A method of modeling a proportional valve

Abstract

The application relates to the technical field of equal proportion valves, and discloses a modeling method of an equal proportion valve, which comprises the following steps: acquiring an initial modeling image of the equal proportion valve; performing image segmentation on the initial modeling image to obtain a plurality of subimages; acquiring the confidence of all the subimages; adjusting the chroma component of the subimages according to the confidence corresponding to the subimages to obtain target subimages; determining a to-be-modeled image according to the target subimages; constructing an initial equal proportion valve model according to the to-be-modeled image; performing simulation and simulation; adjusting the initial equal proportion valve model based on the simulation result; and obtaining a target equal proportion valve model. The application solves the technical problem that an equal proportion valve model cannot be established, accurately tests the performance of the equal proportion valve by establishing the equal proportion valve model, improves the test efficiency, and simplifies the test process.

Description

Technical Field

[0001] This invention relates to the field of proportional valve technology, and in particular to a modeling method for proportional valves. Background Technology

[0002] With the rapid development of my country's industry, large-capacity, high-parameter generator units have become the mainstream. Simulation systems have gradually transformed from pure training systems to play an important role in providing optimization solutions and guiding production. In other words, current high-precision simulation systems are gradually moving from behind the scenes to production, having a more direct impact on actual power generation on-site. This places higher demands on modeling and calculation accuracy.

[0003] Currently, when placing valves in pipelines, the typical method is to search for the required valve component in the component library, then set it at the corresponding location on the pipeline, and then find the next required valve component and set it at the location corresponding to the previous valve component. Since in real-world scenarios, there are many pipelines requiring valves, and each pipeline requires a large number of valves, the quality of the valves is particularly important.

[0004] In existing solutions, proportional valves are calculated based on the frequency response curve of valve individual modal tests to calculate the valve's mass, impact force, or load-bearing capacity. However, this method has the problems of cumbersome testing process, extremely low testing efficiency, and poor test consistency of modal test frequency response curves under different test locations and different technicians. Summary of the Invention

[0005] This invention provides a modeling method for proportional valves to solve the technical problem in the prior art that it is impossible to effectively establish proportional valve models and perform performance tests on proportional valves.

[0006] To achieve the above objectives, the present invention provides a method for modeling proportional valves, comprising: The proportional valve is photographed to obtain the initial modeling image of the proportional valve; The initial modeling image is segmented to obtain multiple sub-images, and the confidence scores of all sub-images are obtained. For each sub-image, the chromaticity components of the sub-image are adjusted according to the confidence level corresponding to the sub-image to obtain a target sub-image, and the image to be modeled is determined based on each target sub-image; The image to be modeled is used as the model input to construct an initial proportional valve model; The initial proportional valve model is simulated, and the initial proportional valve model is adjusted based on the simulation results to obtain the target proportional valve model.

[0007] In one embodiment, the initial modeling image is segmented to obtain multiple sub-images, including: Edge detection is performed on the initial modeling image to determine the image area A of the initial modeling image; The number of sub-images is set based on the image area A of the initial modeling image.

[0008] In one embodiment, the number of sub-image segments is determined based on the image area A of the initial modeling image, including: A preset image area matrix B for the initial modeling image is provided. The image area matrix B includes a first preset image area B1, a second preset image area B2, a third preset image area B3, and a fourth preset image area B4, where B1 < B2 < B3 < B4. A preset segmentation number matrix C for sub-images, wherein the segmentation number matrix C includes a first preset segmentation number C1, a second preset segmentation number C2, a third preset segmentation number C3, a fourth preset segmentation number C4, and a fifth preset segmentation number C5, and C1 < C2 < C3 < C4 < C5; The number of sub-image segments is determined based on the relationship between the image area A of the initial modeling image and the areas of each preset image: When A < B1, the first preset segmentation number C1 is selected as the segmentation number of the sub-image; When B1≤A<B2, the second preset segmentation number C2 is selected as the segmentation number of the sub-image; When B2≤A<B3, the third preset segmentation number C3 is selected as the segmentation number of the sub-image; When B3≤A<B4, the fourth preset segmentation number C4 is selected as the segmentation number of the sub-image; When B4≤A, the fifth preset segmentation number C5 is selected as the segmentation number of the sub-image.

