Underwater equipment defense strategy evaluation optimization method and device, equipment and storage medium

Abstract

The invention provides an underwater equipment defense strategy evaluation optimization method and device, equipment and a storage medium, and relates to the technical field of underwater defense strategies, and the method comprises the steps: obtaining an optimization target, a to-be-optimized design variable and a constraint condition of an underwater equipment defense strategy; constructing a simulation model corresponding to the defense process of the underwater equipment; determining a plurality of groups of initial design variable parameter value combinations based on the constraint condition, the parameter value range of the design variable and the sampling strategy; based on the simulation model, simulation results of the key efficiency indexes under different initial design variable parameter value combinations are obtained through large sample simulation, and the defense strategy efficiency under the different initial design variable parameter combinations is evaluated according to the simulation results; and based on the optimization target and the constraint condition of the underwater equipment defense strategy, a target optimization algorithm is adopted to optimize the design variables, and an optimal parameter value combination of the design variables is obtained. Through the method, automatic processing of strategy optimization can be realized.

Description

Technical Field

[0001] This application relates to the field of underwater defense strategy technology, and in particular to a method, apparatus, equipment and storage medium for evaluating and optimizing underwater equipment defense strategies. Background Technology

[0002] In response to the main threats faced by underwater equipment, effective defense strategies must be adopted when underwater equipment performs its missions. The quality of these defense strategies directly affects the survivability of underwater equipment. Therefore, it is necessary to evaluate and optimize the defense strategies of underwater equipment.

[0003] Currently, underwater equipment defense strategies are mainly evaluated by manually setting parameters and rules. The optimization of defense strategies mainly relies on experience to optimize parameters. When there are many experimental factors, a large sample space, and complex optimization objectives and constraint functions, this method has problems such as long time consumption, low efficiency, and difficulty in finding the global optimal solution. Summary of the Invention

[0004] In view of this, this application proposes a method, apparatus, device and storage medium for evaluating and optimizing underwater equipment defense strategies.

[0005] Firstly, this application provides a method for evaluating and optimizing underwater equipment defense strategies, including:

[0006] To obtain the optimization objectives, design variables to be optimized, and constraints of the underwater equipment defense strategy;

[0007] A simulation model corresponding to the underwater equipment defense process is constructed, and the design variables are parameterized.

[0008] Based on the constraints, the parameter value range of the design variables, and the sampling strategy, multiple sets of initial design variable parameter value combinations are determined;

[0009] Based on the simulation model, simulation results of key performance indicators under different combinations of initial design variable parameters are obtained through large-sample simulation, and the effectiveness of defense strategies under different combinations of initial design variable parameters is evaluated based on the simulation results.

[0010] Based on the optimization objectives and constraints of the underwater equipment defense strategy, the combination of parameter values ​​of each initial design variable is used as the initial candidate solution set, the effectiveness of the defense strategy is used as the objective function, and the objective optimization algorithm is used to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

[0011] In one embodiment, the simulation model includes a kinematic sub-model of underwater equipment encountering a threat, a passive detection sub-model, and an active detection sub-model. The passive detection sub-model is based on the passive sonar equations, and the active detection sub-model is based on the active sonar equations.

[0012] In one embodiment, determining multiple combinations of initial design variable parameter values ​​based on the constraints, the parameter value range of the design variables, and the sampling strategy includes:

[0013] Based on the parameter value range of each design variable and the constraints, n level values ​​are selected for each design variable;

[0014] Orthogonal sampling method is used to sample the selected level values ​​to obtain multiple sets of initial design variable parameter values.

[0015] In one embodiment, the step of obtaining simulation results of key performance indicators under different combinations of initial design variable parameter values ​​through large-sample simulation based on the simulation model, and evaluating the effectiveness of the defense strategy under different combinations of initial design variable parameter values ​​based on the simulation results, includes:

[0016] Based on the combinations of initial design variable parameters, a Monte Carlo large-sample simulation was conducted on the underwater equipment defense process. The number of successful defenses and simulations of the underwater equipment against incoming threats under each combination of initial design variable parameters were counted.

[0017] The defense success rate under each combination of initial design variable parameter values ​​is obtained based on the number of successes and simulations corresponding to each combination of initial design variable parameter values.

[0018] In one embodiment, the Monte Carlo large-sample simulation of the underwater equipment defense process based on the combination of values ​​of each of the initial design variable parameters includes:

[0019] The initial coordinates and initial heading of the incoming attack threat are set as random variables;

[0020] The underwater equipment defense process is simulated and deduced based on the current initial design variable parameter value combination. The number of simulations and the number of successful defenses are recorded, and the defense success rate of this simulation process is determined based on the number of simulations and the number of successful defenses.

[0021] The simulation results are judged to converge based on the change in the success rate of the defense. If they do not converge, the simulation will return to the step of performing a simulation of the underwater equipment defense process based on the current combination of initial design variable parameters, until the current simulation results are determined to converge. If they converge, the simulation will proceed to the next combination of initial design variable parameters, until each combination of initial design variable parameters has been simulated.

