Civil aircraft assembly tolerance optimization method based on improved NSGA-II framework and storage medium

Abstract

The invention discloses a civil aircraft assembly tolerance optimization method based on an improved NSGA-II framework and a storage medium. The method comprises the following steps: constructing a comprehensive cost evaluation module, and establishing a multi-target cost function; establishing a tolerance optimization model, and defining a tolerance optimization function by taking a key tolerance design index as a constraint condition and combining a reliability requirement, machining feasibility and machining cost; based on a tolerance optimization module of an improved NSGA-II framework, generating a Pareto frontier solution set through non-dominated sorting and congestion degree calculation; a filial generation generator module combining a multi-head attention mechanism and a tournament algorithm is adopted, and the generation efficiency of a Pareto leading-edge solution set is optimized; process data support is provided through the assembly process database module, and it is ensured that the tolerance optimization range does not exceed the current executable process category; iterative optimization is carried out until the design index with the lowest total cost is met, and a final tolerance allocation scheme is output. According to the method, on the premise of meeting design indexes, the total cost index is reduced as much as possible, and the benefits of assembly production are improved.

Description

Technical Field

[0001] The present invention relates to the field of aviation manufacturing, and in particular to a civil aircraft assembly tolerance optimization method based on an improved NSGA-II framework and a storage medium. Background Art

[0002] Tolerance design for civil aircraft refers to the consideration of dimensional deviations that may occur during the manufacturing and assembly of parts during the aircraft design phase. The rational allocation of tolerances is used to ensure the assembly quality and functional performance of the product. This design is closely related to the assembly quality of the final engineering product and can be categorized into the following aspects:

[0003] 1) Quality Assurance: Reasonable tolerance design scheme can ensure that products are manufactured and assembled within the specified tolerance range, thereby ensuring product quality and performance;

[0004] 2) Cost control: By optimizing tolerances, we can reduce the excessive requirements for part accuracy, lower manufacturing costs, and reduce rework and scrap caused by improper tolerances, further controlling costs;

[0005] 3) Assembly efficiency: Good tolerance design can reduce adjustment time during assembly, improve assembly efficiency, and shorten product R&D and production cycles;

[0006] 4) Problem prevention and resolution: Tolerance design can predict and reduce problems that may occur during the assembly process, such as verifying the design through simulation analysis, reducing the need for assembly tools, and enabling fast and reliable assembly and replacement.

[0007] In the aircraft manufacturing industry, because the assembly process encompasses numerous different processes and operational steps, careful consideration of the combined impact of these processes on tolerance allocation is crucial. This helps manufacturers strike a balance between economic benefits and product quality standards and make appropriate decisions. At the same time, to ensure precise fit between components and maintain the required functionality, attention to the efficiency, precision, and reliability of the assembly process cannot be ignored. In response to the unique characteristics of the aircraft assembly process, the engineering community needs to optimize tolerance design. This involves not only improving the assembly quality of intensive products but also shortening assembly cycles and reducing assembly costs. In this process, multiple cost objectives, including manufacturing costs, assembly performance, and quality loss, must be comprehensively considered to maximize cost-effectiveness. Through this multifaceted consideration and optimization, the aircraft assembly process can be driven toward higher quality and lower costs. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to overcome the above technical defects and design a civil aircraft assembly tolerance optimization method and storage medium based on an improved NSGA-II framework, which can comprehensively consider multiple cost factors such as the time, process, and product quality of the fuselage assembly, construct an optimization objective function, and establish a tolerance optimization model with key tolerance design indicators as constraint conditions to ensure that the tolerance optimization object does not exceed the scope of the currently executable process; at the same time, on the premise of meeting the design indicators, the total cost indicator is reduced as much as possible.

[0009] To solve the above technical problem, the technical solution provided by the present invention is as follows:

[0010] A civil aircraft assembly tolerance optimization method based on an improved NSGA-II framework, which includes the following steps:

[0011] (S1) Construct a comprehensive cost evaluation module and establish a multi-objective cost function based on time cost, manufacturing cost, and quality loss;

[0012] (S2) Establish a tolerance optimization model, define a tolerance optimization function with key tolerance design indicators as constraint conditions, and combine reliability requirements, processing feasibility, and processing cost;

[0013] (S3) A tolerance optimization module based on the improved NSGA-II framework generates a Pareto front solution set through non-dominated sorting and crowding degree calculation;

[0014] (S4) Adopt a child generation module that combines a multi-head attention mechanism and a tournament algorithm to optimize the generation efficiency of the Pareto front solution set;

[0015] (S5) Provide process data support through the assembly process database module to ensure that the tolerance optimization range does not exceed the scope of the currently executable process;

[0016] (S6) Iteratively optimize until the design indicator of the lowest total cost is met, and output the final tolerance allocation plan.

[0017] A further improvement of the present invention is that in the step (S1), the multi-objective cost function determines the weights of each cost objective through the analytic hierarchy process.

[0018] A further improvement of the present invention is that in the step (S3), the improved NSGA-II framework optimizes the solution selection process by introducing a multi-head attention mechanism and improves the population diversity by combining a tournament algorithm.

[0019] A further improvement of the present invention is that the assembly process database module includes a process data management function and a call function, and the process data includes tolerance limits, debugging parameters, and machining parameters.

[0020] A further improvement of the present invention lies in that, in the step (S4), the offspring generator module dynamically allocates and optimizes resources through a multi-head attention mechanism, and screens high-quality solutions through a tournament algorithm.

[0021] A further improvement of the present invention lies in that, in the step (S6), the iterative optimization process updates the feasible region in real time through a process database to ensure that the solution of each iteration conforms to process constraints.

[0022] A further improvement of the present invention lies in that the tolerance optimization model is solved by a nonlinear programming method under multiple constraints, and finally outputs a Pareto optimal solution set.

[0023] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0024] The technical solution provided by the present invention has the following technical effects: This patent provides a novel tolerance optimization method based on an improved NSGA-II framework for dealing with complex civil aircraft product assembly tolerances. Compared with common tolerance optimization methods, this method can comprehensively consider multiple cost factors such as the time, process, and product quality of fuselage assembly, construct an optimization objective function, and establish a tolerance optimization model with key tolerance design indicators as constraint conditions and the content of the process database as the optimization feasible region to ensure that the tolerance optimization object does not exceed the scope of the currently executable process; at the same time, on the premise of meeting the design indicators, the total cost index is reduced as much as possible, improving the efficiency of assembly production.

[0025] The following will further illustrate the concept, specific structure and technical effects generated by the present invention with reference to the accompanying drawings, so as to fully understand the purpose, features and effects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is the method flow chart of NSGA-II adopted by the civil aircraft assembly tolerance optimization method;

[0027] Figure 2 is the overall design diagram of the civil aircraft assembly tolerance optimization method;

[0028] Figure 3 is the schematic diagram of the process cost library and the part database;

[0029] Figure 4 is the schematic diagram of the tolerance optimization algorithm flow;

[0030] Figure 5 is the multi-constraint tolerance optimization analysis result and software integration diagram. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The following specific examples illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0032] Combined with the attached Figure 1 、 Figure 2 As shown, the embodiment of the present invention provides a civil aircraft assembly tolerance optimization method based on an improved NSGA-II framework. Based on the technical characteristics of the aircraft assembly process, a method for analyzing and evaluating numerous processes and technologies involved in the assembly link from the perspective of comprehensive cost objectives such as time cost, manufacturing cost, and product quality loss is provided. And an assembly process information database is established as an optimization reference to ensure that the tolerance optimization range does not exceed the process scope executable by the current technology. It includes the following steps:

[0033] (S1) Construct a comprehensive cost evaluation module, and establish a multi-objective cost function based on time cost, manufacturing cost, and quality loss; the multi-objective cost function determines the weight of each cost objective through the Analytic Hierarchy Process (AHP).

[0034] (2) Establish a tolerance optimization model, use the key tolerance design index as a constraint condition, and combine the reliability requirement, machining feasibility, and machining cost to define a tolerance optimization function;

[0035] (3) The tolerance optimization module based on the improved NSGA-II framework generates the Pareto front solution set through non-dominated sorting and crowding degree calculation. The improved NSGA-II framework optimizes the solution selection process by introducing the multi-head attention mechanism (MHA) and improves the population diversity by combining the tournament algorithm. Aircraft tolerance allocation is a large-scale non-linear optimization problem with a large number of decision variables. A tolerance optimization method based on the improved NSGA-II framework is proposed for the above characteristics. The NSGA framework uses non-dominated sorting to divide the individuals in the population into different levels to identify the Pareto optimal solutions. In addition, the concept of crowding degree is introduced. By calculating the distribution density of individuals in the objective space, premature convergence to local optimal solutions is avoided. Therefore, it has been successfully applied to tolerance optimization problems in many fields such as engineering design, resource management, and economics. At the same time, improvements have been made in the solution generator based on the elitist strategy, adopting the combination of the multi-head attention mechanism (Multi-Head Attention Mechanism, MHA) and the tournament algorithm (Tournament Selection), which improves the efficiency of relevant solution generation.

