High-loading-density aviation equipment product assembly sequence intelligent planning method

Abstract

The invention relates to an intelligent planning method for an assembly sequence of a high-loading-density aviation equipment product. The intelligent planning method solves the problems that the efficiency is low and errors are prone to occurring when the assembly sequence is manually formulated. Comprising the following steps: Step 1: establishing an extraction method and a standardized expression method of three types of object information of parts, an assembly process and assembly constraints in a process information model, and forming an assembly process information model integrating a product structure, an assembly process, an assembly tool and the like; 2, related assembly process knowledge and resources are carded, an interference matrix, a connection matrix and a support matrix are formed to serve as input and constraint conditions of assembly sequence planning, an assembly sequence solving space is formed, an assembly sequence planning mathematical model is finally formed, and an assembly sequence candidate set is generated; step 3, carrying out the construction of an assembly sequence evaluation index; designing an assembly sequence evaluation index calculation mode, constructing an assembly sequence evaluation index calculation method, establishing a multi-criterion assembly sequence optimization method, and supporting acquisition of an optimal assembly sequence.

Description

Technical Field

[0001] The present invention relates to an intelligent planning method for assembly sequence of aviation equipment products with high packing density, belonging to the technical field of overall assembly of aviation equipment products. Background Art

[0002] The formulation of assembly sequence is the premise and basis for assembly. The assemblability, assembly cost and assembly quality of the product are all affected by the quality of the assembly sequence. At present, the formulation of product assembly sequence is mainly completed manually, usually relying on the professional knowledge and experience of process personnel to formulate the assembly sequence. Aviation equipment products have the characteristics of large size, complex shape, large number of parts and connectors, so that the assembly sequence of their products shows a combinatorial explosive growth as the number of parts increases. At this time, the manual formulation of assembly sequence is inefficient, which will lead to the extension of product production cycle and increase in cost; secondly, different personnel have different evaluation criteria for assembly sequence, which makes it difficult to ensure standardization and consistency of manual formulation of assembly sequence, causing difficulties for subsequent actual assembly. Therefore, the manual formulation of assembly sequence is difficult to apply to the assembly process design of complex aviation equipment products, and an automated assembly sequence formulation solution is urgently needed.

[0003] The formulation of assembly sequence should be based on the given design scheme, taking into account the constraints such as assembly environment and assembly process, satisfying all geometric constraints and shortening assembly time and reducing assembly complexity as much as possible, so as to find a reasonable and feasible assembly sequence, thereby reducing assembly cost and optimizing product performance. Through the current research and analysis, there are several difficulties in the formulation of assembly sequence: First, the representation of assembly model, which needs to intuitively and comprehensively express part information, matching information and process information; second, there are few evaluation indicators for assembly sequence, and assembly sequence should not only meet the most basic geometric feasibility, but also further evaluate the feasible assembly sequence from other aspects, and finally obtain a feasible and optimized assembly sequence; third, the generation of assembly sequence, as the number of product parts increases and the structure becomes more and more complex, it is very difficult to generate assembly sequence manually, which is prone to errors and cannot obtain the best assembly sequence, so it is necessary to find a more efficient and accurate way to generate assembly sequence. Summary of the invention

[0004] The present invention provides an intelligent planning method for assembly sequence of high-packing-density aviation equipment products, thereby solving the problems that the current assembly model representation is incomplete or non-intuitive, the assembly sequence evaluation indexes are few, and the manual assembly sequence formulation is inefficient and error-prone.

[0005] In response to technical problems such as long manual sequence planning cycle, low accuracy, high cost, and poor assembly quality, we have developed assembly information extraction and representation technology for assembly sequences, assembly sequence evaluation index construction, solution and optimization technology, and assembly sequence solution technology based on intelligent algorithms. The focus is on solving the problems of incomplete or non-intuitive assembly model representation, few assembly sequence evaluation indicators, and low efficiency and error-prone manual assembly sequence formulation.