[0022] In one embodiment, the optimization objective and constraints based on the underwater equipment defense strategy, using the combinations of initial design variable parameter values ​​as the initial candidate solution set, and the defense strategy effectiveness as the objective function, employs an objective optimization algorithm to optimize the design variables, obtaining the optimal combination of design variable parameter values, including:

[0023] Based on the optimization objectives and constraints of the underwater equipment defense strategy, the initial design variable parameter value combinations are used as the initial population, and the defense strategy effectiveness is used as the fitness function. A genetic algorithm is used to iteratively optimize the design variables to obtain the optimal parameter value combinations of the design variables. In the iterative optimization process of the design variables, Monte Carlo large-sample simulation is used to calculate the fitness under the current design variable parameter value combinations.

[0024] In one embodiment, based on the optimization objective and constraints of the underwater equipment defense strategy, the initial design variable parameter value combinations are used as the initial population, and the defense strategy effectiveness is used as the fitness function. A genetic algorithm is used to iteratively optimize the design variables to obtain the optimal parameter value combinations of the design variables, including:

[0025] The value space of the design variables is encoded using binary encoding;

[0026] The defense success rate under the combination of design variable parameter values ​​corresponding to the string is selected as the fitness function, and the binary string corresponding to each combination of initial design variable parameter values ​​is used as the initial population.

[0027] The selection operator, crossover operator, and mutation operator are applied sequentially to the current population to obtain the next generation population. The selection operator randomly selects n strings according to the fitness ratio; the crossover operator repeatedly selects two strings randomly, randomly generates a single crossover point, and produces two offspring, until all strings have been selected once; the mutation operator reverses each character in all strings with a preset probability.

[0028] The maximum fitness value of the next generation population is calculated using Monte Carlo large-sample simulation. If the maximum fitness value has not converged, the next generation population is taken as the new current population, and the steps of applying the selection operator, crossover operator, and mutation operator to the current population are returned. If the maximum fitness value has converged, the combination of design variable parameter values ​​corresponding to the string of the maximum fitness value is taken as the optimal combination of design variable parameter values.

[0029] Secondly, this application also provides an underwater equipment defense strategy evaluation and optimization device, comprising:

[0030] The acquisition module is used to acquire the optimization objectives, design variables to be optimized, and constraints of the underwater equipment defense strategy;

[0031] The simulation modeling module is used to construct a simulation model corresponding to the underwater equipment defense process and to parameterize the design variables.

[0032] The experimental design module is used to determine multiple combinations of initial design variable parameter values ​​based on the constraints, the parameter value range of the design variables, and the sampling strategy.

[0033] The simulation and deduction module is used to obtain the simulation results of key performance indicators under different combinations of initial design variable parameter values ​​through large-sample simulation based on the simulation model, and to evaluate the effectiveness of the defense strategy under different combinations of initial design variable parameter values ​​based on the simulation results.

[0034] The optimization module is used to optimize the design variables based on the optimization objectives and constraints of the underwater equipment defense strategy. It takes the combination of parameter values ​​of each initial design variable as the initial candidate solution set, takes the effectiveness of the defense strategy as the objective function, and uses the objective optimization algorithm to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

[0035] Thirdly, this application also provides an electronic device, including a processor and a memory; the memory has a computer program stored thereon, wherein the computer program, when executed by the processor, implements the underwater equipment defense strategy evaluation and optimization method as described in the first aspect.

[0036] Fourthly, this application also provides a computer storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the underwater equipment defense strategy evaluation and optimization method as described in the first aspect.

[0037] The underwater equipment defense strategy evaluation and optimization method proposed in this application has the following advantages over related technologies:

[0038] 1. The underwater equipment defense strategy evaluation and optimization method of this application defines a clear direction and boundary for the optimization process by obtaining the optimization objective, design variables to be optimized, and constraints of the underwater equipment defense strategy. Then, a simulation model corresponding to the underwater equipment defense process is constructed, and the design variables are parameterized, transforming the actual defense process into a quantifiable and calculable model carrier, thus preparing for simulation. Multiple combinations of initial design variable parameter values ​​are determined based on constraints, the parameter value range of design variables, and sampling strategies. Subsequently, based on the simulation model, simulation results of key performance indicators under different combinations of initial design variable parameter values ​​are obtained through large-sample simulation. The effectiveness of the defense strategy under different combinations of initial design variable parameter values ​​is evaluated based on the simulation results, providing input for further optimization. Finally, based on the optimization objective and constraints of the underwater equipment defense strategy, each combination of initial design variable parameter values ​​is used as an initial candidate solution set, and the effectiveness of the defense strategy is used as the objective function. An objective optimization algorithm is then employed to optimize the design variables, obtaining the optimal combination of design variable parameter values. The above process enables a systematic and automated process from problem definition to strategy optimization, significantly shortening the design cycle of the optimal defense strategy for underwater equipment and overcoming the limitations of traditional manual adjustment of parameters and rules based on experience.

