial flow field cloud map includes the S1 flow surface static pressure cloud map or static entropy cloud map characterizing different blade heights of the blade row.

[0061] According to the embodiments of this application, a compressor can be numerically simulated to obtain numerical simulation data of the fluid flow inside the compressor, and the S1 flow surface static pressure cloud map or static entropy cloud map at different blade heights of the rotor blade row can be extracted from the numerical simulation data of the compressor.

[0062] In one specific embodiment, a typical publicly disclosed transonic compressor rotor is selected as the simulation object to perform numerical simulation of the typical publicly disclosed transonic compressor using the Reynolds-Averaged Navier-Stokes (RANS) equations, obtaining rotor flow field data under different speeds and operating conditions. In this embodiment, the design parameters of the typical publicly disclosed transonic compressor are shown in Table 1.

[0063] Table 1. Basic parameters of a typical transonic compressor

[0064] variable value power 800 kW Torque 350 Nm Maximum speed 21,000 rpm Maximum rotor diameter 0.38 m Wheel hub ratio ~ 0.5 Rotor tip relative Mach number ~ 1.4 Number of rotor blades 16 number of stenozoic blades 29

[0065] In this embodiment, the compressor's grid, turbulence model, and solver need to be determined before performing RANS numerical simulation. The total number of grids in the single-channel computational domain is approximately 2.66 million. The near-wall grid is refined, with an orthogonality greater than 30°. The first layer of the grid is 3 mm from the wall, ensuring y+ < 3, which meets the computational requirements of the turbulence model. The KW turbulence model is used to solve the single-channel three-dimensional Reynolds-averaged Navier-Stokes equations. The inlet is given the total atmospheric temperature and total pressure boundary conditions, the outlet is given the average static pressure, and the wall is given the no-slip boundary conditions. Full three-dimensional flow field data under different flow conditions at 85% and 100% speed are obtained. Batch post-processing is used to obtain the static entropy and static pressure contour maps of the original flow field at the blade tips. Figure 3A and Figure 3B The figures are the original blade tip entropy cloud map and static pressure cloud map extracted from numerical simulation data under different speeds and operating conditions. In the figure, (a) is the 85%n low flow condition, (b) is the 100%n low flow condition, and (c) is the 100%n high flow condition. n is the compressor rotor speed, and high flow or low flow refers to the flow rate of the fluid drawn into the compressor.

[0066] Under constant speed conditions, as the compressor throttle valve gradually closes, the system flow rate decreases accordingly, leading to an increase in the blade angle of attack and a rise in the aerodynamic load at the blade tip. This process intensifies the flow intensity of the tip leakage flow, causing the mainstream / leakage flow interface to continuously advance and eventually break through the leading edge of the blade, resulting in flow instability and inducing compressor rotational stall. Based on entropy distribution characteristics, the mainstream region exhibits low entropy characteristics, while the leakage flow region exhibits high entropy characteristics. The two form a clear and visible target boundary region within the blade passage (e.g., ...). Figure 3A (As shown). Simultaneously, the throttling process enhances the shock wave intensity and causes the axial position of the detached shock wave to shift forward. By monitoring the evolution of the interface position and the changes in shock wave intensity / position parameters, a stability criterion based on multi-feature fusion is constructed to achieve accurate prediction of the compressor stability boundary.

[0067] According to an embodiment of this application, the initial flow field cloud map of the compressor is converted to a color space to obtain a target flow field cloud map, including: cropping the original blade height slice vertically in the blade height direction to remove irrelevant areas such as color bars and borders; then converting the cropped image from RGB space to CIE-Lab space to obtain the target flow field cloud map.

[0068] Figure 4 The color gradient diagrams under different operating conditions according to embodiments of this application are shown.

