A method, equipment, medium, and product for reliability allocation of reusable aerospace equipment.

Abstract

This application discloses a method, device, medium, and product for reliability allocation of reusable aerospace equipment, relating to the field of reliability allocation for reusable aerospace equipment. The method includes: acquiring the failure rate and service life rollback data of each subsystem; determining the reliability function of the reusable aerospace equipment based on the failure rate and service life rollback data of each subsystem; constructing a multi-objective optimization model based on reusable operation and maintenance costs; determining the designer preference structure model using an artificial neural network based on a Pareto boundary designer preference framework; optimizing the multi-objective optimization model with the reliability allocation value of the highest preference value output by the designer preference structure model as the objective function, thereby obtaining a reliability allocation scheme for the reusable aerospace equipment. This application can improve the reliability and efficiency of reusable aerospace equipment.

Description

Technical Field

[0001] This application relates to the field of reliability allocation for reusable aerospace equipment, and in particular to a method, device, medium, and product for reliability allocation of reusable aerospace equipment. Background Technology

[0002] In recent years, the aerospace industry has flourished, continuously setting new records for innovative development with its outstanding achievements. Compared with traditional single-use spacecraft, reusable aerospace equipment has advantages such as reusability, reduced costs, increased efficiency, and promotion of aerospace technology innovation. However, reusable aerospace equipment is characterized by high performance, high value, small batch size, complex structure, and harsh operating environment. Therefore, the rational allocation of reliability has always been a crucial issue in the design and development of reusable aerospace equipment.

[0003] From a design perspective, the design of reusable space equipment must prioritize cost-effectiveness. This means that economic constraints must be fully considered during the design process to ensure that reusable space equipment can significantly reduce costs, shorten delivery cycles, and decrease reliance on production capacity through a sufficient number of reuses. This requires addressing the reuse challenges and life-cycle maintenance management challenges of reusable space equipment during the design phase. To meet these new challenges, reusable space equipment technology cannot be simply viewed as a combination of disposable launch vehicle engine technology and reusable engine technology. Similarly, it cannot be merely a simple improvement upon existing design methods and systems. Instead, a completely new design philosophy is needed to build the design of reusable space equipment from the ground up. In conclusion, there is an urgent need for a reliability allocation method for reusable space equipment to cope with increasingly complex equipment designs and improve the accuracy and efficiency of reliability allocation. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium, and product for reliability allocation of reusable aerospace equipment, which can improve the reliability and efficiency of reusable aerospace equipment.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] In a first aspect, this application provides a reliability allocation method for reusable aerospace equipment, the reusable aerospace equipment reliability allocation method comprising:

[0007] Reusable space equipment is divided into multiple subsystems;

[0008] Acquire failure rate and service age rollback data for each subsystem;

[0009] The reliability function of reusable space equipment is determined based on the failure rate of each subsystem and the service life rollback data.

[0010] A multi-objective optimization model is constructed based on the reliability function of reusable aerospace equipment and the maintenance cost of reusability.

[0011] The Pareto boundary-based designer preference framework utilizes an artificial neural network to determine the designer preference structure model; this model is used to output the reliability assignment value for each subsystem that takes into account the designer's preferences.

[0012] Using the reliability allocation value with the highest preference value output by the designer's preference structure model as the objective function, a multi-objective optimization model is optimized to obtain a reliability allocation scheme for reusable aerospace equipment. The reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

[0013] Optionally, obtaining the failure rate and service life rollback data for each subsystem specifically includes:

[0014] Accelerated experiments were conducted on key components of each subsystem, and formulas were used. Determine the service age regression data for the i-th subsystem when it is reused for the Tth time. Among them, a i Let a be the structural parameter of the i-th subsystem. i T is the structural parameter of the i-th subsystem when it is reused for the Tth time, and e is the natural logarithm.