[0039] 2. When the target optimization algorithm employs a genetic algorithm, binary encoding is used to transform the design variable value space into a string format that can be directly processed by the computer, achieving a unified quantitative mapping of continuous / discrete design variables. Then, the defense success rate is used as the fitness function to directly anchor the optimization target. Iterative optimization is then performed using a combination of genetic algorithm and Monte Carlo large-sample simulation. The Monte Carlo large-sample simulation calculates the fitness, eliminating random errors through statistical regularity and ensuring the accuracy and reliability of fitness evaluation. The convergence judgment mechanism based on the maximum fitness value can terminate the iteration in a timely manner when a stable optimal solution is found, avoiding invalid calculations, and ensuring the accuracy of the optimization results. This allows for faster finding of the globally optimal strategy in complex, multi-variable, and large-sample-space scenarios, significantly improving optimization efficiency and strategy quality, further shortening the design cycle and reducing time costs. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying 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 flowchart illustrating the underwater equipment defense strategy evaluation and optimization method in one embodiment of this application;

[0042] Figure 2 This is a schematic diagram of the process of using a genetic algorithm to iteratively optimize design variables in one embodiment of this application;

[0043] Figure 3 This is a schematic diagram of the underwater equipment defense strategy evaluation and optimization device in one embodiment of this application. Detailed Implementation

[0044] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0045] In some embodiments, such as Figure 1 As shown, this application provides a method for evaluating and optimizing underwater equipment defense strategies, which includes the following steps S101 to S105.

[0046] S101: Obtain the optimization objective, design variables to be optimized, and constraints of the underwater equipment defense strategy.

[0047] One optimization objective for underwater equipment defense strategies is to improve the success rate of underwater equipment defense. The key performance indicator is the success rate, defined as the number of times the underwater equipment successfully defends against incoming enemy threats divided by the total number of simulations. Design variables that need optimization may include the initial speed of the underwater equipment. Maximum speed acceleration angular velocity of rotation Acoustic impedance device tube exit time Avoidance direction Constraints can include all design variables being positive real numbers and the initial speed not exceeding the maximum speed. Acceleration does not exceed the maximum value The angular velocity of rotation does not exceed the maximum value. The exit time of acoustic damping equipment should not be less than the minimum value. wait.

[0048] S102: Construct a simulation model corresponding to the underwater equipment defense process and parameterize the design variables.

[0049] In applications, simulation models can include kinematic sub-models of underwater equipment encountering threats, passive detection sub-models, and active detection sub-models. The passive detection sub-model is based on passive sonar equations, and the active detection sub-model is based on active sonar equations. Then, the initial speed of the underwater equipment is calculated. Maximum speed acceleration angular velocity of rotation Acoustic impedance device tube exit time Avoidance direction Parameterize design variables, etc.

[0050] The kinematic sub-model is applicable to underwater equipment and enemy attack threats, and position changes are calculated iteratively using the following formula:

[0051]

[0052] In the above formula, The pitch angle, Let be the heading angle. The change in heading angle is calculated iteratively using the following formula:

[0053]

[0054] In the formula ω is the gyroscopic angular velocity.

[0055] The acceleration and deceleration of motion are calculated iteratively using the following formula:

[0056]

[0057] In the formula For acceleration. This kinematic sub-model can simulate the uniform linear motion, uniform acceleration, turning, rising and falling motions of the equipment.

[0058] The passive detection sub-model is suitable for underwater equipment to passively detect incoming enemy threats. The passive detection sub-model is shown in the following equation:

[0059]

[0060] In the formula To establish a sonar detection threshold for underwater equipment. This is at the level of a radiation source posing a threat from an enemy attack, or at the level of an active sonar emission source. For sound wave propagation loss, For sonar interference noise levels of underwater equipment, This refers to the sonar directivity index of underwater equipment.

[0061] The active detection sub-model is suitable for actively detecting underwater equipment to counter enemy threats. The active detection sub-model is shown in the following equation:

[0062]

[0063] In the formula Enemy attack threat triggers active sonar source-level emission. For sound wave propagation loss, The acoustic target intensity of underwater equipment. The sonar interference noise level posed by an incoming enemy attack. A sonar directivity index indicating an incoming enemy threat. It is an active, self-guided detection threshold for enemy attack threats.

[0064] S103: Determine multiple combinations of initial design variable parameter values ​​based on constraints, the parameter range of design variables, and sampling strategies.

[0065] It is understandable that using constraints as hard boundaries ensures that all generated parameter combinations meet the feasibility requirements of physical or practical applications, avoiding invalid or unreasonable values. Secondly, by considering the parameter value range of each design variable, clear numerical boundaries are defined for the parameter combinations, ensuring that the values ​​fall within a reasonable exploration range. Finally, through a pre-defined sampling strategy, multiple representative parameter combinations are selected based on the first two conditions, resulting in multiple sets of initial design variable parameter value combinations. These combinations not only cover key areas in the design variable value space but also reduce redundancy through strategic sampling, ensuring the diversity and effectiveness of the initial samples.

[0066] S104: Based on the simulation model, the simulation results of key performance indicators under different combinations of initial design variable parameters are obtained through large-sample simulation, and the effectiveness of the defense strategy under different combinations of initial design variable parameters is evaluated based on the simulation results.

