A cluster-based skeleton process procedure planning method and system and a storage medium

Abstract

The application relates to the technical field of aircraft manufacturing, and discloses a skeleton process procedure planning method and system based on clustering and a storage medium, which comprises the following steps: constructing a skeleton part set and setting an assembly threshold and a distance threshold used for classifying skeleton parts; obtaining the centroid coordinates of each skeleton part in the skeleton part set; randomly selecting the centroid of k skeleton parts from the skeleton part set to form k clusters; distributing the skeleton parts into the k clusters to form k cluster part subsets; obtaining the centroid coordinates of each cluster part subset; calculating the contour coefficients of the skeleton parts, obtaining the skeleton part with the largest distance in the corresponding cluster part subset, and distributing the skeleton part into the cluster part subset with the smallest distance to the skeleton part, so that the classification of the skeleton parts is completed. The application classifies and groups the skeleton parts by using a clustering algorithm based on the centroid coordinates of the skeleton parts in an MBD numerical model, and solves the problems of low classification efficiency and low accuracy during skeleton process procedure planning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aircraft manufacturing, in particular to a skeleton process planning method and system based on clustering and a storage medium. BACKGROUND

[0002] A process plan is a production process document prepared by the process department according to design requirements, process technology requirements and quality requirements. The process plan not only includes process information, but also production information and quality information, which guides workers to perform specific work instructions for the actual operation of the specified assembly process, including operation instructions, processes, assembly timing, change records and other information.

[0003] The difficulty of assembling aircraft skeleton parts lies in the inability to accurately and efficiently determine the granularity of the assembled parts, i.e., the inability to effectively complete the rapid classification and grouping of skeleton part assembly. The assembly of aircraft skeleton parts is usually completed by process personnel based on experience, and due to the high degree of human intervention and inconsistent process personnel capabilities, the skeleton planning results are inaccurate. How to effectively group and assemble skeleton parts requires repeated deduction and demonstration in process design, which has been a problem for process designers and increased the workload of process designers. In some existing technologies, a similarity calculation model is used to push the process according to the part code, and the cost replacement accuracy constructed by the analytic hierarchy model fails to effectively improve the work efficiency of the process.

[0004] Therefore, in the prior art, when planning a skeleton process plan, the low classification efficiency and accuracy caused by high human intervention are technical problems. SUMMARY

[0005] The purpose of the present application is to provide a skeleton process planning method and system based on clustering and a storage medium, which solves the problem of low classification efficiency and accuracy in the prior art when planning a skeleton process plan.

[0006] The present application is implemented by the following technical solutions:

[0007] In a first aspect, a skeleton process planning method based on clustering is used to classify skeleton parts in skeleton process planning, comprising the following steps:

[0008] S01, constructing a set of skeleton parts and setting an assembly threshold and a distance threshold for classifying the skeleton parts;

[0009] S02, obtaining the centroid coordinates of each skeleton part in the set of skeleton parts;

[0010] S03, randomly selecting the centroids of k skeleton parts from the set of skeleton parts to form k clusters;

[0011] S04. Obtain the minimum distance between each skeleton part and each cluster. Based on the principle that the minimum distance is less than a distance threshold and the number of parts in the current cluster part subset is less than an assembly threshold, the skeleton parts are allocated to k clusters to form k cluster part subsets.

[0012] S05, obtaining the centroid coordinates of each cluster part subset;

[0013] S06. Calculate the silhouette coefficient of each skeleton part. When the silhouette coefficient is less than a preset value, obtain the skeleton part with the largest distance from the corresponding cluster part subset, and assign the skeleton part to the other cluster part subset with the smallest distance from it.

[0014] S07. Repeat steps S05 and S06 to complete the classification of the skeleton parts.

[0015] In order to better implement the present invention, further, the method of constructing the skeleton parts assembly includes:

[0016] Build a skeleton parts rule library based on MBD digital model data, identify skeleton parts according to the rule, and form a skeleton parts collection , n is the number of skeleton parts.

[0017] In order to better implement the present invention, further, the skeleton parts assembly threshold is set smx , the skeleton parts assembly threshold is configured so that the number of parts assembled each time is less than smx ;

[0018] Set the distance threshold for skeleton parts kmx , the skeleton part distance threshold is configured as the distance between parts is less than kmx .

[0019] In order to better implement the present invention, further, based on the MBD digital model, the digital model coordinates are analyzed to obtain the center of mass coordinates of each skeleton part.

[0020] In order to better implement the present invention, further, step S04 includes:

[0021] Calculate the i The distance from each skeleton part to the cluster , get the minimum distance dmin i ,like , cparts i The number of skeleton parts in is less than smx , put the skeleton part into the cluster part subset cparts i Among them, si For the i The coordinates of the center of mass of the skeleton parts, k i For the i The centroid coordinates of the clusters, , j A subset of cluster parts cparts i Repeat the above steps to form k cluster part subsets.