[0009] In one embodiment, for each sub-image, the chromaticity components of the sub-image are adjusted according to the confidence level corresponding to the sub-image to obtain a target sub-image, and the image to be modeled is determined based on each target sub-image, including: The confidence score of each sub-image is compared with the confidence threshold. For each of the sub-images, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the sub-image is taken as the target sub-image. For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the sub-image is regarded as a non-target sub-image; If all sub-images are target sub-images, then the chromaticity components of all sub-images are not changed, and the initial modeling image is used as the image to be modeled. If any of the sub-images is a non-target sub-image, then all sub-images are divided into image sets according to the relationship between the confidence scores of all sub-images and the confidence threshold, wherein: For each sub-image, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the corresponding sub-image is assigned to the first image set. For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the corresponding sub-image is assigned to the second image set; and chroma component enhancement processing is performed on each sub-image in the second image set to obtain the third image set. The sub-images with enhanced chroma components in the third image set are fused with the sub-images in the first image set to obtain the image to be modeled.

[0010] In one embodiment, a third image set is obtained by performing chroma component enhancement processing on a sub-image in the second image set, including: Obtain the chromaticity components of each sub-image in the second image set; Calculate the average chromaticity component E of the second image set based on the chromaticity components of each sub-image in the second image set; The color intensity value of each sub-image in the second image set is set based on the average value E of the chromaticity components; A third image set is obtained by performing chroma component enhancement processing on each sub-image in the second image set based on the color intensity values.

[0011] In one embodiment, setting the color intensity value of each sub-image in the second image set based on the average value E of the chromaticity components includes: A preset average value matrix W is defined for the chromaticity components of the second image set. The average value matrix W includes the first preset chromaticity component average value W1, the second preset chromaticity component average value W2, the third preset chromaticity component average value W3, and the fourth preset chromaticity component average value W4, where W1 < W2 < W3 < W4. A preset color intensity value matrix D is provided, which includes a first preset color intensity value D1, a second preset color intensity value D2, a third preset color intensity value D3, a fourth preset color intensity value D4, and a fifth preset color intensity value D5, wherein D1 < D2 < D3 < D4 < D5. The color intensity value of the sub-image in the second image set is set according to the relationship between the average value E of the chromaticity components of the second image set and the average value of each preset chromaticity component: When E < W1, the first preset color intensity value D1 is selected as the color intensity value of the sub-image in the second image set; When W1≤E<W2, the second preset color intensity value D2 is selected as the color intensity value of the sub-image in the second image set; When W2≤E<W3, the third preset color intensity value D3 is selected as the color intensity value of the sub-image in the second image set; When W3≤E<W4, the fourth preset color intensity value D4 is selected as the color intensity value of the sub-image in the second image set; When W4≤E, the fifth preset color intensity value D5 is selected as the color intensity value of the sub-image in the second image set.

[0012] In one embodiment, it further includes: Obtain the luminance component of each sub-image in the second image set; Calculate the average value F of the luminance components of the second image set based on the luminance components of each sub-image in the second image set; The color intensity values ​​of the sub-images in the second image set are corrected based on the average value F of the luminance component.

[0013] In one embodiment, the color intensity values ​​of sub-images in the second image set are corrected based on the average value F of the luminance components, including: A preset brightness component average value matrix G of a second image set is provided. The brightness component average value matrix G includes a first preset brightness component average value G1, a second preset brightness component average value G2, a third preset brightness component average value G3 and a fourth preset brightness component average value G4, and G1 < G2 < G3 < G4. A preset color intensity value correction coefficient matrix h, wherein the correction coefficient matrix h includes a first preset color intensity value correction coefficient h1, a second preset color intensity value correction coefficient h2, a third preset color intensity value correction coefficient h3, a fourth preset color intensity value correction coefficient h4 and a fifth preset color intensity value correction coefficient h5, and 0.8 < h1 < h2 < h3 < h4 < h5 < 1.2; When setting the color intensity value of each sub-image in the second image set to the i-th preset color intensity value Di, i=1, 2, 3, 4, 5, the color intensity value of the sub-image in the second image set is corrected according to the relationship between the average value F of the luminance component of the second image set and the average value of each preset luminance component: When F < G1, the first preset color intensity value correction coefficient h1 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h1; When G1≤F<G2, the second preset color intensity value correction coefficient h2 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h2. When G2≤F<G3, the third preset color intensity value correction coefficient h3 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h3; When G3≤F<G4, the fourth preset color intensity value correction coefficient h4 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h4. When G4≤F, the fifth preset color intensity value correction coefficient h5 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h5.