[0067] It is understandable that after constructing the simulation model, the simulation model simulating the actual process of underwater equipment defense can be used as a computational platform. By executing a large number of simulation calculations, the corresponding key performance indicators can be calculated for each pre-determined combination of initial design variable parameters. This large-sample design can effectively reduce the interference of random factors on the results in a single simulation and improve data reliability. Subsequently, based on these quantitative indicators obtained through simulation, the effectiveness of the underwater equipment defense strategy corresponding to each combination of initial parameters can be evaluated. For example, combinations with high defense success rates correspond to more effective strategies, while those with lower success rates are less effective, ultimately forming an effectiveness evaluation conclusion for all initial strategies.

[0068] S105: Based on the optimization objective and constraints of the underwater equipment defense strategy, the combination of parameter values ​​of each initial design variable is used as the initial candidate solution set, the effectiveness of the defense strategy is used as the objective function, and the objective optimization algorithm is used to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

[0069] It is understandable that the previously determined combinations of initial design variable parameter values ​​serve as the starting point for optimization, i.e., the initial candidate solution set. These combinations all satisfy the constraints, providing a feasible initial exploration basis for the optimization algorithm. Simultaneously, the defense strategy effectiveness obtained through simulation evaluation is used as the objective function to quantitatively measure the merits of each candidate solution, ensuring that the optimization direction always adheres to the core objective of improving defense effectiveness. Based on this, the objective optimization algorithm iteratively optimizes the combinations of design variable values ​​while satisfying the constraints, retaining more effective combinations, eliminating inefficient combinations, and generating new potential solutions through a specific mechanism, continuously exploring a better parameter space. Finally, after multiple iterations, the algorithm outputs a set of design variable parameter values ​​that satisfies all constraints and has the optimal defense strategy effectiveness—the optimal design variable parameter value combination. This achieves efficient optimization from the initial feasible solution to the global optimal solution, ensuring that the underwater equipment defense strategy achieves optimal effectiveness in complex constraint and multivariate coupling scenarios.

[0070] The aforementioned method for evaluating and optimizing underwater equipment defense strategies defines a clear direction and boundary for the optimization process by obtaining the optimization objective, design variables to be optimized, and constraints of the underwater equipment defense strategy. Then, a simulation model corresponding to the underwater equipment defense process is constructed, and the design variables are parameterized, transforming the actual defense process into a quantifiable and calculable model carrier, thus preparing for simulation. Multiple combinations of initial design variable parameter values ​​are determined based on constraints, the parameter value range of design variables, and sampling strategies. Subsequently, based on the simulation model, simulation results of key performance indicators under different combinations of initial design variable parameter values ​​are obtained through large-sample simulations. The effectiveness of the defense strategy under different combinations of initial design variable parameter values ​​is evaluated based on the simulation results, providing initial parameters for further optimization. Finally, based on the optimization objective and constraints of the underwater equipment defense strategy, each combination of initial design variable parameter values ​​is used as an initial candidate solution set, and the effectiveness of the defense strategy is used as the objective function. An objective optimization algorithm is then employed to optimize the design variables, yielding the optimal combination of design variable parameter values. The above process enables a systematic and automated process from problem definition to strategy optimization, significantly shortening the design cycle of the optimal defense strategy for underwater equipment and overcoming the limitations of traditional manual adjustment of parameters and rules based on experience.

[0071] In some embodiments, determining multiple sets of initial design variable parameter value combinations based on constraints, parameter value ranges of design variables, and sampling strategies includes: selecting n level values ​​for each design variable based on the parameter value ranges and constraints of each design variable; and sampling the selected level values ​​using an orthogonal sampling method to obtain multiple sets of initial design variable parameter value combinations.

[0072] For example, by using an orthogonal sampling method, sampling can be performed to obtain no less than Group the possible combinations of parameter values ​​for design variables. Examples are shown below:

[0073] Initial speed Maximum speed acceleration angular velocity of rotation Acoustic impedance device tube exit time Avoidance direction There are a total of 6 design variables, denoted by A, B, C, D, E, and F. Each design variable has 2 level values, denoted by 0 and 1 respectively.

[0074] Based on the orthogonal sampling method, a seven-factor, two-level approach can be used. The orthogonal array yields 8 sets of design variable parameter value combinations, as shown in Table 1 below. Select any 6 columns corresponding to the design variables, and then conduct experiments row by row. The level combination of each design variable in each row is the experimental condition for each time.

[0075] Table 1 shows... Orthogonal array

[0076]

[0077] Understandably, based on the parameter value range and constraints of each design variable, n level values ​​are first selected for each design variable. The continuous or broad value range of each variable is discretized into n representative specific values, and all level values ​​satisfy the constraints to avoid invalid values. Subsequently, orthogonal sampling is used to sample these selected level values. The core advantage of orthogonal sampling is that it can scientifically select a small number of combinations with "uniform dispersion and neat comparability" from all possible level combinations. This ensures that the sampling results cover the key areas of the design variable value space, avoiding the omission of important parameter combinations, and significantly reduces redundant sampling. Finally, multiple sets of initial design variable parameter value combinations that balance representativeness and economy are obtained, thus providing reliable starting data for subsequent processes.

