A method for generating fuselage canopy AO, electronic equipment, and computer storage medium

Abstract

The present invention belongs to the field of aircraft manufacturing technology and discloses a method for generating a fuselage canopy AO, as well as electronic equipment and a computer storage medium. The method comprises: constructing a fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library based on three-dimensional model data; using a semantic recognition algorithm to obtain assembly objects and connectors of assembly objects from the fuselage canopy AO model semantic library, and respectively constructing an assembly object library and a connector library; constructing a connection relationship library based on the fuselage canopy AO model relationship library, the assembly object library, and the connector library; obtaining the assembly sequence of assembly objects based on the assembly content in the assembly plan, and constructing an assembly object logical sequence library; traversing the assembly object logical sequence library, obtaining corresponding assembly objects from the assembly object library and corresponding connectors from the connection relationship library based on the assembly sequence of the assembly objects, and generating the fuselage canopy AO. The present invention solves the problems of low efficiency and poor accuracy in existing batch generation of fuselage canopy AO.

Description

Technical Field

[0001] The present invention belongs to the technical field of aircraft manufacturing, and in particular relates to a method for generating a fuselage canopy AO, an electronic device, and a computer storage medium. Background Art

[0002] The assembly outline (AO) is a crucial component of assembly execution during aircraft manufacturing. Traditional AO generation methods rely primarily on manual planning, which can lead to issues such as unclear process knowledge, non-intuitive generation, difficulty evaluating generated results, and low efficiency.

[0003] Fuselage canopies have the characteristics of a wide variety of assembly objects, complex assembly logic, and a strong correlation between assembly sequence and assembly objects. The existing fuselage canopy AO generation method, during the fuselage canopy AO generation process, uses the traditional logical relationship of "and" and "or", which makes it difficult to generate fuselage canopy AO in batches and efficiently. In addition, the generation process is not intuitive, the expression of process knowledge is not explicit during the generation process, and the generation results are not standardized and unified. These problems lead to low efficiency and poor accuracy of fuselage canopy AO generation. In addition, using the existing fuselage canopy AO generation method, process personnel need to spend a lot of time sorting out the logical assembly relationship of the fuselage canopy, which is prone to missing assembly objects, resulting in poor accuracy of fuselage canopy AO generation. Summary of the Invention

[0004] The object of the present invention is to provide a method for generating fuselage canopy AO, an electronic device, and a computer storage medium to solve the problems of low efficiency and poor accuracy in the existing batch generation of fuselage canopy AO.

[0005] The present invention is achieved through the following technical solutions:

[0006] A method for generating an AO of a fuselage canopy, comprising:

[0007] Constructing a fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library based on the three-dimensional model data, wherein the fuselage canopy AO model semantic library includes all assembly object information extracted from the digital model of the three-dimensional model, and the fuselage canopy AO model relationship library includes all connection relationship information between assembly objects extracted from the digital model of the three-dimensional model;

[0008] Semantic recognition algorithm is used to obtain assembly objects and connectors of assembly objects in the fuselage canopy AO model semantic library, and the assembly object library and connector library are constructed respectively.

[0009] According to the fuselage canopy AO model relationship library, assembly object library and connector library, semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly objects and construct a connection relationship library;

[0010] Obtain the assembly sequence of the assembly objects according to the assembly contents in the assembly scheme, and construct a logical sequence library of the assembly objects;

[0011] Traverse the assembly object logical sequence library, obtain the corresponding assembly object in the assembly object library according to the assembly sequence of the assembly object, obtain the corresponding connection parts in the connection relationship library, and generate the fuselage canopy AO.

[0012] In some embodiments, the fuselage canopy AO model semantic library is represented as O{O1, O2, O3...O i …O N}, where O i represents the semantic content extracted from the i-th digital model of the 3D model, N represents the number of digital models in the 3D model, and the semantic content is the assembly objects and connectors in the 3D model of the fuselage canopy. The associated semantic information of a certain semantic content is represented as A{A1,A2,A3,…A i …A M}, A i represents the i-th associated semantics, and M represents the number of associated semantics in a certain semantic content.