[0015] Optionally, the step of determining the reliability function of reusable space equipment based on the failure rate of each subsystem and service life rollback data specifically includes:

[0016] Using formula Determine the reliability function for reusable aerospace equipment;

[0017] Where R(T) represents the reliability of reusable aerospace equipment after being used T times. This assigns an initial reliability value to the i-th subsystem, where Tn is the number of reuses and n is the number of subsystems. This is the service life regression data for the i-th subsystem when it is reused for the Tth time.

[0018] Optionally, the step of constructing a multi-objective optimization model based on the reliability function of reusable aerospace equipment and the cost of reusable operation and maintenance specifically includes:

[0019] Using formula Determine the objective function of the multi-objective optimization model;

[0020] Using formula Determine the constraints of the multi-objective optimization model;

[0021] Among them, C d For costs related to the maintenance process; C m For the total life-cycle maintenance costs, C m For total life-cycle maintenance costs, C s C represents the total life-cycle maintenance costs, R represents the reusable maintenance costs, and C represents the reusable operation and maintenance costs. u C is the minimum reliability allowed for reusable space equipment. o C represents the maximum maintainability-related costs over the entire product lifecycle. i Let be the reusable maintenance cost of the i-th subsystem.

[0022] Optionally, a designer preference framework based on Pareto boundaries utilizes artificial neural networks to determine a designer preference structure model, specifically including:

[0023] Using formula Determine the weight vector space Λ for n iterations n The weights are used to characterize the reliability allocation values.

[0024] in, and Let ω represent the weights ω of the i-th subsystem after n iterations. i The upper and lower bounds are given by ω, where ω is the input weight vector.

[0025] Optionally, using the reliability allocation value with the highest preference value output by the designer's preferred structural model as the objective function, a multi-objective optimization model is optimized to obtain a reliability allocation scheme for reusable aerospace equipment, specifically including:

[0026] Using formula The objective function is to determine the reliability assignment value of the highest preference value output by the designer preference structure model; where ANN(ω) represents the preference structure when the input weight vector is ω, calculated using the designer preference structure model.

[0027] The NSGA-II algorithm is used for multi-objective optimization model optimization.

[0028] Secondly, this application provides a reliability allocation device for reusable aerospace equipment, the reusable aerospace equipment reliability allocation device comprising:

[0029] The partitioning module is used to divide reusable space equipment into multiple subsystems;

[0030] The data acquisition module is used to acquire the failure rate and service life regression data of each subsystem;

[0031] The reliability function determination module is used to determine the reliability function of reusable aerospace equipment based on the failure rate of each subsystem and service life rollback data.

[0032] The multi-objective optimization model construction module is used to construct a multi-objective optimization model based on the reliability function of reusable aerospace equipment and the reusability maintenance cost;

[0033] The designer preference structure model determination module is used to determine the designer preference structure model based on the Pareto boundary framework and using an artificial neural network; the designer preference structure model is used to output the reliability allocation value of each subsystem considering the designer preferences.

[0034] The reliability allocation scheme determination module is used to optimize a multi-objective optimization model with the reliability allocation value with the highest preference value output by the designer's preference structure model as the objective function, and obtain a reliability allocation scheme for reusable aerospace equipment. The reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

[0035] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the reusable aerospace equipment reliability allocation method described above.

[0036] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method for allocating reliability of reusable aerospace equipment.

[0037] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method for allocating reliability of reusable aerospace equipment.

[0038] According to the specific embodiments provided in this application, this application has the following technical effects:

[0039] This application provides a method, device, medium, and product for reliability allocation of reusable aerospace equipment. First, it collects failure rate and service life rollback data for reusable aerospace equipment subsystems, establishes a multi-objective optimization model considering aerospace engine maintenance costs and reliability, then uses an artificial neural network based on a Pareto boundary-based designer preference framework to determine the designer preference structure model. Finally, it optimizes the multi-objective optimization model using the reliability allocation value with the highest preference value output from the designer preference structure model as the objective function, obtaining a reliability allocation scheme for reusable aerospace equipment. This application can handle the uncertainty in reliability assessment of reusable aerospace equipment, provides a decision-making tool for reliability allocation, effectively solves the multi-objective allocation of reliability indicators for reusable aerospace equipment, maximizes the reliability of reusable aerospace equipment, and improves the economic benefits of reusable aerospace equipment. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic flowchart of a reliability allocation method for reusable aerospace equipment according to an embodiment of this application;