[0078] In some embodiments, based on a simulation model, simulation results of key performance indicators under different combinations of initial design variable parameter values ​​are obtained through large-sample simulation, and the effectiveness of defense strategies under different combinations of initial design variable parameter values ​​is evaluated based on the simulation results. This includes: performing Monte Carlo large-sample simulation deduction of the underwater equipment defense process based on each combination of initial design variable parameter values, and counting the number of successful defenses and simulations of the underwater equipment against incoming threats under each combination of initial design variable parameter values; and obtaining the defense success rate under each combination of initial design variable parameter values ​​based on the number of successful defenses and simulations corresponding to each combination of initial design variable parameter values.

[0079] It is understandable that Monte Carlo large-sample simulations of underwater equipment defense processes based on various initial design variable parameter combinations are crucial. The core of this approach is to simulate the entire process of underwater equipment responding to enemy threats through numerous repeated random simulation experiments for each pre-determined initial parameter combination. This large-sample design effectively counteracts the interference of random factors in the simulation results, ensuring data reliability. In the simulation of each parameter combination, two key data points are simultaneously statistically analyzed: the "number of successful defenses" and the "total number of simulations" for that parameter combination. Then, based on the calculation rule "defense success rate = number of successful defenses / total number of simulations," the defense success rate corresponding to each initial design variable parameter combination is calculated. Finally, a quantitative performance evaluation result is assigned to each initial parameter combination. These results will directly serve as core data support for the objective function in subsequent optimization algorithms, helping the algorithm select high-quality parameter combinations and advance iterative optimization.

[0080] In some embodiments, a Monte Carlo large-sample simulation of the underwater equipment defense process is performed based on various combinations of initial design variable parameter values. This includes: setting the initial coordinates and initial heading of the incoming threat as random variables; performing a simulation of the underwater equipment defense process based on the current combination of initial design variable parameter values, recording the number of simulations and the number of successful defenses, and determining the defense success rate of this simulation process based on the number of simulations and the number of successful defenses; determining whether the current simulation result has converged based on the change in the defense success rate; if it has not converged, returning to the step of performing a simulation of the underwater equipment defense process based on the current combination of initial design variable parameter values ​​until the current simulation result is determined to have converged; if it has converged, performing a simulation under the next set of initial design variable parameter value combinations, until a simulation has been performed for each set of initial design variable parameter value combinations.

[0081] It is understandable that setting the initial coordinates and initial heading of the incoming threat as random variables can simulate the uncertainty of the threat's movement state in real-world scenarios, making the simulation closer to real-world application scenarios and avoiding result deviations caused by fixed initial threat states. Subsequently, for the current set of initial design variable parameter combinations, the underwater equipment defense process is repeatedly simulated and extrapolated. Each extrapolation is based on a randomly generated initial threat state, and the cumulative number of simulations and successful defenses is recorded simultaneously. The current cumulative defense success rate is then calculated, and the convergence of the results is determined by monitoring the change in the defense success rate. If the success rate fluctuates very little after multiple extrapolations (e.g., the change is below a preset threshold), it indicates that the current number of simulations is sufficient to reflect the true effectiveness of the set of parameters, and the results tend to stabilize. If convergence has not occurred, the extrapolation continues until the convergence condition is met, thus balancing simulation accuracy and computational efficiency. Once the simulation results of a set of parameter combinations converge, the above process is repeated for the next set of initial design variable parameter combinations until all combinations have been extrapolated. Ultimately, through the above simulation and deduction methods, a stable and reliable defense success rate can be generated for each set of initial design variable parameter value combinations, thus providing a high-quality quantitative basis for subsequent strategy effectiveness evaluation and optimization algorithm iteration.

[0082] In some embodiments, based on the optimization objective and constraints of the underwater equipment defense strategy, the initial design variable parameter value combinations are used as the initial candidate solution set, the defense strategy effectiveness is used as the objective function, and the design variables are optimized using an objective optimization algorithm to obtain the optimal parameter value combination of the design variables. This includes: based on the optimization objective and constraints of the underwater equipment defense strategy, using the initial design variable parameter value combinations as the initial population, the defense strategy effectiveness as the fitness function, and using a genetic algorithm to iteratively optimize the design variables to obtain the optimal parameter value combination of the design variables. The step of calculating the fitness under the current design variable parameter value combination is performed using Monte Carlo large-sample simulation during the iterative optimization process of the design variables.

[0083] It is understood that the target optimization algorithm in this embodiment employs a genetic algorithm. Based on this, with a clearly defined objective and constraints as a framework, the optimal strategy is efficiently found by leveraging the iterative optimization capability of the genetic algorithm and the precise evaluation capability of Monte Carlo simulation. Specifically, firstly, based on the optimization objective and constraints, multiple sets of initial design variable parameter values, determined previously, are used as the initial population for the genetic algorithm. These combinations all satisfy the constraints, providing the algorithm with a feasible and diverse initial search starting point, avoiding ineffective exploration that might result from randomly generating initial solutions. Simultaneously, the effectiveness of the defense strategy (e.g., defense success rate) is used as the fitness function, directly measuring the quality of each individual in the population by its effectiveness, ensuring that the algorithm's evolutionary direction always closely aligns with the core objective of improving defense effectiveness.

[0084] In each iteration of the iterative optimization process, the fitness of each combination of design variable parameters in the current population is calculated through Monte Carlo large-sample simulation. This large-sample simulation introduces random variables such as the initial state of the incoming threat to simulate the uncertainty in actual combat. Then, random errors are offset by a large number of repeated experiments to ensure that the obtained defense effectiveness can truly reflect the actual performance of the combination, providing an accurate basis for the selection, crossover and mutation of the algorithm.

[0085] After multiple iterations, the individual with the highest fitness in the population will gradually converge to a stable optimal state. The final set of parameters is the optimal combination of design variable parameter values ​​that satisfies the constraints and achieves the best defensive effectiveness. This method overcomes the limitations of traditional manual optimization, ensuring the reliability and optimality of optimization results in complex and random scenarios, and efficiently realizing the automated optimization of underwater equipment defense strategies.

[0086] In some embodiments, such as Figure 2 As shown, based on the optimization objective and constraints of the underwater equipment defense strategy, the combination of parameter values ​​of each initial design variable is used as the initial population, the effectiveness of the defense strategy is used as the fitness function, and the genetic algorithm is used to iteratively optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables, including the following steps S201 to S204.

[0087] S201: Use binary encoding to encode the value space of design variables.

[0088] In application, for each design variable, the required number of binary bits is first determined based on its parameter value range. Then, the specific value of the variable is mapped to a unique binary bit string using numerical mapping rules. For example, the initial speed can be encoded using strings 000, 001, 010, 011, 100, 101, 110, and 111, respectively. Maximum speed acceleration angular velocity of rotation Acoustic impedance device tube exit time Avoidance direction The eight level values ​​result in a string containing 18 characters, for example, 001 010 011 100 101 110 represents the initial speed. Take the second horizontal value and the maximum speed. Take the third horizontal value, acceleration Take the 4th horizontal value and the rotational angular velocity. Take the 5th level value and the time of exit of the acoustic impedance device. Take the 6th level value and avoid the direction. Take the 7th level value.

[0089] By binary encoding the value space of design variables, the value space of continuous or discrete design variables can be uniformly transformed into a standardized binary bit string, providing an operable "gene" carrier for operations such as selection, crossover, and mutation in genetic algorithms.

[0090] S202: Select the defense success rate under the combination of design variable parameter values ​​corresponding to the string as the fitness function, and use the binary string corresponding to each initial combination of design variable parameter values ​​as the initial population.

[0091] Among them, the binary strings corresponding to the combinations of initial design variable parameter values ​​can be used as the initial population. ,in This represents a string containing 18 characters.

[0092] S203: Apply the selection operator, crossover operator, and mutation operator sequentially to the current population to obtain the next generation population. Specifically, the selection operator randomly selects n strings according to their fitness ratio; the crossover operator repeatedly and randomly selects two strings, randomly generates a single crossover point, and produces two offspring, until all strings have been selected once; the mutation operator reverses each character in all strings with a preset probability.

[0093] It's understandable that the selection operator randomly selects n strings based on their fitness ratio. This means that strings with higher fitness have a greater probability of being selected. For example, if the fitness of string A is twice that of string B, then the probability of A being selected is approximately twice that of B. This selection mechanism prioritizes the retention of parameter combinations with better defense effectiveness in the population, laying a high-quality foundation for the next generation. At the same time, the random selection characteristic avoids the search limitations caused by retaining only a single optimal individual.

[0094] The crossover operator can be used to repeatedly and randomly select two strings from the selected n strings as parents, randomly generate a crossover point, and exchange the latter half of the genes of the two parents at the crossover point to form two new offspring strings. This process continues until all strings have been selected once. The core of the crossover operation is to combine the superior characteristics of different parents through gene recombination to generate new combinations of design variables, thereby expanding the search space and exploring potential better solutions while inheriting advantages.

[0095] The mutation operator is applied to invert each character (0 becomes 1 or 1 becomes 0) of all offspring strings generated after crossover with a preset probability (e.g., 0.01). This random mutation operation introduces new genetic features, preventing the population from getting trapped in local optima due to crossover. The preset probability controls the mutation intensity, ensuring sufficient diversity to explore new regions while preventing excessive mutation from destroying existing high-quality gene combinations. By sequentially applying the selection operator, crossover operator, and mutation operator, the generated next-generation population inherits the core features with high fitness from the previous generation and generates new parameter combinations through crossover and mutation, thus providing a population foundation with greater evolutionary potential for subsequent iterative optimization.

[0096] S204: The maximum fitness value of the next generation population is calculated using Monte Carlo large-sample simulation. If the maximum fitness value has not converged, the next generation population is taken as the new current population, and the steps of applying the selection operator, crossover operator, and mutation operator to the current population are returned. If the maximum fitness value has converged, the combination of design variable parameter values ​​corresponding to the string of the maximum fitness value is taken as the optimal combination of design variable parameter values.

