Modeling method, device, computer equipment and storage medium for GIS equipment

Abstract

The present application relates to a modeling method, device, computer equipment and storage medium for GIS equipment. The method includes obtaining multiple frames of video images, industrial CT images and drawing design parameters of GIS equipment, reversely constructing an external digital model of GIS equipment according to the video images of each GIS equipment, reversely constructing an internal digital model of GIS equipment according to the industrial CT images, and constructing a GIS equipment model according to the drawing design parameters, the external digital model of GIS equipment and the internal digital model of GIS equipment. The panoramic information of the equipment can be reversed based on the video and industrial CT images of the GIS equipment collected on site, and the edge gaps and internal structures of the equipment model can be made more in line with the actual situation on site by combining the idealized model parameters (drawing design parameters) with the panoramic information of the equipment (video images and industrial CT images), so that it can be transformed from virtual to real, laying a strong foundation for the subsequent simulation calculation of the GIS digital twin model.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a modeling method, apparatus, device and storage medium for GIS equipment. Background Art

[0002] Gas-insulated metal-enclosed switchgear (GIS) has the advantages of convenient configuration, small size, reliable operation and long service life, and is widely used in power systems.

[0003] Therefore, how to analyze and monitor GIS equipment to guide production and operation is particularly important. In the prior art, when analyzing and monitoring GIS equipment, a model can be constructed according to the design parameters of the GIS equipment drawings, and then the model can be analyzed and monitored to guide the production and operation of the GIS equipment.

[0004] However, the current method of constructing GIS equipment models is not in line with the actual situation at the application site and has low accuracy. Summary of the invention

[0005] Based on this, it is necessary to provide a more accurate GIS equipment modeling method, device, computer equipment and storage medium that can be applied to the actual situation on site in order to address the above technical problems.

[0006] In a first aspect, the present application provides a modeling method for a GIS device, the method comprising:

[0007] Obtain multi-frame video images, industrial CT images and drawing design parameters of GIS equipment;

[0008] Based on the video images of each GIS device, reversely construct the external digital model of the GIS device;

[0009] Based on industrial CT images, reverse engineering is used to build the internal digital model of GIS equipment;

[0010] Construct the GIS equipment model according to the drawing design parameters, the external digital model of the GIS equipment and the internal digital model of the GIS equipment.

[0011] In one embodiment, based on the video images of each GIS device, reverse engineering is performed to construct an external digital model of the GIS device, including:

[0012] Determine a key frame video image from each video image;

[0013] Determine the seed patch of the external model according to the key frame video image;

[0014] Based on the seed patch, build the external digital model of the GIS equipment.

[0015] In one embodiment, determining a key frame video image from each video image includes:

[0016] Processing the grayscale value of each video image, and calculating the grayscale change rate of each video image using the average gradient method;

[0017] The grayscale change rate is compared with the change rate threshold, and if the grayscale change rate is greater than the change rate threshold, the video image is determined to be a key frame video image.

[0018] In one embodiment, determining a seed patch of an external model according to a key frame video image includes:

[0019] Extracting feature points of key frame video images and determining feature matching points of two consecutive key frame video images;

[0020] According to the feature matching points, the center coordinates of the seed patch are determined by triangulation method;

[0021] Determine the normal vector of the seed patch according to the center coordinates of the seed patch and the center coordinates of the camera;

[0022] The seed patch is constructed according to the center coordinates of the seed patch, the normal vector of the seed patch and the reference image.

[0023] In one embodiment, extracting feature points of a key frame video image and determining feature matching points of two consecutive key frame video images includes:

[0024] Obtain the average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image;

[0025] If the average energy change is greater than the preset energy change threshold, the central pixel point at the location of the local detection window is extracted as a feature point;

[0026] Obtaining a pixel distance between a first feature point on a first key frame video image and a second feature point on a second key frame video image; the first key frame video image and the second key frame video image are any two consecutive frames of video images;

[0027] Taking the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold as reference matching points, and judging whether the reference matching points satisfy the limit constraint rule;

[0028] If satisfied, the reference matching point is determined as a pair of feature matching points.

[0029] In one embodiment, an external digital model of a GIS device is constructed based on a seed patch, including:

[0030] Determine the adjacent seed patches according to the center coordinates of the seed patch and the normal vector of the seed patch;

[0031] Adjacent seed patches are stitched together to obtain the external digital model of the GIS equipment.

[0032] In one embodiment, the internal digital model of the GIS equipment is reversely constructed based on the industrial CT image, including:

[0033] Preprocess the industrial CT images to obtain segmented images of different areas of the GIS equipment;

[0034] The contour points of each segmented image are determined by using the 8-field single pixel tracking method, and the closed contour plane graph of each segmented image is formed according to the contour points of each segmented image;

[0035] The closed contour plane image is reconstructed by fitting a cubic spline surface to obtain the surface patches of each segmented image.

[0036] The surface patches of each segmented image are spliced ​​together to construct the internal digital model of the GIS equipment.

[0037] In one embodiment, the industrial CT image is preprocessed to obtain segmented images of different areas of the GIS device, including:

[0038] Perform grayscale nonlinear transformation on the industrial CT image to obtain an enhanced industrial CT image;

[0039] A filtering algorithm is used to reduce noise on the enhanced industrial CT image to obtain a reduced-noise industrial CT image;

[0040] According to the image grayscale information of the denoised industrial CT image, the denoised image is segmented to obtain segmented images of different areas of the GIS equipment.