[0042] Figure 2 This is a schematic diagram of a reusable aerospace equipment structure in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram illustrating the multi-objective optimization iterative generation of Pareto optimal solutions in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of a neural network framework based on designer preferences in an embodiment of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0047] In one exemplary embodiment, such as Figure 1 As shown, a reliability allocation method for reusable aerospace equipment is provided, which includes the following steps S101 to S106. Wherein:

[0048] S101 divides reusable space equipment into multiple subsystems;

[0049] S102, obtain the failure rate and service age rollback data for each subsystem;

[0050] Accelerated experiments were conducted on key components of each subsystem, and formulas were used. Determine the service age regression data for the i-th subsystem when it is reused for the Tth time. Among them, a i Let a be the structural parameter of the i-th subsystem. i T is the structural parameter of the i-th subsystem when it is reused for the Tth time, and e is the natural logarithm.

[0051] As service time increases and the number of maintenance operations rises, maintenance has less and less effect on reducing the service life of the equipment, exhibiting signs of repair fatigue.

[0052] like Figure 2 As shown, this embodiment uses a reusable aerospace engine structure that includes a two-stage subsystem. With a design baseline of 10 reuses, accelerated testing was conducted to obtain failure rate and service life rollback data for the thrust chamber, turbopump, gas generator, and starter.

[0053] S103, determine the reliability function of reusable space equipment based on the failure rate of each subsystem and service life rollback data;

[0054] This application assumes that the rollback increment changes exponentially. By fusing service life rollback data and failure rate (service life factor), a comprehensive system reliability model can be constructed. This system reliability model not only covers the inherent reliability of the system but also considers the reliability state after maintenance.

[0055]

[0056] Among them, D f Let be the failure threshold of the subsystem, and φ be the cumulative distribution function of the standard normal distribution. The diffusion coefficient is... The drift coefficient, Let T be the service life regression data of the i-th subsystem when it is reused for the Tth time, where T is the number of reuses.

[0057] S103 specifically includes:

[0058] Using formula Determine the reliability function for reusable space equipment;

[0059] Where R(T) represents the reliability of reusable aerospace equipment after being used T times. This assigns an initial reliability value to the i-th subsystem, where Tn is the number of reuses and n is the number of subsystems. This is the service life regression data for the i-th subsystem when it is reused for the Tth time.

[0060] Table 1 shows the failure rate, weight, service life rollback data, and operation and maintenance cost assessment results for each subsystem. The weight ω for each subsystem is... i (i = 1, 2, 3, 4), randomly generated, and The data on service age regression increases with the number of reuses T, exhibiting an exponential distribution.

[0061] Table 1

[0062]

[0063]

[0064] S104, a multi-objective optimization model is constructed based on the reliability function of reusable aerospace equipment and the reusable operation and maintenance cost;

[0065] In the reliability allocation of reusable aerospace equipment, both the system reliability model and the operation and maintenance cost model are related to the weights allocated to each subsystem in the initial state. Therefore, this application establishes a mathematical model that comprehensively considers the reliability and operation and maintenance costs of multi-stage reusable aerospace equipment systems to make trade-offs. The mathematical model is as follows:

[0066]

[0067] Where x is the decision vector, f1(x) is the weight vector of the subsystem, f2(x) are the two objective functions of the reliability of the reusable aerospace engine and the operation and maintenance cost, respectively; g1(x) and g2(x) are the constraints of the reliability of the reusable aerospace equipment and the operation and maintenance cost, respectively.

