A method for identifying aircraft duct parts

Abstract

The present invention relates to the technical field of computer-aided design and discloses a method for identifying aircraft duct parts. The method comprises adopting a multi-stage screening and comparison identification method. Specifically, all aircraft parts are screened based on two aspects: part name keywords and the proportion of the sum of the curved surface areas of the parts in the surface area. The digital models of irrelevant parts are filtered to reduce the computational complexity of duct digital model recognition, and a part candidate set is obtained. In the part candidate set, a shape similarity calculation method is used to determine whether other parts assembled on each part contain a pipe sleeve part. This method can avoid the influence of the shape uncertainty of the duct part on the recognition process, thereby achieving successful duct part recognition.

Description

Technical Field

[0001] The invention relates to the technical field of computer-aided design, in particular to an aircraft duct part recognition method. Background Art

[0002] Aircraft products are often highly complex, with tens of thousands of parts. Therefore, identifying target parts is a challenging problem, particularly for duct part identification. Current duct identification methods primarily rely on keyword searches within their names. However, part naming is highly subjective and lacks standardization, making this approach incapable of achieving comprehensive results.

[0003] The patent "A Method for Calculating Similarity of 3D CAD Models Based on a Discrete Bat Algorithm (CN110334108A, Publication Date: October 15, 2019)" calculates face shape similarity based on the difference in the number of edges between each face matching pair of the source and target models. The structural similarity of face matching pairs is then calculated using the adjacency relationship between these matching pairs, thereby finding similar 3D models. However, catheter parts are flexible and their appearance and shape vary significantly depending on the body structure. Therefore, using similarity methods generally does not produce good results.

[0004] The patent "A Method for Recognizing Manufacturing Features of 3D CAD Solid Models Based on PCA and CNN (CN107463533A, Publication Date: December 12, 2017)" uses principal component analysis to reduce the dimensionality of a five-dimensional point cloud dataset of a 3D CAD solid model to be identified to two dimensions, thereby obtaining a two-dimensional point cloud dataset of the 3D CAD solid model to be identified. The data of the 3D CAD solid model to be identified is then input into a trained CNN manufacturing feature identifier, which then outputs all manufacturing features of the 3D CAD solid model based on the data. However, this method uses supervised learning, requiring a large number of 3D models as training samples and multiple iterations of tuning to achieve accurate 3D model recognition, which presents difficulties for enterprises to implement. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for identifying aircraft duct parts to solve the problem that duct parts are difficult to obtain effectively in complex aircraft structures.

[0006] The present invention is implemented through the following technical solution: a method for identifying aircraft duct parts, which adopts a multi-stage screening and comparison identification method, specifically comprising the following steps:

[0007] Step S1: traverse all the parts models of the aircraft and add the parts models containing the keyword "tube" in their names to the first-level parts collection ;

[0008] Step S2: Assemble the first-level parts according to their geometric characteristics. Further filtering will The digital models of parts that meet the requirements are added to the secondary collection ;

[0009] Step S3: Get The shape vectors of the digital models of each part and its assembly parts;

[0010] Step S4: constructing a digital model data set of the pipe sleeve part and extracting its shape vector;

[0011] Step S5, judge and Whether the assembly part digital models in which the various part digital models are connected are pipe sleeve parts, thereby realizing the identification of catheter parts.

[0012] In order to better implement the present invention, further, in step S2, the first-level part set is classified according to the geometric characteristics of the parts. The specific steps for further filtering include:

[0013] Step S21: Acquire All surface elements of the digital model of each part are divided into four types: plane, cylindrical surface, free-form surface and other surfaces;

[0014] Step S22: Count the sum of the surface areas of each type of surface in the digital model of the part, and record them as 、 、 and ,in 、 Denote the specific surface area, 、 Recorded as other surface area;

[0015] Step S23: Calculate the ratio of the specific surface area to the other surface areas , the calculation method is:

[0016] ;

[0017] Step S24: Setting the surface ratio threshold , if the part model satisfies , then add it to the secondary collection ;

[0018] Step S25, traverse Repeat steps S21 to S24 for all parts in the digital model to obtain the final .