[0006] The present invention is achieved by the following technical solutions:

[0007] An intelligent planning method for assembly sequence of high-packing density aviation equipment products comprises the following steps:

[0008] Step 1: Assembly information extraction and representation: Considering the assembly process decomposition and model hierarchy of complex products, the information demand analysis of assembly sequence planning is carried out, and the extraction method and standardized expression method of the three types of object information in the process information model are established: parts, assembly process, and assembly constraints. The product assembly information representation framework is established using the association graph model to form an assembly process information model that integrates product structure, assembly process, and assembly tools, providing an information source for product assembly sequence planning;

[0009] Step 2: Solving assembly sequence based on intelligent algorithm: Sort out relevant assembly process knowledge and resources, form interference matrix, connection matrix and support matrix as input and constraint conditions of assembly sequence planning, clarify the basic conditions that a feasible assembly sequence needs to meet, and form assembly sequence solution space. In the sequence solution space, factors such as product assembly stability and assembly aggregation are used as evaluation indicators, and constraint parameters and calculation methods of the objective function are given. Maximizing the target benefit is used as the solution goal of the assembly sequence planning problem, and finally a mathematical model of assembly sequence planning is formed. A heuristic algorithm is selected to generate and optimize a feasible assembly sequence according to the corresponding fitness function and evaluation indicators, and finally a candidate set of assembly sequences is generated;

[0010] Step 3: Construction, calculation and optimization of evaluation indicators: Analyze the product structure and assembly process characteristics of aviation equipment, and start from the two levels of key parts and assembly to construct assembly sequence evaluation indicators; design the calculation method of assembly sequence evaluation indicators, and construct the calculation method of assembly sequence evaluation indicators to support the evaluation of assembly sequences; based on assembly sequence evaluation indicators, establish a multi-criteria assembly sequence optimization method to support the acquisition of the best assembly sequence.

[0011] Furthermore, the specific steps of Step 1 are:

[0012] 1) Create the assembly process information model of the product: First, establish the part information model of the product, including part quality, symmetry, fit clearance, connection type and other information. Secondly, establish the assembly process information and assembly resource information. The assembly process information includes the number of assembly direction changes of each part, assembly tool type, assembly tool transformation times, parts assembly priority relationship, assembly action and other information. This type of information is stored in the form of a matrix to facilitate the input of the solution algorithm. Finally, establish the assembly constraint information model between parts, including fixed constraints, coincidence constraints, offset constraints, fixed connection constraints, surface contact, straight line contact, contact constraints and angle constraints. Map various types of constraints to corresponding values ​​and store them in the form of a matrix.

[0013] 2) Extract assembly information: For assemblies, the inherent information of the model includes two aspects: one is the part information, including part name, part geometry, part quality, etc.; the other is the assembly information between parts, including the matching relationship, etc. The depth-first traversal algorithm is used to obtain relevant information for the UG model assembly tree;

[0014] 3) Characterizing assembly information: The part information involved in the complex product assembly process design process is combined with the assembly information, and mapped to a directed graph framework to form an assembly relationship graph model. The graph model is used to express the positioning relationship information, assembly resource information, and assembly operation information of the assembly object. For assembly a, its corresponding descriptor G a It can be expressed as:

[0015] G a =(V a , E a )

[0016] Where:

[0017] V a ——A set of descriptor vertices, and V a = {v a1 , v a2 , …, v an}, where n is the number of vertices;

[0018] E a ——A set of descriptor edges, and E a ={e a1 , e a2 ,…,e am}, where m is the number of edges;

[0019] Furthermore, the specific steps of Step 2 are:

[0020] 1) Build a relationship matrix

[0021] Constructing interference matrix: The simulation assembly method of human-computer interaction means that the assembly is fixed in three-dimensional space, and the posture does not change. The active parts are controlled by the user through step length and posture transformation operations, including translation and rotation, so that the active parts constantly change their posture during the disassembly process. In the process of changing posture, real-time collision detection is performed with other parts, interference information is recorded, and the interference matrix is ​​obtained;

[0022] Construct the connectivity matrix:

[0023] Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model;

[0024] Step 2: Set the static interference inspection order of the parts, do not inspect the inspected parts again, assign values ​​based on the original inspection results, and perform clearance analysis on the uninspected parts;

[0025] Step 3: Determine whether the gap Dc between the parts is greater than 0. If Dc>0, it is determined that the two parts have no connection relationship and go to step 5. Otherwise, go to step 4.

[0026] Step 4: According to the part properties, determine whether the parts are in a stable connection relationship. If so, go to step 5. Otherwise, determine that the two parts are in a contact connection relationship, and go to step 5.

[0027] Step 5: Determine whether all parts have been inspected. If so, output the connection matrix. Otherwise, go to step 2.