[0068] Mathematical function of operation and maintenance costs related to the entire life cycle of reusable aerospace equipment:

[0069]

[0070] Among them, C d For costs related to the maintenance process; C m C is the total life-cycle maintenance cost; mi The total lifecycle maintenance cost of the i-th maintenance unit; C 1iC represents the total lifecycle restorative repair cost of the i-th repair unit; 2i The system downtime loss caused by the failure of the i-th maintenance unit: C ui C represents the unit time cost of restorative repair for the i-th repair unit; ii C represents the loss due to product downtime per unit of time; s Costs related to maintenance throughout the entire life cycle.

[0071] Furthermore, the objective function describing the reliability and maintenance cost of reusable aerospace equipment systems can be derived as follows:

[0072]

[0073] Constraints of the multi-objective optimization model:

[0074]

[0075] Among them, C d For costs related to the maintenance process; C m For the total life-cycle maintenance costs, C m For total life-cycle maintenance costs, C s C represents the total life-cycle maintenance costs, R represents the reusable maintenance costs, and C represents the reusable operation and maintenance costs. u C is the minimum reliability allowed for reusable space equipment. o C represents the maximum maintainability-related costs over the entire product lifecycle. i Let be the reusable maintenance cost of the i-th subsystem.

[0076] S105, a designer preference framework based on Pareto boundaries, using an artificial neural network to determine a designer preference structure model; the designer preference structure model is used to output the reliability allocation value of each subsystem considering designer preferences; the designer preference structure model obtains the weights of relevant subsystems in the online decision-making stage;

[0077] The designer uses the offline training phase of the preference structure model and the preference scoring interaction to collect training datasets, and uses the proximal policy optimization method to train the agent and optimize the neural network parameters.

[0078] S105 specifically includes:

[0079] Construct a weight vector [ω1,ω2,...,ω] m ] as the model parameter vector;

[0080] Using formula Determine the weight vector space Λ for n iterations n The weights are used to characterize the reliability allocation values.

[0081] in, and Let ω represent the weights ω of the i-th subsystem after n iterations. i The upper and lower bounds, where ω is the input weight vector. make

[0082] S106, using the reliability allocation value with the highest preference value output by the designer's preferred structural model as the objective function, optimize the multi-objective optimization model to obtain a reliability allocation scheme for reusable aerospace equipment; the reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

[0083] S106 specifically includes:

[0084] Using formula The objective function is to determine the reliability assignment value of the highest preference value output by the designer preference structure model; where ANN(ω) represents the preference structure when the input weight vector is ω, calculated using the designer preference structure model.

[0085] In the weight vector space, K weight vectors are randomly generated. If T > 1, the first weight vector is replaced with the best weight vector ω obtained in the previous iteration. T-1 Optimal weight vector ω T-1 The Pareto solutions were obtained by solving the optimization problem using the designer's preferred structural model, and some of the generated Pareto solutions are shown in Table 2.

[0086] Table 2

[0087]

[0088] The designer preference structure model takes the model parameter vector as input and the designer's preference information expressed on representative samples at the Pareto boundary as the expected output. An artificial neural network is used to build the designer preference structure model. Then, using the Pareto solution obtained through iteration as the training set, the weight vector as input, and the corresponding preference value as the expected output, a feedforward neural network is trained to obtain the designer preference structure model. The structure diagram of the designer preference structure model is shown below. Figure 4 As shown, the input layer contains four neurons, the output layer has one neuron, and the hidden layers have ten neurons. With a training set containing four input neurons and one output neuron, this artificial neural network is generally considered a structurally simple and high-performing model.

[0089] The NSGA-II algorithm is used for multi-objective optimization model optimization.

[0090] After clarifying the multi-objective optimization objectives and constraints, NSGA-II is used for multi-objective optimization. First, in the evaluation phase, the fitness of each individual is quantified to determine their performance in the problem domain. Next, in the selection phase, suitable parent individuals are selected from the basic population to generate the next generation based on the evaluation results. Finally, in the modification phase, the newly generated offspring individuals undergo genetic operations such as crossover and mutation to simulate the evolutionary process in nature, thereby generating a new generation of population.

[0091] Assume the initial population size is P0, the maximum number of generations is M, and the population size in generation t is P. t The elite population is P s .

