CN120354180A - Method, system, equipment and medium for classifying finished product installation types based on typical structural features - Google Patents
Method, system, equipment and medium for classifying finished product installation types based on typical structural featuresInfo
- Publication number
- CN120354180A CN120354180A CN202510847101.0A CN202510847101A CN120354180A CN 120354180 A CN120354180 A CN 120354180A CN 202510847101 A CN202510847101 A CN 202510847101A CN 120354180 A CN120354180 A CN 120354180A
- Authority
- CN
- China
- Prior art keywords
- finished product
- classification result
- classification
- classifying
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及飞机制造技术领域，具体地说，涉及一种基于典型结构特征的成品安装类型分类方法、系统、设备及介质；该方法首先根据获取的STG模型，分析提取得到结构化的描述内容；其次根据结构化的描述内容构建成品安装分类规则库，并根据获取的成品外形特征初步分类成品，得到第一分类结果；然后根据获取的成品基本特征，得到第二分类结果；最后根据获取的成品连接特征，得到第三分类结果，并根据第三分类结果判断得到最终分类结果，实现了基于典型结构特征的成品安装类型分类，完成了对成品类别准确清晰的判断。
The present invention relates to the field of aircraft manufacturing technology, and in particular, to a method, system, device and medium for classifying the installation type of finished products based on typical structural features. The method firstly analyzes and extracts structured description content based on an acquired STG model. Secondly, a finished product installation classification rule base is constructed based on the structured description content, and the finished products are preliminarily classified according to the acquired finished product appearance features to obtain a first classification result. Then, a second classification result is obtained based on the acquired basic features of the finished products. Finally, a third classification result is obtained based on the acquired connection features of the finished products, and a final classification result is obtained based on the third classification result, thereby realizing the classification of the installation type of finished products based on typical structural features and completing an accurate and clear judgment of the finished product category.
Description
Technical Field
The invention relates to the technical field of aircraft manufacturing, in particular to a finished product installation type classification method, system, equipment and medium based on typical structural characteristics.
Background
The technical rules are written productive process files according to design requirements, process technical requirements and quality requirements by a process department. The technical rules not only comprise process information, but also production information and quality information, and specific work instructions for guiding workers to actually operate the appointed assembly process flow include information such as operation instructions, working procedures, assembly time sequences, change records and the like.
At present, the technological rules still mainly adopt a manual programming mode, the working period of the technological rules is longer, the standard of the technological rules programming result is poor, and even some quality errors can occur. Therefore, the automatic programming of the technical regulations is an urgent problem to be solved in the development and production of the aircraft, and the automatic identification of the parts and the characteristics of the aircraft is an important factor for restricting the automatic programming and planning of the technical regulations.
Aircraft manufacturing and installation is a complex and accurate process involving multiple stages, from design to final delivery, including mainly conceptual design, detailed design, simulation and testing, component manufacturing, assembly and integration, internal installation, test verification, delivery acceptance, and the like.
Because of the complexity of the aircraft, the number of parts is large, and each part is provided by different manufacturers, the types of finished products are large, and the installation positions are different, so that the method has important roles in accurately identifying and classifying the types of the finished products, and automatically programming/planning the technical regulations and accurately programming the technical regulations.
Disclosure of Invention
Aiming at the problems that the existing classification method is easy to cause the misloading and neglected loading of finished products, which are different in types and mounting positions of the finished products, the invention provides a finished product mounting type classification method, system, equipment and medium based on typical structural characteristics; the method comprises the steps of firstly analyzing and extracting structured descriptive contents according to an obtained STG model, secondly constructing a finished product installation classification rule base according to the structured descriptive contents, primarily classifying finished products according to the obtained appearance characteristics of the finished products to obtain a first classification result, then obtaining a second classification result according to the obtained basic characteristics of the finished products, finally obtaining a third classification result according to the obtained connection characteristics of the finished products, judging according to the third classification result to obtain a final classification result, classifying the finished product installation types based on typical structural characteristics, and accurately and clearly judging the types of the finished products.
The invention has the following specific implementation contents:
A finished product installation type classification method based on typical structural features comprises the steps of firstly analyzing and extracting structured description contents according to an obtained STG model, secondly constructing a finished product installation classification rule base according to the structured description contents, primarily classifying finished products according to the obtained appearance features of the finished products to obtain a first classification result, then obtaining a second classification result according to the obtained basic features of the finished products, finally obtaining a third classification result according to the obtained connecting features of the finished products, and judging according to the third classification result to obtain a final classification result.
In order to better implement the invention, the method for classifying the installation types of the finished products based on the typical structural characteristics specifically comprises the following steps:
step S1, analyzing and extracting to obtain structured description content according to an obtained STG model, wherein the STG model is a model which is built by taking local features of a three-dimensional model as vertexes and taking adjacent relations among the local features as edges;
S2, constructing a finished product installation classification rule base according to the structured descriptive content, and primarily classifying finished products according to the acquired finished product model image to obtain a first classification result;
s3, according to the obtained basic attribute characteristics of the finished products, invoking a semantic analysis method to classify the preliminarily classified finished products to obtain a second classification result;
and S4, classifying to obtain a third classification result according to the obtained connection relation characteristics of the finished products and the second classification result, and judging to obtain a final classification result according to the third classification result.