[0028] Construct the support matrix:

[0029] Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model;

[0030] Step 2: Select the support direction and set the step length;

[0031] Step 3: Set the static interference inspection order of the parts and perform clearance analysis on the parts;

[0032] Step 4: Determine whether the parts interfere with each other. If there is no interference between the two parts, it is determined that there is no support relationship between the parts, and the support matrix elements between the parts are assigned a value of 0;

[0033] Step 5: When the motion step length is set, implement the step-by-step interference test;

[0034] Step 6: Determine whether the normal vector of the contact surface between part i and part j is consistent with the direction of gravity. If the two directions are consistent, it is determined that part i has a stable connection relationship with part j, s ij =1, otherwise s ij =0;

[0035] Step 7: Determine whether all parts have been identified. If so, output the support matrix. Otherwise, go to step 3.

[0036] 2) Constructing mathematical models

[0037] For an assembly consisting of n parts, A = {c1, c2, ..., c n}, in order to obtain its reasonable assembly sequence set S = {s1, s2, ..., s n The key to} is the following two points:

[0038] a. The assembly sequence is geometrically feasible. Geometric feasibility is a strong constraint on the assembly sequence. Only when the assembly sequence is geometrically feasible can it be optimized based on the target constraints.

[0039] b. Assembly sequence optimization: Assembly sequence optimization is a series of indicators that form an objective function or fitness function. When a feasible sequence makes the fitness function optimal, the sequence is considered to be a reasonable assembly sequence.

[0040] 3) Design intelligent algorithms

[0041] 4) Assembly sequence planning process based on DPSO algorithm

[0042] The specific steps of the discrete particle swarm algorithm applied to the assembly sequence planning problem are as follows:

[0043] Step 1: Input interference matrix, connection matrix, support matrix, and assembly tool set;

[0044] Step 2: Set the population size n size , inertia weight w and learning factors c1, c2; set the maximum number of iterations G max The initial iteration step number is t = 1. The velocity vector V and the position vector X are randomly generated in the initial population;

[0045] Step 3: Calculate the fitness function value of each assembly sequence. For each assembly sequence in a certain iteration process, if the comprehensive evaluation function value of the current assembly sequence is better than the individual historical optimal assembly sequence P i If it is excellent, the current assembly sequence is used as the new individual historical optimal solution and the original assembly sequence is updated;

[0046] Step 4: Compare all individual historical optimal assembly sequences P i The fitness function value of the optimal assembly sequence P is selected i As the global optimal assembly sequence P g ;

[0047] Step 5: Update the position and speed of each assembly sequence;

[0048] Step 6: Evaluate the fitness function value of the updated assembly sequence. If the comprehensive evaluation function value of the existing assembly sequence is better, use the current assembly sequence to update the individual historical optimal assembly sequence P i , otherwise it will not be updated.

[0049] Step 7: Compare all current assembly sequences P i , and take the optimal assembly sequence as the global optimal assembly sequence P g ;

[0050] Step 8: Update the number of iterations t = t + 1, if t ≤ G max , then go to step 3 and repeat the operation, otherwise, go to step 9 and repeat the operation;

[0051] Step 9: Output the optimal assembly sequence P g And the fitness function value f, the optimal assembly sequence obtained by DPSO search is the reasonable assembly sequence.

[0052] Furthermore, the specific steps of Step 3 are:

[0053] 1) Constructing evaluation indicators

[0054] The factors affecting the processability of assembly are analyzed. Starting from the two levels of key parts and assembly, the assembly sequence evaluation index is constructed. 12 assembly sequence evaluation indexes are described, which are divided into two categories: part-level evaluation index and assembly-level evaluation index. The index code is U i Indicated by, where superscript i is the index number, for part-level evaluation index, the independent attribute value of each part under the part-level index is expressed as Indicates, i represents the index number, k is the part number in the sequence;

[0055] 2) Assembly sequence optimization guided by evaluation index

[0056] According to the available reasonable assembly and part parameters, the part-level assembly sequence evaluation index and the assembly-level sequence evaluation index are calculated respectively. Finally, the weight matrix W = (w1, w2, ... w 12 ) and each index membership matrix F = (f 1 , f 2 , …f 12 ) T The comprehensive evaluation value of each reasonable assembly sequence is calculated by multiplying the product of , so as to select the best assembly sequence.