[0069] According to an embodiment of this application, calculating the gradient magnitude of a pixel in different chroma channels and generating a color gradient map based on the gradient magnitude of multiple pixels includes: for any direction, generating a gradient magnitude of the direction based on the Sobel operator and the chroma channel values ​​of at least two chroma channels of the pixel in the direction; and generating a color gradient map based on the gradient magnitude of multiple pixels in different directions.

[0070] According to an embodiment of this application, the a and b chromaticity channels of each pixel are extracted from the target flow field cloud map, and their horizontal x and vertical y gradients are calculated using a 5×5 Sobel operator, as shown in the following formula:

[0071]

[0072]

[0073] in, It is the Sobel gradient operator. This represents the chroma channel value in the x-direction. This represents the chroma channel value in the y-direction.

[0074] According to embodiments of this application, a color gradient map is generated based on the gradient magnitudes of multiple pixels in different directions, such as... Figure 4 As shown.

[0075] Figure 5 The binary color gradient maps under different operating conditions according to embodiments of this application are shown.

[0076] According to an embodiment of this application, the above method further includes: determining a brightness threshold based on the brightness of different pixels in the color gradient map; and performing binarization processing on the color gradient map based on the brightness threshold to obtain a binarized color gradient map.

[0077] According to an embodiment of this application, in order to suppress background interference, a very high brightness threshold L (e.g., L > 240, assuming a brightness range of 0-255) is set based on the brightness of the color gradient map, because areas close to pure white have very high brightness. All pixels with brightness values ​​greater than this threshold are marked as 0 (black, representing the background) in the mask, and the remaining areas are marked as 255 (white, representing the foreground, such as shock waves, mains leakage flow interfaces). At positions where the mask is black (background), the gradient values ​​of G(x) and G(y) are forcibly set to 0, thereby obtaining a binarized color gradient map, such as... Figure 5 As shown.

[0078] According to an embodiment of this application, the color attributes of each pixel in the color gradient map are adjusted based on a preset threshold and gradient magnitude to obtain a color mask image, including: determining a preset threshold from the color gradient map using the Otsu thresholding method; and performing a discrete binary mask on the color attributes of each pixel in the color gradient map based on the preset threshold to obtain a color mask image.

[0079] According to an embodiment of this application, the values ​​of all pixels in the gradient map are linearly scaled to a standard range for normalization; the Otsu adaptive thresholding method (i.e., Otsu thresholding method) is used to find the optimal preset threshold T, so that the "difference" between the two types of pixels after segmentation, such as the interface between shock waves and mainstream leakage flows and the "background", such as non-critical areas, is maximized.

[0080] According to an embodiment of this application, a color mask image is obtained by performing a discrete binary mask on the color attributes of each pixel in the color gradient map using a preset threshold.

[0081] According to an embodiment of this application, a discrete binary mask is applied to the color attribute of each pixel in the color gradient map based on a preset threshold to obtain a color mask image. The method includes: for any pixel, if the gradient magnitude of the pixel is greater than the preset threshold, adjusting the color attribute of the pixel to the target color; if the gradient magnitude of the pixel is not greater than the preset threshold, adjusting the color attribute of the pixel to a reference color different from the target color.

[0082] According to an embodiment of this application, for any pixel with a gradient value G_normalized(x) > T: the point is set to 255 (white, i.e., the target color) in the output image; for any pixel with a gradient value G_normalized(x) <= T: the point is set to 0 (black, i.e., the reference color) in the output image, resulting in a binary mask image with only pure black and pure white, i.e., a color mask image, where the white spots or lines are the most likely locations of the interface between the shock wave, the main flow, and the leakage flow, i.e., the target area.

[0083] Figure 6 The color mask images under different conditions after noise and artifact removal according to another embodiment of this application are shown.

[0084] According to an embodiment of this application, determining the connected regions of the target color in a color mask image as the target region at the interface of the shock wave, the main stream, and the leakage flow includes: performing morphological operations on the color mask image to obtain a target mask image, wherein the morphological operations include at least one of the following: opening operation, dilation, and closing operation based on pixel distance; identifying the connected regions of the target color in the target mask image, and determining the connected regions as the target region.

