A multi-objective optimization method, system, device and medium for a high-power microwave source
By employing a multi-criteria decision analysis method and a small-population evolutionary genetic algorithm, the inefficiency problem in the multi-objective optimization design of high-power microwave sources was solved. This method generated niche elite individuals that considered objective priorities, thus achieving efficient multi-objective optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2022-09-26
- Publication Date
- 2026-07-28
AI Technical Summary
Existing optimization design methods for high-power microwave sources struggle to effectively handle multiple performance indicators, resulting in low optimization efficiency. Furthermore, classical multi-objective optimization algorithms cannot adapt to the range performance characteristics of high-power microwave sources, leading to invalid solutions.
The multi-criteria decision analysis method FSAWS is adopted. Through structural parameterization and small population evolution genetic algorithms, niche elite individuals are generated. The global solution set is updated using Pareto non-dominated solution set to achieve multi-objective optimization of high-power microwave source.
It improves the efficiency and accuracy of high-power microwave source optimization, generates niche elite individuals that take into account target priorities, filters out invalid solutions, and enhances the effectiveness of the design.
Smart Images
Figure CN115544869B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of high-power microwave source multi-objective optimization technology, and specifically relates to a high-power microwave source multi-objective optimization method, system, device and medium. Background Technology
[0002] High-power microwave (HPM) sources operate based on the complex nonlinear interaction between electromagnetic fields and charged particles, and can be used to generate high-power microwaves with operating frequencies of 1–300 GHz and microwave output power greater than 100 MW.
[0003] Since the introduction of high-power microwave source devices, researchers both domestically and internationally have primarily focused on physical mechanisms, using theoretical analysis to design device structures and combining this with particle-in-cell (PIC) simulation methods for verification and optimization. In recent years, with the continuous development of high-power microwave source technology, complex device structures and new performance indicators have been constantly proposed, increasing the design difficulty of high-power microwave sources and posing new challenges to traditional high-power microwave source optimization design methods based solely on theoretical analysis and PIC numerical simulations.
[0004] In recent years, researchers have used evolutionary optimization algorithms (such as genetic algorithms and particle swarm optimization) to assist in the optimal design of high-power microwave sources, achieving some results. However, these research results mainly focus on single performance parameters such as operating frequency, output power, and beam conversion efficiency, lacking comprehensive consideration of multiple performance indicators. Therefore, in order to better and more efficiently complete the structural design of high-power microwave source devices, it is necessary to propose a multi-objective, multi-parameter optimization design method suitable for high-power microwave sources.
[0005] In optimization problems, problems involving multiple objectives are called multi-objective optimization problems. Classical multi-objective optimization algorithms include those based on mathematical concepts (such as linear weighted methods, ε-constraint methods, and sorting methods for approximating ideal solutions) and those based on swarm heuristics (such as PAES (pareto archived evolution strategy), NSGA (nondominated sorting genetic algorithm), NSGA-II, SPEA-II (strength Pareto evolutionary algorithm), and MOMPA (multi-objective marine predator algorithm)). Mathematically-based algorithms require converting multiple objectives into single-objective mathematical problems and are suitable for solving relatively simple optimization problems. Swarm heuristic evolutionary optimization algorithms, based on the concept of Pareto nondominated solutions, are suitable for solving complex optimization problems. However, when directly applied to the optimization design of high-power microwave sources, they cannot well adapt to the performance parameters of high-power microwave sources, potentially introducing a large amount of unnecessary computation and leading to a decrease in optimization efficiency.
[0006] High-power microwave sources encompass numerous performance metrics across various ranges, such as operating frequency, particle throughput, and frequency purity. The rating of these performance metrics must be based on the specific range in which they are implemented. For example, when designing a Ka-band high-power microwave source, if the target operating frequency is assumed to be 30 GHz, then during priority evaluation, a small range around 30 GHz should be considered the optimal solution for meeting the design requirements, rather than strictly limiting the target operating frequency to a specific value of 30 GHz.