[0019] In order to better implement the present invention, further, the step S3 obtains The specific steps for the shape vectors of the digital models of each part and its assembly parts are as follows:

[0020] Step S31: Parts digital model p , obtain the digital model of the part p A collection of assembly parts with connection relationships ,in Indicates the i Parts digital model p Digital models of connected assembly parts, , n Representation and part modeling p The number of digital models of assembly parts that have connection relationships;

[0021] Step S32: Obtaining the digital model of the part p and collection The shape information of the digital model of each assembly part in is described as a k-dimensional shape vector, which is recorded as: ,in ;

[0022] Step S33, traverse Repeat steps S31 and S32 for all parts in the digital model until the traversal is completed.

[0023] In order to better implement the present invention, further, in step S31, computer-aided interference inspection is performed to obtain the part digital model. p A digital model set of assembly parts with connection relationships .

[0024] In order to better realize the present invention, further, in step S32, by p and collection Random point sampling is performed on the surface of each assembly part digital model, and the shape distribution algorithm is used to obtain the shape information of the part digital model and its assembly part digital model.

[0025] In order to better implement the present invention, further, the specific steps of constructing the pipe sleeve part digital model data set and extracting its shape vector in step S4 are as follows:

[0026] Step S41: sorting out all types of pipe sleeve parts in the aircraft;

[0027] Step S42: Obtain the shape information of the digital model of each type of pipe sleeve parts and describe it as k dimensional shape vector, denoted as ,in , and add it to the collection GT .

[0028] In order to better implement the present invention, further, in step S42, random point sampling is performed on the surface of the digital model of each type of pipe sleeve part, and a shape distribution algorithm is used to obtain the shape information of each digital model of the pipe sleeve part.

[0029] In order to better implement the present invention, further, the step S5 determines The specific steps to determine whether the assembly part digital models in which the parts digital models are connected are the pipe sleeve parts are as follows:

[0030] Step S51: Parts digital model p , assuming Is the same as the parts digital model p Digital models of assembly parts with connection relationships, Digital model for assembly parts q The shape vector of the assembly parts is calculated q and GT Similarity of the digital model of the middle pipe sleeve part :

[0031] ;

[0032] in, , represents the shape vector of a type of pipe sleeve part digital model; for The first i The value of the dimension, for The first i The value of the dimension;

[0033] Step S52: Setting similarity threshold , assuming there is an assembly part digital model , there is also a , making , then it is considered that the part digital model p For catheter parts;

[0034] Step S53, traverse , repeat step S51-step S52 to complete the identification of all duct parts of the aircraft.

[0035] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0036] (1) In the present invention, process personnel construct a data set of pipe sleeve parts in an aircraft based on their work experience and business needs. Then, all parts in the aircraft are screened based on two aspects: the part name keywords and the proportion of the sum of the curved surface areas of the parts in the surface area. The digital models of irrelevant parts are filtered to reduce the computational complexity of duct part recognition, and a part candidate set is obtained. In the part candidate set, a shape similarity calculation method is used to determine whether other parts assembled on each part contain pipe sleeve parts. This can avoid the influence of the shape uncertainty of duct parts on the recognition process, thereby achieving successful recognition of duct parts.

[0037] (2) The technical solution proposed by the present invention is simple and feasible. It only requires statistics on simple information such as the surface area, patch area, and shape of each part. The required information can be directly extracted from 3D modeling software and can be quickly deployed and applied in aviation companies.

[0038] (3) The catheter parts identification method proposed in the present invention is universal and has good applicability to different types of aircraft. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is the overall flow chart of the present invention.

[0040] Figure 2 Schematic diagram of a digital model of a pipeline assembly in an embodiment of the present invention.

[0041] Figure 3 Schematic diagram of calculation of the proportion of the curved surface area of ​​three parts in the digital model of the embodiment of the present invention.

[0042] Figure 4 This is a schematic diagram of the digital model of the first type of pipe sleeve parts in an embodiment of the present invention.

[0043] Figure 5 This is a schematic diagram of the digital model of the second type of pipe sleeve parts in an embodiment of the present invention.

[0044] Figure 6 This is a schematic diagram of the digital model of the third type of pipe sleeve parts in an embodiment of the present invention.