[0085] According to embodiments of this application, in order to avoid real shock waves or leakage vortices being segmented into multiple fragments by fine gaps, morphological operations are performed on the binary color mask image, including but not limited to opening operations, dilation operations, and pixel distance-based closing operations, to ensure that a complete physical structure (such as a continuous shock wave) can also be identified as a complete, connected white area on the target mask image, thereby determining the white area as the target boundary region.

[0086] According to embodiments of this application, all external connected regions can further be extracted from the target mask image. And remove false detection areas that are too small or too close to the image edge to eliminate image noise or artifacts introduced by the border near the image edge, such as... Figure 6 As shown.

[0087] Figure 7 The diagram shows flow field cloud maps under different operating conditions with added identifiers according to embodiments of this application.

[0088] According to an embodiment of this application, a stability prediction result is generated based on the distance between the target region and the leading edge of the compressor blade, including: determining the centroid of the pixel in the target region as the feature center; calculating the distance between the feature center and the leading edge of the blade, and calculating the ratio of the distance to the blade length; when the ratio is a first value, the stability prediction result indicates that the compressor is in an unstable state; when the ratio is greater than a second value, the stability prediction result indicates that the compressor is in a stable state; when the ratio is between the first and second values, the stability prediction result indicates that the compressor is in a near-unstable state.

[0089] According to an embodiment of this application, all connected regions retained after filtering are traversed. The centroid of each pixel in a connected region is used as the feature center. They were marked with dots on the original image and labeled accordingly.

[0090] In one specific embodiment, all the connected regions that remain after filtering are traversed. The centroid of each pixel in a connected region is used as the feature center. In this embodiment, the flow field cloud map is marked with red dots and labeled. Figure 7 The flow field cloud map is obtained under different speeds and operating conditions after automatic labeling. The outline in the figure is the main flow / leakage flow interface that is automatically identified. Connecting S1-S3 can obtain the axial position of the interface in the blade passage. Aerodynamic stability can be determined based on this axial position under different operating conditions.

[0091] According to an embodiment of this application, the distance between the feature center and the leading edge of the blade is calculated, and the ratio of the distance to the blade length is calculated. If the ratio is a first value (e.g., 0), it indicates that the compressor is in an unstable state. If it is greater than a second value (e.g., 0.2), it indicates that the compressor is in a stable state. If it is between the first and second values, it indicates that the compressor is in a near-unstable state.

[0092] Figure 8 The diagram illustrates the location of shock waves and leakage flow in the blade passage under different operating conditions according to embodiments of this application.

[0093] According to an embodiment of this application, the above method further includes: for any connected region, calculating an average gradient magnitude based on the center of the connected region and the gradient magnitude of each pixel in the connected region in different directions; and comparing the average gradient magnitude with a magnitude threshold to correct the compressor stability prediction result.

[0094] According to an embodiment of this application, the area is calculated for each connected component. The average gradient intensity is used to characterize the spatial scale and boundary strength of the feature region, and the average gradient magnitude. The calculation formula is as follows:

[0095]

[0096] According to an embodiment of this application, the magnitude of the amplitude threshold corresponds to the type of compressor operating condition. For example, in the 100%n low flow condition, the amplitude threshold can be 1800, and in the 100%n low flow condition, the amplitude threshold can be 1742, where n is the rotational speed of the compressor rotor.

[0097] According to an embodiment of this application, if the average gradient amplitude is greater than the amplitude threshold, it indicates that the compressor is in an unstable state. The stability prediction result based on distance determination is corrected by the judgment result to accurately identify the working state of the compressor.