[0013] In some embodiments, the step of constructing a connection relationship library includes:

[0014] The assembly object library {OEn} and the connector library {REm} are analyzed by three-dimensional digital model. The fuselage canopy AO model relationship library is represented by R{ <O i ,O j >}, indicating the assembly object O i , O j There is a contact relationship in the digital-analog connection;

[0015] Combined with the fuselage canopy AO model relationship library and the results of parsing the assembly object library {OEn} and the connector library {REm}, the semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly object. <O i , O j >}, O i Get the object in {OEn}, O j Get the object in {OEn}, R k The value is taken from {REm}, which is expressed as RE{<OEi,REk,OEj>}, where OEi and OEj represent assembly objects in the assembly object library, and REk represents the corresponding connector;

[0016] A connection relationship library is constructed based on the actual connection relationship of the fuselage canopy assembly objects.

[0017] In some embodiments, the step of generating the fuselage canopy AO includes:

[0018] The assembly object corresponding to the first assembly object in the assembly object logical sequence library is obtained in the assembly object library by using semantic / lexical matching. The assembly objects corresponding to the upper and lower nodes of the assembly object are searched in the connection relationship library according to the depth-first search algorithm, and the connector corresponding to the assembly object is obtained. The assembly object, the assembly objects corresponding to the upper and lower nodes, and the connector are extracted to generate the AO corresponding to the assembly object.

[0019] According to the assembly order of the assembly objects in the assembly object logical sequence library, the assembly objects in the assembly object logical sequence library are traversed, and the AO corresponding to each assembly object is generated in sequence to obtain the fuselage canopy AO.

[0020] In some embodiments, after completing the traversal of the assembly object logical sequence library, the method further includes using a graph traversal algorithm to search for isolated nodes or missing nodes in the assembly object library and the connection relationship library, and generating a supplementary AO for the assembly objects corresponding to the isolated nodes or missing nodes, and adding the supplementary AO to the generated fuselage canopy AO.

[0021] The present invention also relates to an electronic device, comprising: a processor and a memory; the memory is used to store executable instructions of the processor, and the processor is configured to execute the above-mentioned method for generating a fuselage canopy AO by executing the executable instructions.

[0022] The present invention also relates to a computer storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a fuselage canopy AO is implemented.

[0023] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0024] The present invention constructs a fuselage cabin cover AO model semantic library and a fuselage cabin cover AO model relationship library based on three-dimensional model data, adopts a semantic recognition algorithm to obtain assembly objects and connectors of assembly objects in the fuselage cabin cover AO model semantic library, and constructs an assembly object library and a connector library respectively, adopts semantic matching logic to obtain actual connection relationships of fuselage cabin cover assembly objects according to the fuselage cabin cover AO model relationship library, the assembly object library and the connector library, constructs a connection relationship library, obtains the assembly sequence of assembly objects according to the assembly content in the assembly plan, constructs an assembly object logical sequence library, traverses the assembly object logical sequence library, obtains corresponding assembly objects in the assembly object library according to the assembly sequence of assembly objects, obtains corresponding connectors in the connection relationship library, generates fuselage cabin cover AO, realizes a clear and intuitive expression of the fuselage cabin cover AO generation process, and improves the efficiency and accuracy of batch generation of fuselage cabin cover AO.

[0025] A graph traversal algorithm is used to find isolated or missing nodes, analyze the completeness of assembly object planning, ensure that no assembly objects are missed, and ensure that the generated fuselage canopy AO contains all assembly objects. This realizes the adjustment of the fuselage canopy AO generation results, thereby further improving the accuracy of fuselage canopy AO batch generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings in the embodiments will be briefly introduced below. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 4 is a flow chart of a method for generating a fuselage canopy AO in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0029] Example 1

[0030] A method for generating fuselage canopy AO, referring to Figure 1 , including the following steps:

[0031] S1. Construct a fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library based on the three-dimensional model data.