[0007] Therefore, directly applying existing multi-objective optimization algorithms to the optimization design of high-power microwave sources will lead to the following drawbacks and shortcomings:
[0008] Optimization algorithms based on mathematical ideas need to transform multi-objective problems into single-objective mathematical problems. However, in the optimization design of high-power microwave sources, many device performance indicators are interval indicators, and it is impossible to specify an accurate optimal solution. Therefore, it is difficult to transform multi-objective problems into single-objective optimization problems by setting weights, setting constraints, or calculating the Minkowski distance between superior and inferior solutions.
[0009] Population-based heuristic multi-objective evolutionary optimization algorithms are all based on the concept of Pareto non-dominated solutions and population-based heuristic optimization algorithms. Since the performance indicators of high-power microwave sources include many interval indicators, directly using the classic Pareto non-dominated solution set concept may introduce a large number of invalid solutions, leading to a significant reduction in optimization efficiency. Summary of the Invention
[0010] The purpose of this invention is to provide a multi-objective optimization method, system, device, and medium for high-power microwave sources, in order to solve the problems that existing optimization design techniques for high-power microwave sources are difficult to transform multi-objective problems into single-objective optimization problems by setting weights, setting constraints, or calculating the Minkowski distance between superior and inferior solutions, and that directly using multi-objective evolutionary optimization algorithms based on the classical Pareto non-dominated solution set concept will introduce a large number of invalid solutions, resulting in low optimization efficiency.
[0011] To achieve the above objectives, the present invention adopts the following technical solution:
[0012] A multi-objective optimization method for a high-power microwave source includes:
[0013] The structure of the high-power microwave source to be optimized is parameterized to determine the range and accuracy of the structural parameters. An initial population is generated using the structural parameter information, and several sub-populations are generated from the initial population. A genetic algorithm based on FSAWS fitness evaluation is used to evolve all sub-populations to generate niche elite individuals.
[0014] Generate a niche Pareto non-dominated solution set using elite individuals from a small population evolution; update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0015] The initial population is updated using the global Pareto non-dominated solution set; the optimal Pareto non-dominated solution set is generated iteratively.
[0016] Furthermore, high-power microwave source device structure parameterization: based on the numerical model of the high-power microwave source device, structural parameters are constructed to describe the structure of the high-power microwave source device. The structural parameters to be optimized are set as variables, and the range and precision of the variables are set.
[0017] Furthermore, an initial population is generated using structural parameter information: the initial population is generated using a uniform random algorithm by utilizing the variation range and precision information of the parameters to be optimized, and floating-point gene encoding is performed on the individuals in the population.
[0018] Furthermore, several smaller populations are generated from the initial population: based on the set number of individuals in each smaller population, a random sampling method is used to extract the corresponding number of individuals from the initial population and generate several smaller populations.
[0019] Furthermore, the small population is optimized using a genetic algorithm based on FSAWS fitness evaluation: the selection, crossover, and mutation algorithms of the genetic algorithm are used to realize the evolution of the small population; the device structural parameter information contained in the individual population is used to generate a concrete numerical model of the high-power microwave source device; the concrete numerical models of all devices are numerically simulated in parallel using particle simulation software; based on the numerical simulation results and the pre-set performance index rating criteria, the fitness of individuals is evaluated using the FSAWS method, and niche elite individuals are generated in an iterative manner.
[0020] Furthermore, niche Pareto non-dominated solutions are generated using niche elite individuals obtained from small population evolution: all niche elite individuals obtained from small population evolution are compared, and niche Pareto non-dominated solutions are generated based on the concept of Pareto non-dominated solutions.
[0021] Furthermore, by comparing the aforementioned niche Pareto non-dominated solution set with the global Pareto non-dominated solution set, dominated individuals in the global Pareto non-dominated solution set are removed, while undominated individuals are retained, thus realizing the updating of the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0022] Furthermore, each individual in the global Pareto non-dominated solution set is compared with a randomly selected individual from the initial population. Dominated individuals in the initial population are removed, while non-dominated individuals are retained, thus updating the initial population.
[0023] Furthermore, several smaller populations are regenerated using the updated initial population. A genetic algorithm based on FSAWS fitness evaluation is used to evolve these smaller populations, generating new niche Pareto non-dominated solution sets. The global Pareto non-dominated solution set is then iteratively updated using the newly generated niche Pareto non-dominated solution sets to obtain the optimal Pareto non-dominated solution set.