[0022] In order to better implement the present invention, further, the centroid coordinates of the cluster part subset in step S05 are .

[0023] In order to better implement the present invention, further, step S06 includes:

[0024] Calculate the silhouette factor of skeleton parts ,in, a(i) yes cparts i In, i The average distance between a skeleton part and all other skeleton parts in its cluster part subset, b(i) It is i The average distance between a skeleton part and all skeleton parts in the subset of the nearest cluster parts;

[0025] when F(i) When it is less than the preset value, get cparts i For the skeleton part with the largest distance, the Euclidean distance is used to calculate the minimum distance between the skeleton part and other cluster part subsets and assign it to the cluster part subset corresponding to the minimum distance.

[0026] In a second aspect, the present invention further provides a clustering-based skeleton process specification planning system for classifying skeleton parts using a clustering-based skeleton process specification planning method, comprising:

[0027] A skeleton parts set construction module, the skeleton parts set construction module is used to identify skeleton parts based on MBD digital model data according to a skeleton parts rule library and construct a skeleton parts set;

[0028] A skeleton parts cluster establishment module, wherein the skeleton parts cluster establishment module is used to allocate skeleton parts to various clusters to form cluster parts subsets;

[0029] The skeleton part classification module is used to reallocate the skeleton parts with the largest distance in each cluster part subset to other cluster part subsets according to the silhouette coefficient of each skeleton part.

[0030] In a third aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the cluster-based skeleton process planning method.

[0031] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0032] The present application adopts a clustering algorithm to classify and group the skeleton parts based on the centroid coordinates of the skeleton parts in the MBD model, sets a distance threshold to ensure that there is an assembly relationship between the skeleton parts allocated to the same group, thereby improving the accuracy of the classification, sets an assembly threshold to control the number of skeleton parts in each group, thereby ensuring the efficiency of the skeleton part classification and the skeleton process planning, and the efficiency of the subsequent assembly, and adopts a contour coefficient to ensure the rationality of the clustering and improve the accuracy of the classification. BRIEF DESCRIPTION OF DRAWINGS

[0033] The present application is further illustrated in combination with the following drawings and examples, and all the conceptual innovations of the present application should be regarded as the disclosed content and the protection scope of the present application.

[0034] Figure 1 The skeleton process planning method flowchart in the embodiments of the present application. DETAILED DESCRIPTION

[0035] The skeleton of an aircraft mainly includes:

[0036] The fuselage skeleton, such as fuselage frames and fuselage stringers, constitutes the main structure of the aircraft, supports the weight of the aircraft, and bears various forces during flight.

[0037] The wing skeleton, such as spars and ribs, constitutes the structure of the wing, supports the shape of the wing, and bears the aerodynamic load during flight.

[0038] The tail skeleton, such as the frames and stringers of the horizontal tail and the vertical tail, constitutes the structure of the tail, controls the flight direction and stability of the aircraft.

[0039] The landing gear skeleton, such as landing gear struts, wheels, and brakes, constitutes the landing gear system of the aircraft, enabling the aircraft to take off and land and move on the ground.

[0040] Other skeleton parts, such as engine pylons, flaps, slats, ailerons, elevators, and rudders, are various control surfaces and components on the aircraft, which play an important role in the flight performance and safety of the aircraft.

[0041] The cluster-based skeleton process planning method of the present application is used for automatic classification of skeleton parts in skeleton process planning, and through the automatic classification of skeleton parts, it is convenient to realize the automatic compilation of skeleton process planning and improve the efficiency of skeleton process planning.

[0042] In some embodiments of the present application, the skeleton process planning method based on clustering comprises the following steps: Figure 1 S01, constructing a skeleton part set and setting an assembly threshold and a distance threshold for classifying skeleton parts;

[0043] S02, obtaining the centroid coordinates of each skeleton part in the skeleton part set;

[0044] S03, randomly selecting the centroid of k skeleton parts from the skeleton part set to form k clusters;

[0045] S04, obtaining the minimum distance between each skeleton part and each cluster, and distributing the skeleton parts to the k clusters to form k cluster part subsets based on the principle that the minimum distance is less than the distance threshold and the number of parts in the current cluster part subset is less than the assembly threshold;

[0046] S05, obtaining the centroid coordinates of each cluster part subset;

[0047] S06, calculating the contour coefficient of each skeleton part, when the contour coefficient is less than a preset value, obtaining the skeleton part with the maximum distance in the corresponding cluster part subset, and distributing the skeleton part to the other cluster part subset with the minimum distance;

[0048] S07, repeating steps S05 and S06 to complete the classification of the skeleton parts.

[0049] In this embodiment, the method for constructing the skeleton part set comprises:

[0050] constructing a skeleton part rule library rule, identifying skeleton parts based on MBD model data according to rule, and forming a skeleton part set , n The number of skeleton parts.

[0051] Specifically, the skeleton part rule library rule can include frame, stringer, engine suspension, flap, slot wing, aileron, etc. skeleton parts, effectively providing support for planning according to clustering.

[0052] Further, the method for setting the skeleton part assembly threshold and the distance threshold comprises:

[0053] setting the skeleton part assembly threshold smx , the skeleton part assembly threshold is configured to be less than smx the number of parts assembled at a time;

[0054] setting the skeleton part distance threshold kmx , the skeleton part distance threshold is configured to be less than kmx the distance between parts.

[0055] In this embodiment, the distance threshold of the skeleton parts is used kmx The number of parts to be assembled is constrained, and the assembly efficiency is effectively controlled by setting the threshold between parts. kmx , ensuring the assembly relationship between parts and improving the reliability and accuracy of classification planning.

[0056] Furthermore, based on the MBD digital model, the digital model coordinates are analyzed to obtain the center of mass coordinates of each skeleton part.

[0057] Furthermore, step S04 includes:

[0058] Calculate the i The distance from each skeleton part to the cluster , get the minimum distance dmin i ,like , cparts i The number of skeleton parts in is less than smx , put the skeleton part into the cluster part subset cparts i Among them, s i For the i The coordinates of the center of mass of the skeleton parts, k i For the i The centroid coordinates of the clusters, , j A subset of cluster parts cparts i Repeat the above steps to form k cluster part subsets.

[0059] Furthermore, in step S05, i The centroid coordinates of a subset of cluster parts can be expressed as ,in, j A subset of cluster parts cparts i The number of skeleton parts, s i is the first i The coordinates of the center of mass of each skeleton part.

[0060] Furthermore, step S06 includes:

[0061] Calculate the silhouette factor of skeleton parts ,in, a(i) yes cparts i In, i The average distance between a skeleton part and all other skeleton parts in its cluster part subset, b(i) It isi average distance of the skeleton part to all skeleton parts in the nearest cluster part subset;

[0062] When F(i) is less than the preset value, obtaining cparts i The skeleton part with the maximum distance is obtained, the Euclidean distance is used to calculate the minimum distance of the skeleton part to other cluster part subsets, and the minimum distance is assigned to the cluster part subset corresponding to the minimum distance.

[0063] By using the embodiment, the classification efficiency is effectively improved, the unreasonable clustering is avoided, and the classification accuracy is improved.

[0064] The cluster-based skeleton process plan planning method of the present application will be described in detail below in conjunction with specific embodiments. It includes the following steps:

[0065] Step S101, constructing a part set, specifically constructing a skeleton part rule library, denoted as rule=(frame, beam...), identifying the skeleton parts based on the MBD model data according to the rule, and forming a skeleton part set , n is the number of skeleton parts;

[0066] Step S102, setting a skeleton part assembly threshold, specifically setting the skeleton part assembly threshold as smx , i.e., less than smx parts are assembled each time;

[0067] Step S103, setting a skeleton part distance threshold, specifically setting the skeleton part distance threshold as kmx , i.e., the distance between parts is less than kmx ;

[0068] Step S104, based on the MBD model, analyzing the model coordinates, and calculating the centroid coordinates of each skeleton part, specifically extracting the coordinates of each skeleton part according to the parts in step S101, denoted as ;

[0069] Step S105, randomly selecting k skeleton part centroid points to form k clusters, specifically randomly selecting k skeleton centroid points k ( k 1 ... k k ) to form k clusters;

[0070] Step S106, calculating the iDistance of a skeleton part to a cluster , obtaining the minimum distance dmin i , if , cparts i the number of skeleton parts in smx put the skeleton part into the cluster part subset cparts i , wherein s i is the centroid coordinate of the i th skeleton part, k i is the centroid coordinate of the i th cluster, , j is the number of skeleton parts in the cluster part subset cparts i ; repeating the above steps to form k cluster part subsets;

[0071] Step S107, the centroid coordinate of each cluster part subset is represented as ;

[0072] Step S108, calculating the contour coefficient, specifically calculating the contour coefficient according to , wherein a(i) is the cparts i , the i th skeleton part and all other skeleton parts in the cluster part subset it belongs to, i.e. the intra-cluster distance; b(i) is the average distance between the i th skeleton part and all skeleton parts in the nearest cluster part subset;

[0073] if , obtaining the skeleton part with the maximum distance in the i th cluster part subset cparts i , using the Euclidean distance to calculate the minimum distance of the skeleton part with the maximum distance to other cluster part subsets, and assigning the skeleton part with the maximum distance to the cluster corresponding to the minimum distance;

[0074] Step S109, recalculating step S107 and step S108, recalculating the centroid coordinate of the cluster part subset after reassignment, and calculating the contour coefficient until the contour coefficient is greater than a preset value, completing the classification of the skeleton parts.

[0075] On the other hand, some embodiments of the present application relate to a clustering-based skeleton process plan planning system for implementing the skeleton process plan planning method in the above embodiments, comprising:

[0076] The skeleton part set construction module is configured to identify skeleton parts and construct a skeleton part set based on MBD numerical model data according to a skeleton part rule library;

[0077] The skeleton part cluster establishment module is configured to distribute the skeleton parts into respective clusters to form cluster part subsets.

[0078] The skeleton part classification module is configured to re-distribute skeleton parts farthest away from each other in respective cluster part subsets into other cluster part subsets according to profile coefficients of the skeleton parts.

[0079] In another aspect, some embodiments of the present application relate to a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the cluster-based skeleton process planning method described above.

[0080] The above description is only the preferred embodiment of the present application, and does not limit the present application in any form. Any simple modification or equivalent change made to the above embodiment according to the technical essence of the present application falls within the scope of protection of the present application.

Claims

1. A clustering-based skeleton process planning method, characterized in that: The classification of skeleton parts used in the preparation of skeleton process regulations includes the following steps: S01. Construct a skeleton part set and set an assembly threshold and a distance threshold for classifying the skeleton parts; S02. Obtain the centroid coordinates of each skeleton part in the skeleton part set; S03, randomly selecting k centroids of skeleton parts from the skeleton parts set to form k clusters; S04. Obtain the minimum distance between each skeleton part and each cluster. Based on the principle that the minimum distance is less than a distance threshold and the number of parts in the current cluster part subset is less than an assembly threshold, the skeleton parts are allocated to k clusters to form k cluster part subsets. S05, obtaining the centroid coordinates of each cluster part subset; S06. Calculate the silhouette coefficient of each skeleton part. When the silhouette coefficient is less than a preset value, obtain the skeleton part with the largest distance from the corresponding cluster part subset, and assign the skeleton part to the other cluster part subset with the smallest distance from it. S07. Repeat steps S05 and S06 to complete the classification of the skeleton parts.

2. The clustering-based skeleton process planning method according to claim 1 is characterized in that: Methods for building a skeleton parts collection include: Build a skeleton parts rule library based on MBD digital model data, identify skeleton parts according to the rule, and form a skeleton parts collection , n is the number of skeleton parts.

3. The clustering-based skeleton process planning method according to claim 2, characterized in that: Setting the skeleton part assembly threshold smx , the skeleton parts assembly threshold is configured so that the number of parts assembled each time is less than smx ; Set the distance threshold for skeleton parts kmx , the skeleton part distance threshold is configured as the distance between parts is less than kmx .

4. The clustering-based skeleton process planning method according to claim 1, characterized in that: Based on the MBD digital model, the digital model coordinates are analyzed to obtain the center of mass coordinates of each skeleton part.

5. The clustering-based skeleton process planning method according to claim 3, characterized in that: Step S04 includes: Calculate the i The distance from each skeleton part to the cluster , get the minimum distance dmin i ,like , cparts i The number of skeleton parts in is less than smx , put the skeleton part into the cluster part subset cparts i Among them, s i For the i The coordinates of the center of mass of the skeleton parts, k i For the i The centroid coordinates of the clusters, , j Cluster part subset cparts i Repeat the above steps to form k cluster part subsets.

6. The clustering-based skeleton process planning method according to claim 5, characterized in that: The centroid coordinates of the cluster part subset in step S05 are .

7. The clustering-based skeleton process planning method according to claim 5, characterized in that: Step S06 includes: Calculate the silhouette factor of skeleton parts ,in, a(i) yes cparts i In, i The average distance between a skeleton part and all other skeleton parts in its cluster part subset, b(i) It is i The average distance between a skeleton part and all skeleton parts in the subset of the nearest cluster parts; when F(i) When it is less than the preset value, get cparts i For the skeleton part with the largest distance, the Euclidean distance is used to calculate the minimum distance between the skeleton part and other cluster part subsets and assign it to the cluster part subset corresponding to the minimum distance.

8. A clustering-based skeleton process planning system, characterized in that: Used to classify skeleton parts using the clustering-based skeleton process planning method according to any one of claims 1 to 7, comprising: A skeleton parts set building module, the skeleton parts set building module is used to identify skeleton parts and build a skeleton parts set; A skeleton parts cluster establishment module, wherein the skeleton parts cluster establishment module is used to allocate skeleton parts to various clusters to form cluster parts subsets; The skeleton part classification module is used to reallocate the skeleton parts with the largest distance in each cluster part subset to other cluster part subsets according to the silhouette coefficient of each skeleton part.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the clustering-based skeleton process procedure planning method according to any one of claims 1 to 7 is implemented.

Images