[0014] In one embodiment, the initial proportional valve model is simulated, and the initial proportional valve model is adjusted based on the simulation results to obtain a target proportional valve model, including: The initial proportional valve model is simulated to obtain the first test curve of the initial proportional valve model; The proportional valve was tested to obtain a second test curve for the proportional valve. When there is a deviation between the first test curve and the second test curve, it is determined that the initial proportional valve model needs to be adjusted to obtain the target proportional valve model. When there is no deviation between the first test curve and the second test curve, it is determined that no adjustment is needed to the initial proportional valve model, and the initial proportional valve model is used as the target proportional valve model.

[0015] In one embodiment, when it is determined that the initial proportional valve model needs adjustment, the following steps are taken: The deviation value of the initial proportional valve model is determined based on the first test curve and the second test curve; The initial proportional valve model is adjusted based on the deviation value to obtain the target proportional valve model.

[0016] This invention provides a modeling method for proportional valves, which has the following advantages compared to existing technologies: This invention discloses a modeling method for a proportional valve. The method involves acquiring an initial modeling image of the proportional valve, segmenting the initial modeling image to obtain multiple sub-images, obtaining the confidence scores of all sub-images, adjusting the chromaticity components of the sub-images based on their corresponding confidence scores to obtain target sub-images, determining the images to be modeled based on each target sub-image, constructing an initial proportional valve model based on the images to be modeled, and performing simulation. Based on the simulation results, the initial proportional valve model is adjusted to obtain the target proportional valve model. This invention solves the technical problem of being unable to establish a proportional valve model, and by establishing a proportional valve model, accurately performs performance testing on proportional valves, improving testing efficiency and simplifying the testing process. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a modeling method for a proportional valve according to an embodiment of the present invention is shown. Figure 2 This illustration shows a flowchart of determining the image to be modeled based on each target sub-image in an embodiment of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0019] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0021] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0022] The following is a description of preferred embodiments of the present invention in conjunction with the accompanying drawings.

[0023] like Figure 1 As shown, an embodiment of the present invention discloses a modeling method for a proportional valve, the method comprising: S110: Take an image of the proportional valve to obtain an initial modeling image of the proportional valve; S120: Perform image segmentation on the initial modeling image to obtain multiple sub-images, and obtain the confidence scores of all sub-images; In this embodiment, confidence level refers to the confidence level corresponding to the color intensity of the sub-image.

[0024] In some embodiments of this application, the initial modeling image is segmented to obtain multiple sub-images, including: Edge detection is performed on the initial modeling image to determine the image area A of the initial modeling image; The number of sub-images is set based on the image area A of the initial modeling image.

[0025] In some embodiments of this application, the number of sub-image segments is set according to the image area A of the initial modeling image, including: A preset image area matrix B for the initial modeling image is provided. The image area matrix B includes a first preset image area B1, a second preset image area B2, a third preset image area B3, and a fourth preset image area B4, where B1 < B2 < B3 < B4. A preset segmentation number matrix C for sub-images, wherein the segmentation number matrix C includes a first preset segmentation number C1, a second preset segmentation number C2, a third preset segmentation number C3, a fourth preset segmentation number C4, and a fifth preset segmentation number C5, and C1 < C2 < C3 < C4 < C5; The number of sub-image segments is determined based on the relationship between the image area A of the initial modeling image and the areas of each preset image: When A < B1, the first preset segmentation number C1 is selected as the segmentation number of the sub-image; When B1≤A<B2, the second preset segmentation number C2 is selected as the segmentation number of the sub-image; When B2≤A<B3, the third preset segmentation number C3 is selected as the segmentation number of the sub-image; When B3≤A<B4, the fourth preset segmentation number C4 is selected as the segmentation number of the sub-image; When B4≤A, the fifth preset segmentation number C5 is selected as the segmentation number of the sub-image.