In order to better implement the present invention, further, the step S1 specifically includes the following steps:
Step S11, according to the acquired STG model, calling a model extraction technology to acquire three-dimensional coordinate information of a finished product, and carrying out normalized display;
And step S12, extracting basic attribute information and shape data of the STG model according to the obtained STG model, analyzing to obtain structured description content, wherein the basic attribute information comprises a finished product code, a finished product name and a finished product connection relation, and the shape data is stored in an image form.
In order to better realize the invention, in step S2, an identification algorithm is called to learn the shape data, and the first classification result is obtained by primarily classifying the finished product.
In order to better implement the present invention, further, the step S4 specifically includes the following steps:
step S41, classifying to obtain a third classification result according to the obtained connection relation characteristic of the finished product and the second classification result, wherein the connection relation characteristic comprises a connection mode and connection key materials;
And S42, judging to obtain a final classification result according to the third classification result, if the repeated result is more than 2, reserving the third classification result as the final classification result of the finished product, otherwise, taking the second classification result as the final classification result of the finished product.
In order to better implement the present invention, further, the step S41 specifically includes the following steps:
Step S411, describing the name and shape information of the obtained finished product;
Step S412, obtaining the connection relation between parts by adopting a double interference test method, and establishing an adjacent model;
Step S413, calculating a connection relation feature set matched with the finished product installation classification rule base according to the name and shape information of the finished product;
step S414, taking the matching relation as a search space to obtain a connection mode and connection key materials;
step 415, according to the connection mode and the connection key materials, combining the second classification result classification to obtain a third classification result;
in order to better implement the present invention, further, the step S411 specifically includes the following steps:
Step S4111, initializing a part class set;
Step S4112, obtaining the name id p of the model file corresponding to the part p;
Step S4113, judging whether the part class c p of the part p belongs to a class set, if not, calling a shape distribution algorithm to describe the shape information of the part p as a k-dimensional shape vector S p, establishing a part descriptor < id p,sp >, and adding the part p as a new part class c p to the class set;
Step S4114, if the name id p=idq,idq∈cq of the part model file, establishing a part descriptor < id q,sq>,idq as the name of the model file corresponding to the part q, and c q as the part category of the part q;
Step S4115 repeat steps S4112-S4114 until all parts are traversed.
In order to better implement the present invention, further, the step S412 specifically includes the following steps:
S4121, acquiring an assembly I from a finished product installation classification rule base, initializing an m multiplied by m dimensional adjacency matrix G, and calculating an AABB bounding box R of the part, wherein m is the number of the part in a complex product model A to be identified;
step S4122, selecting a part p' from the assembly I, and initializing a set S;
Step S4123 randomly acquiring part q from assembly I, if bounding box R p'∩Rq is not equal to Adding the part q into the set S, wherein R p' is the AABB bounding box of the part p', and R q is the AABB bounding box of the part q;
Step S4124, according to the part q in the set S, calling an octree trunk interference detection algorithm to spatially interfere and detect the part p' and the part q, and if the detection result is contact or interference, the adjacent matrix G p'q =1;
step S4125 repeat steps S4122-S4124 until all parts of the assembly I are traversed.
In order to better implement the present invention, further, the step S413 specifically includes the following steps:
step S4131, initializing a matched part set Com p;
step S4132, adding the part with the name of id p in the finished product model A to be identified into a matched part set Com p;
Step S4133, calculating the similarity between the shape vector S p of the part p and the shape vector S i of the part in the ith class in the part class set C;
step S4134, judging whether the similarity is larger than or equal to the shape similarity threshold according to the set shape similarity threshold, if so, adding all the parts in the ith category to the matched part set Com p.
In order to better implement the present invention, further, the formula for calculating the similarity between the shape vector S p of the part p and the shape vector S i of the part in the ith class in the part class set C in step S4133 is:
;
Where s p represents the shape vector of part p, s q represents the shape vector of part q in the ith class, k represents the dimension of the k-dimensional shape vector of part, l j p represents the j-dimensional shape vector of part p, and l j q represents the j-dimensional shape vector of part q.
In order to better realize the invention, the specific operation of the step S4134 is that according to the set shape similarity threshold valueIf the similarity sim (s p,si) is not less thanAll parts in the ith class are added to the matching part set Com p,si as the shape vector for the parts in the ith class.
In order to better realize the invention, the specific operation of the step S414 is to use the matching relationship of the parts as a search space, call Ullmann sub-graph matching algorithm to search the adjacent matrix G A of the to-be-identified finished product model A for sub-graph matching results with the same structure as the adjacent matrix G I of the assembly I, and identify the connection mode and the connection key materials.