[0024] Furthermore, a high-power microwave source multi-objective optimization system includes:
[0025] The structural parameterization module is used to perform structural parameterization on the high-power microwave source device to be optimized, and to determine the range and accuracy of the structural parameters.
[0026] The niche elite individual generation module is used to generate an initial population using structural parameter information, generate several subpopulations using the initial population, and optimize all subpopulations using a genetic algorithm based on FSAWS fitness evaluation to generate niche elite individuals.
[0027] The non-dominated solution set update module is used to generate a niche Pareto non-dominated solution set using niche elite individuals obtained from small population evolution; and to update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0028] The optimal solution generation module is used to update the initial population using the global Pareto non-dominated solution set; it generates the optimal Pareto non-dominated solution set through an iterative process.
[0029] Furthermore, a computer device includes 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 steps such as those of a multi-objective optimization method for a high-power microwave source.
[0030] Furthermore, a computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of a multi-objective optimization system for a high-power microwave source.
[0031] Compared with the prior art, the present invention has the following technical effects:
[0032] This invention utilizes the rating approach of the Multi-Criterion Decision Analysis Method (FSAWS) to classify the performance indicators of high-power microwave sources into interval indicators and trend indicators. It then uses the rating methods of objective attributes and subjective attributes in FSAWS to conduct the rating, achieving relatively simple weight settings and target rating suitable for the characteristics of high-power microwave source performance indicators, which can be used to evaluate the fitness of individuals in a population.
[0033] This invention improves the micro-genetic algorithm by transforming it into a form where multiple small populations evolve simultaneously, thereby enhancing the parallel efficiency of optimization.
[0034] This invention uses the multi-criteria decision analysis method (FSAWS) to evaluate the fitness of individuals in a population. By introducing target priority information into the small population evolution process, it can generate niche elite individuals that take target priority into account. The niche Pareto non-dominated solution set generated based on these niche elite individuals filters out invalid solutions to a certain extent, effectively improving optimization efficiency. Attached Figure Description
[0035] Figure 1 This is a detailed flowchart of the multi-objective optimization method.
[0036] Figure 2 This is a flowchart of the present invention.
[0037] Figure 3 This is a system structure diagram of the present invention.
[0038] Figure 4This is a schematic diagram of the numerical model structure parameterization of a relativistic backward wave tube device. Detailed Implementation
[0039] The present invention will be further described below with reference to the accompanying drawings:
[0040] A multi-objective optimization method for a high-power microwave source includes:
[0041] The structure of the high-power microwave source to be optimized is parameterized to determine the range and accuracy of the structural parameters.
[0042] An initial population is generated using structural parameter information. Several smaller populations are then generated from the initial population. All smaller populations are optimized using a genetic algorithm based on FSAWS fitness evaluation to generate niche elite individuals.
[0043] Generate a niche Pareto non-dominated solution set using elite individuals from a small population evolution; update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0044] The initial population is updated using the global Pareto non-dominated solution set; the optimal Pareto non-dominated solution set is generated iteratively.
[0045] High-power microwave source device structure parameterization: Based on the numerical model of the high-power microwave source device, structural parameters are constructed to describe the structure of the high-power microwave source device. The structural parameters to be optimized are set as variables, and the range and precision of the variables are set.
[0046] Initial population generated using structural parameter information: Using the variation range and precision information of the parameters to be optimized, an initial population is generated through a uniform random algorithm, and floating-point gene encoding is performed on the individuals in the population.
[0047] Several subpopulations are generated from the initial population: Based on the number of individuals in the predefined subpopulations, a random sampling method is used to extract the corresponding number of individuals from the initial population and generate several subpopulations.
[0048] A genetic algorithm based on FSAWS fitness evaluation is used to optimize small populations: The selection, crossover, and mutation algorithms of the genetic algorithm are used to achieve small population evolution; a concrete numerical model of a high-power microwave source device is generated using the device structural parameter information contained in the individual population; numerical simulations of all device concrete numerical models are performed in parallel using particle simulation software; based on the numerical simulation results and pre-defined performance index rating criteria, the fitness of individuals is evaluated using the FSAWS method, and niche elite individuals are generated iteratively.
