Secondary circuit model conversion method based on CAD drawing recognition technology and related device

Abstract

The embodiment of the invention relates to the field of model conversion, and provides a secondary circuit model conversion method based on a CAD drawing recognition technology and a related device, and the method comprises the steps: scanning a to-be-converted secondary circuit model, and obtaining a first data value of the to-be-converted secondary circuit model; according to the first data value, obtaining model features of the secondary loop model to be converted by adopting a geometric feature matching and recognition method; performing curved surface fitting reconstruction according to the model features to obtain an initial three-dimensional CAD model; the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted, the extracted model features of the secondary circuit model to be converted can be adopted to carry out surface fitting reconstruction to obtain the initial three-dimensional CAD model, the initial three-dimensional CAD model is corrected to obtain the target three-dimensional CAD model, and the accuracy during model reconstruction is improved.

Description

Technical Field

[0001] The present application relates to the field of model conversion technology, and in particular to a secondary circuit model conversion method and related devices based on CAD drawing recognition technology. Background Art

[0002] Secondary circuit refers to all low-voltage circuits such as measurement circuit, relay protection circuit, switch control and signal circuit, operating power circuit, circuit breaker and disconnector electrical interlocking circuit, which are interconnected by secondary equipment to form an electrical circuit for monitoring, controlling, adjusting and protecting primary equipment. It is a circuit in the electrical system composed of the secondary winding of the mutual inductor, measuring and monitoring instruments, relays, automatic devices, etc. connected by control cables. The secondary circuit model shows the commonly used models of secondary circuits. If the naming, numbering or annotation text information conventions between the CAD (Computer Aided Design) model database and the user are different, the text-based CAD model retrieval may return inaccurate candidate models. In order to overcome the shortcomings of text-based CAD model retrieval, researchers have proposed content-based CAD model retrieval, which constructs descriptors through the content of the CAD model itself to complete the CAD model retrieval.

[0003] However, the existing secondary circuit model conversion method based on CAD image recognition technology does not perform surface reconstruction on the secondary circuit model to be converted, which will reduce the accuracy of model reconstruction and conversion. Summary of the invention

[0004] The embodiment of the present application provides a secondary circuit model conversion method and related devices based on CAD image recognition technology, which can use the extracted model features of the secondary circuit model to be converted to perform surface fitting reconstruction to obtain an initial three-dimensional CAD model and perform correction to obtain a target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0005] A first aspect of an embodiment of the present application provides a secondary circuit model conversion method based on CAD drawing recognition technology, the method comprising:

[0006] Scanning the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted;

[0007] According to the first data value, a geometric feature matching and recognition method is used to obtain the model features of the secondary circuit model to be converted;

[0008] Perform surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model;

[0009] The initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0010] In this example, the secondary circuit model to be converted is scanned to obtain a first data value of the secondary circuit model to be converted, and according to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted, and surface fitting and reconstruction are performed according to the model features to obtain an initial three-dimensional CAD model, and the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted. Therefore, the extracted model features of the secondary circuit model to be converted can be used to perform surface fitting and reconstruction to obtain the initial three-dimensional CAD model and correct it to obtain the target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0011] In a possible implementation, performing surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model includes:

[0012] Perform surface fitting according to the model characteristics to obtain a fitting surface;

[0013] Fitting and reconstruction are performed according to the fitting surface to obtain the initial three-dimensional CAD model.

[0014] In a possible implementation, performing surface fitting according to the model characteristics to obtain a fitting surface includes:

[0015] Construct a k×l spline surface;

[0016] Obtaining data points in a topological rectangular array by interpolation;

[0017] Determine the control vertices of the spline surface according to the data points to obtain a control vertex set;

[0018] Surface fitting is performed according to the control vertex set to obtain the fitting surface.

[0019] In a possible implementation, the method further includes:

[0020] The key surfaces in the initial three-dimensional CAD model are obtained by using a particle swarm optimization algorithm.

[0021] In a possible implementation, the method further includes data acquisition, and the data acquisition includes scattered data acquisition, scan line data acquisition, grid data acquisition, and multi-deformation data acquisition.

[0022] A second aspect of the embodiment of the present application provides a secondary circuit model conversion device based on CAD drawing recognition technology, the device comprising:

[0023] A scanning module, used for scanning the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted;

[0024] An acquisition module, configured to acquire the model features of the secondary circuit model to be converted by using a geometric feature matching and recognition method according to the first data value;

[0025] A reconstruction module, used for performing fitting reconstruction according to the model features to obtain an initial three-dimensional CAD model;

[0026] The correction module is used to correct the initial three-dimensional CAD model to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0027] In this example, the secondary circuit model to be converted is scanned to obtain a first data value of the secondary circuit model to be converted, and according to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted, and surface fitting and reconstruction are performed according to the model features to obtain an initial three-dimensional CAD model, and the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted. Therefore, the extracted model features of the secondary circuit model to be converted can be used to perform surface fitting and reconstruction to obtain the initial three-dimensional CAD model and correct it to obtain the target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0028] In a possible implementation, the reconstruction module is specifically used to:

[0029] Perform surface fitting according to the model characteristics to obtain a fitting surface;

[0030] Fitting and reconstruction are performed according to the fitting surface to obtain the initial three-dimensional CAD model.

[0031] In a possible implementation, in performing surface fitting according to model features to obtain a fitting surface, the reconstruction module is specifically used to:

[0032] Construct a k×l spline surface;

[0033] Obtaining data points in a topological rectangular array by interpolation;

[0034] Determine the control vertices of the spline surface according to the data points to obtain a control vertex set;

[0035] Surface fitting is performed according to the control vertex set to obtain the fitting surface.

[0036] In a possible implementation, the device is further used for:

[0037] The key surfaces in the initial three-dimensional CAD model are obtained by using a particle swarm optimization algorithm.

[0038] In a possible implementation, the device is also used for data acquisition, and the data acquisition includes scattered data acquisition, scan line data acquisition, grid data acquisition and multi-deformation data acquisition.

[0039] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0040] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0041] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic flow chart of a secondary circuit model conversion method based on CAD image recognition technology is provided for an embodiment of the present application;

[0044] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0045] Figure 3 A structural schematic diagram of a secondary circuit model conversion device based on CAD drawing recognition technology is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0048] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0049] See also Figure 1 , Figure 1 The present application provides a flow chart of a secondary circuit model conversion method based on CAD image recognition technology. Figure 1 As shown, the secondary circuit model conversion method based on CAD drawing recognition technology includes:

[0050] 101. Scan a secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted.

[0051] Among them, the secondary circuit model to be converted can be a common model for displaying secondary circuits. The secondary circuit refers to all low-voltage circuits such as measurement circuits, relay protection circuits, switch control and signal circuits, operating power circuits, circuit breakers and disconnectors. The electrical circuits are interconnected by secondary equipment to form electrical circuits for monitoring, controlling, regulating and protecting primary equipment. In the electrical system, the secondary windings of the transformer, measuring and monitoring instruments, relays, automatic devices, etc. are connected through control cables.

[0052] The first data value of the secondary circuit model to be converted can be understood as data obtained by clamping the secondary circuit model to be converted multiple times.

[0053] After obtaining the first data value, the first data value needs to be preprocessed. The preprocessing includes: multi-view stitching, noise processing and data simplification. Multi-view stitching is also called coordinate unification. Its task is to fuse the data obtained by multiple clamping into a unified coordinate system. Noise processing is achieved by smoothing the measured point cloud data. The filtering methods include Gaussian, average and median filtering. Data simplification needs to reduce the number of measurement points according to certain requirements. Different types of point clouds use different simplification methods. Specifically, conventional multi-view stitching, noise processing and data simplification can be used to obtain the processed first data value for subsequent model reconstruction. When acquiring data, data acquisition methods include data contact acquisition, etc.

[0054] 102. According to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted.

[0055] A general geometric feature matching and recognition method can be used to obtain the model features of the secondary circuit model to be converted from the first data value.

[0056] 103. Perform surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model.

[0057] A specific method of performing surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model includes:

[0058] A1. Perform surface fitting according to the model characteristics to obtain a fitting surface;

[0059] A2. Perform fitting and reconstruction according to the fitting surface to obtain the initial three-dimensional CAD model.

[0060] The initial three-dimensional CAD model can be obtained by performing fitting reconstruction based on the fitting surface in a general manner.

[0061] Specifically, performing surface fitting according to the model characteristics to obtain the fitting surface includes:

[0062] B1. Construct a k×1 spline surface;

[0063] B2, obtaining data points in a topological rectangular array by interpolation;

[0064] B3, determining the control vertices of the spline surface according to the data points to obtain a control vertex set;

[0065] B4. Performing surface fitting according to the control vertex set to obtain the fitting surface.

[0066] Specifically, the interpolation of data points on a surface is also called surface inversion. According to the model characteristics, a k×1 spline surface is constructed, and the data points Pii (i=0, 1, ...r) in a topological rectangular array are interpolated. The spline surface equation is P(u, v)=d i , the control vertex is replaced by the control curve, c i (v) = d i , fixing a parameter value v, gives m+1 points c on these control curves i (v) is used as a control point to define the isoparametric lines of the surface. When the parameter sweeps across its entire definition domain, an infinite number of isoparametric lines describe the entire surface. Obviously, among the infinite number of isoparametric lines of the surface, there are n+1 cross-sectional curves given by interpolation. The control vertices of these cross-sectional curves are obtained by inverse calculation of the spline interpolation curve. Right now The surface with these section curves as isoparametric lines requires a set of control curves to define the control vertices c of the section curves. l (v l+i ), select the parameter v l+i To control the nodes of the curve, the spline difference surface (m+1)×(n+1) control vertices are obtained by calculation, and the fitting surface is constructed.

[0067] 104. Correct the initial three-dimensional CAD model to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0068] Among them, a general correction processing method can be used to correct the initial three-dimensional CAD model to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0069] Specifically, the inverse transformation of the transformation matrix is ​​called on the initial 3D CAD model to obtain the CAD geometric model of the replica, the structural geometry transformation is repeated, the replica CAD geometric model is saved in the CAD geometric model list of the prototype area, and a mapping between the replica CAD geometric model and the container area name, and a mapping between the container area name and the prototype area name are established, and the replica CAD collection model is determined as the target 3D CAD model.

[0070] In this example, the secondary circuit model to be converted is scanned to obtain a first data value of the secondary circuit model to be converted, and according to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted, and surface fitting and reconstruction are performed according to the model features to obtain an initial three-dimensional CAD model, and the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted. Therefore, the extracted model features of the secondary circuit model to be converted can be used to perform surface fitting and reconstruction to obtain the initial three-dimensional CAD model and correct it to obtain the target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0071] In a possible implementation, the method further includes:

[0072] The key surfaces in the initial 3D CAD model are obtained by using a particle swarm optimization algorithm. Specifically, it can be:

[0073] S1. Initialize the position and velocity of the particle swarm and disperse the particles in the search space. Random initialization is generally used to distribute the particles roughly evenly in the entire search space.

[0074] S2. Calculate the fitness value of each particle according to the fitness function and compare them with each other to determine the individual historical optimal position of the particle and the group historical optimal position. If the fitness function value of a particle is better than its individual historical optimal value, its individual historical optimal value will be updated to this value, and the individual historical optimal position will be updated at the same time. If the fitness function value of any particle is better than the previous group historical optimal value, the group historical optimal value will be updated to this value, and the group historical optimal position will be updated at the same time.

[0075] S3. The speed and position of each particle will be updated, and the particle speed V and position x are updated as follows:

[0076] v i (t+1)=wv i (t)+c1r1[p i (t)-x i (t)]+c2r2[g(t)-x i (t)];

[0077] x i (t+1)=x i (t)+v i (t+1);

[0078] Among them, v i (t+1) is the updated particle velocity, v i (t) is the particle velocity before updating, p i (t) is the particle point, g(t)-xi (t) is the correlation function, x i (t) is the position before updating, x i (t+1) is the updated position, c1r1 is the first weight, and c2r2 is the second weight.

[0079] S4: Continuously iterate and update the speed and position of the particles until the termination condition is met, and output the final historical optimal position of the group. The termination condition of the particle swarm optimization algorithm is related to the convergence of the algorithm. Generally, the particle swarm optimization algorithm jumps out of the loop by setting a threshold or reaching a fixed number of iterations.

[0080] In a possible implementation, the method further includes data acquisition, and the data acquisition includes scattered data acquisition, scan line data acquisition, grid data acquisition, and multi-deformation data acquisition.

[0081] In a specific embodiment, the present application also provides another secondary circuit model conversion method based on CAD image recognition technology, which is as follows:

[0082] Step 1: digitizing the secondary circuit model; scanning the secondary circuit model to obtain data values ​​of the secondary circuit model;

[0083] Step 2: Obtain model features: Use geometric feature matching and recognition methods to obtain the design and processing features of the secondary circuit model;

[0084] Step 3: Reconstruct the model; fit and reconstruct the acquired model features to achieve secondary circuit model reconstruction;

[0085] Step 4: Check and correct the reconstructed model; redesign and create the reconstructed 3D CAD model, and finally generate IGES (Initialized Graphics Exchange Specification) and STL (Standard Template Library) data, check and correct the reconstructed model, and complete the transformation of the secondary circuit model.

[0086] Among them, the secondary loop model transformation includes data acquisition, data preprocessing and model reconstruction. Data acquisition is divided into data contact acquisition and data contact acquisition. Using different measurement methods and measurement software, the measurement data are organized in different ways.

[0087] Data preprocessing includes multi-view stitching, noise processing and data simplification. Multi-view stitching is also called coordinate unification. Its task is to fuse the data obtained from multiple clamping into a unified coordinate system. Noise processing is achieved by smoothing the measured point cloud data using Gaussian, average and median filtering. Data simplification requires reducing the number of measurement points according to certain requirements. Different types of point clouds use different simplification methods.

[0088] Surface fitting is required in the reconstruction model. The interpolation of the surface to the data points is also called surface inversion. A k×1 spline surface is constructed to interpolate the given data points Pii (i=0, 1, …r; i=0, 1, …, s) in a topological rectangular array. The spline surface equation is P(u, v)=d i , the control vertex is replaced by the control curve, c i (v) = d i , fixing a parameter value v, gives m+1 points c on these control curves i (v) is used as a control point to define the isoparametric lines of the surface. When the parameter sweeps across its entire definition domain, an infinite number of isoparametric lines describe the entire surface. Obviously, among the infinite number of isoparametric lines of the surface, there are n+1 cross-sectional curves given by interpolation. The control vertices of these cross-sectional curves are obtained by inverse calculation of the spline interpolation curve. Right now The surface with these section curves as isoparametric lines requires a set of control curves to define the control vertices c of the section curves. l (v l+i ), select the parameter v l+i To control the nodes of the curve, the spline difference surface (m+1)×(n+1) control vertices are obtained by calculation, and the fitting surface is constructed.

[0089] Furthermore, the reconstruction of the model requires data preprocessing, which mainly includes noise removal, which can be done by selecting the distance between points to remove noise points, simplification of redundant data, which can be selected by setting the reduction percentage and the size of the target point cloud, local and overall smoothing, boundary smoothing, which can be done by setting the overall smoothness through the software's built-in overall smoothness slider, and local smoothing with the selection tool, which can also set the smoothness of the contour boundary, and hole filling, which will automatically detect and fill all holes.

[0090] In the process of obtaining model features, the geometric details of the CAD model are used to represent the overall shape and local features of the CAD model using a small number of key surfaces. The key surfaces can be determined by D2P descriptors. When the D2P descriptors of a group of faces are maximally similar to the D2P descriptors of the CAD model, all faces in the group are key surfaces. The particle swarm optimization algorithm is used to determine the key surfaces in the CAD model.

[0091] The specific steps of the particle swarm optimization algorithm are as follows:

[0092] S1. Initialize the position and velocity of the particle swarm and disperse the particles in the search space. Random initialization is generally used to distribute the particles roughly evenly in the entire search space.

[0093] S2. Calculate the fitness value of each particle according to the fitness function and compare them with each other to determine the individual historical optimal position of the particle and the group historical optimal position. If the fitness function value of a particle is better than its individual historical optimal value, its individual historical optimal value will be updated to this value, and the individual historical optimal position will be updated at the same time. If the fitness function value of any particle is better than the previous group historical optimal value, the group historical optimal value will be updated to this value, and the group historical optimal position will be updated at the same time.

[0094] S3. The speed and position of each particle will be updated, and the particle speed V and position x are updated to v i (t+1)=wv i (t)+c1r1[p i (t)-x i (t)]+c2r2[g(t)-x i (t)],x i (t+1)=x i (t)+v i (t+1);

[0095] S4, continuously iterate and update the speed and position of the particles until the termination condition is met, and output the final historical optimal position of the group. The termination condition of the particle swarm optimization algorithm is related to the convergence of the algorithm. Generally, the particle swarm optimization algorithm jumps out of the loop by setting a threshold or reaching a fixed number of iterations.

[0096] Among them, i represents the particle, t represents the number of iterations, p represents the individual historical optimal position of the particle, g represents the historical optimal position of the entire particle group, and the update of the particle speed is controlled by three components, namely the inertia component wv i (t), individual component c1r1[p i (t)-x i (t)] and the group component c2r2[g(t)-x i (t)], in the inertia component, w is the inertia weight, which is used to maintain a part of the previous speed, and is generally taken as 0.5. In the individual learning component and the group learning component, c1 and c2 are the individual learning factor and the group learning factor respectively. Generally, c1=c2=1 is set, and r1 and r2 are random numbers in the interval [0, 1].

[0097] In this embodiment, by describing the more essential attributes of the CAD model, namely the topological structure, the CAD model that meets the user's expectations can be accurately retrieved. When the topological structure descriptor contains too few geometric details, the retrieval accuracy of the candidate model is difficult to guarantee. When the topological structure descriptor contains rich geometric details, the retrieval accuracy of the candidate model is very sensitive to the differences in geometric details between CAD models, and the retrieval efficiency is often low.

[0098] Data acquisition is divided into scattered data, scan line data, gridded data and polygonal data. The data points of scattered data have no obvious geometric distribution characteristics and are in a disordered state. The data points of scan line data are composed of a group of scan lines, and the points on the scan lines are arranged in order. All points in the point cloud of gridded data correspond to vertices of a uniform grid in the parameter domain. The data points of polygonal data are distributed in a series of parallel planes, and several adjacent points with the smallest distance in the same plane are sequentially connected by small line segments to form a set of nested planar polygons.

[0099] The specific operation of model conversion is to call the inverse transformation of the transformation matrix on the CAD geometric model of the prototype area to obtain the CAD geometric model of the replica, repeat the structural geometry transformation to complete, save the replica CAD geometric model in the CAD geometric model list of the area, and establish a mapping between the replica CAD geometric model and the container area name, and a mapping between the container area name and the prototype area name.

[0100] Model retrieval is required to obtain model features, including offline database establishment and online similarity comparison. When establishing the database offline, the descriptors of all CAD models in the CAD model database are extracted and saved to the CAD model feature library, and an index structure is established at the same time. When comparing similarity online, the descriptors of the input query model are first extracted, and then the similarity between the query model descriptor and the descriptor in the CAD model feature library is calculated. Finally, they are sorted according to the similarity and the retrieved candidate models are returned.

[0101] For the above embodiments, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, such as Figure 2 As shown, it includes a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0102] Scanning the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted;

[0103] According to the first data value, a geometric feature matching and recognition method is used to obtain the model features of the secondary circuit model to be converted;

[0104] Perform surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model;

[0105] The initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0106] In this example, the secondary circuit model to be converted is scanned to obtain a first data value of the secondary circuit model to be converted, and according to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted, and surface fitting and reconstruction are performed according to the model features to obtain an initial three-dimensional CAD model, and the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted. Therefore, the extracted model features of the secondary circuit model to be converted can be used to perform surface fitting and reconstruction to obtain the initial three-dimensional CAD model and correct it to obtain the target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0107] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0109] In line with the above, see Figure 3 , Figure 3 The present application provides a schematic diagram of a secondary circuit model conversion device based on CAD image recognition technology. Figure 3 As shown, the device comprises:

[0110] A scanning module 301 is used to scan the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted;

[0111] An acquisition module 302 is used to acquire the model features of the secondary circuit model to be converted by using a geometric feature matching and recognition method according to the first data value;

[0112] A reconstruction module 303 is used to perform fitting reconstruction according to the model features to obtain an initial three-dimensional CAD model;

[0113] The correction module 304 is used to correct the initial three-dimensional CAD model to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

[0114] In this example, the secondary circuit model to be converted is scanned to obtain a first data value of the secondary circuit model to be converted, and according to the first data value, a geometric feature matching and recognition method is used to obtain model features of the secondary circuit model to be converted, and surface fitting and reconstruction are performed according to the model features to obtain an initial three-dimensional CAD model, and the initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted. Therefore, the extracted model features of the secondary circuit model to be converted can be used to perform surface fitting and reconstruction to obtain the initial three-dimensional CAD model and correct it to obtain the target three-dimensional CAD model, thereby improving the accuracy of model reconstruction.

[0115] In a possible implementation, the reconstruction module 303 is specifically used to:

[0116] Perform surface fitting according to the model characteristics to obtain a fitting surface;

[0117] Fitting and reconstruction are performed according to the fitting surface to obtain the initial three-dimensional CAD model.

[0118] In a possible implementation, in performing surface fitting according to model features to obtain a fitting surface, the reconstruction module 303 is specifically used to:

[0119] Construct a k×l spline surface;

[0120] Obtaining data points in a topological rectangular array by interpolation;

[0121] Determine the control vertices of the spline surface according to the data points to obtain a control vertex set;

[0122] Surface fitting is performed according to the control vertex set to obtain the fitting surface.

[0123] In a possible implementation, the device is further used for:

[0124] The key surfaces in the initial three-dimensional CAD model are obtained by using a particle swarm optimization algorithm.

[0125] In a possible implementation, the device is also used for data acquisition, and the data acquisition includes scattered data acquisition, scan line data acquisition, grid data acquisition and multi-deformation data acquisition.

[0126] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any secondary circuit model conversion method based on CAD drawing recognition technology recorded in the above method embodiments.

[0127] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any secondary circuit model conversion method based on CAD drawing recognition technology recorded in the above method embodiments.

[0128] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0129] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0130] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0133] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0134] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0135] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A secondary circuit model conversion method based on CAD image recognition technology, characterized in that: The method comprises: Scanning the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted; According to the first data value, a geometric feature matching and recognition method is used to obtain the model features of the secondary circuit model to be converted; Perform surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model; The initial three-dimensional CAD model is corrected to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

2. The secondary circuit model conversion method based on CAD drawing recognition technology according to claim 1 is characterized in that: The step of performing surface fitting and reconstruction according to the model features to obtain an initial three-dimensional CAD model comprises: Perform surface fitting according to the model characteristics to obtain a fitting surface; Fitting and reconstruction are performed according to the fitting surface to obtain the initial three-dimensional CAD model.

3. The secondary circuit model conversion method based on CAD drawing recognition technology according to claim 2 is characterized in that: The step of performing surface fitting according to the model characteristics to obtain a fitting surface includes: Construct a k×l spline surface; Obtaining data points in a topological rectangular array by interpolation; Determine the control vertices of the spline surface according to the data points to obtain a control vertex set; Surface fitting is performed according to the control vertex set to obtain the fitting surface.

4. The secondary circuit model conversion method based on CAD image recognition technology according to any one of claims 1 to 3, characterized in that: The method further comprises: The key surfaces in the initial three-dimensional CAD model are obtained by using a particle swarm optimization algorithm.

5. The secondary circuit model conversion method based on CAD drawing recognition technology according to claim 4 is characterized in that: The method further comprises data acquisition, which comprises scattered data acquisition, scan line data acquisition, gridded data acquisition and multi-deformation data acquisition.

6. A secondary circuit model conversion device based on CAD image recognition technology, characterized in that: The device comprises: A scanning module, used for scanning the secondary circuit model to be converted to obtain a first data value of the secondary circuit model to be converted; An acquisition module, configured to acquire the model features of the secondary circuit model to be converted by using a geometric feature matching and recognition method according to the first data value; A reconstruction module, used for performing fitting reconstruction according to the model features to obtain an initial three-dimensional CAD model; The correction module is used to correct the initial three-dimensional CAD model to obtain a target three-dimensional CAD model corresponding to the secondary circuit model to be converted.

7. The secondary circuit model conversion device based on CAD drawing recognition technology according to claim 6 is characterized in that: The reconstruction module is specifically used for: Perform surface fitting according to the model characteristics to obtain a fitting surface; Fitting and reconstruction are performed according to the fitting surface to obtain the initial three-dimensional CAD model.

8. The secondary circuit model conversion device based on CAD drawing recognition technology according to claim 7 is characterized in that: In the aspect of performing surface fitting according to the model features to obtain the fitting surface, the reconstruction module is specifically used for: Construct a k×l spline surface; Obtaining data points in a topological rectangular array by interpolation; Determine the control vertices of the spline surface according to the data points to obtain a control vertex set; Surface fitting is performed according to the control vertex set to obtain the fitting surface.

9. A terminal, characterized in that: It includes a processor, an input device, an output device and a memory, which are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the secondary circuit model conversion method based on CAD drawing recognition technology as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the secondary circuit model conversion method based on CAD drawing recognition technology as described in any one of claims 1 to 5.

Images