[0032] Based on the fuselage canopy 3D model data and the existing BERT recognition algorithm and digital model analysis algorithm, a fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library are constructed; including:

[0033] The model data of the three-dimensional model is parsed and processed to obtain the three-dimensional model data, and the fuselage canopy AO model semantic library and the fuselage canopy AO model relationship library are constructed based on the three-dimensional model data.

[0034] The fuselage canopy AO model semantic library includes all assembly object information extracted from the digital model of the 3D model. The fuselage canopy AO model semantic library is used as a corpus for extracting assembly objects. The fuselage canopy AO model semantic library is represented as O{O1, O2, O3…O i …O N}, where O irepresents the semantic content extracted from the i-th digital model of the 3D model, N represents the number of digital models in the 3D model, and the semantic content is the assembly objects and connectors in the 3D model of the fuselage canopy. The associated semantic information of a certain semantic content is represented as A{A1,A2,A3,…A i …A M}, A i represents the i-th associated semantics, and M represents the number of associated semantics in a certain semantic content.

[0035] The fuselage canopy AO model relationship library includes all the connection relationship information between the assembly objects extracted from the digital model of the 3D model. The fuselage canopy AO model relationship library is used as a support library for establishing the assembly logic relationship between the assembly objects. The fuselage canopy AO model relationship library is represented as R{ <O i ,R k ,O j >}, indicating the assembly object O i With assembly object O j There is a connection relationship in the three-dimensional model, where R k Indicates the object used to connect the assembly O i With assembly object O j connector.

[0036] For example, a fuselage canopy has a fuselage canopy AO model semantic library O{canopy, explosion-proof rope..., fuselage frame...}, the fuselage canopy's associated semantic information A{name, number, quantity...}, and a fuselage canopy AO model relationship library R{<fuselage frame..., high-lock bolts..., explosion-proof rope...>, <fuselage frame..., rivets..., canopy...>, ...}.

[0037] S2. Use semantic recognition algorithm to obtain assembly objects and connectors of assembly objects in the fuselage canopy AO model semantic library, and build assembly object library and connector library respectively.

[0038] Semantic recognition algorithms such as BERT and FastTest are used to extract the assembly objects of the fuselage canopy from the semantic library of the fuselage canopy AO model, and obtain the assembly objects and the connectors of the assembly objects. An assembly object library and a connector library are constructed based on the assembly objects and the connectors of the assembly objects, respectively. The assembly object library is denoted as {OEn}, and the connector library is denoted as {REm}.

[0039] Assembly objects refer to the objects to be connected; connectors of assembly objects refer to the objects used for connection.

[0040] For example, for a fuselage canopy, according to the fuselage canopy AO model semantic library, through semantic recognition, its assembly objects {canopy, explosion-proof rope, fuselage frame} and its assembly object connectors {high-lock bolts, rivets, ...} are obtained.

[0041] S3. According to the fuselage canopy AO model relationship library, assembly object library and connector library, semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly objects, and a connection relationship library is constructed.

[0042] Parse the assembly object library {OEn} and the connector library {REm};

[0043] Combined with the fuselage canopy AO model relationship library and the results of parsing the assembly object library {OEn} and the connector library {REm}, the semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly object. <O i , O j >}, O i Get the object in {OEn}, O j Get the object in {OEn}, R k The value is taken from {REm}, which is expressed as RE{<OEi,REk,OEj>}, where OEi and OEj represent assembly objects in the assembly object library, and REk represents the corresponding connector;

[0044] A connection relationship library is constructed based on the actual connection relationship of the fuselage canopy assembly objects.

[0045] For example, for a fuselage hatch, the actual connection relationship RE of its assembly objects includes: {high-lock bolts, rivets, ...}, {<fuselage frame, high-lock bolts, explosion-proof cable>, <fuselage frame, rivets, hatch>, ...}.