[0098] According to the embodiments of this application, the prediction method of this embodiment is repeatedly executed, and the positions of shock waves and leakage flow in the blade passage are automatically marked with black dots under different speeds and operating conditions. Figure 8 As shown in the figure, S1 and S4 are the locations of leakage flow, S2 and S5 are the leading edge of the blade tip, and S3 and S6 are the locations of detached shock waves. By comparing the degree of detachment of the shock waves under different operating conditions with the flow direction distance between S3-S2 or S5-S6, the larger the axial distance, the closer the operating condition is to the instability boundary.

[0099] In one embodiment, the shock wave boundary intensity, shock wave location and leading edge flow direction distance, and mainstream-leakage flow interface and leading edge axial distance under different operating conditions obtained by the prediction method of this embodiment are shown in Table 2. The comparison of shock wave boundary intensity under each operating condition is as follows: 85%n small flow rate condition < 100%n large flow rate condition < 100%n small flow rate condition; the comparison of the shock wave location and leading edge flow direction distance level is as follows: 85%n small flow rate condition > 100%n small flow rate condition > 100%n large flow rate condition; the comparison of the mainstream-leakage flow interface and leading edge axial distance level is as follows: 100%n small flow rate condition < 85%n small flow rate condition < 100%n large flow rate condition. A larger shock wave location and leading edge flow direction distance indicates a higher level and a more unstable flow field, while a smaller mainstream-leakage flow interface and leading edge axial distance indicate a higher level and a more unstable flow field. Therefore, in summary, both the 85%n low flow rate condition and the 100%n low flow rate condition are near-stall conditions, while the 100%n high flow rate condition is a stable condition.

[0100] Table 2

[0101] Operating conditions 85%n low flow rate conditions 100% low flow rate conditions 100% high flow rate conditions <![CDATA[Average gradient intensity S k > 1488.95 1802.01 1742.23 S3-S2 Shock Wave Location Level 3 2 1 Mainstream Leakage Flow Interface Location Level 2 3 1

[0102] As can be seen from the above description, according to the embodiments of this application, this application replaces the traditional subjective and cumbersome analysis work that relies on manual judgment of aerodynamic stability with a complete image processing algorithm. This method can automatically and batch process massive flow field data, outputting objective and unified quantitative indicators, eliminating reliance on expert experience and greatly improving the efficiency of flow field analysis. Simultaneously, it directly performs quantitative tracking of the microscopic evolution of instability-related flow structures such as shock waves and blade tip leakage, enabling it to keenly capture instability precursor signals before they lead to compressor instability, significantly improving the predictive accuracy and predictive power. Furthermore, the output quantitative parameters such as characteristic area and average gradient intensity provide a unified standard for describing complex flow structures. These quantitative parameters, together with operating conditions and geometric parameters, constitute a high-dimensional feature space, which can be used to build more accurate data-driven prediction models and be accumulated into a valuable expert knowledge base, thereby deeply empowering the intelligent and digital design of future compressors.

[0103] Figure 9 A block diagram of a compressor aerodynamic stability prediction device according to an embodiment of this application is shown.

[0104] like Figure 9 As shown, the compressor aerodynamic stability prediction device 900 includes a conversion module 910, a generation module 920, an adjustment module 930, a determination module 940, and a prediction module 950.

[0105] The conversion module 910 is used to perform color space conversion on the initial flow field cloud map of the compressor to obtain the target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels.

[0106] The generation module 920 is used to calculate the gradient magnitude of any pixel in the target flow field cloud map in different chromaticity channels, and generate a color gradient map based on the gradient magnitude of multiple pixels.

[0107] The adjustment module 930 is used to adjust the color attributes of each pixel in the color gradient map based on a preset threshold and gradient magnitude to obtain a color mask image.

[0108] The determination module 940 is used to determine the connected regions of the target colors in the color mask image as the target regions at the interface of the shock wave, the main flow, and the leakage flow.

[0109] The prediction module 950 is used to generate stability prediction results based on the distance between the target area and the leading edge of the compressor blades, wherein the stability prediction results characterize whether the compressor is in an unstable or stable state.