[0057] The present invention is an intelligent assembly sequence planning method proposed to address the problems of complex assembly process, difficult assembly path planning, high rework rate, and high cycle risk in highly integrated systems of aviation equipment products. It can effectively avoid technical problems such as on-site rework caused by many product parts and insufficient experience of process personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of the parts information requirement of the present invention;

[0059] Figure 2 It is a schematic diagram of the assembly depth-first traversal flow chart of the present invention;

[0060] Figure 3 It is a flow chart of the connection matrix generation algorithm of the present invention;

[0061] Figure 4 is a flow chart of the support matrix generation algorithm of the present invention;

[0062] Figure 5 It is the flow chart of DPSO algorithm of the present invention;

[0063] Figure 6 is the assembly sequence evaluation index of the present invention;

[0064] Figure 7 It is a flow chart of comprehensive evaluation of assembly sequence of the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention is further described in detail below through the accompanying drawings and implementation examples.

[0066] Implementation process:

[0067] 1) Create an assembly process information model for the product: First, establish a part information model for the product, including information such as part quality, symmetry, fit clearance, connection type, etc. Secondly, establish assembly process information and assembly resource information. Assembly process information includes the number of assembly direction changes for each part, assembly tool type, number of assembly tool changes, parts assembly priority relationship, assembly actions, etc. This type of information is stored in a matrix form to facilitate the input of the solution algorithm. Finally, establish an assembly constraint information model between parts, including fixed constraints, coincident constraints, offset constraints, fixed connection constraints, surface contact, straight line contact, contact constraints, and angle constraints. Map various types of constraints to corresponding values ​​and store them in a matrix form (attached Figure 1 ).

[0068] 2) Extract assembly information: For assemblies, the inherent information of the model includes two aspects: one is the part information, such as part name, part geometry, part quality, etc.; the other is the assembly information between parts, such as the matching relationship, etc. The depth-first traversal algorithm is used to obtain relevant information on the UG model assembly tree (see Appendix). Figure 2 ).

[0069] 3) Characterizing assembly information: The part information involved in the complex product assembly process design process is combined with the assembly information, and mapped to a directed graph framework to form an assembly relationship graph model. The graph model is used to express the positioning relationship information, assembly resource information, and assembly operation information of the assembly object. For assembly a, its corresponding descriptor G a It can be expressed as:

[0070] G a =(V a , E a )

[0071] Where:

[0072] V a ——A set of descriptor vertices, and V a = {v a1 , v a2 , …, v an}, where n is the number of vertices;

[0073] E a ——A set of descriptor edges, and E a ={e a1 , e a2 ,…,e am}, where m is the number of edges;

[0074] 4) Build a relationship matrix

[0075] Constructing interference matrix: The simulation assembly method of human-computer interaction means that the assembly is fixed in three-dimensional space and its posture does not change. The active parts are controlled by the user through step length and posture transformation operations, such as translation and rotation, so that the active parts constantly change their posture during the disassembly process. In the process of changing posture, real-time collision detection is performed with other parts, interference information is recorded, and the interference matrix is ​​obtained.

[0076] Construct the connectivity matrix:

[0077] Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model;

[0078] Step 2: Set the static interference inspection order of the parts, do not inspect the inspected parts again, assign values ​​based on the original inspection results, and perform clearance analysis on the uninspected parts;

[0079] Step 3: Determine whether the gap Dc between the parts is greater than 0. If Dc>0, it is determined that the two parts have no connection relationship and go to step 5. Otherwise, go to step 4.

[0080] Step 4: According to the part properties, determine whether the parts are in a stable connection relationship. If so, go to step 5. Otherwise, determine that the two parts are in a contact connection relationship, and go to step 5.

[0081] Step 5: Determine whether all parts have been inspected. If so, output the connection matrix; otherwise, go to step 2.

[0082] The specific process of the algorithm is as follows Figure 3 shown.