[0046] S4. Obtain the assembly sequence of the assembly objects according to the assembly contents in the assembly plan, and construct a logical sequence library of the assembly objects.

[0047] Obtain the assembly content in the fuselage canopy assembly plan; based on the assembly content, use semantic understanding algorithms such as ELMo to build a logical sequence library of assembly objects, denoted as L.

[0048] For example, a fuselage canopy has an assembly object logical sequence library L{fuselage frame, canopy, explosion-proof cable, ...}.

[0049] S5. Traverse the assembly object logical sequence library, obtain the corresponding assembly object in the assembly object library according to the assembly sequence of the assembly object, obtain the corresponding connection part in the connection relationship library, and generate the fuselage canopy AO.

[0050] The assembly object corresponding to the first assembly object in the assembly object logical sequence library is obtained in the assembly object library by using semantic / lexical matching. The assembly objects corresponding to the upper and lower nodes of the assembly object are searched in the connection relationship library, and the connector corresponding to the assembly object is obtained. The assembly object, the assembly objects corresponding to the upper and lower nodes, and the connector are extracted to generate the AO corresponding to the assembly object.

[0051] According to the assembly order of the assembly objects in the assembly object logical sequence library, the assembly objects in the assembly object logical sequence library are traversed, and the AO corresponding to each assembly object is generated in sequence to obtain the fuselage canopy AO.

[0052] For example, for a fuselage canopy, its assembly object logical sequence library L{fuselage frame, canopy, explosion-proof cable...} generates three AOs in total. The first AO is for fuselage frame installation, its assembly object is the fuselage frame, and the connecting parts of the assembly object are high-lock bolts; the second AO is for canopy installation AO, its assembly object is the canopy, and the connecting parts of the assembly object are rivets; the third AO is for explosion-proof cable installation AO, its assembly object is the explosion-proof cable, and the connecting parts of the assembly object are high-lock bolts.

[0053] After traversing the assembly object logical sequence library, a graph traversal algorithm is used to find isolated or missing nodes in the assembly object library and the connection relationship library. Supplementary AOs are generated for the assembly objects corresponding to these isolated or missing nodes and added to the generated fuselage canopy AO. A separate AO is generated for each isolated or missing node.

[0054] Isolated nodes are nodes in the graph that have no relationship with surrounding nodes and are retrieved through global traversal of the graph. Missing nodes are nodes in the graph that have no AO planned.

[0055] For example, all assembly objects of a fuselage canopy have been found, and there is no missed assembly object.

[0056] A fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library are constructed based on the 3D model data. A semantic recognition algorithm is used to obtain assembly objects and connectors of assembly objects from the fuselage canopy AO model semantic library, and an assembly object library and a connector library are respectively constructed. Based on the fuselage canopy AO model relationship library, the assembly object library, and the connector library, semantic matching logic is used to obtain the actual connection relationships of the fuselage canopy assembly objects, and a connection relationship library is constructed. The assembly sequence of the assembly objects is obtained based on the assembly content in the assembly plan, and an assembly object logical sequence library is constructed. The assembly object logical sequence library is traversed, and the corresponding assembly objects are obtained from the assembly object library and the corresponding connectors are obtained from the connection relationship library based on the assembly sequence of the assembly objects, and the fuselage canopy AO is generated. This achieves a clear and intuitive expression of the fuselage canopy AO generation process, and improves the efficiency and accuracy of batch generation of fuselage canopy AO. A graph traversal algorithm is used to find isolated or missing nodes, analyze the completeness of assembly object planning, ensure that no assembly objects are missed, and ensure that the generated fuselage canopy AO contains all assembly objects. This realizes the adjustment of the fuselage canopy AO generation results, thereby further improving the accuracy of fuselage canopy AO batch generation.

[0057] The present invention also relates to an electronic device, comprising: a processor and a memory; the memory is used to store executable instructions of the processor, and the processor is configured to execute the above-mentioned method for generating a fuselage canopy AO by executing the executable instructions.

[0058] The present invention also relates to a computer storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for generating the fuselage canopy AO is implemented.