[0026] The beneficial effects of the above technical solution are: the number of sub-images is set according to the relationship between the image area A of the initial modeling image and the area of ​​each preset image. By setting the number of sub-images, the present invention can effectively segment the initial modeling image, thereby providing reliable data support for the modeling of proportional valves.

[0027] S130: For each sub-image, adjust the chromaticity component of the sub-image according to the confidence level corresponding to the sub-image to obtain a target sub-image, and determine the image to be modeled according to each target sub-image; like Figure 2 As shown, in some embodiments of this application, for each sub-image, the chromaticity components of the sub-image are adjusted according to the confidence level corresponding to the sub-image to obtain a target sub-image, and the image to be modeled is determined based on each target sub-image, including: S131: Compare the confidence score of each sub-image with the confidence threshold; For each of the sub-images, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the sub-image is taken as the target sub-image. For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the sub-image is regarded as a non-target sub-image; S132: If all sub-images are target sub-images, then the chromaticity components of all sub-images are not changed, and the initial modeling image is used as the image to be modeled; If any of the sub-images is a non-target sub-image, then all sub-images are divided into image sets according to the relationship between the confidence scores of all sub-images and the confidence threshold, wherein: S133: For each sub-image, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the corresponding sub-image is assigned to the first image set; S134: For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the corresponding sub-image is assigned to the second image set; and chroma component enhancement processing is performed on each sub-image in the second image set to obtain the third image set. S135: The sub-image with enhanced chroma components in the third image set is fused with the sub-image in the first image set to obtain the image to be modeled.

[0028] In this embodiment, the confidence threshold can be set according to the actual situation, and no specific limitation is made here.

[0029] The beneficial effects of the above technical solution are: by performing chroma component enhancement processing on the sub-images in the second image set, the present invention can avoid the phenomenon that the sub-images in the second image set have poor sense of layering, unclear distinction between primary and secondary objects, and lack of transparency.

[0030] In some embodiments of this application, a third image set is obtained by performing chroma component enhancement processing on sub-images in the second image set, including: Obtain the chromaticity components of each sub-image in the second image set; Calculate the average chromaticity component E of the second image set based on the chromaticity components of each sub-image in the second image set; The color intensity value of each sub-image in the second image set is set based on the average value E of the chromaticity components; A third image set is obtained by performing chroma component enhancement processing on each sub-image in the second image set based on the color intensity values.

[0031] In some embodiments of this application, setting the color intensity value of each sub-image in the second image set based on the average value E of the chromaticity components includes: A preset average value matrix W is defined for the chromaticity components of the second image set. The average value matrix W includes the first preset chromaticity component average value W1, the second preset chromaticity component average value W2, the third preset chromaticity component average value W3, and the fourth preset chromaticity component average value W4, where W1 < W2 < W3 < W4. A preset color intensity value matrix D is provided, which includes a first preset color intensity value D1, a second preset color intensity value D2, a third preset color intensity value D3, a fourth preset color intensity value D4, and a fifth preset color intensity value D5, wherein D1 < D2 < D3 < D4 < D5. The color intensity value of the sub-image in the second image set is set according to the relationship between the average value E of the chromaticity components of the second image set and the average value of each preset chromaticity component: When E < W1, the first preset color intensity value D1 is selected as the color intensity value of the sub-image in the second image set; When W1≤E<W2, the second preset color intensity value D2 is selected as the color intensity value of the sub-image in the second image set; When W2≤E<W3, the third preset color intensity value D3 is selected as the color intensity value of the sub-image in the second image set; When W3≤E<W4, the fourth preset color intensity value D4 is selected as the color intensity value of the sub-image in the second image set; When W4≤E, the fifth preset color intensity value D5 is selected as the color intensity value of the sub-image in the second image set.

[0032] In this embodiment, the chromaticity component describes the proportion of different wavelengths that constitute a color.

[0033] In this embodiment, the color intensity value refers to a value used to enhance the color of each sub-image in the second image set.

[0034] The beneficial effects of the above technical solution are as follows: the color intensity value of the sub-image in the second image set is set according to the relationship between the average value E of the chromaticity components of the second image set and the average value of each preset chromaticity component. By setting the color intensity value of the sub-image in the second image set, the present invention can effectively enhance the color of the sub-image in the second image set, thereby realizing confidence enhancement processing of the sub-image in the second image set, eliminating phenomena such as image line segment disappearance and poor sense of layering, and ensuring the modeling accuracy of the proportional valve.