[0049] Using niche elite individuals obtained from small population evolution to generate Pareto non-dominated solution sets: The performance parameters of devices described by all niche elite individuals obtained from small population evolution are compared, and niche Pareto non-dominated solution sets are generated based on the concept of Pareto non-dominated solution sets.
[0050] Update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set: Compare the above niche Pareto non-dominated solution set with the global Pareto non-dominated solution set, remove dominated individuals from the global Pareto non-dominated solution set, and retain non-dominated individuals, thereby updating the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0051] Update the initial population using the global Pareto non-dominated solution set: Compare each individual in the global Pareto non-dominated solution set with a randomly selected individual in the initial population, remove dominated individuals from the initial population, and retain non-dominated individuals to update the initial population.
[0052] The optimal Pareto non-dominated solution set is generated iteratively: several small populations are regenerated using the updated initial population, and a genetic algorithm based on FSAWS fitness evaluation is used to evolve these small populations, generating new niche Pareto non-dominated solution sets. The global Pareto non-dominated solution set is then continuously updated using the newly generated niche Pareto non-dominated solution sets through iteration to obtain the optimal Pareto non-dominated solution set.
[0053] Please see Figure 1 (1) Perform structural parameterization on the high-power microwave source device to be optimized;
[0054] The numerical model of the device is parameterized. Assume there are n parameters of the device to be optimized, denoted as x = {x1, x2, ..., xn}. n The parameter variation range and precision are set as shown in Table 1. Taking a high-power microwave source device in the form of a relativistic backwave tube as an example, one numerical simulation parameterization method for this device is as follows: Figure 4 As shown.
[0055] Table 1
[0056]
[0057] (2) Generate an initial population using structural parameter information;
[0058] Within the range of parameter variation, specific parameter values x are generated using a uniform random method. i ={x i1 ,x i2 ,…,x inThe structural parameters are encoded using floating-point gene coding, and the encoded individuals in the population are named Chromosomes. i ={x i1 x i2 …x in The floating-point precision is determined based on the precision of the device's structural parameters. The encoded individuals form the initial population.
[0059] (3) Use the initial population to generate several small populations.
[0060] Based on a pre-defined number M of individuals in each subpopulation, N subpopulations are randomly selected from the initial population. Each subpopulation contains M individuals.
[0061] (4) Small population evolution
[0062] Referring to genetic algorithms, selection, crossover, and mutation are used to achieve population evolution, preserving elite individuals from the original population. A concrete numerical model of a high-power microwave source device is generated using the device structural parameter information contained in the individuals. Device parameters, such as operating frequency, output power, frequency purity, energy conversion efficiency, and particle throughput, are determined as optimization targets. Numerical simulations of each device structure are performed using full electromagnetic particle simulation software to obtain the numerical simulation results for the desired specific performance indicators. The individual fitness is calculated using the FSAWS-based individual fitness evaluation method, and small-scale population evolution is achieved through iterative methods to generate niche elite individuals.
[0063] (5) Individual fitness assessment
[0064] The target weight W is determined based on the priority of the indicators. The target weight is set in five levels with reference to the FSAWS method, as shown in Table 2.
[0065] Table 2
[0066]
[0067] Based on the indicator type, interval indicators and trend indicators are rated separately. Among them, interval indicators adopt a graded evaluation method, and the indicator rating is divided into 9 levels according to FSAWS, as shown in Table 3.
[0068] Table 3
[0069]
[0070] Trend indicators can be divided into two categories: positive trend indicators and negative trend indicators. For positive trend indicators, a relatively large value is preferred, while for negative trend indicators, a relatively small value is preferred. The output power of a high-power microwave source is a positive trend indicator; the larger the relative value, the higher the rating.
[0071] Assume f o (x) is the describing function of the trend index of high-power microwave sources. f o The evaluation function (x) has p sets of results in the set to be evaluated. If the trend indicator is a positive trend indicator, the larger the value, the better. Then, the evaluation is carried out according to the FSAWS method as shown in (1) and (2):
[0072] F o (f o (x))=(f oi (x) / max(f oi (x)))×100,(i=1,2,...,p),f oi (x)>0 (1)
[0073] If the trend target is a negative trend indicator, a relatively small value is preferred:
[0074] F o (f o (x))=(min(f oi (x)) / f oi (x))×100, (i=1,2,...,p),f oi (x)>0 (2)
[0075] Based on the above objective evaluation method, the fitness of an individual can be determined as follows:
[0076]
[0077] Where W is the weight of the indicator, F s For the rating of the interval indicator, F o Rating for trend indicators.