[0083] Construct the support matrix:

[0084] Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model;

[0085] Step 2: Select the support direction and set the step length;

[0086] Step 3: Set the static interference inspection order of the parts and perform clearance analysis on the parts;

[0087] Step 4: Determine whether the parts interfere with each other. If there is no interference between the two parts, it is determined that there is no support relationship between the parts, and the support matrix elements between the parts are assigned a value of 0;

[0088] Step 5: When the motion step length is set, implement the step-by-step interference test;

[0089] Step 6: Determine whether the normal vector of the contact surface between part i and part j is consistent with the direction of gravity. If the two directions are consistent, it is determined that part i has a stable connection relationship with part j, s ij =1, otherwise s ij =0;

[0090] Step 7: Determine whether all parts have been identified. If so, output the support matrix. Otherwise, go to step 3.

[0091] The specific process of the algorithm is as follows Figure 4 shown.

[0092] 5) Constructing mathematical models

[0093] For an assembly consisting of n parts, A = {c1c2, ..., c n}, in order to obtain its reasonable assembly sequence set S = {s1, s2, ..., s n The key to} is the following two points:

[0094] The assembly sequence is geometrically feasible. Geometric feasibility is a strong constraint on the assembly sequence. Only when the assembly sequence is geometrically feasible, it is meaningful to optimize the target constraints.

[0095] Assembly sequence optimization. Assembly sequence optimization is a series of indicators that constitute the objective function or fitness function. When the feasible sequence makes the fitness function optimal, the sequence is considered to be a reasonable assembly sequence.

[0096] 6) Design intelligent algorithms

[0097] 7) Assembly sequence planning process based on DPSO algorithm (Appendix Figure 5 )

[0098] The specific steps of the discrete particle swarm algorithm applied to the assembly sequence planning problem are as follows:

[0099] Step 1: Input interference matrix, connection matrix, support matrix, and assembly toolset.

[0100] Step 2: Set the population size n size , inertia weight w and learning factors c1, c2; set the maximum number of iterations G max The initial iteration step number t = 1. The velocity vector V and the position vector X are randomly generated in the initial population.

[0101] Step 3: Calculate the fitness function value of each assembly sequence. For each assembly sequence in a certain iteration process, if the comprehensive evaluation function value of the current assembly sequence is better than the individual historical optimal assembly sequence P i If it is excellent, the current assembly sequence is used as the new individual historical optimal solution and the original assembly sequence is updated.

[0102] Step 4: Compare all individual historical optimal assembly sequences P i The fitness function value of the optimal assembly sequence P is selected i As the global optimal assembly sequence P g .

[0103] Step 5: Update the position and speed of each assembly sequence.

[0104] Step 6: Evaluate the fitness function value of the updated assembly sequence. If the comprehensive evaluation function value of the existing assembly sequence is better, use the current assembly sequence to update the individual historical optimal assembly sequence P i , otherwise it will not be updated.

[0105] Step 7: Compare all current assembly sequences P i , and take the optimal assembly sequence as the global optimal assembly sequence P g .

[0106] Step 8: Update the number of iterations t = t + 1, if t ≤ G max , then go to step 3 and repeat the operation; otherwise, go to step 9 and repeat the operation.

[0107] Step 9: Output the optimal assembly sequence Pg And the fitness function value f, the optimal assembly sequence obtained by DPSO search is the reasonable assembly sequence.

[0108] 8) Construct evaluation indicators (attached Figure 6 )

[0109] The factors affecting the processability of assembly are analyzed. Starting from the two levels of key parts and assembly, the assembly sequence evaluation index is constructed. 12 assembly sequence evaluation indexes are described, which are divided into two categories: part-level evaluation index and assembly-level evaluation index. The index code is U i Indicated by, where superscript i is the index number, for part-level evaluation index, the independent attribute value of each part under the part-level index is expressed as Indicates, i represents the index number, and k is the part number in the sequence).

[0110] 9) Assembly sequence optimization guided by evaluation index (Appendix Figure 7 )

[0111] According to the available reasonable assembly and part parameters, the part-level assembly sequence evaluation index and the assembly-level sequence evaluation index are calculated respectively. Finally, the weight matrix W = (w1, w2, ... w 12 ) and each index membership matrix F = (f 1 , f 2 , …f 12 ) T The comprehensive evaluation value of each reasonable assembly sequence is calculated by multiplying the product of , so as to select the best assembly sequence.

[0112] Through the above steps, intelligent planning of the assembly sequence of the assembly can be achieved.