[0035] In some embodiments of this application, it also includes: Obtain the luminance component of each sub-image in the second image set; Calculate the average value F of the luminance components of the second image set based on the luminance components of each sub-image in the second image set; The color intensity values ​​of the sub-images in the second image set are corrected based on the average value F of the luminance component.

[0036] In some embodiments of this application, the color intensity values ​​of sub-images in the second image set are corrected based on the average value F of the luminance components, including: A preset brightness component average value matrix G of a second image set is provided. The brightness component average value matrix G includes a first preset brightness component average value G1, a second preset brightness component average value G2, a third preset brightness component average value G3 and a fourth preset brightness component average value G4, and G1 < G2 < G3 < G4. A preset color intensity value correction coefficient matrix h, wherein the correction coefficient matrix h includes a first preset color intensity value correction coefficient h1, a second preset color intensity value correction coefficient h2, a third preset color intensity value correction coefficient h3, a fourth preset color intensity value correction coefficient h4 and a fifth preset color intensity value correction coefficient h5, and 0.8 < h1 < h2 < h3 < h4 < h5 < 1.2; When setting the color intensity value of each sub-image in the second image set to the i-th preset color intensity value Di, i=1, 2, 3, 4, 5, the color intensity value of the sub-image in the second image set is corrected according to the relationship between the average value F of the luminance component of the second image set and the average value of each preset luminance component: When F < G1, the first preset color intensity value correction coefficient h1 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h1; When G1≤F<G2, the second preset color intensity value correction coefficient h2 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h2. When G2≤F<G3, the third preset color intensity value correction coefficient h3 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h3; When G3≤F<G4, the fourth preset color intensity value correction coefficient h4 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h4. When G4≤F, the fifth preset color intensity value correction coefficient h5 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h5.

[0037] In this embodiment, the luminance component refers to the brightness of the image.

[0038] The beneficial effects of the above technical solution are as follows: when the color intensity value of the sub-image in the second image set is set to the i-th preset color intensity value Di, i=1, 2, 3, 4, 5, the color intensity value of the sub-image in the second image set is corrected according to the relationship between the average value F of the luminance component of the second image set and the average value of each preset luminance component. By correcting the color intensity value of the sub-image in the second image set, the present invention can further ensure the color intensity effect of the sub-image in the second image set and avoid large errors.

[0039] S140: Use the image to be modeled as the model input to construct an initial proportional valve model; S150: Simulate the initial proportional valve model and adjust it based on the simulation results to obtain the target proportional valve model. In some embodiments of this application, the initial proportional valve model is simulated, and the initial proportional valve model is adjusted based on the simulation results to obtain a target proportional valve model, including: The initial proportional valve model is simulated to obtain the first test curve of the initial proportional valve model; The proportional valve was tested to obtain a second test curve for the proportional valve. When there is a deviation between the first test curve and the second test curve, it is determined that the initial proportional valve model needs to be adjusted to obtain the target proportional valve model. When there is no deviation between the first test curve and the second test curve, it is determined that no adjustment is needed to the initial proportional valve model, and the initial proportional valve model is used as the target proportional valve model.

[0040] In this embodiment, impact tests, wear resistance tests, and stress tests are performed on the proportional valves using a proportional model, and corresponding test results are obtained. A first test curve is generated based on the test results.

[0041] In this embodiment, impact tests, wear resistance tests, and stress tests are performed directly on the proportional valves to obtain the corresponding test results, and a second test curve is generated based on the test results.

[0042] The beneficial effects of the above technical solution are: the present invention can test the initial proportional valve model, thereby improving the modeling accuracy of the proportional valve model, avoiding large deviations in subsequent use, ensuring modeling accuracy, and improving testing efficiency.

[0043] In some embodiments of this application, when it is determined that the initial proportional valve model needs adjustment, the following steps are included: The deviation value of the initial proportional valve model is determined based on the first test curve and the second test curve; The initial proportional valve model is adjusted based on the deviation value to obtain the target proportional valve model.

[0044] In this embodiment, the deviation value can be one of the test results, such as impact test, wear resistance test, or stress test. The specific value can be selected according to the actual situation and is not specifically limited here.