[0110] According to embodiments of this application, a target flow field cloud map is obtained by color space conversion of the initial flow field cloud map. The gradient magnitude of each pixel in the target flow field cloud map on different chromaticity channels is calculated, thereby adjusting the color gradient map to determine the target region of the interface between the shock wave, the main flow, and the leakage flow from the obtained color mask image. The distance between the target region and the leading edge of the compressor blades determines whether the compressor is in an unstable or stable state. Through the above-described flow field cloud map processing method, the aerodynamic stability of the compressor can be predicted automatically, in batches, and quickly, improving the efficiency of flow field analysis and aerodynamic stability prediction.

[0111] According to embodiments of this application, the initial flow field cloud map is generated by a data acquisition unit and a first generation unit, or by a simulation unit and a second generation unit.

[0112] The acquisition unit is used to acquire airflow characteristics from the casing wall of the compressor using a probe.

[0113] The first generation unit is used to generate an initial flow field cloud map based on fluid flow characteristics, wherein the initial flow field cloud map represents the static pressure cloud map of the flow surface at the blade tip at the compressor rotor.

[0114] The simulation unit is used to perform numerical simulations of the compressor and obtain numerical simulation data of the fluid flow inside the compressor.

[0115] The second generation unit is used to generate an initial flow field cloud map based on numerical simulation data. The initial flow field cloud map includes a surface static pressure cloud map or a static entropy cloud map representing different blade heights in the blade row.

[0116] According to an embodiment of this application, the generation module 920 includes a third generation unit and a fourth generation unit.

[0117] The third generation unit is used to generate the gradient magnitude of any direction based on the Sobel operator and the chroma channel values ​​of at least two chroma channels of the pixel in that direction.

[0118] The fourth generation unit is used to generate a color gradient map based on the gradient magnitude of multiple pixels in different directions.

[0119] According to an embodiment of this application, the compressor aerodynamic stability prediction device 900 further includes a first determining unit and a processing unit.

[0120] The first determining unit is used to determine the brightness threshold based on the brightness of different pixels in the color gradient map.

[0121] The processing unit is used to binarize the color gradient map based on the brightness threshold to obtain a binarized color gradient map.

[0122] According to an embodiment of this application, the adjustment module 930 includes a second determining unit and a mask unit.

[0123] The second determining unit is used to determine a preset threshold from the color gradient map using the Otsu thresholding method.

[0124] The mask unit is used to perform discrete binary masking on the color attributes of each pixel in the color gradient map based on a preset threshold, so as to obtain a color mask image.

[0125] According to an embodiment of this application, the mask unit includes a first adjustment subunit and a second adjustment subunit.

[0126] The first adjustment subunit is used to adjust the color attribute of any pixel to the target color when the gradient magnitude of the pixel is greater than a preset threshold.

[0127] The second adjustment subunit is used to adjust the color attribute of a pixel to a reference color that is different from the target color, provided that the gradient magnitude of the pixel is not greater than a preset threshold.

[0128] According to an embodiment of this application, the determining module 940 includes a calculation unit and a third determining unit.

[0129] The operation unit is used to perform morphological operations on the color mask image to obtain the target mask image. The morphological operations include at least one of the following: opening operation, dilation, and pixel distance-based closing operation.

[0130] The third determining unit is used to identify connected regions of target color from the target mask image and determine the connected regions as target regions.

[0131] According to an embodiment of this application, the prediction module 950 includes a fourth determining unit, a calculation unit, a first prediction unit, a second prediction unit, and a third prediction unit.

[0132] The fourth determining unit is used to determine the centroid of the pixels in the target region as the feature center.

[0133] The calculation unit is used to calculate the distance between the feature center and the leading edge of the blade, and to calculate the ratio of the distance to the blade length.

[0134] The first prediction unit is used to characterize the compressor as being in an unstable state when the ratio is the first value.