[0045] Figure 7 This is a schematic diagram of the digital model of the fourth type of pipe sleeve parts in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0048] Example 1:

[0049] This embodiment provides a method for identifying aircraft duct parts, which adopts a multi-level screening and comparison identification method. Figure 1 , specifically including the following steps:

[0050] Step S1: traverse all the parts models of the aircraft and add the parts models containing the keyword "tube" in their names to the first-level parts collection ;

[0051] Step S2: The digital model of each part in the first-level part set is sorted according to the geometric characteristics of the parts (the proportion of the sum of the surface area of ​​the parts in the surface area). Further filtering will The digital models of parts that meet the requirements are added to the secondary collection ;

[0052] Step S3: Get The shape vectors of the digital models of each part and its assembly parts;

[0053] Step S4: constructing a digital model data set of the pipe sleeve part and extracting its shape vector;

[0054] Step S5, judge and Whether the assembly part digital models in which the various part digital models are connected are pipe sleeve parts, thereby realizing the identification of catheter parts.

[0055] In this embodiment, the sleeve part refers to the standard part that connects the two ends of the catheter part, which is usually used to connect the catheter part with other parts. The sleeve part and the catheter part together form Figure 2 Piping shown.

[0056] Example 2:

[0057] This embodiment is further expanded on the basis of embodiment 1. In step S2, the first-level part set is sorted according to the geometric characteristics of the parts. The specific steps for further filtering include:

[0058] Step S21: Acquire All surface elements of the digital model of each part are divided into four types: plane, cylindrical surface, free-form surface and other surfaces;

[0059] Step S22: Count the sum of the surface areas of each type of surface in the digital model of the part, and record them as 、 、 and ,in 、 Denote the specific surface area, 、 Recorded as other surface area;

[0060] Step S23: Calculate the ratio of the specific surface area to the other surface areas , the calculation method is:

[0061] ;

[0062] Step S24: Setting the surface ratio threshold =0.95, if the part model satisfies , then add it to the secondary collection ;exist Figure 3 If the last two parts involved meet the conditions, they will be added to the secondary set ;

[0063] Step S25, traverse Repeat steps S21 to S24 for each part model in the , this is the part candidate set.

[0064] In step S3, the The specific steps for the shape vectors of the digital models of each part and its assembly parts are as follows:

[0065] Step S31: A part model in p , obtain the digital model of the part p A collection of assembly parts with connection relationships ,in Indicates the i Parts digital modelp Digital models of connected assembly parts, , n Representation and part modeling p The number of digital models of assembly parts that have connection relationships;

[0066] Step S32, by digital modeling of parts p and collection Random point sampling is performed on the surface of the digital model of each assembly part, and the shape distribution algorithm is used to obtain the digital model of the part. p and collection The shape information of each assembly part model in is described as a k-dimensional shape vector, which is recorded as: ,in ;

[0067] Step S33, traverse Repeat steps S31 and S32 for all parts in the digital model until the traversal is completed.

[0068] In step S31, computer-aided interference inspection is performed to obtain the part digital model. p A digital model set of assembly parts with connection relationships .

[0069] The specific steps of constructing the pipe sleeve part digital model data set and extracting its shape vector in step S4 are as follows:

[0070] Step S41: Process personnel sort out all types of pipe sleeve parts in the aircraft according to actual conditions, referring to Figure 4 、 Figure 5 、 Figure 6 and Figure 7 There are four different types of sleeve parts;

[0071] Step S42: Random point sampling is performed on the surface of the digital model of the pipe sleeve parts of each category, and the shape distribution algorithm is used to obtain the shape information of the digital model of the pipe sleeve parts of each category, and described as k dimensional shape vector, denoted as ,in , and add it to the collection GT .

[0072] In step S5, it is judged that The specific steps to determine whether the assembly part digital models in which the parts digital models are connected are the pipe sleeve parts are as follows:

[0073] Step S51: A part model in p , assuming is with p Digital models of assembly parts with connection relationships, Digital model for assembly parts q The shape vector of the assembly parts is calculated q and GT Similarity of the digital model of the middle pipe sleeve part :

[0074] ;

[0075] in, , represents the shape vector of a type of pipe sleeve part digital model; for The first i The value of the dimension, for The first i The value of the dimension;

[0076] Step S52: Setting similarity threshold , assuming there is an assembly part digital model , there is also a , making , then it is considered that the part digital model p For conduit parts; for example, Figure 2 In the pipeline, there is an assembly part in the GT that is connected to the conduit part, and its similarity is 0.9943. If it meets the conditions, the digital model of the assembly part is the pipe sleeve part. p Identified as a conduit part.

[0077] Step S53, traverse , repeat step S51-step S52 to complete the identification of all duct parts of the aircraft.