[0059] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification or equivalent change made to the above embodiment based on the technical essence of the present invention shall fall within the scope of protection of the present invention.

Claims

1. A method for generating fuselage canopy AO, characterized in that: include: Constructing a fuselage canopy AO model semantic library and a fuselage canopy AO model relationship library based on the fuselage canopy 3D model data, wherein the fuselage canopy AO model semantic library includes all assembly object information extracted from the digital model of the 3D model, and the fuselage canopy AO model relationship library includes all connection relationship information between assembly objects extracted from the digital model of the 3D model; Semantic recognition algorithm is used to obtain assembly objects and connectors of assembly objects in the fuselage canopy AO model semantic library, and the assembly object library and connector library are constructed respectively. According to the fuselage canopy AO model relationship library, assembly object library and connector library, semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly objects and construct a connection relationship library; Obtain the assembly sequence of the assembly objects according to the assembly contents in the assembly scheme, and construct a logical sequence library of the assembly objects; Traverse the assembly object logical sequence library, obtain the corresponding assembly object in the assembly object library according to the assembly sequence of the assembly object, obtain the corresponding connection part in the connection relationship library, and generate the fuselage canopy AO; The steps to construct the connection relationship library include: The assembly object library {OEn} and the connector library {REm} are analyzed by three-dimensional digital model. The fuselage canopy AO model relationship library is represented by R{ <O i ,O j >}, indicating the assembly object O i , O j There is a contact relationship in the digital-analog connection; combined with the fuselage canopy AO model relationship library and the results of the analysis of the assembly object library {OEn} and the connection library {REm}, the semantic matching logic is used to obtain the actual connection relationship of the fuselage canopy assembly object, and the R{ <O i , O j >}, O i Get the object in {OEn}, O j Get the object in {OEn}, R k The value is taken from {REm}, which is expressed as RE{<OEi,REk,OEj>}, where OEi and OEj represent assembly objects in the assembly object library, and REk represents the corresponding connector. A connection relationship library is constructed based on the actual connection relationship of the fuselage canopy assembly object. The steps to generate fuselage canopy AO include: The assembly object corresponding to the first assembly object in the assembly object logical sequence library is obtained from the assembly object library using a semantic / lexical matching method. The assembly objects corresponding to the upper and lower nodes of the assembly object are searched in the connection relationship library using a depth-first search algorithm, and the connector corresponding to the assembly object is obtained. The assembly object, the assembly objects corresponding to the upper and lower nodes, and the connector are extracted to generate the AO corresponding to the assembly object. According to the assembly order of the assembly objects in the assembly object logical sequence library, the assembly objects in the assembly object logical sequence library are traversed, and the AO corresponding to each assembly object is generated in sequence to obtain the fuselage canopy AO. After completing the traversal of the assembly object logical sequence library, the method also includes the steps of using a graph traversal algorithm to find isolated nodes or missing nodes in the assembly object library and the connection relationship library, generating a supplementary AO for the assembly objects corresponding to the isolated nodes or missing nodes, and adding the supplementary AO to the generated fuselage canopy AO.

2. The method for generating a fuselage hatch cover AO according to claim 1, characterized in that: The fuselage canopy AO model semantic library is represented as O{O1, O2, O3…O i …O N }, where O i represents the semantic content extracted from the i-th digital model of the 3D model, N represents the number of digital models in the 3D model, and the semantic content is the assembly objects and connectors in the 3D model of the fuselage canopy. The associated semantic information of a certain semantic content is represented as A{A1,A2,A3,…A i …A M }, A i represents the i-th associated semantics, and M represents the number of associated semantics in a certain semantic content.

3. An electronic device, characterized in that include: processor and memory; The memory is used to store executable instructions of the processor, and the processor is configured to execute the method for generating a fuselage canopy AO according to any one of claims 1 to 2 by executing the executable instructions.

4. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a fuselage canopy AO according to any one of claims 1 to 2 is implemented.

Images