[0135] The second prediction unit is used to characterize the compressor as being in a stable state when the ratio is greater than the second value.

[0136] The third prediction unit is used to characterize the compressor as being in a near-instability state when the ratio is between the first and second values.

[0137] According to an embodiment of this application, the compressor aerodynamic stability prediction device 900 further includes a calculation module and a correction module.

[0138] The calculation module is used to calculate the average gradient magnitude for any connected region, based on the center of the connected region and the gradient magnitude of each pixel in different directions within the connected region.

[0139] The correction module is used to correct the compressor stability prediction results by comparing the average gradient magnitude with the magnitude threshold.

[0140] Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as hardware circuits, such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems-on-a-chip, systems-on-a-substrate, systems-on-package, application-specific integrated circuits (ASICs), or implemented by hardware or firmware in any other reasonable manner by integrating or packaging circuits, or implemented in any one of software, hardware, and firmware, or in a suitable combination of any of these. Alternatively, one or more of the modules, submodules, units, and subunits according to the embodiments of this application can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0141] For example, any multiple of the conversion module 910, generation module 920, adjustment module 930, determination module 940, and prediction module 950 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this application, at least one of the conversion module 910, generation module 920, adjustment module 930, determination module 940, and prediction module 950 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the conversion module 910, generation module 920, adjustment module 930, determination module 940, and prediction module 950 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0142] It should be noted that the compressor aerodynamic stability prediction device part in the embodiments of this application corresponds to the compressor aerodynamic stability prediction method part in the embodiments of this application. For a detailed description of the compressor aerodynamic stability prediction device part, please refer to the compressor aerodynamic stability prediction method part, which will not be repeated here.

[0143] Figure 10 A block diagram of an electronic device suitable for implementing the methods described above, according to an embodiment of this application, is shown. Figure 10 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0144] like Figure 10As shown, an electronic device 1000 according to an embodiment of this application includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0145] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 1002 and / or RAM 1003. It should be noted that the programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0146] According to embodiments of this application, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The electronic device 1000 may also include one or more of the following components connected to the input / output (I / O) interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0147] According to embodiments of this application, the method flow according to embodiments of this application can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, it performs the functions defined in the system of embodiments of this application. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0148] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0149] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0150] For example, according to embodiments of this application, a computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.

[0151] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this application. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of this application.

[0152] When the computer program is executed by the processor 1001, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc. described above can be implemented by computer program modules.

[0153] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1009, and / or installed from a removable medium 1011. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0154] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0155] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations are not explicitly described in this application. In particular, without departing from the spirit and teachings of this application, the features described in the various embodiments of this application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of this application.

[0156] The embodiments of this application have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of this application. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. This application does not depart from its scope, and those skilled in the art can make various substitutions and modifications, all of which should fall within the scope of this application.

Claims

1. A method for predicting the aerodynamic stability of a compressor, characterized in that, include: The initial flow field cloud map of the compressor is converted to a color space to obtain a target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels; For any pixel in the target flow field cloud map, calculate the gradient magnitude of the pixel in different chroma channels, and generate a color gradient map based on the gradient magnitudes of multiple pixels; Based on a preset threshold and gradient magnitude, the color attributes of each pixel in the color gradient map are adjusted to obtain a color mask image. The connected regions of the target colors in the color mask image are defined as the target regions at the interface of the shock wave, the main flow, and the leakage flow. Based on the distance between the target region and the leading edge of the compressor blades, a stability prediction result is generated, wherein the stability prediction result indicates whether the compressor is in an unstable or stable state.

2. The method according to claim 1, characterized in that, The initial flow field contour map was generated in the following manner: Airflow characteristics were collected from the casing wall of the compressor using a probe; An initial flow field cloud map is generated based on the fluid flow characteristics, wherein the initial flow field cloud map represents the static pressure cloud map of the flow surface at the tip of the rotor blades of the compressor. or Numerical simulation of the compressor was performed to obtain numerical simulation data of the fluid flow inside the compressor; The initial flow field cloud map is generated based on the numerical simulation data, wherein the initial flow field cloud map includes a surface static pressure cloud map or a static entropy cloud map characterizing different blade heights of the blade row.