In order to better realize the invention, the establishing process of the STG model in the step S1 comprises the steps of firstly establishing a vertex adjacency graph according to the topological relation among the acquired B-rep data geometric elements, secondly searching the biggest group in the adjacency graph and taking the geometric area corresponding to the biggest group as the local feature of the entity model, then transferring the shape information of the local feature into a feature vector to form a feature space, adopting an unsupervised learning algorithm to differentially inhibit the local feature, and finally establishing the STG model taking the local feature as the vertex and the adjacency relation among the local features as the edge.
In order to better realize the invention, the invention further provides a finished product installation type classification system based on the typical structural characteristics, which is used for executing the finished product installation type classification method based on the typical structural characteristics, and comprises an analysis and extraction unit, a preliminary classification unit, an attribute classification unit and a classification output unit;
The analysis and extraction unit is used for analyzing and extracting structured descriptive contents according to the acquired STG model;
the primary classification unit constructs a finished product installation classification rule base according to the structured description content, and primarily classifies finished products according to the acquired finished product model image to obtain a first classification result;
the attribute classification unit is used for classifying the primarily classified finished products according to the acquired basic attribute information of the finished products to obtain a second classification result;
the classification output unit is used for classifying according to the obtained connection relation characteristics of the finished products and the second classification result to obtain a third classification result, and judging according to the third classification result to obtain a final classification result.
In order to better realize the invention, the invention further provides electronic equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is executed on the processor to realize the finished product installation type classification method based on the typical structural characteristics.
In order to better implement the present invention, further, a computer readable storage medium is provided, wherein the computer readable storage medium stores computer instructions, and when the computer instructions are executed on the electronic device, the method for classifying the installation type of the finished product based on the typical structural features is implemented.
The invention has the following beneficial effects:
(1) The invention constructs a finished product installation type map network, realizes the classification of the finished product installation types based on typical structural characteristics, efficiently identifies the types of the finished products, and solves the problem that the finished products are easy to miss-install and misplace.
(2) The invention realizes the classification of the installation types of the finished products based on typical structural features based on the clustering and other reasoning logic technologies, and completes the accurate and clear judgment of the classification of the finished products.
Drawings
Fig. 1 is a schematic block flow diagram of a method for classifying installation types of finished products based on typical structural features.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it should be understood that the described embodiments are only some embodiments of the present invention, but not all embodiments, and therefore should not be considered as limiting the scope of protection. All other embodiments, which are obtained by a worker of ordinary skill in the art without creative efforts, are within the protection scope of the present invention based on the embodiments of the present invention.
In the description of the present invention, unless explicitly stated or limited otherwise, the terms "disposed," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically connected, electrically connected, directly connected, indirectly connected via an intermediate medium, or in communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1:
According to the embodiment, firstly, structured description contents are obtained through analysis and extraction according to an obtained STG model, secondly, a finished product installation classification rule base is constructed according to the structured description contents, a first classification result is obtained through preliminary classification of finished products according to the obtained appearance characteristics of the finished products, a second classification result is obtained according to the obtained basic characteristics of the finished products, finally, a third classification result is obtained according to the obtained connection characteristics of the finished products, and a final classification result is obtained through judgment according to the third classification result.
The working principle is that the finished product installation type classification method based on typical structural characteristics is realized by constructing the finished product installation type map network, the types of the finished products are efficiently identified, and the problem that the finished products are easy to miss-install and misplace is solved.
Example 2:
The present embodiment is described in the form of steps based on the above embodiment 1, and as shown in fig. 1, the method for classifying the installation type of the finished product based on the typical structural features specifically includes the following steps:
And step S1, analyzing and extracting to obtain structured descriptive contents according to the acquired STG model.
The step S1 specifically comprises the following steps:
Step S11, according to the acquired STG model, calling a model extraction technology to acquire three-dimensional coordinate information of a finished product, and carrying out normalized display;
And step S12, extracting basic attribute information and shape data of the STG model according to the obtained STG model, analyzing to obtain structured description content, wherein the basic attribute information comprises a finished product code, a finished product name and a finished product connection relation, and the shape data is stored in an image form.
And S2, constructing a finished product installation classification rule base according to the structured description content, and primarily classifying the finished products according to the acquired finished product model image to obtain a first classification result.
The step S2 specifically includes the following steps:
S21, constructing a finished product installation classification rule base according to the structured descriptive content;
and S22, invoking an identification algorithm to learn the shape data, and primarily classifying the finished product to obtain a first classification result.
And step S3, classifying the primarily classified finished products according to the acquired basic attribute characteristics of the finished products to obtain a second classification result.
The specific operation of the step S3 is that a semantic analysis method is called to classify the primarily classified finished products according to the acquired basic attribute information of the finished products, and a second classification result is obtained.
And S4, classifying to obtain a third classification result according to the obtained connection relation characteristics of the finished products and the second classification result, and judging to obtain a final classification result according to the third classification result.