Claims

1. An intelligent planning method for assembly sequence of high-packing density aviation equipment products, characterized by: The following steps are involved: Step 1: Assembly information extraction and representation: Considering the assembly process decomposition and model hierarchy of complex products, the information demand analysis of assembly sequence planning is carried out, and the extraction method and standardized expression method of the three types of object information in the process information model are established: parts, assembly process, and assembly constraints. The product assembly information representation framework is established using the association graph model to form an assembly process information model that integrates product structure, assembly process, and assembly tools, providing an information source for product assembly sequence planning; Step 2: Solving assembly sequence based on intelligent algorithm: Sort out relevant assembly process knowledge and resources, form interference matrix, connection matrix and support matrix as input and constraint conditions of assembly sequence planning, clarify the basic conditions that a feasible assembly sequence needs to meet, and form assembly sequence solution space. In the sequence solution space, factors such as product assembly stability and assembly aggregation are used as evaluation indicators, and constraint parameters and calculation methods of the objective function are given. Maximizing the target benefit is used as the solution goal of the assembly sequence planning problem, and finally a mathematical model of assembly sequence planning is formed. A heuristic algorithm is selected to generate and optimize a feasible assembly sequence according to the corresponding fitness function and evaluation indicators, and finally a candidate set of assembly sequences is generated; Step 3: Construction, calculation and optimization of evaluation indicators: Analyze the product structure and assembly process characteristics of aviation equipment, and start from the two levels of key parts and assembly to construct assembly sequence evaluation indicators; design the calculation method of assembly sequence evaluation indicators, and construct the calculation method of assembly sequence evaluation indicators to support the evaluation of assembly sequences; based on assembly sequence evaluation indicators, establish a multi-criteria assembly sequence optimization method to support the acquisition of the best assembly sequence.

2. According to claim 1, a method for intelligent planning of assembly sequence of high-packing density aviation equipment products is characterized by: The specific steps of Step 1 are: 1) Create the assembly process information model of the product: First, establish the part information model of the product, including part quality, symmetry, fit clearance, connection type and other information. Secondly, establish the assembly process information and assembly resource information. The assembly process information includes the number of assembly direction changes of each part, assembly tool type, assembly tool transformation times, parts assembly priority relationship, assembly action and other information. This type of information is stored in the form of a matrix to facilitate the input of the solution algorithm. Finally, establish the assembly constraint information model between parts, including fixed constraints, coincidence constraints, offset constraints, fixed connection constraints, surface contact, straight line contact, contact constraints and angle constraints. Map various types of constraints to corresponding values ​​and store them in the form of a matrix. 2) Extract assembly information: For assemblies, the inherent information of the model includes two aspects: one is the part information, including part name, part geometry, part quality, etc.; the other is the assembly information between parts, including the matching relationship, etc. The depth-first traversal algorithm is used to obtain relevant information for the UG model assembly tree; 3) Characterizing assembly information: The part information involved in the complex product assembly process design process is combined with the assembly information, and mapped to a directed graph framework to form an assembly relationship graph model. The graph model is used to express the positioning relationship information, assembly resource information, and assembly operation information of the assembly object. For assembly a, its corresponding descriptor G a It can be expressed as: G a =(V a ,E a ) Where: V a ——A set of descriptor vertices, and V a = {v a1 , v a2 , …, v an }, where n is the number of vertices; E a ——A set of descriptor edges, and E a ={e a1 , e a2 ,…,e am }, where m is the number of edges.