3. The method according to claim 1, characterized in that, Calculating the gradient magnitude of the pixel on different chroma channels, and generating a color gradient map based on the gradient magnitudes of multiple pixels, includes: For any direction, the gradient magnitude in the direction is generated based on the Sobel operator according to the chroma channel values ​​of at least two chroma channels of the pixel in that direction; The color gradient map is generated based on the gradient magnitude of multiple pixels in different directions.

4. The method according to claim 3, characterized in that, Also includes: Based on the brightness of different pixels in the color gradient map, a brightness threshold is determined; The color gradient map is binarized based on the brightness threshold to obtain a binarized color gradient map.

5. The method according to claim 1, characterized in that, Based on a preset threshold and gradient magnitude, the color attributes of each pixel in the color gradient map are adjusted to obtain a color mask image, including: The preset threshold is determined from the color gradient map using the Otsu adaptive thresholding method. Based on the preset threshold, a discrete binary mask is applied to the color attribute of each pixel in the color gradient map to obtain the color mask image.

6. The method according to claim 5, characterized in that, Based on the preset threshold, a discrete binary mask is applied to the color attribute of each pixel in the color gradient map to obtain the color mask image, including: For any pixel, if the gradient magnitude of the pixel is greater than the preset threshold, the color attribute of the pixel is adjusted to the target color; If the gradient magnitude of the pixel is not greater than the preset threshold, the color attribute of the pixel is adjusted to a reference color that is different from the target color.

7. The method according to claim 1, characterized in that, The connected regions of the target colors in the color mask image are defined as the target regions at the interface between the shock wave, the main flow, and the leakage flow, including: Morphological operations are performed on the color mask image to obtain a target mask image, wherein the morphological operations include at least one of the following: opening operation, dilation, and pixel distance-based closing operation; Identify connected regions of the target color from the target mask image and determine the connected regions as the target region.

8. The method according to claim 1, characterized in that, Based on the distance between the target region and the leading edge of the compressor blades, stability prediction results are generated, including: The centroid of the pixels in the target region is determined as the feature center; Calculate the distance between the feature center and the leading edge of the blade, and calculate the ratio of the distance to the blade length; When the ratio is a first value, the stability prediction result indicates that the compressor is in an unstable state; When the ratio is greater than the second value, the stability prediction result indicates that the compressor is in a stable state; When the ratio is between the first value and the second value, the stability prediction result indicates that the compressor is in a near-instability state.

9. The method according to claim 1, characterized in that, Also includes: For any connected region, the average gradient magnitude is calculated based on the center of the connected region and the gradient magnitude of each pixel in the connected region in different directions. The stability prediction results of the compressor are corrected by comparing the average gradient magnitude with the magnitude threshold.

10. A compressor aerodynamic stability prediction device, characterized in that, include: A conversion module is used to perform color space conversion on the initial flow field cloud map of the compressor to obtain a target flow field cloud map, wherein the target flow field cloud map includes at least two chromaticity channels; The generation module is used to calculate the gradient magnitude of any pixel in the target flow field cloud map on different chroma channels, and generate a color gradient map based on the gradient magnitude of multiple pixels. The adjustment module is used to adjust the color attributes of each pixel in the color gradient map based on a preset threshold and gradient magnitude to obtain a color mask image. The determination module is used to determine the connected regions of the target colors in the color mask image as the target regions at the interface of the shock wave, the main flow, and the leakage flow. The prediction module is used to generate a stability prediction result based on the distance between the target area and the leading edge of the compressor blades, wherein the stability prediction result indicates whether the compressor is in an unstable or stable state.

Images