[0041] In one embodiment, a GIS device model is constructed according to the drawing design parameters, the external digital model of the GIS device, and the internal digital model of the GIS device, including:

[0042] The design parameters of the drawing are respectively substituted into the external digital model of the GIS equipment and the internal digital model of the GIS equipment to obtain the digital twin model of the GIS equipment as the GIS equipment model.

[0043] In a second aspect, the present application provides a modeling device for a GIS device, the device comprising:

[0044] Acquisition module, used to acquire multi-frame video images, industrial CT images and drawing design parameters of GIS equipment;

[0045] The external digital model building module is used to reversely build the external digital model of the GIS device based on the video images of each GIS device;

[0046] Internal digital model building module, used to reversely build the internal digital model of GIS equipment based on industrial CT images;

[0047] The GIS equipment model determination module is used to construct the GIS equipment model according to the drawing design parameters, the external digital model of the GIS equipment and the internal digital model of the GIS equipment.

[0048] In a third aspect, the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0049] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method in any one of the embodiments of the first aspect above.

[0050] The modeling method, device, computer equipment and storage medium of the above-mentioned GIS equipment obtains multiple frames of video images, industrial CT images and drawing design parameters of the GIS equipment, reversely constructs the external digital model of the GIS equipment according to the video images of each GIS equipment, reversely constructs the internal digital model of the GIS equipment according to the industrial CT images, and constructs the GIS equipment model according to the drawing design parameters, the external digital model of the GIS equipment and the internal digital model of the GIS equipment. It is possible to reverse the panoramic information of the equipment based on the video and industrial CT images of the GIS equipment collected on site, and combine the idealized model parameters (drawing design parameters) with the panoramic information of the equipment (video images and industrial CT images) to make the edge gaps and internal structures of the equipment model more in line with the actual situation on site, so that it can move from virtual to real, and lay a strong foundation for the simulation calculation of the GIS digital twin model in the future. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 An application environment diagram of a modeling method for a GIS device in one embodiment;

[0052] Figure 2 A schematic diagram of a flow chart of a modeling method for a GIS device in one embodiment;

[0053] Figure 3 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0054] Figure 4 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0055] Figure 5 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0056] Figure 6 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0057] Figure 7 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0058] Figure 8 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0059] Fig. 9 A schematic diagram of a flow chart of a modeling method for a GIS device in another embodiment;

[0060] Fig.10 A structural block diagram of a modeling device for a GIS device in one embodiment;

[0061] Fig.11 A structural block diagram of a modeling device for a GIS device in another embodiment;

[0062] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] Gas-insulated metal switchgear (GIS) is the main switchgear in the power grid, and is an important high-voltage electrical device in the UHV power grid. GIS equipment is widely used in power systems due to its advantages such as convenient configuration, small size, reliable operation and long service life. However, in the large-scale and long-term use of GIS equipment, substation accidents caused by GIS have gradually increased, which has had a serious impact on the stable operation of the power grid. Therefore, it is particularly important to analyze and monitor GIS equipment to guide production operations.

[0065] With the rapid development of emerging technologies such as information fusion, intelligent sensing and network information, the integration of power equipment with network information technology, intelligent technology and digital technology has become a development trend in the power industry. Digital Twin is the best technology to achieve the transformation and upgrading of traditional power plants to smart power plants. Digital Twin is actually a digital model that integrates multi-probability, multi-scale and multi-physical fields. It builds a virtual model that maps with the actual physical model based on the actual physical model. Through a large amount of historical data and real-time data transmitted by sensors, it reflects and describes the full life cycle of the physical model. Therefore, by deeply integrating digital twin technology with GIS equipment, the physical entity of GIS equipment and its digital twin can be interactively integrated and mapped to each other, so as to realize the functions of real-time simulation, optimization analysis, supervision and alarm of GIS equipment, so as to provide intelligent optimization guidance for operators.

[0066] The modeling method of GIS equipment provided in this application can be applied to Figure 1 In the application environment shown. The application environment includes: terminal 101, camera 102, industrial CT machine 103, GIS equipment 104. Among them, the terminal 101 can communicate with the camera 102 and the industrial CT machine 103 through the network. The external image of the GIS equipment can be captured in all directions by the camera 102, and the captured image is transmitted to the terminal. The industrial CT machine 103 captures the internal components of the GIS equipment and transmits the captured internal image to the terminal. The terminal 101 analyzes and processes the external image and the internal image to construct the internal and external digital model of the GIS equipment. Among them, the terminal 101 can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices.

[0067] In one embodiment, Figure 2 As shown in the figure, a modeling method for GIS equipment is provided, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0068] S202, obtaining multi-frame video images, industrial CT images and drawing design parameters of the GIS device.

[0069] The video images are video images of GIS equipment taken by cameras in various directions. The industrial CT images are industrial CT images of the inside of GIS equipment taken by industrial CT machines. The drawing design parameters are parameters used when designing GIS equipment, and may include the length, width, and height of GIS equipment, which are not limited here.