The step S4 specifically includes the following steps:
step S41, classifying to obtain a third classification result according to the obtained connection relation characteristic of the finished product and the second classification result, wherein the connection relation characteristic comprises a connection mode and connection key materials;
The connection mode and the acquisition mode of the connection key materials in the step S41 are that firstly, the name and the shape information of the acquired finished products are described, secondly, the connection relation among the parts is acquired by adopting a double interference inspection method, an adjacent model is established, then, a connection relation feature set matched with a finished product installation classification rule base is calculated according to the name and the shape information of the finished products, and finally, the connection mode and the connection key materials are obtained by taking the matching relation as a search space.
And S42, judging to obtain a final classification result according to the third classification result, if the repeated result is more than 2, reserving the third classification result as the final classification result of the finished product, otherwise, taking the second classification result as the final classification result of the finished product.
The working principle is that the embodiment constructs a finished product installation type map network through methods such as semantic recognition, model extraction, map construction and the like, and realizes a finished product installation type classification method based on typical structural features based on inference logic technologies such as clustering and the like, thereby completing accurate and clear judgment of the category of the finished product.
Other portions of this embodiment are the same as those of embodiment 1 described above, and thus will not be described again.
Example 3:
This embodiment will be described in detail with reference to one specific example on the basis of any one of the above embodiments 1 to 2.
And S1, processing the existing STG three-dimensional model by using methods such as vocabulary analysis, grammar analysis, syntactic analysis, model extraction technology and the like to obtain structured description content.
The three-dimensional model is an important carrier for bearing aircraft assembly information and comprises important information such as the installation position of a finished product, basic attribute information of the finished product, the appearance of the finished product and the like, wherein the basic attribute information of the finished product is finished product codes, finished product names and the like.
And obtaining three-dimensional coordinate information of the finished product through a model extraction technology, storing the three-dimensional coordinate information in the form of (X, Y, Z), and carrying out normalized display on the three-dimensional coordinate information to obtain coordinate values (X1, Y1, Z1).
Meanwhile, basic attribute information in the model is extracted, and the basic attribute information comprises data such as product codes, product names, product connection relations and the like. The profile data is stored in the form of pictures.
The STG model obtained in the step S1 of the embodiment is to firstly establish a vertex adjacency graph according to the topological relation between geometric elements such as vertices and faces in B-rep data, to search for a biggest group in the graph and use a geometric area corresponding to the biggest group as a local feature of the model, to convert the shape information of the local feature into feature vectors based on a statistical method to form a feature space, to perform local feature difference suppression by adopting an unsupervised learning algorithm to enable the local features with similar shapes to have the same code, and to finally establish the STG model with the local feature as the vertex and the adjacency relation as the edge.
And S2, constructing a finished product installation classification rule base, and completing judgment on finished product classification based on the rule base.
The product installation classification rule base defines classification rules of the product.
Model pictures of various finished products are learned through a machine learning mode, and are roughly classified according to a classification algorithm to obtain classification results Rp { Rp1, rp2, rp3.
And S3, classifying the basic attribute information according to the information. The classification is carried out according to the characteristics of the finished product, and the classification is mainly carried out according to basic information thereof in a semantic recognition mode by codes, names and the like. The classification result RL { RL1, RL2, RL 3..rln }, wherein Rli represents the classification result of the ith finished product. For example, a product may be classified into { mechanical products, electrical products, etc., and the properties of the mechanical products include information such as brackets, pipes, frames, struts, and braces, etc., and the electrical products include plugs, rear accessories, and sensor electrical products.
And S4, classifying the connection relation features according to the connection relation features. And classifying finished products due to different connection modes and connection key materials. The classification result RR1 is obtained, RR2, RR3. Where RRi represents the classification result of the ith finished product. { mechanical product electrical end product. The mechanical finished product connecting object is a part, the electric finished product connecting object is a cable plug.
Through the three dimensions, three classification results of a finished product are respectively obtained, wherein the logic for obtaining the final result is that if the repeated result is greater than 2, the result is reserved as the final classification result of the finished product. Otherwise, the classification result of the basic attribute information is used as the reference. Through the above classification, the finished products can be obtained into mechanical finished products and electrical finished products.
The connection relation characteristic acquisition method in the step S4 of the embodiment is that a part class is built according to a finished product name, shape information of parts in each class is extracted, a predefined finished product installation classification rule base is used as input, the matching relation of the parts is rapidly judged by integrating the class information and the shape information, and on the basis, the connection relation and the connection key materials are used as typical structures by using a graph matching algorithm, so that effective identification of the connection relation and the connection key materials is realized.
Other portions of this embodiment are the same as any of embodiments 1 to 2, and thus will not be described again.
Example 4:
this embodiment describes step S4 in detail with a specific embodiment based on any one of the above embodiments 1 to 3.
The step S4 specifically includes the following steps:
and S41, classifying to obtain a third classification result according to the obtained connection relation characteristic of the finished product and the second classification result, wherein the connection relation characteristic comprises a connection mode and connection key materials.