3. According to claim 1, a method for intelligent planning of assembly sequence of high-packing density aviation equipment products is characterized by: The specific steps of Step 2 are: 1) Build a relationship matrix Constructing interference matrix: The simulation assembly method of human-computer interaction means that the assembly is fixed in three-dimensional space, and the posture does not change. The active parts are controlled by the user through step length and posture transformation operations, including translation and rotation, so that the active parts constantly change their posture during the disassembly process. In the process of changing posture, real-time collision detection is performed with other parts, interference information is recorded, and the interference matrix is ​​obtained; Construct the connectivity matrix: Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model; Step 2: Set the static interference inspection order of the parts, do not inspect the inspected parts again, assign values ​​based on the original inspection results, and perform clearance analysis on the uninspected parts; Step 3: Determine whether the gap Dc between the parts is greater than 0. If Dc>0, it is determined that the two parts have no connection relationship and go to step 5. Otherwise, go to step 4. Step 4: According to the part properties, determine whether the parts are in a stable connection relationship. If so, go to step 5. Otherwise, determine that the two parts are in a contact connection relationship, and go to step 5. Step 5: Determine whether all parts have been inspected. If so, output the connection matrix. Otherwise, go to step 2. Construct the support matrix: Step 1: Obtain the overall 3D model information of the product assembly and record the 3D geometric information of each part in the model; Step 2: Select the support direction and set the step length; Step 3: Set the static interference inspection order of the parts and perform clearance analysis on the parts; Step 4: Determine whether the parts interfere with each other. If there is no interference between the two parts, it is determined that there is no support relationship between the parts, and the support matrix elements between the parts are assigned a value of 0; Step 5: When the motion step length is set, implement the step-by-step interference test; Step 6: Determine whether the normal vector of the contact surface between part i and part j is consistent with the direction of gravity. If the two directions are consistent, it is determined that part i has a stable connection relationship with part j, s ij =1, otherwise S ij =0; Step 7: Determine whether all parts have been identified. If so, output the support matrix. Otherwise, go to step 3. 2) Constructing mathematical models For an assembly consisting of n parts, A = {c1, c2, ..., c n }, in order to obtain its reasonable assembly sequence set S = {s1, s2, ..., s n The key to} is the following two points: a. The assembly sequence is geometrically feasible. Geometric feasibility is a strong constraint on the assembly sequence. Only when the assembly sequence is geometrically feasible can it be optimized based on the target constraints. b. Assembly sequence optimization: Assembly sequence optimization is a series of indicators that form an objective function or fitness function. When a feasible sequence makes the fitness function optimal, the sequence is considered to be a reasonable assembly sequence. 3) Design intelligent algorithms 4) Assembly sequence planning process based on DPSO algorithm The specific steps of the discrete particle swarm algorithm applied to the assembly sequence planning problem are as follows: Step 1: Input interference matrix, connection matrix, support matrix, and assembly tool set; Step 2: Set the population size n size , inertia weight w and learning factors c1, c2; set the maximum number of iterations C max The initial iteration step number is t = 1. The velocity vector V and the position vector X are randomly generated in the initial population; Step 3: Calculate the fitness function value of each assembly sequence. For each assembly sequence in a certain iteration process, if the comprehensive evaluation function value of the current assembly sequence is better than the individual historical optimal assembly sequence P i If it is excellent, the current assembly sequence is used as the new individual historical optimal solution and the original assembly sequence is updated; Step 4: Compare all individual historical optimal assembly sequences P i The fitness function value of the optimal assembly sequence P is selected i As the global optimal assembly sequence P g ; Step 5: Update the position and speed of each assembly sequence; Step 6: Evaluate the fitness function value of the updated assembly sequence. If the comprehensive evaluation function value of the existing assembly sequence is better, use the current assembly sequence to update the individual historical optimal assembly sequence P i , otherwise it will not be updated. Step 7: Compare all current assembly sequences P i , and take the optimal assembly sequence as the global optimal assembly sequence P g ; Step 8: Update the number of iterations t = t + 1, if t ≤ G max , then go to step 3 and repeat the operation, otherwise, go to step 9 and repeat the operation; Step 9: Output the optimal assembly sequence P g And the fitness function value f, the optimal assembly sequence obtained by DPSO search is the reasonable assembly sequence.

4. According to claim 1, a method for intelligent planning of assembly sequence of high-packing density aviation equipment products is characterized by: The specific steps of Step 3 are: 1) Constructing evaluation indicators The factors affecting the process of assembly are analyzed. Starting from the two levels of key parts and assembly, the assembly sequence evaluation index is constructed. 12 assembly sequence evaluation indexes are explained, which are divided into two categories: part-level evaluation index and assembly-level evaluation index. The index code is U i Indicated by, where superscript i is the index number, for part-level evaluation index, the independent attribute value of each part under the part-level index is expressed as Indicates, i represents the index number, k is the part number in the sequence; 2) Assembly sequence optimization guided by evaluation index According to the available reasonable assembly and part parameters, the part-level assembly sequence evaluation index and the assembly-level sequence evaluation index are calculated respectively. Finally, the weight matrix W = (w1, w2, ... w 12 ) and each index membership matrix F = (f 1 , f 2 , …f 12 ) T The comprehensive evaluation value of each reasonable assembly sequence is calculated by multiplying the product of , so as to select the best assembly sequence.

Images