[0045] The beneficial effects of the above technical solution are: by adjusting the initial proportional valve model according to the deviation value, the present invention can further obtain a qualified model, thereby improving the accuracy of the model.

[0046] In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0047] Although the invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, features in the embodiments disclosed herein can be combined with each other in any manner, provided there is no structural conflict. The omission of all such combinations in this specification is merely for brevity and resource conservation. Therefore, the invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

[0048] It will be understood by those skilled in the art that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A modeling method for proportional valves, characterized in that, The method includes: The proportional valve is photographed to obtain the initial modeling image of the proportional valve; Edge detection is performed on the initial modeling image to determine the image area A of the initial modeling image; the number of sub-images is set according to the image area A of the initial modeling image, and the confidence scores of all sub-images are obtained; For each sub-image, the chromaticity components of the sub-image are adjusted according to the confidence level corresponding to the sub-image to obtain a target sub-image, and the image to be modeled is determined based on each target sub-image; The image to be modeled is used as the model input to construct an initial proportional valve model; The initial proportional valve model is simulated, and the initial proportional valve model is adjusted based on the simulation results to obtain the target proportional valve model; The number of sub-image segments is determined based on the image area A of the initial modeling image, including: A preset image area matrix B for the initial modeling image is provided. The image area matrix B includes a first preset image area B1, a second preset image area B2, a third preset image area B3, and a fourth preset image area B4, where B1 < B2 < B3 < B4. A preset segmentation number matrix C for sub-images, wherein the segmentation number matrix C includes a first preset segmentation number C1, a second preset segmentation number C2, a third preset segmentation number C3, a fourth preset segmentation number C4, and a fifth preset segmentation number C5, and C1 < C2 < C3 < C4 < C5; The number of sub-image segments is determined based on the relationship between the image area A of the initial modeling image and the areas of each preset image: When A < B1, the first preset segmentation number C1 is selected as the segmentation number of the sub-image; When B1≤A<B2, the second preset segmentation number C2 is selected as the segmentation number of the sub-image; When B2≤A<B3, the third preset segmentation number C3 is selected as the segmentation number of the sub-image; When B3≤A<B4, the fourth preset segmentation number C4 is selected as the segmentation number of the sub-image; When B4≤A, the fifth preset segmentation number C5 is selected as the segmentation number of the sub-image.

2. The modeling method for proportional valves according to claim 1, characterized in that, For each sub-image, the chromaticity components of the sub-image are adjusted according to the confidence level corresponding to the sub-image to obtain a target sub-image, and the image to be modeled is determined based on each target sub-image, including: The confidence score of each sub-image is compared with the confidence threshold. For each of the sub-images, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the sub-image is taken as the target sub-image. For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the sub-image is regarded as a non-target sub-image; If all sub-images are target sub-images, then the chromaticity components of all sub-images are not changed, and the initial modeling image is used as the image to be modeled. If any of the sub-images is a non-target sub-image, then all sub-images are divided into image sets according to the relationship between the confidence scores of all sub-images and the confidence threshold, wherein: For each sub-image, if the confidence level corresponding to the sub-image is greater than or equal to the confidence level threshold, then the corresponding sub-image is assigned to the first image set. For each sub-image, if the confidence level corresponding to the sub-image is less than the confidence level threshold, then the corresponding sub-image is assigned to the second image set. A third image set is obtained by performing chroma component enhancement processing on each sub-image in the second image set. The sub-images with enhanced chroma components in the third image set are fused with the sub-images in the first image set to obtain the image to be modeled.

3. The modeling method for proportional valves according to claim 2, characterized in that, A third image set is obtained by performing chroma component enhancement processing on the sub-images in the second image set, including: Obtain the chromaticity components of each sub-image in the second image set; Calculate the average chromaticity component E of the second image set based on the chromaticity components of each sub-image in the second image set; The color intensity value of each sub-image in the second image set is set based on the average value E of the chromaticity components; A third image set is obtained by performing chroma component enhancement processing on each sub-image in the second image set based on the color intensity values.