[0092] Step 1: Initialize n solutions to generate an initial population P0, and set the iteration count t = 0.

[0093] Step 2: Use binary encoding and tournament selection method to choose P. t Each individual proceeds to the next step.

[0094] Step 3: Perform crossover and mutation operations on the selected individuals to generate new individuals that enter Q. t .

[0095] Step 4: Calculate P t and Q t The fitness of individuals.

[0096] Step 5: Place P t and Q t Elite individuals are stored in P s If the number of elite individuals does not exceed P at this time s If the scale is such that P is then... t and Q t The elite individuals among the remaining individuals are stored in P. s And so on, until at some point the scale exceeds P. s The maximum size. At this point, a truncation algorithm is used: first, the crowding distance of individuals in the last elite population is calculated, and then individuals with larger crowding distances are prioritized to enter P. t+1 until the size equals N.

[0097] Step 6: If t < T, then t = t + 1, go to Step 2; otherwise, set P... t+1 Individual units are output as results; the iterative process is as follows: Figure 3As shown, the generated Pareto solutions are used as the training set to train the designer preference structure model. The specific training parameters are set as follows: maximum number of iterations: 1000; target error: 0.01; learning rate: 0.01. The dataset is split into three parts: 70% as the training set, 15% as the validation set, and 15% as the test set.

[0098] The reliability allocation scheme for reusable aerospace equipment in this embodiment is shown in Table 3. The weights of the thrust chamber, turbopump, gas generator, and starter are ω. ideal = [0.42 0.21 0.29 0.18];

[0099] Table 3

[0100]

[0101] Based on the same inventive concept, this application also provides a reusable aerospace equipment reliability allocation device for implementing the reusable aerospace equipment reliability allocation method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the reusable aerospace equipment reliability allocation device provided below can be found in the limitations of the reusable aerospace equipment reliability allocation method described above, and will not be repeated here.

[0102] In one exemplary embodiment, a reusable aerospace equipment reliability allocation device is provided, comprising:

[0103] The partitioning module is used to divide reusable space equipment into multiple subsystems;

[0104] The data acquisition module is used to acquire the failure rate and service life regression data of each subsystem;

[0105] The reliability function determination module is used to determine the reliability function of reusable aerospace equipment based on the failure rate of each subsystem and service life rollback data.

[0106] The multi-objective optimization model construction module is used to construct a multi-objective optimization model based on the reliability function of reusable aerospace equipment and the reusability maintenance cost;

[0107] The designer preference structure model determination module is used to determine the designer preference structure model based on the Pareto boundary framework and using an artificial neural network; the designer preference structure model is used to output the reliability allocation value of each subsystem considering the designer preferences.

[0108] The reliability allocation scheme determination module is used to optimize a multi-objective optimization model with the reliability allocation value with the highest preference value output by the designer's preference structure model as the objective function, and obtain a reliability allocation scheme for reusable aerospace equipment. The reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

[0109] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a reliability allocation method for reusable aerospace equipment.

[0110] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0111] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0112] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0113] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0114] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0115] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0116] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for reliability allocation of reusable aerospace equipment, characterized in that, The method for allocating reliability of reusable aerospace equipment includes: Reusable space equipment is divided into multiple subsystems; Acquire failure rate and service age rollback data for each subsystem; The reliability function of reusable space equipment is determined based on the failure rate of each subsystem and the service life rollback data. A multi-objective optimization model is constructed based on the reliability function of reusable aerospace equipment and the maintenance cost of reusability. The Pareto boundary-based designer preference framework utilizes an artificial neural network to determine the designer preference structure model; this model is used to output the reliability assignment value for each subsystem that takes into account the designer's preferences. Using the reliability allocation value with the highest preference value output by the designer's preference structure model as the objective function, a multi-objective optimization model is optimized to obtain a reliability allocation scheme for reusable aerospace equipment. The reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

2. The reliability allocation method for reusable aerospace equipment according to claim 1, characterized in that, The acquisition of failure rate and service life rollback data for each subsystem specifically includes: Accelerated experiments were conducted on key components of each subsystem, and formulas were used. Determine the service age regression data for the i-th subsystem when it is reused for the Tth time. Among them, a i Let a be the structural parameter of the i-th subsystem. i T is the structural parameter of the i-th subsystem when it is reused for the Tth time, and e is the natural logarithm.