[0078] (6) Update the global Pareto non-dominated solution set
[0079] By comparing the niche elite individuals obtained from the evolution of all small populations, a niche Pareto non-dominated solution set is generated. This solution set is then compared with the global Pareto non-dominated solution set. Dominated individuals in the global Pareto non-dominated solution set are removed, while undominated individuals are retained, thus updating the global Pareto non-dominated solution set.
[0080] (7) Initial Population Update
[0081] Each individual in the global Pareto non-dominated solution set is compared with a randomly selected individual in the initial population. Dominated individuals are removed, and non-dominated individuals are retained, thus updating the initial population.
[0082] (8) Iterative convergence process
[0083] Repeat steps (3)-(7) iteratively until the iteration is complete. The global Pareto non-dominated solution set after iterative convergence is the optimal Pareto non-dominated solution set. Finally, select the device structure that best meets the design requirements from the optimal Pareto non-dominated solution set through manual screening.
[0084] In another embodiment of the present invention, a high-power microwave source multi-objective optimization system is provided, which can be used to implement the above-mentioned high-power microwave source multi-objective optimization method. Specifically, the high-power microwave source multi-objective optimization system includes:
[0085] The structural parameterization module is used to perform structural parameterization on the high-power microwave source device to be optimized, and to determine the range and accuracy of the structural parameters.
[0086] The niche elite individual generation module is used to generate an initial population using structural parameter information, generate several subpopulations using the initial population, and optimize all subpopulations using a genetic algorithm based on FSAWS fitness evaluation to generate niche elite individuals.
[0087] The non-dominated solution set update module is used to generate a niche Pareto non-dominated solution set using niche elite individuals obtained from small population evolution; and to update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
[0088] The optimal solution generation module is used to update the initial population using the global Pareto non-dominated solution set; it generates the optimal Pareto non-dominated solution set through an iterative process.
[0089] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.
[0090] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a multi-objective optimization method for a high-power microwave source.
[0091] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the multi-objective optimization method for a high-power microwave source in the above embodiments.
[0092] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0093] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A multi-objective optimization method for a high-power microwave source, characterized in that, include: The structure of the high-power microwave source to be optimized is parameterized to determine the range and accuracy of the structural parameters. An initial population is generated using structural parameter information. Several smaller populations are then generated from the initial population. A genetic algorithm based on FSAWS fitness evaluation is used to evolve all the smaller populations, generating elite individuals for niche habitats. Generate a niche Pareto non-dominated solution set using elite individuals from a small population evolution; update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set. Update the initial population using the global Pareto non-dominated solution set; generate the optimal Pareto non-dominated solution set iteratively. Determine the target weight based on indicator priority. The target weight setting is divided into multiple levels, referencing the FSAWS method; Based on the indicator type, interval indicators and trend indicators are rated separately. Among them, interval indicators adopt a graded evaluation method, and the indicator rating is divided into multiple levels with reference to FSAWS. Trend indicators are divided into two categories: positive trend indicators and negative trend indicators. Among them, positive trend indicators are better when the value is relatively large, and negative trend indicators are better when the value is relatively small. The output power of a high-power microwave source is a positive trend indicator, and the larger the value, the higher the rating. Assumption This is a descriptive function for the trend index of high-power microwave sources. for The evaluation function, the set to be evaluated contains a total of Group results; if the trend indicator is a positive trend indicator, the larger the value, the better, and the evaluation is as shown in (1) by referring to the FSAWS method: , （1） If the trend indicator is a negative trend indicator, then a relatively small value is preferred: , , （2） Based on the above objective evaluation method, the fitness of an individual is determined as follows: （3） in, The weighting of trend indicators, Weights of interval indicators For the rating of the interval indicator, Rating for trend indicators.
2. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, High-power microwave source device structure parameterization: Based on the numerical model of the high-power microwave source device, structural parameters are constructed to describe the structure of the high-power microwave source device. The structural parameters to be optimized are set as variables, and the range and precision of the variables are set.
3. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, Initial population generated using structural parameter information: Using the variation range and precision information of the structural parameters to be optimized, an initial population is generated through a uniform random algorithm, and floating-point gene encoding is performed on the individuals in the population; Several subpopulations are generated from the initial population: Based on the number of individuals in the predefined subpopulations, a random sampling method is used to extract the corresponding number of individuals from the initial population and generate several subpopulations.
4. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, The small population is optimized using a genetic algorithm based on FSAWS fitness evaluation: the selection, crossover, and mutation algorithms of the genetic algorithm are used to generate the small population evolution; the device structural parameter information contained in the population individuals is used to generate a concrete numerical model of the high-power microwave source device; the concrete numerical models of all devices are numerically simulated in parallel using particle simulation software; based on the numerical simulation results and the pre-set performance index rating criteria, the fitness of individuals is evaluated using the FSAWS method, and niche elite individuals are generated in an iterative manner.
5. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, Using niche elite individuals obtained from small population evolution to generate niche Pareto non-dominated solution sets: The performance parameters of devices described by all niche elite individuals obtained from small population evolution are compared, and niche Pareto non-dominated solution sets are generated based on the concept of Pareto non-dominated solution sets. Update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set: Compare the above niche Pareto non-dominated solution set with the global Pareto non-dominated solution set, remove dominated individuals from the global Pareto non-dominated solution set, and retain non-dominated individuals, thereby updating the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set.
6. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, Update the initial population using the global Pareto non-dominated solution set: Compare each individual in the global Pareto non-dominated solution set with a randomly selected individual in the initial population, remove dominated individuals from the initial population, and retain non-dominated individuals to update the initial population.
7. The multi-objective optimization method for a high-power microwave source according to claim 1, characterized in that, The optimal Pareto non-dominated solution set is generated iteratively: several small populations are regenerated using the updated initial population, and a genetic algorithm based on FSAWS fitness evaluation is used to evolve the small populations, generating new niche Pareto non-dominated solution sets; the global Pareto non-dominated solution set is continuously updated using the newly generated niche Pareto non-dominated solution set through iterative methods to obtain the optimal Pareto non-dominated solution set.
8. A high-power microwave source multi-objective optimization system, characterized in that, include: The structural parameterization module is used to perform structural parameterization on the high-power microwave source device to be optimized, and to determine the range and accuracy of the structural parameters. The niche elite individual generation module is used to generate an initial population using structural parameter information, generate several subpopulations using the initial population, and optimize all subpopulations using a genetic algorithm based on FSAWS fitness evaluation to generate niche elite individuals. The non-dominated solution set update module is used to generate a niche Pareto non-dominated solution set using niche elite individuals obtained from small population evolution; and to update the global Pareto non-dominated solution set using the niche Pareto non-dominated solution set. The optimal solution generation module is used to update the initial population using the global Pareto non-dominated solution set and to generate the optimal Pareto non-dominated solution set through an iterative process. Determine the target weight based on indicator priority. The target weight setting is divided into multiple levels, referencing the FSAWS method; Based on the indicator type, interval indicators and trend indicators are rated separately. Among them, interval indicators adopt a graded evaluation method, and the indicator rating is divided into multiple levels with reference to FSAWS. Trend indicators are divided into two categories: positive trend indicators and negative trend indicators. Among them, positive trend indicators are better when the value is relatively large, and negative trend indicators are better when the value is relatively small. The output power of a high-power microwave source is a positive trend indicator, and the larger the value, the higher the rating. Assumption This is a descriptive function for the trend index of high-power microwave sources. for The evaluation function, the set to be evaluated contains a total of Group results; if the trend indicator is a positive trend indicator, the larger the value, the better, and the evaluation is as shown in (1) by referring to the FSAWS method: , , （1） If the trend indicator is a negative trend indicator, then a relatively small value is preferred: , , （2） Based on the above objective evaluation method, the fitness of an individual is determined as follows: （3） in, The weighting of trend indicators, Weights of interval indicators For the rating of the interval indicator, Rating for trend indicators.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the high-power microwave source multi-objective optimization method as described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the multi-objective optimization method for a high-power microwave source as described in any one of claims 1 to 7.