4. The modeling method for proportional valves according to claim 3, characterized in that, Based on the average value E of the chromaticity components, the color intensity value of each sub-image in the second image set is set, including: A preset average value matrix W is defined for the chromaticity components of the second image set. The average value matrix W includes the first preset chromaticity component average value W1, the second preset chromaticity component average value W2, the third preset chromaticity component average value W3, and the fourth preset chromaticity component average value W4, where W1 < W2 < W3 < W4. A preset color intensity value matrix D is provided, which includes a first preset color intensity value D1, a second preset color intensity value D2, a third preset color intensity value D3, a fourth preset color intensity value D4, and a fifth preset color intensity value D5, wherein D1 < D2 < D3 < D4 < D5. The color intensity value of the sub-image in the second image set is set according to the relationship between the average value E of the chromaticity components of the second image set and the average value of each preset chromaticity component: When E < W1, the first preset color intensity value D1 is selected as the color intensity value of the sub-image in the second image set; When W1≤E<W2, the second preset color intensity value D2 is selected as the color intensity value of the sub-image in the second image set; When W2≤E<W3, the third preset color intensity value D3 is selected as the color intensity value of the sub-image in the second image set; When W3≤E<W4, the fourth preset color intensity value D4 is selected as the color intensity value of the sub-image in the second image set; When W4≤E, the fifth preset color intensity value D5 is selected as the color intensity value of the sub-image in the second image set.

5. The modeling method for proportional valves according to claim 4, characterized in that, Also includes: Obtain the luminance component of each sub-image in the second image set; Calculate the average value F of the luminance components of the second image set based on the luminance components of each sub-image in the second image set; The color intensity values ​​of the sub-images in the second image set are corrected based on the average value F of the luminance component.

6. The modeling method for proportional valves according to claim 5, characterized in that, The color intensity values ​​of the sub-images in the second image set are corrected based on the average value F of the luminance component, including: A preset brightness component average value matrix G of a second image set is provided. The brightness component average value matrix G includes a first preset brightness component average value G1, a second preset brightness component average value G2, a third preset brightness component average value G3 and a fourth preset brightness component average value G4, and G1 < G2 < G3 < G4. A preset color intensity value correction coefficient matrix h, wherein the correction coefficient matrix h includes a first preset color intensity value correction coefficient h1, a second preset color intensity value correction coefficient h2, a third preset color intensity value correction coefficient h3, a fourth preset color intensity value correction coefficient h4 and a fifth preset color intensity value correction coefficient h5, and 0.8 < h1 < h2 < h3 < h4 < h5 < 1.2; When setting the color intensity value of each sub-image in the second image set to the i-th preset color intensity value Di, i=1, 2, 3, 4, 5, the color intensity value of the sub-image in the second image set is corrected according to the relationship between the average value F of the luminance component of the second image set and the average value of each preset luminance component: When F < G1, the first preset color intensity value correction coefficient h1 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h1; When G1≤F<G2, the second preset color intensity value correction coefficient h2 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h2. When G2≤F<G3, the third preset color intensity value correction coefficient h3 is selected to correct the color intensity value of the sub-image in the second image set, and the corrected color intensity value of the sub-image in the second image set is Di*h3; When G3≤F<G4, the fourth preset color intensity value correction coefficient h4 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h4. When G4≤F, the fifth preset color intensity value correction coefficient h5 is selected to correct the color intensity value of the sub-image in the second image set. The corrected color intensity value of the sub-image in the second image set is Di*h5.

7. The modeling method for proportional valves according to claim 1, characterized in that, The initial proportional valve model is simulated, and the initial proportional valve model is adjusted based on the simulation results to obtain the target proportional valve model, including: The initial proportional valve model is simulated to obtain the first test curve of the initial proportional valve model; The proportional valve was tested to obtain a second test curve for the proportional valve. When there is a deviation between the first test curve and the second test curve, it is determined that the initial proportional valve model needs to be adjusted to obtain the target proportional valve model. When there is no deviation between the first test curve and the second test curve, it is determined that no adjustment is needed to the initial proportional valve model, and the initial proportional valve model is used as the target proportional valve model.

8. The modeling method for proportional valves according to claim 7, characterized in that, When it is determined that the initial proportional valve model needs adjustment, the following applies: The deviation value of the initial proportional valve model is determined based on the first test curve and the second test curve; The initial proportional valve model is adjusted based on the deviation value to obtain the target proportional valve model.

Images