The step S41 specifically includes the following steps:
Step S411, describing the name and shape information of the obtained finished product;
the step S411 specifically includes the following steps:
Step S4111, initializing a part class set;
Step S4112, obtaining the name id p of the model file corresponding to the part p;
Step S4113, judging whether the part class c p of the part p belongs to a class set, if not, calling a shape distribution algorithm to describe the shape information of the part p as a k-dimensional shape vector S p, establishing a part descriptor < id p,sp >, and adding the part p as a new part class c p to the class set;
Step S4114, if the name id p=idq,idq∈cq of the part model file, establishing a part descriptor < id q,sq>,idq as the name of the model file corresponding to the part q, and c q as the part category of the part q;
Step S4115 repeat steps S4112-S4114 until all parts are traversed.
Step S412, a double interference test method is adopted to obtain the connection relation between the parts, and an adjacent model is established.
The step S412 specifically includes the following steps:
S4121, acquiring an assembly I from a finished product installation classification rule base, initializing an m multiplied by m dimensional adjacency matrix G, and calculating an AABB bounding box R of the part, wherein m is the number of the part in a complex product model A to be identified;
step S4122, selecting a part p' from the assembly I, and initializing a set S;
Step S4123 randomly acquiring part q from assembly I, if bounding box R p'∩Rq is not equal to Adding the part q into the set S, wherein R p' is the AABB bounding box of the part p', and R q is the AABB bounding box of the part q;
Step S4124, according to the part q in the set S, calling an octree trunk interference detection algorithm to spatially interfere and detect the part p' and the part q, and if the detection result is contact or interference, the adjacent matrix G p'q =1;
step S4125 repeat steps S4122-S4124 until all parts of the assembly I are traversed.
And S413, calculating a connection relation feature set matched with the finished product installation classification rule base according to the name and shape information of the finished product.
The step S413 specifically includes the following steps:
step S4131, initializing a matched part set Com p;
step S4132, adding the part with the name of id p in the finished product model A to be identified into a matched part set Com p;
Step S4133, calculating the similarity between the shape vector S p of the part p and the shape vector S i of the part in the ith class in the part class set C;
The specific operation of step S4133 is as follows:
;
Where s p represents the shape vector of part p, s q represents the shape vector of part q in the ith class, k represents the dimension of the k-dimensional shape vector of part, l j p represents the j-dimensional shape vector of part p, and l j q represents the j-dimensional shape vector of part q.
Step S4134, judging whether the similarity is larger than or equal to the shape similarity threshold according to the set shape similarity threshold, if so, adding all the parts in the ith category to the matched part set Com p.
The specific operation of the step S4134 is that according to the set shape similarity threshold valueJudging whether the similarity sim (s p,si) is larger than or equal to a shape similarity threshold value, if so, the similarity sim (s p,si) is larger than or equal toThen add all parts in the ith class to the matching part set Com p,si as the shape vector of the parts in the ith class, i.e., com p=Comp∪{cq|sim(sp,sq). Gtoreq.A process of the polymer (c) is performed, wherein i is more than or equal to 1 and less than or equal to n and q+.p.
And step S414, taking the matching relation as a search space to obtain a connection mode and connection key materials.
The specific operation of step S414 is that the matching relationship of the parts is used as a search space, the Ullmann sub-graph matching algorithm is invoked to search the adjacent matrix G A of the to-be-identified finished product model a for the sub-graph matching result with the same structure as the adjacent matrix G I of the assembly body I, and the connection mode and the connection key material are identified.
Step 415, according to the connection mode and the connection key materials, combining the second classification result classification to obtain a third classification result;
And S42, judging to obtain a final classification result according to the third classification result, if the repeated result is more than 2, reserving the third classification result as the final classification result of the finished product, otherwise, taking the second classification result classified by the basic attribute characteristics as the final classification result of the finished product.
Other portions of this embodiment are the same as any of embodiments 1 to 3, and thus will not be described again.
Example 5:
The embodiment provides a finished product installation type classification system based on typical structural features on the basis of any one of the embodiment 1 to embodiment 4, which is used for executing the finished product installation type classification method based on the typical structural features;
The analysis and extraction unit is used for analyzing and extracting structured descriptive contents according to the acquired STG model;
the primary classification unit constructs a finished product installation classification rule base according to the structured description content, and primarily classifies finished products according to the acquired finished product model image to obtain a first classification result;
the attribute classification unit is used for classifying the primarily classified finished products according to the acquired basic attribute information of the finished products to obtain a second classification result;
the classification output unit is used for classifying according to the obtained connection relation characteristics of the finished products and the second classification result to obtain a third classification result, and judging according to the third classification result to obtain a final classification result.
The embodiment also provides electronic equipment, which comprises a memory and a processor, wherein the memory is stored with a computer program, and the method for classifying the installation types of the finished products based on the typical structural characteristics is realized when the computer program is executed on the processor.
The embodiment also provides a computer readable storage medium, wherein the computer storage medium is stored with computer instructions, and when the computer instructions are executed on the electronic equipment, the method for classifying the installation types of the finished products based on the typical structural characteristics is realized.