[0097] It is understandable that using Monte Carlo large-sample simulation to calculate the maximum fitness of the next generation population can ensure the accuracy of the evaluation results. Then, the iteration is terminated by judging whether the maximum fitness value converges. If it does not converge, it means that the current population still has room for evolution. Therefore, the next generation population is taken as the new current population, and selection, crossover, and mutation operations are performed to continue to drive the population evolution and explore a better parameter space through gene recombination and mutation. If it converges, it means that after multiple generations of iteration, the optimal fitness of the population has tended to stabilize, and further iteration is unlikely to significantly improve the defense effectiveness. At this time, the string corresponding to the current maximum fitness value is the global optimal solution that satisfies the optimization objective and constraints. Therefore, the combination of design variable parameter values ​​corresponding to it is taken as the optimal combination of design variable parameter values. By using a genetic algorithm to construct the framework of the iterative optimization process, combined with Monte Carlo large-sample simulation, the reliability of the optimization results is ensured, while balancing the optimization efficiency and effect, ultimately achieving efficient evolution from the initial population to the optimal strategy.

[0098] In application, the optimal combination of design variable parameters can be simulated and evaluated using Monte Carlo simulations to verify whether the final result meets the target requirements. The optimization process can also be visualized in real time, displaying strategy evaluation data (e.g., defense success rate), strategy optimization results (optimal combination of design variable parameters), and the relationship between strategy and effectiveness evaluation results.

[0099] In some embodiments, please refer to Figure 3This application provides an underwater equipment defense strategy evaluation and optimization device 30, comprising: an acquisition module 31, a simulation modeling module 32, an experimental design module 33, a simulation deduction module 34, and an optimization module 35; wherein,

[0100] The acquisition module 31 is used to acquire the optimization objectives, design variables to be optimized, and constraints of the underwater equipment defense strategy;

[0101] Simulation modeling module 32 is used to construct a simulation model corresponding to the underwater equipment defense process and to parameterize the design variables.

[0102] The experimental design module 33 is used to determine multiple combinations of initial design variable parameter values ​​based on constraints, the parameter range of design variables, and sampling strategies.

[0103] The simulation and deduction module 34 is used to obtain the simulation results of key performance indicators under different combinations of initial design variable parameters based on the simulation model and through large-sample simulation, and to evaluate the effectiveness of the defense strategy under different combinations of initial design variable parameters based on the simulation results.

[0104] The optimization module 35 is used to optimize the design variables based on the underwater equipment defense strategy and the constraints. It takes the combination of parameter values ​​of each initial design variable as the initial candidate solution set, takes the effectiveness of the defense strategy as the objective function, and uses the objective optimization algorithm to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

[0105] It should be noted that the underwater equipment defense strategy evaluation and optimization device 30 provided in this application embodiment and the underwater equipment defense strategy evaluation and optimization method provided in this application embodiment are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned underwater equipment defense strategy evaluation and optimization method, and the repeated parts will not be described again.

[0106] In some embodiments, an electronic device provided in this application includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the above-described underwater equipment defense strategy evaluation and optimization method.

[0107] Specifically, the processor may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor may also include onboard memory for caching purposes. The processor may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0108] Memory can be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, memory can include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, instruments, or propagation media. Specific examples of memory include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and also random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0109] This application also provides a computer-readable medium storing a computer program thereon, which, when executed by a processor, implements the above-described underwater equipment defense strategy evaluation and optimization method. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method as described in the embodiments of this application.

[0110] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0111] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for evaluating and optimizing underwater equipment defense strategies, characterized in that, include: To obtain the optimization objectives, design variables to be optimized, and constraints of the underwater equipment defense strategy; A simulation model corresponding to the underwater equipment defense process is constructed, and the design variables are parameterized. Based on the constraints, the parameter value range of the design variables, and the sampling strategy, multiple sets of initial design variable parameter value combinations are determined; Based on the simulation model, simulation results of key performance indicators under different combinations of initial design variable parameters are obtained through large-sample simulation, and the effectiveness of defense strategies under different combinations of initial design variable parameters is evaluated based on the simulation results. Based on the optimization objectives and constraints of the underwater equipment defense strategy, the combination of parameter values ​​of each initial design variable is used as the initial candidate solution set, the effectiveness of the defense strategy is used as the objective function, and the objective optimization algorithm is used to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

2. The underwater equipment defense strategy evaluation and optimization method as described in claim 1, characterized in that, The simulation model includes a kinematic sub-model of underwater equipment encountering threats, a passive detection sub-model, and an active detection sub-model. The passive detection sub-model is based on the passive sonar equations, and the active detection sub-model is based on the active sonar equations.

3. The underwater equipment defense strategy evaluation and optimization method as described in claim 1, characterized in that, The process of determining multiple combinations of initial design variable parameter values ​​based on the constraints, the parameter value range of the design variables, and the sampling strategy includes: Based on the parameter value range of each design variable and the constraints, n level values ​​are selected for each design variable; Orthogonal sampling method is used to sample the selected level values ​​to obtain multiple sets of initial design variable parameter values.

4. The underwater equipment defense strategy evaluation and optimization method as described in claim 1, characterized in that, The process of obtaining simulation results of key performance indicators under different combinations of initial design variable parameters based on the simulation model through large-sample simulation, and evaluating the effectiveness of the defense strategy under different combinations of initial design variable parameters based on the simulation results, includes: Based on the combinations of initial design variable parameters, a Monte Carlo large-sample simulation was conducted on the underwater equipment defense process. The number of successful defenses and simulations of the underwater equipment against incoming threats under each combination of initial design variable parameters were counted. The defense success rate under each combination of initial design variable parameter values ​​is obtained based on the number of successes and simulations corresponding to each combination of initial design variable parameter values.

5. The underwater equipment defense strategy evaluation and optimization method as described in claim 4, characterized in that, The Monte Carlo large-sample simulation of the underwater equipment defense process based on the combination of values ​​of the initial design variable parameters includes: The initial coordinates and initial heading of the incoming attack threat are set as random variables; The underwater equipment defense process is simulated and deduced based on the current initial design variable parameter value combination. The number of simulations and the number of successful defenses are recorded, and the defense success rate of this simulation process is determined based on the number of simulations and the number of successful defenses. The simulation results are judged to converge based on the change in the success rate of the defense. If they do not converge, the simulation will return to the step of performing a simulation of the underwater equipment defense process based on the current combination of initial design variable parameter values, until the current simulation results are determined to converge. If they converge, the simulation will proceed to the next combination of initial design variable parameter values, until each combination of initial design variable parameter values ​​has been simulated.

6. The underwater equipment defense strategy evaluation and optimization method as described in claim 1, characterized in that, The optimization objective and constraints of the underwater equipment defense strategy are defined by using the initial design variable parameter value combinations as the initial candidate solution set, the defense strategy effectiveness as the objective function, and employing an objective optimization algorithm to optimize the design variables, thereby obtaining the optimal parameter value combinations for the design variables, including: Based on the optimization objectives and constraints of the underwater equipment defense strategy, the initial design variable parameter value combinations are used as the initial population, and the defense strategy effectiveness is used as the fitness function. A genetic algorithm is used to iteratively optimize the design variables to obtain the optimal parameter value combinations of the design variables. In the iterative optimization process of the design variables, Monte Carlo large-sample simulation is used to calculate the fitness under the current design variable parameter value combinations.

7. The underwater equipment defense strategy evaluation and optimization method as described in claim 6, characterized in that, Based on the optimization objective and constraints of the underwater equipment defense strategy, the initial design variable parameter value combinations are used as the initial population, and the defense strategy effectiveness is used as the fitness function. A genetic algorithm is used to iteratively optimize the design variables to obtain the optimal parameter value combinations of the design variables, including: The value space of the design variables is encoded using binary encoding; The defense success rate under the combination of design variable parameter values ​​corresponding to the string is selected as the fitness function, and the binary string corresponding to each combination of initial design variable parameter values ​​is used as the initial population. The selection operator, crossover operator, and mutation operator are applied sequentially to the current population to obtain the next generation population. The selection operator randomly selects n strings according to the fitness ratio; the crossover operator repeatedly selects two strings randomly, randomly generates a single crossover point, and produces two offspring, until all strings have been selected once; the mutation operator reverses each character in all strings with a preset probability. The maximum fitness value of the next generation population is calculated using Monte Carlo large-sample simulation. If the maximum fitness value has not converged, the next generation population is taken as the new current population, and the steps of applying the selection operator, crossover operator, and mutation operator to the current population are returned. If the maximum fitness value has converged, the combination of design variable parameter values ​​corresponding to the string of the maximum fitness value is taken as the optimal combination of design variable parameter values.

8. A device for evaluating and optimizing underwater equipment defense strategies, characterized in that, include: The acquisition module is used to acquire the optimization objectives, design variables to be optimized, and constraints of the underwater equipment defense strategy; The simulation modeling module is used to construct a simulation model corresponding to the underwater equipment defense process and to parameterize the design variables. The experimental design module is used to determine multiple combinations of initial design variable parameter values ​​based on the constraints, the parameter value range of the design variables, and the sampling strategy. The simulation and deduction module is used to obtain the simulation results of key performance indicators under different combinations of initial design variable parameter values ​​through large-sample simulation based on the simulation model, and to evaluate the effectiveness of the defense strategy under different combinations of initial design variable parameter values ​​based on the simulation results. The optimization module is used to optimize the design variables based on the optimization objectives and constraints of the underwater equipment defense strategy. It takes the combination of parameter values ​​of each initial design variable as the initial candidate solution set, takes the effectiveness of the defense strategy as the objective function, and uses the objective optimization algorithm to optimize the design variables to obtain the optimal combination of parameter values ​​of the design variables.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the underwater equipment defense strategy evaluation and optimization method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, implements the underwater equipment defense strategy evaluation and optimization method as described in any one of claims 1 to 7.

Images