[0078] This embodiment shows that the aircraft duct parts identification method proposed in the present invention can be used to quickly identify all duct parts in aircraft products and can achieve good results.

[0079] 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 falls within the scope of protection of the present invention.

Claims

1. A method for identifying aircraft duct parts, characterized in that: The method of multi-stage screening and control identification is adopted, which specifically includes the following steps: Step S1: traverse all the parts models of the aircraft and add the parts models containing the keyword "tube" in their names to the first-level parts collection ; Step S2: Assemble the first-level parts according to their geometric characteristics. Further filtering will The digital models of parts that meet the requirements are added to the secondary collection ; Step S3: Get The shape vectors of the digital models of each part and its assembly parts; Step S4: constructing a digital model data set of the pipe sleeve part and extracting its shape vector; Step S5, judge and Whether the assembly part digital models in which the various part digital models are connected are pipe sleeve parts, thereby realizing the identification of catheter parts.

2. The method for identifying aircraft duct parts according to claim 1, characterized in that: In step S2, the first-level part set is sorted according to the geometric characteristics of the parts. The specific steps for further filtering include: Step S21: Acquire All surface elements of the digital model of each part are divided into four types: plane, cylindrical surface, free-form surface and other surfaces; Step S22: Count the sum of the surface areas of each type of surface in the digital model of the part, and record them as 、 、 and ,in 、 Denote the specific surface area, 、 Recorded as other surface area; Step S23: Calculate the ratio of the specific surface area to the other surface areas , the calculation method is: ； Step S24: Setting the surface ratio threshold , if the part model satisfies , then add it to the secondary collection ; Step S25, traverse Repeat steps S21 to S24 for all parts in the digital model to obtain the final .

3. The method for identifying aircraft duct parts according to claim 2, characterized in that: In step S3, the The specific steps for the shape vectors of the digital models of each part and its assembly parts are as follows: Step S31: Parts digital model p , obtain the digital model of the part p A collection of assembly parts with connection relationships ,in Indicates the i Parts digital model p Digital models of connected assembly parts, , n Representation and part modeling p The number of digital models of assembly parts that have connection relationships; Step S32: Obtaining the digital model of the part p and collection The shape information of the digital model of each assembly part in is described as a k-dimensional shape vector, which is recorded as: ,in ; Step S33, traverse Repeat steps S31 and S32 for all parts in the digital model until the traversal is completed.

4. The method for identifying aircraft duct parts according to claim 3, characterized in that: In step S31, computer-aided interference inspection is performed to obtain the p A digital model set of assembly parts with connection relationships .

5. The method for identifying aircraft duct parts according to claim 3, characterized in that: In step S32, by p and collection Random point sampling is performed on the surface of each assembly part digital model, and the shape distribution algorithm is used to obtain the shape information of the part digital model and its assembly part digital model.

6. The method for identifying aircraft duct parts according to claim 3, characterized in that: The specific steps of constructing the pipe sleeve part digital model data set and extracting its shape vector in step S4 are as follows: Step S41: sorting out all types of pipe sleeve parts in the aircraft; Step S42: Obtain the shape information of the digital model of each type of pipe sleeve parts and describe it as k dimensional shape vector, denoted as ,in , and add it to the collection GT .

7. The method for identifying aircraft duct parts according to claim 6, characterized in that: In step S42, random point sampling is performed on the surface of the digital model of each type of pipe sleeve part, and a shape distribution algorithm is used to obtain the shape information of each digital model of the pipe sleeve part.

8. The method for identifying aircraft duct parts according to claim 6, characterized in that: In step S5, it is judged that The specific steps to determine whether the assembly part digital models in which the parts digital models are connected are the pipe sleeve parts are as follows: Step S51: Parts digital model p , assuming Is the same as the parts digital model p Digital models of assembly parts with connection relationships, Digital model for assembly parts q The shape vector of the assembly parts is calculated q and GT Similarity of the digital model of the middle pipe sleeve part : ； in, , represents the shape vector of a type of pipe sleeve part digital model; for The first i The value of the dimension, for The first i The value of the dimension; Step S52: Setting similarity threshold , assuming there is an assembly part digital model , there is also a , making , then it is considered that the part digital model p For catheter parts; Step S53, traverse , repeat step S51-step S52 to complete the identification of all duct parts of the aircraft.

Images