Other portions of this embodiment are the same as any of embodiments 1 to 4, and thus will not be described again.
The processor referred to in the embodiments of the present application may be a chip. For example, it may be a field programmable gate array (field programmable GATE ARRAY, FPGA), an Application Specific Integrated Chip (ASIC), a system on chip (SoC), a central processing unit (central processorunit, CPU), a network processor (network processor, NP), a digital signal processing circuit (DIGITALSIGNAL PROCESSOR, DSP), a microcontroller (micro controller unit, MCU), a programmable controller (programmable logic device, PLD) or other integrated chip.
The memory to which embodiments of the present application relate may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (programmableROM, PROM), an erasable programmable read-only memory (erasable PROM, EPROM), an electrically erasable programmable read-only memory (electricallyEPROM, EEPROM), or a flash memory, among others. The volatile memory may be random access memory (random aCCess memory, RAM) which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (double DATA RATE SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (ENHANCEDSDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (directrambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, apparatus and module may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described device embodiments are merely illustrative, e.g., the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules or components may be combined or integrated into another device, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physically separate, i.e., may be located in one device, or may be distributed over multiple devices. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present application may be integrated in one device, or each module may exist alone physically, or two or more modules may be integrated in one device.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more servers, data centers, etc. that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (Solid STATE DISK, SSD)), etc.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (15)
1. The method for classifying the installation types of the finished products based on the typical structural characteristics is characterized by comprising the following steps of:
step S1, analyzing and extracting to obtain structured description content according to an obtained STG model, wherein the STG model is a model which is built by taking local features of a three-dimensional model as vertexes and taking adjacent relations among the local features as edges;
S2, constructing a finished product installation classification rule base according to the structured descriptive content, and primarily classifying finished products according to the acquired finished product model image to obtain a first classification result;
s3, according to the obtained basic attribute characteristics of the finished products, invoking a semantic analysis method to classify the preliminarily classified finished products to obtain a second classification result;
and S4, classifying to obtain a third classification result according to the obtained connection relation characteristics of the finished products and the second classification result, and judging to obtain a final classification result according to the third classification result.
2. The method for classifying finished product installation types based on typical structural features according to claim 1, wherein said step S1 specifically comprises the steps of:
Step S11, according to the acquired STG model, calling a model extraction technology to acquire three-dimensional coordinate information of a finished product, and carrying out normalized display;
And step S12, extracting basic attribute information and shape data of the STG model according to the obtained STG model, analyzing to obtain structured description content, wherein the basic attribute information comprises a finished product code, a finished product name and a finished product connection relation, and the shape data is stored in an image form.
3. The method for classifying the installation types of the finished products based on the typical structural features according to claim 1, wherein in the step S2, the recognition algorithm is called to learn the shape data, and the finished products are classified primarily to obtain a first classification result.
4. The method for classifying finished product installation types based on typical structural features according to claim 1, wherein said step S4 specifically comprises the steps of:
step S41, classifying to obtain a third classification result according to the obtained connection relation characteristic of the finished product and the second classification result, wherein the connection relation characteristic comprises a connection mode and connection key materials;
And S42, judging to obtain a final classification result according to the third classification result, if the repeated result is more than 2, reserving the third classification result as the final classification result of the finished product, otherwise, taking the second classification result as the final classification result of the finished product.
5. The method for classifying a finished product installation type based on typical structural features according to claim 4, wherein said step S41 specifically comprises the steps of:
Step S411, describing the name and shape information of the obtained finished product;
Step S412, obtaining the connection relation between parts by adopting a double interference test method, and establishing an adjacent model;
Step S413, calculating a connection relation feature set matched with the finished product installation classification rule base according to the name and shape information of the finished product;
step S414, taking the matching relation as a search space to obtain a connection mode and connection key materials;
And step 415, classifying according to the connection mode and the connection key materials and combining the second classification result to obtain a third classification result.
6. The method for classifying a finished product installation type based on typical structural features according to claim 5, wherein said step S411 specifically comprises the steps of:
Step S4111, initializing a part class set;
Step S4112, obtaining the name id p of the model file corresponding to the part p;
Step S4113, judging whether the part class c p of the part p belongs to a class set, if not, calling a shape distribution algorithm to describe the shape information of the part p as a k-dimensional shape vector S p, establishing a part descriptor < id p,sp >, and adding the part p as a new part class c p to the class set;
Step S4114, if the name id p=idq,idq∈cq of the part model file, establishing a part descriptor < id q,sq>,idq as the name of the model file corresponding to the part q, and c q as the part category of the part q;
Step S4115 repeat steps S4112-S4114 until all parts are traversed.