[0070] Specifically, the terminal obtains multiple frames of video images of the GIS device in various directions captured by the camera. For example, multiple frames of video images of the GIS device in eight directions, namely, east, south, west, north, northeast, northwest, southeast, and southwest, are captured and transmitted to the terminal. An industrial CT machine is used to capture the GIS device, and the captured industrial CT images are sent to the terminal. The drawing design parameters may be data pre-stored in the terminal.

[0071] S204, reversely constructing an external digital model of the GIS device based on the video images of each GIS device.

[0072] Specifically, after the terminal obtains multiple video images of the GIS device, the multiple video images are enhanced and filtered, and then the video images are analyzed to obtain feature parameters for constructing an external digital model, and the external digital model is constructed. Among them, the feature parameters of the video images can be extracted by inputting the multiple video images into the neural network model, for example, the feature points of each video image are extracted. According to the feature points of each video image, a pair of matching feature points of two video images is determined, and multiple seed patches are constructed. The seed patches are spliced ​​to obtain the external digital model of the GIS device. It can also be that the grayscale parameters of the video images are determined by grayscale processing of each video image, and then the key frame video images are screened according to the grayscale parameters. The key frame video images are analyzed and processed, the feature points of the key frame video images are extracted, and the matching feature points of two consecutive key frame video images are determined by using a fast nearest neighbor method, and seed patches are established according to the matching feature points, and the seed patches are spliced ​​according to preset rules to obtain the external digital model, which is not limited here.

[0073] S206, reversely constructing an internal digital model of the GIS equipment based on the industrial CT image.

[0074] Specifically, after the industrial CT image is acquired, the industrial CT image can be analyzed and processed, for example, grayscale value processing and segmentation processing can be performed on the industrial CT image. For example, after the GT industrial image is segmented, the contour points of each segmented industrial CT image can be tracked to obtain the contour plane of each segmented industrial CT image, and a surface can be generated according to the contour plane, and multiple surfaces can be spliced ​​to obtain an internal digital model. Alternatively, the industrial CT image can be input into a pre-built neural network model to obtain contour planes of different regions of the internal components of each GIS device, and after each contour plane is curved, the surfaces are spliced ​​to obtain an internal digital model of the GIS device, which is not limited here.

[0075] S208, constructing a GIS device model according to the drawing design parameters, the external digital model of the GIS device, and the internal digital model of the GIS device.

[0076] Specifically, the drawing design parameters can be substituted into the external digital model of the GIS device and the internal digital model of the GIS device to obtain the digital twin model of the GIS device as the GIS device model. Alternatively, the drawing design parameters can be substituted into the external digital model of the GIS device and the internal digital model of the GIS device, and then the external digital model of the GIS device and the internal digital model of the GIS device are merged to obtain the GIS device model, which is not limited here.

[0077] In the above-mentioned modeling method of GIS equipment, by acquiring multi-frame video images, industrial CT images and drawing design parameters of GIS equipment, the external digital model of GIS equipment is reversely constructed according to the video images of each GIS equipment, the internal digital model of GIS equipment is reversely constructed according to the industrial CT images, and the GIS equipment model is constructed according to the drawing design parameters, the external digital model of GIS equipment and the internal digital model of GIS equipment. Based on the video images and industrial CT images of GIS equipment collected on site, the panoramic information of the equipment can be reversed, and the edge gaps and internal structures of the equipment model can be made more in line with the actual situation on site by combining the idealized model parameters (drawing design parameters) with the panoramic information of the equipment (video images and industrial CT images), so that it can move from virtual to real, laying a strong foundation for the subsequent simulation calculation of the GIS digital twin model.

[0078] The above embodiment has described the modeling method of GIS equipment. Now, an embodiment is used to further describe how to construct the external digital model of GIS equipment. In one embodiment, Figure 3 As shown, based on the video images of each GIS device, the external digital model of the GIS device is reversely constructed, including:

[0079] S302: Determine a key frame video image from each video image.

[0080] Specifically, the key frame video images can be obtained by inputting each video image into a preset neural network model, or the key frame video images can be determined according to the gray value parameters by processing the gray value of each video image. The gray value parameters may include the gray value change rate of each pixel in the video image.

[0081] Furthermore, if Figure 4 As shown, from each video image, a key frame video image is determined, including:

[0082] S402, performing grayscale value processing on each video image, and calculating the grayscale change rate of each video image using an average gradient method.

[0083] Specifically, the grayscale processing can be performed by direct grayscale transformation, image inversion, logarithmic transformation, etc., which are not limited here. After grayscale value processing, the average gradient method is used to reflect the grayscale change rate of the video image in multi-dimensional directions, that is, according to the formula Solve the average gradient value of each pixel in the image as the grayscale change rate; where S(f,I) represents the average gradient value of the image, I represents the entire image domain except the image boundary, #(I) represents the number of pixels in the image domain, x and y are pixel coordinates, and f represents the grayscale.

[0084] S404, comparing the grayscale change rate with the change rate threshold, if the grayscale change rate is greater than the change rate threshold, determining that the video image is a key frame video image.

[0085] Specifically, the grayscale change rate is compared with the change rate advance, which can be done by difference, quotient or direct comparison, which is not limited here. If the grayscale change rate is greater than the change rate advance, the video image is determined to be a key frame video image.

[0086] S304: Determine a seed patch of the external model according to the key frame video image.

[0087] Specifically, after obtaining the key frame image, feature points of the key frame image may be extracted, and the distance relationship between the feature points may be used to construct seed patches of multiple external models.

[0088] Furthermore, if Figure 5 As shown, according to the key frame video image, the seed patch of the external model is determined, including:

[0089] S502, extracting feature points of key frame video images, and determining feature matching points of two consecutive key frame video images.

[0090] Specifically, the key frame images may be input into a preset feature point extraction neural network to extract feature points of the key frame images, and after the feature points of each key frame image are determined, feature points of two consecutive key frame images are extracted and matched. Optionally, the number of feature points is at least one.

[0091] Furthermore, if Figure 6 As shown, extracting feature points of key frame video images and determining feature matching points of two consecutive key frame video images include:

[0092] S602, obtaining an average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image.

[0093] Specifically, after the key frame video image is acquired, the preset rejection detection window is moved along different directions on the key frame image to obtain the average energy change of the local detection window at each moving position. For example, the autocorrelation matrix of the image brightness of the key frame video image is set to: In the formula, Harris feature point response function is: R = det(M)-k(trace(M)) 2 >TIn the formula, det(M)=λ1λ2=PQ-O 2 ; trace(M) = λ1 + λ2 = P + Q; k is an empirical value, generally 0.1.

[0094] S604: If the average energy change is greater than a preset energy change threshold, the central pixel point at the location of the local detection window is extracted as a feature point.

[0095] Specifically, the average energy change is compared with a preset energy change threshold. If the average energy change is greater than the preset energy change threshold, the central pixel point of the local detection window is extracted as a feature point. The feature point corresponds to the local maximum point of the function R. When the R value of a pixel on the image is greater than a given threshold T, the point is considered to be an image feature point. There can be multiple feature points in each frame of the image.

[0096] S606, obtaining a pixel distance between a first feature point on a first key frame video image and a second feature point on a second key frame video image; the first key frame video image and the second key frame video image are any two consecutive frames of video images.

[0097] Specifically, after obtaining the feature points of each key frame video image, it is necessary to determine the matching feature points of two consecutive key frame video images. The pixel distance between the first feature point on the first key frame video image and the second feature point on the second key frame video image can be obtained, and the formula Calculate, where (x p1 ,y p1 ) is the pixel coordinate of the first feature point p1 in the first key frame video image, (x p2 ,y p2 ) is the pixel coordinate of the second feature point p2 in the second key frame video image.

[0098] S608: Use the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold as reference matching points, and determine whether the reference matching points meet the limit constraint rule.

[0099] Specifically, the first feature point and the second feature point whose pixel distance D is less than or equal to the preset distance threshold r are used as reference matching points. At this time, it is necessary to determine whether the first feature point p1 and the second feature point p2 meet the limit constraint rule, that is, p2Fp1=0. Where p1, p2 are the pixel coordinate vectors in the corresponding key frame, p1=[x p1 y p1 ], F is the basic matrix, and the least squares method is generally used to estimate the basic matrix F.

[0100] S610: If satisfied, the reference matching point is determined as a pair of feature matching points.

[0101] Specifically, if the condition is satisfied, the reference matching point is determined as a pair of feature matching points of the first key frame video image and the second key frame video image.

[0102] S504: Determine the center coordinates of the seed patch using a triangulation method based on the feature matching points.

[0103] Specifically, after the feature matching points are obtained, the center coordinates c(p) of the seed patch are determined according to the coordinates of the feature matching points using triangulation.

[0104] S506, determining the normal vector of the seed patch according to the center coordinates of the seed patch and the center coordinates of the camera.

[0105] Among them, the center coordinate of the camera is the camera optical center O(Ii).

[0106] Specifically, according to the formula n(p)←c(p)O(I i ) / |c(p)O(I i )|, determine the normal vector n(p) of the seed patch.

[0107] S508, constructing a seed patch according to the center coordinates of the seed patch, the normal vector of the seed patch and the reference image.

[0108] Specifically, the seed patch is constructed with the center coordinate point of the seed patch as the center and the normal vector of the seed patch referring to the reference image taken by the camera.

[0109] S306, constructing an external digital model of the GIS device based on the seed patch.

[0110] Specifically, after a plurality of seed patches are determined, it is necessary to use a preset splicing rule to splice the seed patches to construct an external digital model of the GIS device.

[0111] Furthermore, if Figure 7 As shown in the figure, based on the seed patch, the external digital model of the GIS equipment is constructed, including:

[0112] S702: Determine adjacent seed patches according to the center coordinates of the seed patch and the normal vector of the seed patch.

[0113] Specifically, based on the characteristics that adjacent patches have similar normal vectors and positions, the spatial patches around the seed patch are gradually reconstructed. The conditions for judging whether two patches are adjacent can be as follows: |(c(p1)-c(p2))·n(p1)|+|(c(p1)-c(p2))·n(p2)|<ρ, where c(p1) is the center of the first seed patch, c(p2) is the center of the second seed patch, n(p1) is the normal vector of the first seed patch, n(p2) is the normal vector of the second seed patch, and ρ is the distance threshold. When the proximity relationship is satisfied, it is an adjacent seed patch. Among them, the degree of diffusion of the expansion can be determined by whether the depth of the pixel points in the key frame of the GIS device video is continuous.

[0114] S704, stitching adjacent seed patches together to obtain an external digital model of the GIS device.

[0115] Specifically, by splicing adjacent seed patches, an external digital model of the GIS device can be obtained.

[0116] In this embodiment, by determining the key frame video image from each video image, determining the seed patch of the external model based on the key frame video image, and constructing the external digital model of the GIS device based on the seed patch, the model can be constructed based on the external image of the GIS device taken at the application site, which is close to the GIS device actually used.

[0117] The above embodiment describes how to construct an external digital model of a GIS device. Now, an embodiment is used to describe how to construct an internal digital model of a GIS device. In one embodiment, Figure 8 As shown in the figure, based on the industrial CT images, the internal digital model of the GIS equipment is reversely constructed, including:

[0118] S802, preprocessing the industrial CT image to obtain segmented images of different areas of the GIS device.

[0119] The preprocessing may include image enhancement, image noise reduction, image segmentation, etc., which are not limited here.

[0120] Specifically, after acquiring the industrial CT image, the image can be preprocessed such as image noise reduction and enhancement, and the processed image can be input into a preset segmentation neural network model to achieve segmentation of different areas of each device of the GIS equipment in the industrial CT image and obtain segmented images of each device area.

[0121] Furthermore, if Fig. 9 As shown, the industrial CT image is preprocessed to obtain segmented images of different areas of the GIS equipment, including:

[0122] S902, performing grayscale nonlinear transformation on the industrial CT image to obtain an enhanced industrial CT image.

[0123] Specifically, the grayscale value of the original industrial CT image can be changed by grayscale nonlinear transformation to achieve the effect of image grayscale enhancement. Optionally, grayscale logarithmic transformation is used for image enhancement, and the formula is as follows:

[0124] Where f(x, y) represents the grayscale value of the original image; g(x, y) is the new grayscale value after grayscale exponential transformation; a is the vertical offset of the logarithmic curve, and b is the curvature of the logarithmic curve. a and b are used to reflect the nonlinearity of grayscale transformation. The specific values ​​need to be manually determined based on the quality of the CT image to obtain the optimal value.

[0125] S904: Use a filtering algorithm to reduce noise on the enhanced industrial CT image to obtain a reduced-noise industrial CT image.

[0126] Specifically, Gaussian filtering may be used, and the operation is performed through a 3*3 Gaussian template. In the formula, A is a Gaussian template, and the values ​​in the matrix are taken through Gaussian distribution. The CT image is scanned with the template as the receptive field, and a convolution operation is performed. The result after the operation is the denoising result of the CT image.

[0127] S906, segmenting the denoised image according to the image grayscale information of the denoised industrial CT image to obtain segmented images of different areas of the GIS device.

[0128] Specifically, the industrial CT image after the first two steps of preprocessing contains black background, that is, the gray value is near 0; the gray value of the part imaging part is relatively large, and it appears as a white area in the image. Based on the above factors, the image is segmented using the gradient change and similarity of the image gray information. After image segmentation, the image is segmented into segmented images of different device areas of the GIS equipment.

[0129] S804, using an 8-field single-pixel tracking method to determine the contour points of each segmented image, and forming a closed contour plane graph of each segmented image according to the contour points of each segmented image.

[0130] Specifically, on the basis of the industrial CT image being segmented into segmented images of different regions, image contour extraction is performed to obtain cross-sectional contour features. Optionally, the contour points of the industrial CT image of the GIS equipment can be determined by the 8-field single pixel tracking method. That is, as long as there is a point in the 8 fields around the pixel point that is the pixel value corresponding to the background area, the point is a contour point. The specific tracking steps may include: scanning each segmented image of the industrial CT graphics line by line, obtaining the first boundary point in the upper left corner of each segmented image as the starting tracking point; single-area contour tracking; drawing the contour boundary; filling the tracked area, tracking the closed contour, and obtaining a closed contour plane map of each segmented image.

[0131] S806, reconstructing the surface patch of the closed contour plane image by fitting a cubic spline surface, and obtaining the surface patch of each segmented image.

[0132] Specifically, two directions (u, v) can be assigned to each data point of the closed contour plane graph, and the data points can be parameterized using the method of cumulative chord length: In the formula, u i,j is the cumulative chord length in u direction, Q i,j is the u-direction data point sequence, m u , m v Represents the number of upward curves in u and v directions respectively, i and j correspond to the upward curves in u and v directions. The cumulative chord length v in v direction i,j The formula is the same as above. According to the equation of the cubic B-spline surface P(u,v): Reconstruct the surface patch of the closed contour plane image to obtain the surface patch of each segmented image; where d i,j N is the control vertex. i,3 and N j,3 are cubic spline basis functions defined in the u and v directions respectively.

[0133] S808, stitching the surface patches of each segmented image to construct an internal digital model of the GIS device.

[0134] Specifically, for each surface patch of the segmented image, the de-faced patches are spliced ​​according to the unsegmented industrial CT image to obtain the internal digital model of the GIS equipment.

[0135] In this implementation, the industrial CT images are preprocessed to obtain segmented images of different areas of the GIS equipment, and the contour points of each segmented image are determined by the 8-field single pixel tracking method. The closed contour plane graph of each segmented image is formed according to the contour points of each segmented image, and the closed contour plane graph is reconstructed by fitting a cubic spline surface to obtain the surface patch of each segmented image. The internal digital model of the GIS equipment can be constructed based on the industrial CT images taken at the application site, which is more suitable for the actual GIS equipment and has a higher operational guidance significance.

[0136] The above embodiment explains how to construct the external digital model and the internal digital model of the GIS device. After the internal and external digital models are constructed, in order to make the constructed models more accurate, the drawing design parameters of the GIS device can be integrated with the internal and external digital models to make the final constructed GIS device more accurate. Now, an embodiment is used to further explain how to integrate the drawing design parameters, the internal digital model, and the external digital model to construct the GIS device model. In one embodiment, the GIS device model is constructed according to the drawing design parameters, the external digital model of the GIS device, and the internal digital model of the GIS device, including:

[0137] The design parameters of the drawing are respectively substituted into the external digital model of the GIS equipment and the internal digital model of the GIS equipment to obtain the digital twin model of the GIS equipment as the GIS equipment model.

[0138] Specifically, the design parameters of the drawings are respectively substituted into the external digital model of the GIS device and the internal digital model of the GIS device to obtain the digital twin model of the GIS device as the GIS device model. For example, the length, width, and height design parameters of the GIS device are substituted into the external digital model of the GIS device and the internal digital model of the GIS device to obtain the digital twin model of the GIS device that combines numbers and shapes.

[0139] In this embodiment, by substituting the drawing design parameters into the external digital model of the GIS device and the internal digital model of the GIS device, a digital twin model of the GIS device is obtained as the GIS device model. By combining the idealized model parameters (drawing design parameters) with the panoramic information of the device (video images and industrial CT images), the edge gaps and internal structures of the device model can be made more in line with the actual situation on site, making it more realistic and laying a strong foundation for the subsequent simulation calculation of the GIS digital twin model.

[0140] To facilitate understanding by those skilled in the art, a modeling method for a GIS device is further described with an embodiment. In one embodiment, the modeling method for a GIS device includes:

[0141] S101, obtaining multiple video frames, industrial CT images and drawing design parameters of GIS equipment.

[0142] S102, performing grayscale value processing on each video image, and calculating the grayscale change rate of each video image using an average gradient method.

[0143] S103, comparing the grayscale change rate with a change rate threshold, if the grayscale change rate is greater than the change rate threshold, determining that the video image is a key frame video image.

[0144] S104, obtaining an average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image.

[0145] S105: If the average energy change is greater than a preset energy change threshold, the central pixel point at the location of the local detection window is extracted as a feature point.

[0146] S106, obtaining a pixel distance between a first feature point on a first key frame video image and a second feature point on a second key frame video image; the first key frame video image and the second key frame video image are any two consecutive frames of video images.

[0147] S107, taking the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold as reference matching points, and judging whether the reference matching points satisfy the limit constraint rule.

[0148] S108: If satisfied, the reference matching point is determined as a pair of feature matching points.

[0149] S109, determining the center coordinates of the seed patch using a triangulation method based on the feature matching points.

[0150] S110, determining a normal vector of the seed patch according to the center coordinates of the seed patch and the center coordinates of the camera.

[0151] S111, constructing a seed patch according to the center coordinates of the seed patch, the normal vector of the seed patch and the reference image.

[0152] S112, determining adjacent seed patches according to the center coordinates of the seed patch and the normal vector of the seed patch.

[0153] S113, stitching adjacent seed patches together to obtain an external digital model of the GIS device.

[0154] S114, performing grayscale nonlinear transformation on the industrial CT image to obtain an enhanced industrial CT image.

[0155] S115, using a filtering algorithm to reduce noise on the enhanced industrial CT image to obtain a reduced-noise industrial CT image.

[0156] S116, segmenting the denoised image according to the image grayscale information of the denoised industrial CT image to obtain segmented images of different areas of the GIS device.

[0157] S117, using an 8-field single-pixel tracking method to determine the contour points of each segmented image, and forming a closed contour plane graph of each segmented image according to the contour points of each segmented image.

[0158] S118, reconstructing the surface patch of the closed contour plane image by fitting a cubic spline surface, and obtaining the surface patch of each segmented image.

[0159] S119, stitching the surface patches of each segmented image to construct an internal digital model of the GIS device.

[0160] S120, substitute the drawing design parameters into the external digital model of the GIS device and the internal digital model of the GIS device respectively, and obtain the digital twin model of the GIS device as the GIS device model.

[0161] In the above-mentioned modeling method of GIS equipment, by acquiring multi-frame video images, industrial CT images and drawing design parameters of GIS equipment, the external digital model of GIS equipment is reversely constructed according to the video images of each GIS equipment, the internal digital model of GIS equipment is reversely constructed according to the industrial CT images, and the GIS equipment model is constructed according to the drawing design parameters, the external digital model of GIS equipment and the internal digital model of GIS equipment. Based on the video and industrial CT images of GIS equipment collected on site, the panoramic information of the equipment can be reversed, and the edge gaps and internal structures of the equipment model can be made more in line with the actual situation on site by combining the idealized model parameters (drawing design parameters) with the panoramic information of the equipment (video images and industrial CT images), so that it can move from virtual to real, laying a strong foundation for the subsequent simulation calculation of the GIS digital twin model.

[0162] It should be understood that although Figure 2-9 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-9At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0163] The above embodiment describes the modeling method of GIS equipment. Now, an embodiment of the modeling device of GIS equipment is described. In one embodiment, Fig.10 As shown, a modeling device for GIS equipment is provided, comprising:

[0164] An acquisition module 11 is used to acquire multi-frame video images, industrial CT images and drawing design parameters of GIS equipment;

[0165] The external digital model building module 12 is used to reversely build the external digital model of the GIS device based on the video images of each GIS device;

[0166] The internal digital model building module 13 is used to reversely build the internal digital model of the GIS equipment according to the industrial CT image;

[0167] The GIS device model determination module 14 is used to construct a GIS device model according to the drawing design parameters, the external digital model of the GIS device and the internal digital model of the GIS device.

[0168] In the modeling device of the above-mentioned GIS equipment, the acquisition module acquires multiple frames of video images, industrial CT images and drawing design parameters of the GIS equipment, the external digital model construction module reversely constructs the external digital model of the GIS equipment based on the video images of each GIS equipment, the internal digital model construction module reversely constructs the internal digital model of the GIS equipment based on the industrial CT images, and the GIS equipment model determination module constructs the GIS equipment model based on the drawing design parameters, the external digital model of the GIS equipment and the internal digital model of the GIS equipment. It is possible to reverse the panoramic information of the equipment based on the video and industrial CT images of the GIS equipment collected on site, and combine the idealized model parameters (drawing design parameters) with the panoramic information of the equipment (video images and industrial CT images) to make the edge gaps and internal structures of the equipment model more in line with the actual situation on site, so that it can move from virtual to real, and lay a strong foundation for the simulation calculation of the GIS digital twin model in the future.

[0169] In one embodiment, Fig.11 As shown, the external digital model building module 12 includes:

[0170] A first determining unit 121 is used to determine a key frame video image from each video image;

[0171] A second determining unit 122 is used to determine a seed patch of an external model according to the key frame video image;

[0172] The first construction unit 123 is used to construct an external digital model of the GIS device according to the seed patch.

[0173] In one embodiment, the first determination unit is specifically used to process the grayscale values ​​of each video image and calculate the grayscale change rate of each video image using the average gradient method; the grayscale change rate is compared with the change rate threshold, and if the grayscale change rate is greater than the change rate threshold, the video image is determined to be a key frame video image.

[0174] In one embodiment, the second determination unit is specifically used to extract feature points of a key frame video image and determine feature matching points of two consecutive key frame video images; based on the feature matching points, the center coordinates of the seed patch are determined by triangulation; based on the center coordinates of the seed patch and the center coordinates of the camera, the normal vector of the seed patch is determined; based on the center coordinates of the seed patch, the normal vector of the seed patch and the reference image, the seed patch is constructed.

[0175] In one embodiment, the second determination unit is specifically used to obtain the average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image; if the average energy change is greater than a preset energy change threshold, the central pixel point of the position where the local detection window is located is extracted as a feature point; the pixel distance between the first feature point on the first key frame video image and the second feature point on the second key frame video image is obtained; the first key frame video image and the second key frame video image are any two consecutive frames of video images; the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold are used as reference matching points, and it is determined whether the reference matching points meet the limit constraint rules; if so, the reference matching points are determined as a pair of feature matching points.

[0176] In one embodiment, the first construction determination unit is specifically used to determine adjacent seed patches according to the center coordinates of the seed patches and the normal vectors of the seed patches; and to splice the adjacent seed patches to obtain an external digital model of the GIS device.

[0177] In one embodiment, see Fig.11 As shown, the internal digital model building module 13 includes:

[0178] An image processing unit 131 is used to pre-process the industrial CT image to obtain segmented images of different areas of the GIS device;

[0179] A closed contour plane map determining unit 132 is used to determine the contour points of each segmented image by using an 8-field single pixel tracking method, and form a closed contour plane map of each segmented image according to the contour points of each segmented image;

[0180] A surface patch reconstruction unit 133 is used to reconstruct the surface patch of the closed contour plane image by fitting a cubic spline surface to obtain the surface patch of each segmented image;

[0181] The second construction unit 134 is used to splice the surface patches of each segmented image to construct an internal digital model of the GIS device.

[0182] In one embodiment, the image processing unit is specifically used to perform grayscale nonlinear transformation on the industrial CT image to obtain an enhanced industrial CT image; use a filtering algorithm to reduce noise on the enhanced industrial CT image to obtain a noise-reduced industrial CT image; and segment the noise-reduced image according to the image grayscale information of the noise-reduced industrial CT image to obtain segmented images of different areas of the GIS device.

[0183] In one embodiment, the GIS device model determination module is specifically used to substitute the drawing design parameters into the external digital model of the GIS device and the internal digital model of the GIS device, respectively, to obtain a digital twin model of the GIS device as the GIS device model.

[0184] The specific definition of the modeling device of the GIS device can be found in the definition of the modeling method of the GIS device above, which will not be repeated here. Each module in the modeling device of the GIS device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0185] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.12As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a modeling method of a GIS device is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0186] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0187] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0188] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0189] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0190] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0191] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A modeling method for GIS equipment, characterized in that: The method comprises: Obtain multi-frame video images, industrial CT images and drawing design parameters of GIS equipment; Determining a key frame video image from each of the video images; Obtaining an average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image; If the average energy change is greater than a preset energy change threshold, extracting the central pixel point at the location of the local detection window as a feature point; Obtaining a pixel distance between a first feature point on a first key frame video image and a second feature point on a second key frame video image; the first key frame video image and the second key frame video image are any two consecutive frames of video images; Taking the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold as reference matching points, and judging whether the reference matching points satisfy the limit constraint rule; If satisfied, the reference matching point is determined as a pair of feature matching points; According to the feature matching points, the center coordinates of the seed patch are determined by using a triangulation method; Determine the normal vector of the seed patch according to the center coordinates of the seed patch and the center coordinates of the camera; Constructing the seed patch according to the center coordinates of the seed patch, the normal vector of the seed patch and a reference image; constructing an external digital model of the GIS device according to the seed patch; Reversely construct an internal digital model of the GIS equipment based on the industrial CT image; A GIS device model is constructed according to the drawing design parameters, the external digital model of the GIS device and the internal digital model of the GIS device.

2. The method according to claim 1, characterized in that Determining a key frame video image from each of the video images includes: Performing grayscale value processing on each of the video images, and calculating the grayscale change rate of each of the video images using an average gradient method; The grayscale change rate is compared with a change rate threshold, and if the grayscale change rate is greater than the change rate threshold, the video image is determined to be a key frame video image.

3. The method according to claim 1, characterized in that The step of constructing an external digital model of the GIS device according to the seed patch includes: Determine adjacent seed patches according to the center coordinates of the seed patch and the normal vector of the seed patch; The adjacent seed patches are spliced ​​together to obtain an external digital model of the GIS device.

4. The method according to any one of claims 1 to 3, characterized in that: The reverse construction of the internal digital model of the GIS equipment according to the industrial CT image includes: Preprocessing the industrial CT image to obtain segmented images of different areas of the GIS device; Determine the contour points of each segmented image using an 8-field single pixel tracking method, and form a closed contour plane graph of each segmented image according to the contour points of each segmented image; Reconstructing the closed contour plane image by fitting a cubic spline surface to obtain a surface patch of each segmented image; The curved surface patches of each segmented image are spliced ​​to construct an internal digital model of the GIS device.

5. The method according to claim 4, characterized in that The preprocessing of the industrial CT image to obtain segmented images of different areas of the GIS device includes: Performing grayscale nonlinear transformation on the industrial CT image to obtain an enhanced industrial CT image; Using a filtering algorithm to reduce noise on the enhanced industrial CT image to obtain a reduced-noise industrial CT image; According to the image grayscale information of the denoised industrial CT image, the denoised image is segmented to obtain segmented images of different areas of the GIS device.

6. The method according to claim 4, characterized in that The step of stitching the curved surface patches of the segmented images to construct an internal digital model of the GIS device includes: According to the unsegmented industrial CT image, each of the curved surface slices is spliced ​​to obtain an internal digital model of the GIS equipment.

7. The method according to claim 1, characterized in that The step of constructing a GIS device model according to the drawing design parameters, the external digital model of the GIS device and the internal digital model of the GIS device includes: The drawing design parameters are respectively substituted into the external digital model of the GIS device and the internal digital model of the GIS device to obtain the digital twin model of the GIS device as the GIS device model.

8. A modeling device for GIS equipment, characterized in that: The device comprises: Acquisition module, used to acquire multi-frame video images, industrial CT images and drawing design parameters of GIS equipment; An external digital model construction module, used to reversely construct an external digital model of the GIS device based on the video images of each of the GIS devices; An internal digital model building module, used to reversely build an internal digital model of the GIS equipment based on the industrial CT image; A GIS device model determination module, used to construct a GIS device model according to the drawing design parameters, the external digital model of the GIS device and the internal digital model of the GIS device; Wherein, the external digital model construction module includes: A first determining unit, used to determine a key frame video image from each video image; A second determination unit is used to obtain the average energy change of the local detection window at each position when the local detection window moves along different directions on the key frame video image; if the average energy change is greater than a preset energy change threshold, the central pixel point of the position where the local detection window is located is extracted as a feature point; the pixel distance between the first feature point on the first key frame video image and the second feature point on the second key frame video image is obtained; the first key frame video image and the second key frame video image are any two consecutive frames of video images; the first feature point and the second feature point whose pixel distance is less than or equal to the preset distance threshold are used as reference matching points, and it is determined whether the reference matching points meet the limit constraint rule; if so, the reference matching points are determined as a pair of feature matching points; according to the feature matching points, the central coordinates of the seed patch are determined by triangulation; according to the central coordinates of the seed patch and the central coordinates of the camera, the normal vector of the seed patch is determined; according to the central coordinates of the seed patch, the normal vector of the seed patch and the reference image, the seed patch is constructed; The first construction unit is used to construct an external digital model of the GIS device according to the seed surface.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images