[0036] (4) The offspring generator module that combines the multi-head attention mechanism (MHA) and the tournament algorithm optimizes the generation efficiency of the Pareto front solution set. The offspring generator module dynamically allocates optimization resources through the multi-head attention mechanism and screens high-quality solutions through the tournament algorithm. The offspring generator module dynamically allocates optimization resources through the multi-head attention mechanism and screens high-quality solutions through the tournament algorithm.

[0037] (5) Provide process data support through the assembly process database module to ensure that the tolerance optimization range does not exceed the current executable process scope. The assembly process database module includes a process data management function and a call function, and the process data includes tolerance limits, debugging parameters, and machining parameters.

[0038] (6) Iteratively optimize until the design index with the lowest total cost is met, and output the final tolerance allocation plan. The feasible region is updated in real time through the process database during the iterative optimization process to ensure that the solutions of each iteration meet the process constraints. The tolerance optimization model is solved by the non-linear programming method under multiple constraints, and finally the Pareto optimal solution set is output.

[0039] Such as Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 、 Figure 5As shown, the main parts of the platform for implementing the method function and the data flow design between the parts are introduced. The black part is the pre - preparation or pre - input parameters for tolerance optimization, and the red part is the data flow involved in each round of optimization iteration. The arrow direction indicates the flow direction. The following is a detailed description:

[0040] Step 1: Assemble the process database management interface attached to the analysis platform. The process library function is divided into two parts, namely the process data management function and the process data call function. The process data management function includes adding entries, modifying entries, deleting entries, sorting entries (re - ordering), querying entries, and displaying entries. The call function is mainly to input the process number or name of the data, and it can return the tolerance limit and comprehensive cost data corresponding to the process.

[0041] Step 2: Assemble the tolerance optimization task management interface attached to the analysis platform. In the initial stage of optimization, input the tolerance requirements through the platform interface, randomly extract a set of assembly process plans from the process library to form an initial population, which serves as the first set of parental solutions.

[0042] Step 3: Import the cost data of the parental solutions into the evaluation module to return the tolerance evaluation results. The tolerance algorithm screens high - quality solutions according to the evaluation results to form the first - generation offspring solutions. The situation of the first - generation offspring solutions is returned to the process database, and then the tolerance limits corresponding to each group of process plans of the first - generation offspring are passed to the deviation analysis module, and the deviation transfer situation is imported into the tolerance algorithm for secondary screening to obtain the second - generation offspring solutions. The second - generation offspring solutions serve as the parental solutions for the next round of iteration, and steps 4 - 5 are repeated.

[0043] Step 4: Convert the finally optimized data into a corresponding set of assembly process plans to ensure that the tolerance optimization object does not exceed the scope of the currently executable process; at the same time, on the premise of meeting the design indicators, the total cost indicator is reduced as much as possible, improving the efficiency of assembly production.

[0044] The above embodiments only illustrate the principle and its effects of the present invention by way of example, and are not used to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. An optimization method for civil aircraft assembly tolerance based on an improved NSGA-II framework, characterized in that Including the following steps: (S1) Construct a comprehensive cost assessment module and establish a multi-objective cost function based on time cost, manufacturing cost, and quality loss; (S2) Establish a tolerance optimization model, define a tolerance optimization function with key tolerance design indicators as constraints, combined with reliability requirements, processing feasibility, and processing cost; (S3) A tolerance optimization module based on the improved NSGA-II framework generates a Pareto front solution set through non-dominated sorting and crowding degree calculation; (S4) Adopt a child generation module that combines a multi-head attention mechanism and a tournament algorithm to optimize the generation efficiency of the Pareto front solution set; (S5) Provide process data support through the assembly process database module to ensure that the tolerance optimization range does not exceed the current executable process scope; (S6) Iteratively optimize until the design index with the lowest total cost is met, and output the final tolerance allocation scheme.

2. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, wherein In the step (S1), the multi-objective cost function determines the weights of each cost objective through the analytic hierarchy process.

3. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, characterized in that In the step (S3), the improved NSGA-II framework optimizes the solution selection process by introducing a multi-head attention mechanism and improves the population diversity by combining a tournament algorithm.

4. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, wherein The assembly process database module includes a process data management function and a call function, and the process data includes tolerance limits, debugging parameters, and machining parameters.

5. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, characterized in that In the step (S4), the child generation module dynamically allocates optimization resources through a multi-head attention mechanism and screens high-quality solutions through a tournament algorithm.

6. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, characterized in that In the step (S6), the feasible region is updated in real time through the process database during the iterative optimization process to ensure that the solutions of each iteration meet the process constraints.

7. The civil aircraft assembly tolerance optimization method based on the improved NSGA-II framework according to claim 1, characterized in that The tolerance optimization model is solved by a non-linear programming method under multiple constraints, and finally outputs a Pareto optimal solution set.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 7.

Images