7. The method for classifying a finished product installation type based on typical structural features according to claim 6, wherein said step S412 specifically comprises the steps of:
S4121, acquiring an assembly I from a finished product installation classification rule base, initializing an m multiplied by m dimensional adjacency matrix G, and calculating an AABB bounding box R of the part, wherein m is the number of the part in a complex product model A to be identified;
step S4122, selecting a part p' from the assembly I, and initializing a set S;
Step S4123 randomly acquiring part q from assembly I, if bounding box R p'∩Rq is not equal to Adding the part q into the set S, wherein R p' is the AABB bounding box of the part p', and R q is the AABB bounding box of the part q;
Step S4124, for the part q in the set S, calling an octree trunk interference detection algorithm to spatially interfere and detect the part p' and the part q, and if the detection result is contact or interference, the adjacent matrix G p'q =1;
step S4125 repeat steps S4122-S4124 until all parts of the assembly I are traversed.
8. The method for classifying finished product installation types based on typical structural features according to claim 7, wherein said step S413 specifically comprises the steps of:
step S4131, initializing a matched part set Com p;
step S4132, adding the part with the name of id p in the finished product model A to be identified into a matched part set Com p;
Step S4133, calculating the similarity between the shape vector S p of the part p and the shape vector S i of the part in the ith class in the part class set C;
step S4134, judging whether the similarity is larger than or equal to the shape similarity threshold according to the set shape similarity threshold, if so, adding all the parts in the ith category to the matched part set Com p.
9. The method of claim 8, wherein the formula for calculating the similarity between the shape vector S p of the part p and the shape vector S i of the part in the i-th class in the part class set C in step S4133 is:
;
Where s p represents the shape vector of part p, s q represents the shape vector of part q in the ith class, k represents the dimension of the k-dimensional shape vector of part, l j p represents the j-dimensional shape vector of part p, and l j q represents the j-dimensional shape vector of part q.
10. The method for classifying a finished product installation type based on typical structural features as set forth in claim 9, wherein said step S4134 is specifically performed according to a set shape similarity threshold valueIf the similarity sim (s p,si) is not less thanAll parts in the ith class are added to the matching part set Com p,si as the shape vector for the parts in the ith class.
11. The method for classifying the installation types of the finished products based on the typical structural features of claim 10, wherein the specific operation of the step S414 is to use the matching relationship of the parts as a search space, call Ullmann sub-graph matching algorithm to search the adjacent matrix G A of the finished product model a to be identified for sub-graph matching results with the same structure as the adjacent matrix G I of the assembly body I, and identify the connection mode and the connection key materials.
12. A final product installation type classification method based on typical structural features is characterized in that the STG model is established in the step S1, wherein a vertex adjacency graph is established firstly according to the topological relation among the acquired B-rep data geometric elements, the biggest group in the adjacency graph is searched and the geometric area corresponding to the biggest group is used as the local feature of a solid model, then the shape information of the local feature is converted into feature vectors by calling a statistical method to form a feature space, the local feature is restrained in a differential mode by adopting an unsupervised learning algorithm, and finally the STG model taking the local feature as a vertex and the adjacency relation among the local features as an edge is established.
13. A finished product installation type classification system based on typical structural features is used for executing the finished product installation type classification method based on typical structural features as set forth in claim 1, and is characterized by comprising an analysis and extraction unit, a preliminary classification unit, an attribute classification unit and a classification output unit;
The analysis and extraction unit is used for analyzing and extracting structured descriptive contents according to the acquired STG model;
the primary classification unit constructs a finished product installation classification rule base according to the structured description content, and primarily classifies finished products according to the acquired finished product model image to obtain a first classification result;
the attribute classification unit is used for classifying the primarily classified finished products according to the acquired basic attribute information of the finished products to obtain a second classification result;
the classification output unit is used for classifying according to the obtained connection relation characteristics of the finished products and the second classification result to obtain a third classification result, and judging according to the third classification result to obtain a final classification result.
14. An electronic device comprising a memory and a processor, wherein the memory has a computer program stored thereon, and wherein the computer program, when executed on the processor, implements the method of classifying a type of finished product installation based on typical structural features as claimed in any one of claims 1 to 12.
