Assembly model retrieval method based on shape and topological information fusion quantitative representation

Abstract

The application provides an assembly model retrieval method based on shape and topology information fusion quantitative representation, and belongs to the technical field of computer-aided design. The application comprises the following steps: obtaining an assembly model library; uniformly sampling all parts in each assembly model, and constructing a corresponding topological information matrix of the assembly model; obtaining all pairs of parts with topological relationship in the corresponding assembly model according to all topological information matrices, and sequentially calculating the fitting surface and the fitting surface centroid of each pair of parts; obtaining a shape topological distance value set of the corresponding assembly model by using all uniform sampling results and all fitting surface centroids, and obtaining a vector descriptor of the corresponding assembly model; and obtaining a retrieval result of a model to be retrieved by using the cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be retrieved. The application can improve the retrieval accuracy and efficiency of the assembly model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer-aided design, and particularly relates to an assembly model retrieval method based on shape and topology information fusion quantitative representation. BACKGROUND

[0002] In modern manufacturing industry, the assembly model becomes a core component of product design and production, which has important significance in improving research and development efficiency, shortening production cycle and reducing cost, etc. With the increasing number of historical assembly models accumulated by enterprises, it is an important means to improve the reuse rate of assembly models, reduce repeated design and resource waste to study accurate and efficient assembly model retrieval methods.

[0003] To retrieve the assembly model, the information of the assembly model needs to be quantitatively represented first, which is converted into a descriptor that can be compared in similarity, and then the retrieval is performed based on the descriptor.

[0004] At present, there are some methods for retrieving based on information representation of assembly models in the prior art, but there are the following problems:

[0005] For example, in a Chinese invention patent with the title of "Assembly retrieval method based on spatial connection skeleton descriptor", application number CN201810362028.8 and publication date of October 9, 2018, it is proposed to establish a spatial connection skeleton according to the center position of the parts in the assembly, the center position of the fitting surface and the connection relationship between the parts and the fitting surface, to count the spatial distance distribution of all random sampling points on the surface of two parts through the skeleton as the matrix descriptor of the input of the assembly retrieval based on the spatial connection skeleton; then the optimal subsequence matching algorithm is used to calculate the matching distance between the parts, and then the overall matching distance between different assemblies is calculated through the optimization model, and the overall matching distance between the target assembly and the assembly to be compared is arranged in ascending order as the result of similarity retrieval. In this retrieval method, the skeleton path distance between each pair of parts is fixed, which results in that the spatial connection relationship cannot be fully reflected in the matrix descriptor obtained based on the statistical distribution, so that the retrieval result may appear that the constituent parts are similar but the topological relationship is not matched.

[0006] For another example, another Chinese invention patent entitled "An assembly model similarity retrieval method based on spatial point set matching", application number CN202010362580.4, and publication date August 14, 2020, proposes that a feature attribute similarity matrix of the selected model is calculated, and then multiplied with each attribute weight matrix to obtain an attribute comprehensive similarity matrix; from this matrix and the set threshold, the effective elements of each column in the matrix are found, and all effective elements are arranged in combination to form a part set that can be matched; the spatial position similarity matrix is obtained by the center of gravity coordinates of the parts; the attribute comprehensive similarity matrix and the spatial position similarity matrix are calculated according to the formula to obtain a comprehensive similarity matrix; the similarity weight of the reference body and each part assembly is used to multiply each column element in the comprehensive similarity matrix in turn to obtain a model similarity matrix; the elements of the matching part set and the model similarity matrix at each corresponding position are summed to obtain a similarity value; the maximum value of the matching part set similarity is the similarity between the model and the reference body. Although this retrieval method comprehensively considers the attribute information of the parts of the assembly, it still regards each part as an individual, and does not consider the topological relationship between each part in the assembly model. Therefore, the retrieval result may obtain assembly models with similar constituent parts but different topological relationships.

[0007] Therefore, it is necessary to propose a scheme to improve one or more problems in the above-mentioned related technical solutions.

[0008] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0009] The present application provides an assembly model retrieval method based on shape and topological information fusion quantification representation, which comprises the following steps:

[0010] An assembly model library is obtained, which includes a plurality of assembly models, each of which contains a plurality of parts;

[0011] All the parts contained in each of the assembly models are uniformly sampled, and the topological information matrix of the corresponding assembly model is constructed using all the uniform sampling results;

[0012] According to all the topological information matrices, all pairs of parts with topological relationships in the corresponding assembly model are obtained, and the mating surface and mating surface centroid of each part pair are calculated in turn;

[0013] Obtaining a shape topology distance value set of the assembly model respectively according to all the uniform sampling results and all the contact surface centroids;

[0014] Obtaining a search result of the model to be searched by using cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be searched.

[0015] Further, the step of respectively sampling all the parts included in each assembly model uniformly and respectively constructing a topology information matrix of the corresponding assembly model by using all the uniform sampling results comprises:

[0016] Respectively sampling all the parts in each assembly model uniformly according to the same sampling interval to obtain a point cloud corresponding to each part;

[0017] Respectively constructing an initial topology information matrix of each assembly model;

[0018] Respectively calculating, in sequence, a sampling point Euclidean distance between all sampling points included in a point cloud corresponding to one part pair and all sampling points included in a point cloud corresponding to another part pair of any two parts included in each assembly model to respectively obtain a sampling point Euclidean distance set of the corresponding part pair;

[0019] If the sampling point Euclidean distance in the sampling point Euclidean distance set of the part pair is less than the sampling interval, it is considered that there is a topology relationship between the two parts corresponding to the sampling point Euclidean distance;

[0020] Respectively storing all the topology relationships into the initial topology information matrix corresponding to the sampling point Euclidean distance to obtain a topology information matrix of each assembly model.

[0021] Further, the step of respectively obtaining all part pairs having a topology relationship in the corresponding assembly model according to all the topology information matrices and respectively calculating, in sequence, a contact surface and a contact surface centroid of each part pair comprises:

[0022] Traversing all the topology information matrices to respectively obtain all the part pairs having a topology relationship in the corresponding assembly model;

[0023] Respectively calculating the contact surface of each part pair;

[0024] According to the contact surface of all the part pairs, the contact surface centroid corresponding to the contact surface is calculated.

[0025] Furthermore, the expression for the mating surfaces of the part pair is:

[0026] (1)

[0027] in, Indicates the first The first part and the first The mating surfaces of each part Indicates the first The point cloud corresponding to each part Indicates the first The point cloud corresponding to each part Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, To represent any one, Indicates at least one, Indicates the sampling interval. Represents the set of sampling points The first in Each sampling point and sampling point set The first in Euclidean distance between sampling points Represents the set of sampling points The first in Each sampling point and sampling point set The first in The Euclidean distance between sampling points.

[0028] Furthermore, the expression for the centroid of the mating surface of the part pair is:

[0029] (2)

[0030] in, Indicates the first The first part and the first The mating surface center of each part Indicates the first The part and the first The mating surface center of each part Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, .

[0031] Further, the step of obtaining the corresponding shape topological distance value set of the assembly model using all the uniform sampling results and all the mating surface centroids, and obtaining the corresponding vector descriptor of the assembly model using all the shape topological distance value sets includes:

[0032] Randomly select from the point cloud corresponding to all parts of each assembly model to obtain a first random sampling point and a second random sampling point corresponding to each part, and calculate the midpoint of the sampling points of the first random sampling point and the second random sampling point corresponding to each part;

[0033] Using the midpoints of all the sampling points and the centroids of all the mating surfaces, calculate the shape topology distance value of the corresponding assembly model;

[0034] Repeat all the above steps to obtain the set of shape topology distance values ​​for each of the assembly models;

[0035] Each shape topological distance value set is represented by an equidistant histogram to obtain the corresponding vector descriptor of the assembly model.

[0036] Furthermore, the expression for calculating the shape topological distance value is as follows:

[0037] (3)

[0038] in, This represents the shape topological distance value of the assembly model. Indicates the shape distance of the assembly model. This represents the topological distance of the assembly model. Indicates the first random sampling point. Indicates the second random sampling point. This represents the Euclidean distance between the first and second random sampling points. Indicates the first The first part and the first The mating surface center of each part This represents the midpoint between the first and second random sampling points. Indicates the mating surface center and the midpoint of the sampling point The Euclidean distance between them , Representing the assembly model The topological information matrix, Representing the assembly model The Middle The first part and the first The parts have a topological relationship. Representing the assembly model The Middle The first part and the first The parts do not have a topological relationship.

[0039] Furthermore, the expression for the group interval of the isometric histogram is:

[0040] (4)

[0041] in, This represents the group interval of an isometric histogram. This represents the maximum value of the shape topology distance of the assembly model. This represents the minimum value of the shape topological distance of the assembly model. This indicates the number of all intervals in an equidistant histogram;

[0042] The expression for the height of each interval in the isometric histogram is:

[0043] (5)

[0044] in, In the equidistant histogram, the first... The height of each interval In the equidistant histogram, the first... Statistical frequency of each interval.

[0045] Furthermore, the expression for the vector descriptor of the assembly model is:

[0046] v =[ v 1 , v y ,…, v z ] v y = h y (1≤ y ≤ z ) (6)

[0047] in, A vector descriptor representing an assembly model. the i-th dimensional vector, the i-th dimensional vector, the i-th dimensional vector in the equidistant histogram.

[0048] Further, the step of obtaining the retrieval result of the model to be retrieved by using the cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be retrieved comprises:

[0049] obtaining the vector descriptor of the model to be retrieved;

[0050] calculating the cosine similarity between the vector descriptor of the model to be retrieved and the vector descriptor of each assembly model respectively;

[0051] arranging all the cosine similarities in descending order to obtain the retrieval result of the model to be retrieved;

[0052] the expression of the cosine similarity is:

[0053] (7)

[0054] wherein, the cosine similarity between the vector descriptor of the assembly model and the vector descriptor of the model to be retrieved, the vector descriptor of the assembly model, the vector descriptor of the model to be retrieved, the norm of the vector descriptor of the assembly model, the norm of the vector descriptor of the model to be retrieved.

[0055] The application provides an assembly model retrieval method based on shape and topological information fusion quantization representation, which has at least the following beneficial effects:

[0056] (1) The application repeatedly calculates the shape topological distance value of the corresponding assembly model by using all uniform sampling results and all fitting surface centroids, and forms a shape topological distance value set of each assembly model, thereby constructing a corresponding vector descriptor, and realizing the fusion representation of the shape information and the topological information of the assembly model.

[0057] (2) This application obtains the model similarity retrieval results of the model to be retrieved by sorting the cosine similarity between the vector descriptors of all assembly models and the vector descriptors of the model to be retrieved in descending order. This allows for a comprehensive consideration of the shape information and topological information of the assembly model, making the retrieval results more accurate and thus improving the reusability of the assembly model. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0059] Figure 1 This illustration shows a step diagram of an assembly model retrieval method based on shape and topology information fusion quantitative representation in an exemplary embodiment of this application;

[0060] Figure 2 This diagram illustrates a flowchart of an assembly model retrieval method based on the fusion and quantitative representation of shape and topological information, as shown in an exemplary embodiment of this application.

[0061] Figure 3 This diagram illustrates the acquisition of an assembly model library in an exemplary embodiment of this application.

[0062] Figure 4 An assembly model is shown in an exemplary embodiment of this application. A schematic diagram;

[0063] Figure 5 An assembly model is shown in an exemplary embodiment of this application. A schematic diagram of the parts assembly;

[0064] Figure 6 An assembly model is shown in an exemplary embodiment of this application. A schematic diagram of the point cloud corresponding to each part;

[0065] Figure 7 An assembly model is shown in an exemplary embodiment of this application. A schematic diagram of the mating surfaces of the 6th and 7th parts that have a topological relationship.

[0066] Figure 8 An assembly model is shown in an exemplary embodiment of this application. A schematic diagram of the shape topological distance values ​​of the sub-assembly model consisting of the 6th and 7th parts that have a topological relationship;

[0067] Figure 9 Fig. 1 shows an assembly model in the exemplary embodiments of the present application; Fig. 2 shows a schematic diagram of a corresponding equidistant histogram;

[0068] Figure 10 Fig. 3 shows a schematic diagram of a retrieval result of a model to be retrieved in the exemplary embodiments of the present application. DETAILED DESCRIPTION

[0069] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0070] In addition, the accompanying drawings are included to provide a further understanding of the present application, and are incorporated herein and constitutepart of this application. The drawings illustrate the principles of the present application and, although not to be exact, they demonstrate the principles of the application. In some instances, detailed

[0071] In the following, a shape and topology information fusion quantization representation based assembly model retrieval method proposed in the present exemplary embodiments will be described in more detail.

[0072] The present exemplary embodiments provide a shape and topology information fusion quantization representation method for assembly model retrieval, as shown in Figure 1 and Figure 2 The method can include the following steps:

[0073] In step S101 of the present embodiments, an assembly model library is acquired. Figure 3 A schematic diagram of the assembly model library utilized in the present embodiments is shown.

[0074] Further, the assembly model library includes a plurality of assembly models, each of which contains a plurality of parts.

[0075] The acquisition process of the vector descriptor of all assembly models in the present embodiments, as well as the acquisition process of the vector descriptor of the model to be retrieved, are obtained according to the method proposed in the present application. Therefore, in the present embodiments, as shown in Figure 4 Let's take an example to illustrate.

[0076] Step S102 of this embodiment: Uniformly sample all parts contained in each assembly model, and construct the topology information matrix of the corresponding assembly model using all uniform sampling results. Step S102 of this embodiment may include the following sub-steps:

[0077] Sub-step S1021: In each assembly model, uniformly sample all parts at the same sampling interval to obtain the point cloud corresponding to each part.

[0078] Furthermore, in this embodiment, as Figure 5 and Figure 6 As shown, assembly model It is a set consisting of 12 parts: that is ,in, Representing the assembly model , Indicates the first One part, , Indicates the first One part, ,and Following the same sampling interval , , for the One part The surface is uniformly sampled to obtain the first... One part Corresponding point cloud , , Point cloud The first in One sampling point, , Point cloud The number of all sampling points in the sample.

[0079] Figure 5 In arrive These represent parts 1 through 12 respectively.

[0080] Figure 6 In arrive These represent the point clouds corresponding to the 1st to 12th parts, respectively.

[0081] Sub-step S1022: Construct the initial topology information matrix for each assembly model.

[0082] Furthermore, the initial topology information matrix refers to the multi-order zero matrix obtained by initializing the topology information matrix of the assembly model. In this embodiment, the assembly model... Initialization topology information matrix It is a 12th-order zero matrix.

[0083] Sub-step S1023: Calculate the Euclidean distance between all the sampling points in the point cloud of one part and all the sampling points in the point cloud of the other part in each part pair of any two parts of the assembly model, and obtain the set of Euclidean distances of the sampling points of the corresponding part pairs.

[0084] Furthermore, in this embodiment, an assembly model is used. parts and parts The following explanation will be based on a pair of components. The corresponding point cloud is ,Component The corresponding point cloud is Calculate the point cloud separately. Each sampling point and point cloud The Euclidean distance between each sampling point in the sample data is used to obtain the set of Euclidean distances for the sampling points of the part pair. , , Point cloud The Middle From sampling points to point cloud The Middle Euclidean distance between sampling points Point cloud The number of all sampling points in the middle, Point cloud The number of all sampling points in the sample.

[0085] Sub-step S1024: If there is a sampling point in the Euclidean distance set of the sampling points of the part pair whose Euclidean distance is less than the sampling interval, then there is a topological relationship between the two corresponding parts.

[0086] Furthermore, in this embodiment, if the assembly model The set of Euclidean distances of sampling points There exists Then let the initial topology information matrix be... Matrix elements This represents the assembly model. parts and parts There exists a topological relationship between them, and conversely, if Then let the initial topology information matrix be... matrix elements in , i.e. representing the assembly model and parts .

[0087] Sub-step S1025: store all topological relations into the corresponding initial topological information matrix respectively, to obtain the topological information matrix of each assembly model.

[0088] Further, in this embodiment, by comparing all sampling points Euclidean distance with sampling interval, the topological relations of all part pairs in the assembly model are obtained, and finally the topological information matrix of the assembly model is obtained. As shown in Table 1 below.

[0089] Table 1: Topological information matrix of the assembly model

[0090]

[0091] Wherein, 0 represents no topological relation, and 1 represents topological relation.

[0092] Step S103 of this embodiment: according to all topological information matrices, all part pairs with topological relations in the corresponding assembly model are obtained respectively, and the fitting surface and fitting surface center of each part pair are calculated in turn. This embodiment step S103 can include the following sub-steps:

[0093] Sub-step S1031: traverse all topological information matrices to obtain all part pairs with topological relations in the corresponding assembly model respectively.

[0094] Further, in this embodiment, according to the topological information matrix of the assembly model , all part pairs with topological relations in the assembly model are obtained, and the part pair set of the assembly model is composed of , . .

[0095] Sub-step S1032: calculate the fitting surface of each part pair respectively.

[0096] Further, in this embodiment, as shown in Figure 7 , for part pair , the fitting surface between part is calculated, , ​​parts Corresponding point cloud The set of sampling points and parts that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Corresponding point cloud It is represented by the union of the sets of sampling points that satisfy the condition that the Euclidean distance between the sampling points is less than the sampling interval. Figure 7 middle, The value is 6. The value is 7, meaning the 6th part is calculated. And the 7th part mating surfaces The expression for calculating the mating surfaces of a pair of parts is as follows, which can be used for the 6th part. And the 7th part Substitute the values ​​into the equations for calculation.

[0097] The expression for the mating surfaces of the part pair is:

[0098] (1)

[0099] in, Indicates the first The first part and the first The mating surfaces of each part Indicates the first The point cloud corresponding to each part Indicates the first The point cloud corresponding to each part Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, To represent any one, Indicates at least one, Indicates the sampling interval. Represents the set of sampling points The first in Each sampling point and sampling point set The first in Euclidean distance between sampling points Represents the set of sampling points The first in Each sampling point and sampling point set The first in The Euclidean distance between sampling points.

[0100] Sub-step S1033: Calculate the centroid of the corresponding mating surface based on the mating surfaces of all part pairs.

[0101] Furthermore, in this embodiment, the calculation part and parts mating surfaces Matching surface center The expression is as follows, where, , , .

[0102] The expression for the centroid of the mating surfaces of the part pair is:

[0103] (2)

[0104] in, Indicates the first The first part and the first The mating surface center of each part Indicates the first The part and the first The mating surface center of each part Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, .

[0105] Step S104 of this embodiment: Using all uniform sampling results and all mating surface centroids, obtain the corresponding shape topology distance value sets of the assembly model, and use all shape topology distance value sets to obtain the corresponding vector descriptors of the assembly model. Step S104 of this embodiment may include the following sub-steps:

[0106] Sub-step S1041: Randomly select from the point cloud corresponding to all parts of each assembly model to obtain the first random sampling point and the second random sampling point corresponding to each part, and calculate the midpoint of the sampling point of the first random sampling point and the second random sampling point corresponding to each part.

[0107] Furthermore, in this embodiment, the assembly model is traversed. parts The first random sampling point is randomly selected from them. Second random sampling point And calculate the midpoint of the sampling points of these two random sampling points. .

[0108] Sub-step S1042: Calculate the shape topology distance value of the corresponding assembly model using the midpoint of all sampling points and the centroid of all mating surfaces.

[0109] Furthermore, in this embodiment, as Figure 8 As shown, the expression for calculating the shape topological distance value is:

[0110] (3)

[0111] in, This represents the shape topological distance value of the assembly model. Indicates the shape distance of the assembly model. This represents the topological distance of the assembly model. Indicates the first random sampling point. Indicates the second random sampling point. This represents the Euclidean distance between the first and second random sampling points. Indicates the first The first part and the first The mating surface center of each part This represents the midpoint between the first and second random sampling points. Indicates the mating surface center and the midpoint of the sampling point The Euclidean distance between them , Representing the assembly model The topological information matrix, Representing the assembly model The Middle The first part and the first The parts have a topological relationship. Representing the assembly model The Middle The first part and the first The parts have a topological relationship.

[0112] According to expression (3), it can be calculated that Figure 8 The shape topology distance value of the sub-assembly model consisting of the 6th and 7th parts shown in the figure.

[0113] Sub-step S1043: Repeat all the above steps to obtain the set of shape topology distance values ​​for each assembly model.

[0114] Furthermore, in this embodiment, the number of repetitions is [number missing]. Each time, the shape topological distance value obtained from the calculation is counted to obtain the assembly model. Shape topological distance value set ,in, Indicates the first The shape topological distance value obtained during the repetition. . Figure 2 of middle, .

[0115] Sub-step S1044: such as Figure 9 As shown, each shape's topological distance value set is represented by an equidistant histogram, resulting in a vector descriptor for the corresponding assembly model.

[0116] Furthermore, the expression for the group interval of an isometric histogram is:

[0117] (4)

[0118] in, This represents the group interval of an isometric histogram. This represents the maximum value of the shape topology distance of the assembly model. This represents the minimum value of the shape topological distance of the assembly model. This indicates the number of intervals in an equidistant histogram.

[0119] Furthermore, the expression for the height of each interval in the isometric histogram is:

[0120] (5)

[0121] in, In the equidistant histogram, the first... The height of each interval In the equidistant histogram, the first... Statistical frequency of each interval.

[0122] Furthermore, the expression for the vector descriptor of the assembly model is:

[0123] v =[ v 1 , v y ,…, v z ] v y = h y (1≤ y ≤ z ) (6)

[0124] wherein, denotes a vector descriptor of the assembly model, denotes the i-th vector dimension in the vector descriptor of the assembly model, denotes the i-th vector dimension in the vector descriptor of the assembly model, denotes the i-th vector dimension in the vector descriptor of the assembly model, denotes the i-th vector dimension in the vector descriptor of the assembly model, denotes the height of the i-th vector dimension in the equi- distance histogram. Here, the number of all vector dimensions in the vector descriptor of the assembly model is equal to the number of all bins in the equi- distance histogram, and one-to-one correspondence exists between them.

[0125] Figure 9 wherein, the abscissa denotes the number of all bins in the equi- distance histogram, and the ordinate denotes the bin height.

[0126] The step S105 of the embodiment: the cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be searched is used to obtain the search result of the model to be searched. The step S1051 of the embodiment can include the following sub-steps:

[0127] Sub-step S1051: obtaining the vector descriptor of the model to be searched.

[0128] Further, in the embodiment, the vector descriptor of the model to be searched can be obtained by the method mentioned in the embodiment. Sub-step S1052: calculating the cosine similarity between the vector descriptor of the model to be searched and the vector descriptor of each assembly model.

[0129] Further, the expression of the cosine similarity is:

[0130] (7)

[0131] wherein, denotes the cosine similarity between the vector descriptor of the assembly model and the vector descriptor of the model to be searched, denotes the vector descriptor of the assembly model, denotes the vector descriptor of the model to be searched, denotes the norm of the vector descriptor of the assembly model, denotes the norm of the vector descriptor of the model to be searched.

[0132] Sub-step S1053: as shown in Figure 10 , all cosine similarities are arranged in descending order to obtain the search result of the model to be searched. ​

[0133] By Figure 10 As can be seen, according to the cosine similarity in descending order, the to-be-retrieved model is compared with each assembly model in descending order, and the assembly model stored in the assembly model library before the to-be-retrieved model is ranked first Therefore, the similarity is 1, the cosine similarity of the second is 0.9614, the cosine similarity of the third is 0.9484, the cosine similarity of the fourth is 0.8931, the cosine similarity of the fifth is 0.8551, and the cosine similarity of the sixth is 0.8026.

[0134] In addition, the terms "first", "second", "third", etc. are used only for descriptive purposes and should not be construed as indicating or implying relative importance or an indicated number of technical features. Therefore, the features defined as "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified.

[0135] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms is not necessarily for the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in the present application.

[0136] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered within the protection scope of the present application.

[0137] Other embodiments of the present application will be readily apparent to those skilled in the art upon considering the disclosure herein, the present application is intended to cover any variations, uses or adaptive changes of the present application, which follow the general principles of the present application and include common knowledge or conventional techniques in the art which are not disclosed in the present application.

Claims

1. A method for retrieving assembly models based on the fusion and quantitative representation of shape and topological information, characterized in that, The method includes the following steps: Obtain an assembly model library, which includes multiple assembly models, each of which contains multiple parts; Uniform sampling is performed on all the parts contained in each assembly model, and the topology information matrix of the corresponding assembly model is constructed using all uniform sampling results. Based on all the aforementioned topological information matrices, obtain all pairs of parts with topological relationships in the corresponding assembly model, and calculate the mating surface and centroid of the mating surface for each pair of parts in sequence, including: Traverse all the topology information matrices to obtain all the part pairs with topological relationships in the corresponding assembly model; Calculate the mating surfaces of each pair of parts; The expression for the mating surfaces of the part pair is: (1) in, Indicates the first The first part and the first The mating surfaces of each part Indicates the first The point cloud corresponding to each part Indicates the first The point cloud corresponding to each part Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Indicates the first The set of sampling points in the point cloud corresponding to each part that satisfy the condition that the Euclidean distance between sampling points is less than the sampling interval. Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, To represent any one, Indicates at least one, Indicates the sampling interval. Represents the set of sampling points The first in Each sampling point and sampling point set The first in Euclidean distance between sampling points Represents the set of sampling points The first in Each sampling point and sampling point set The first in Euclidean distance between sampling points; Calculate the centroid of the corresponding mating surface based on the mating surfaces of all the said part pairs; The expression for the centroid of the mating surface of the part pair is: (2) in, Indicates the first The first part and the first The mating surface center of each part Indicates the first The part and the first The mating surface center of each part Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The number of all sampling points in the middle, Represents the set of sampling points The first in One sampling point, , Represents the set of sampling points The first in One sampling point, ; Using all the uniform sampling results and all the mating surface centroids, obtain the corresponding shape topology distance value set of the assembly model, and use all the shape topology distance value sets to obtain the corresponding vector descriptor of the assembly model; The retrieval results for the model to be retrieved are obtained by using the cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be retrieved.

2. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 1, characterized in that, The step of uniformly sampling all the parts contained in each assembly model and constructing the topology information matrix of the corresponding assembly model using all the uniform sampling results includes: In each of the assembly models, all the parts are uniformly sampled at the same sampling interval to obtain the point cloud corresponding to each part; Construct an initial topology information matrix for each of the assembly models; Calculate the Euclidean distance between all sampling points in the point cloud of one part and all sampling points in the point cloud of the other part in each part pair of any two parts of the assembly model, and obtain the Euclidean distance set of the sampling points of the corresponding part pair. If there is a sampling point in the Euclidean distance set of the part pair whose Euclidean distance is less than the sampling interval, then it is considered that there is a topological relationship between the two corresponding parts. All the topological relationships are stored in the corresponding initial topological information matrix to obtain the topological information matrix of each assembly model.

3. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 1, characterized in that, The steps of obtaining the corresponding shape topology distance value set of the assembly model by utilizing all the uniform sampling results and all the mating surface centroids, and obtaining the corresponding vector descriptor of the assembly model by utilizing all the shape topology distance value sets, include: Randomly select from the point cloud corresponding to all parts of each assembly model to obtain a first random sampling point and a second random sampling point corresponding to each part, and calculate the midpoint of the sampling points of the first random sampling point and the second random sampling point corresponding to each part respectively; Using the midpoints of all the sampling points and the centroids of all the mating surfaces, calculate the shape topology distance value of the corresponding assembly model; Repeat all the above steps to obtain the set of shape topology distance values ​​for each of the assembly models; Each shape topological distance value set is represented by an equidistant histogram to obtain the corresponding vector descriptor of the assembly model.

4. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 3, characterized in that, The expression for calculating the shape topological distance value is: (3) in, This represents the shape topological distance value of the assembly model. Indicates the shape distance of the assembly model. This represents the topological distance of the assembly model. Indicates the first random sampling point. Indicates the second random sampling point. This represents the Euclidean distance between the first and second random sampling points. Indicates the first The first part and the first The mating surface center of each part This represents the midpoint between the first and second random sampling points. Indicates the mating surface center and the midpoint of the sampling point The Euclidean distance between them , Representing the assembly model The topological information matrix, Representing the assembly model The Middle The first part and the first The parts have a topological relationship. Representing the assembly model The Middle The first part and the first The parts do not have a topological relationship.

5. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 3, characterized in that, The expression for the group interval of the isometric histogram is: (4) in, This represents the group interval of an isometric histogram. This represents the maximum value of the shape topology distance of the assembly model. This represents the minimum value of the shape topological distance of the assembly model. This indicates the number of all intervals in an equidistant histogram; The expression for the height of each interval in the isometric histogram is: (5) in, In the equidistant histogram, the first... The height of each interval In the equidistant histogram, the first... Statistical frequency of each interval.

6. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 5, characterized in that, The expression for the vector descriptor of the assembly model is: (6) in, A vector descriptor representing an assembly model. The first vector descriptor representing the assembly model dimensional vector, The first vector descriptor representing the assembly model dimensional vector, Indicates the first The height of the dimensional vector in the isometric histogram.

7. The assembly model retrieval method based on shape and topological information fusion quantitative representation according to claim 1, characterized in that, The step of obtaining the retrieval results for the model to be retrieved by utilizing the cosine similarity between the vector descriptor of each assembly model and the vector descriptor of the model to be retrieved includes: Obtain the vector descriptor of the model to be retrieved; Calculate the cosine similarity between the vector descriptor of the model to be retrieved and the vector descriptor of each assembly model; Arrange all the cosine similarities in descending order to obtain the retrieval results for the model to be retrieved; The expression for the cosine similarity is: (7) in, The cosine similarity between the vector descriptors of the assembly model and the vector descriptors of the model to be retrieved is denoted as . A vector descriptor representing an assembly model. This represents the vector descriptor of the model to be retrieved. The norm of the vector descriptor representing the assembly model. This represents the norm of the vector descriptor of the model to be retrieved.

Images