3. The reliability allocation method for reusable aerospace equipment according to claim 1, characterized in that, The reliability function for determining reusable space equipment based on the failure rate of each subsystem and service life rollback data specifically includes: Using formula Determine the reliability function for reusable space equipment; Where R(T) represents the reliability of reusable aerospace equipment after being used T times. This assigns an initial reliability value to the i-th subsystem, where Tn is the number of reuses and n is the number of subsystems. This is the service life regression data for the i-th subsystem when it is reused for the Tth time.

4. The reliability allocation method for reusable aerospace equipment according to claim 3, characterized in that, The construction of a multi-objective optimization model based on the reliability function of reusable aerospace equipment and the cost of reusable operation and maintenance specifically includes: Using formula Determine the objective function of the multi-objective optimization model; Using formula Determine the constraints of the multi-objective optimization model; Among them, C d For costs related to the maintenance process; C m For the total life-cycle maintenance costs, C m For total life-cycle maintenance costs, C s C represents the total life-cycle maintenance costs, R represents the reusable maintenance costs, and C represents the reusable operation and maintenance costs. u C is the minimum reliability allowed for reusable space equipment. o C represents the maximum maintainability-related costs over the entire product lifecycle. i Let be the reusable maintenance cost of the i-th subsystem.

5. The reliability allocation method for reusable aerospace equipment according to claim 1, characterized in that, The Pareto boundary-based designer preference framework utilizes artificial neural networks to determine the designer preference structure model, specifically including: Using formula Determine the weight vector space Λ for n iterations n The weights are used to characterize the reliability allocation values. in, and Let ω represent the weights ω of the i-th subsystem after n iterations. i The upper and lower bounds are given by ω, where ω is the input weight vector.

6. The reliability allocation method for reusable aerospace equipment according to claim 5, characterized in that, Using the reliability allocation value with the highest preference value output by the designer's preferred structural model as the objective function, a multi-objective optimization model is optimized to obtain a reliability allocation scheme for reusable aerospace equipment, specifically including: Using formula The objective function is to determine the reliability assignment value of the highest preference value output by the designer preference structure model; where ANN(ω) represents the preference structure when the input weight vector is ω, calculated using the designer preference structure model. The NSGA-II algorithm is used for multi-objective optimization model optimization.

7. A reliability allocation device for reusable aerospace equipment, characterized in that, The reusable aerospace equipment reliability allocation device includes: The partitioning module is used to divide reusable space equipment into multiple subsystems; The data acquisition module is used to acquire the failure rate and service life regression data of each subsystem; The reliability function determination module is used to determine the reliability function of reusable aerospace equipment based on the failure rate of each subsystem and service life rollback data. The multi-objective optimization model construction module is used to construct a multi-objective optimization model based on the reliability function of reusable aerospace equipment and the reusability maintenance cost; The designer preference structure model determination module is used to determine the designer preference structure model based on the Pareto boundary framework and using an artificial neural network; the designer preference structure model is used to output the reliability allocation value of each subsystem considering the designer preferences. The reliability allocation scheme determination module is used to optimize a multi-objective optimization model with the reliability allocation value with the highest preference value output by the designer's preference structure model as the objective function, and obtain a reliability allocation scheme for reusable aerospace equipment. The reliability allocation scheme includes the reliability allocation value of each subsystem, the overall reliability of the reusable aerospace equipment, and the reusable operation and maintenance cost.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the reliability allocation method for reusable aerospace equipment as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the reliability allocation method for reusable aerospace equipment as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the reliability allocation method for reusable aerospace equipment as described in any one of claims 1-6.

Images