15. A computer readable storage medium having stored thereon computer instructions which, when executed on an electronic device as claimed in claim 14, implement the method of classifying a finished installation type based on typical structural features as claimed in any of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510847101.0A CN120354180A (en) | 2025-06-24 | 2025-06-24 | Method, system, equipment and medium for classifying finished product installation types based on typical structural features |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510847101.0A CN120354180A (en) | 2025-06-24 | 2025-06-24 | Method, system, equipment and medium for classifying finished product installation types based on typical structural features |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120354180A true CN120354180A (en) | 2025-07-22 |
Family
ID=96406789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510847101.0A Pending CN120354180A (en) | 2025-06-24 | 2025-06-24 | Method, system, equipment and medium for classifying finished product installation types based on typical structural features |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120354180A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050078858A1 (en) * | 2003-10-10 | 2005-04-14 | The Government Of The United States Of America | Determination of feature boundaries in a digital representation of an anatomical structure |
| CN110399657A (en) * | 2019-07-09 | 2019-11-01 | 西安工业大学 | A Method of Exploring Common Structure Based on 3D Assembly Model |
| CN114972862A (en) * | 2022-05-24 | 2022-08-30 | 上海优集工业软件有限公司 | Part machining feature recognition method and device and electronic equipment |
| CN118821322A (en) * | 2024-07-26 | 2024-10-22 | 上海安托信息技术有限公司 | A three-dimensional model driven aircraft assembly process design method and system |
| CN119646729A (en) * | 2024-10-28 | 2025-03-18 | 南京航空航天大学 | Multi-information fusion processing feature recognition method and device based on graph neural network |
| CN119988365A (en) * | 2025-04-11 | 2025-05-13 | 深圳市智慧城市科技发展集团有限公司 | Quality comparison method, device and storage medium based on multi-dimensional data quality |
| CN120086925A (en) * | 2025-04-25 | 2025-06-03 | 成都飞机工业（集团）有限责任公司 | A visual analysis method, system, device and medium for assembly hole structural characteristics based on adjacency matrix |
-
2025
- 2025-06-24 CN CN202510847101.0A patent/CN120354180A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050078858A1 (en) * | 2003-10-10 | 2005-04-14 | The Government Of The United States Of America | Determination of feature boundaries in a digital representation of an anatomical structure |
| CN110399657A (en) * | 2019-07-09 | 2019-11-01 | 西安工业大学 | A Method of Exploring Common Structure Based on 3D Assembly Model |
| CN114972862A (en) * | 2022-05-24 | 2022-08-30 | 上海优集工业软件有限公司 | Part machining feature recognition method and device and electronic equipment |
| CN118821322A (en) * | 2024-07-26 | 2024-10-22 | 上海安托信息技术有限公司 | A three-dimensional model driven aircraft assembly process design method and system |
| CN119646729A (en) * | 2024-10-28 | 2025-03-18 | 南京航空航天大学 | Multi-information fusion processing feature recognition method and device based on graph neural network |
| CN119988365A (en) * | 2025-04-11 | 2025-05-13 | 深圳市智慧城市科技发展集团有限公司 | Quality comparison method, device and storage medium based on multi-dimensional data quality |
| CN120086925A (en) * | 2025-04-25 | 2025-06-03 | 成都飞机工业（集团）有限责任公司 | A visual analysis method, system, device and medium for assembly hole structural characteristics based on adjacency matrix |
Non-Patent Citations (2)
| Title |
|---|
| BIAO WANG 等: "A Topology-Preserving Simplification Method for 3D Building Models", 《INTERNATIONAL JOURNAL OF GEO-INFORMATION》, vol. 10, no. 06, 20 June 2021 (2021-06-20), pages 1 - 23 * |
| 石晓璘: "基于本体的装配精度建模与优化技术研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, no. 2025, 15 April 2025 (2025-04-15), pages 029 - 83 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112990010B (en) | Point cloud data processing method, device, computer equipment and storage medium | |
| CN107066559B (en) | Three-dimensional model retrieval method based on deep learning | |
| US20220222852A1 (en) | Methods and systems for generating end-to-end model to estimate 3-dimensional(3-d) pose of object | |
| CN110941871A (en) | An automatic labeling method and system based on room information in Revit 3D model | |
| CN107273294B (en) | Repetitive code detection method based on neural network language model | |
| CN111340100B (en) | Similarity calculation method of BIM model | |
| US7761265B2 (en) | Method for comparing solid models | |
| Mewada et al. | Automatic room information retrieval and classification from floor plan using linear regression model | |
| CN111914480A (en) | Intelligent processing characteristic identification method based on point cloud semantic segmentation | |
| CN113537324B (en) | House type space matching method and device based on thin geometric plane spline interpolation | |
| CN113282215A (en) | UI element picking method and system based on target detection technology in RPA system | |
| Perez-Gallardo et al. | GEODIM: a semantic model-based system for 3D recognition of industrial scenes | |
| CN111783561A (en) | Method for revising drawing review results, electronic equipment and related products | |
| CN111680346B (en) | House type diagram complement method and device, computer readable storage medium and electronic equipment | |
| CN117710243A (en) | Point cloud denoising method and device, electronic equipment and readable storage medium | |
| CN114239802B (en) | Graph neural network method, device and equipment for keeping similarity transformation invariance | |
| CN113705616B (en) | Model construction method, software defect prediction method, device and electronic device | |
| Jain et al. | 3D object recognition: Representation and matching | |
| CN120354180A (en) | Method, system, equipment and medium for classifying finished product installation types based on typical structural features | |
| CN118397614A (en) | A method and system for identifying automobile parts based on point cloud technology | |
| CN113688700A (en) | Real domain three-dimensional point cloud object identification algorithm based on layered attention sampling strategy | |
| CN110110010A (en) | Data processing method and device | |
| CN111522570A (en) | Target library updating method and device, electronic equipment and machine-readable storage medium | |
| CN118799850A (en) | Base station equipment identification method, device, equipment and medium | |
| CN117149710A (en) | A three-dimensional model retrieval method, device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |