Full-closed-loop radar signal level simulation system and method based on intelligent optimization

Abstract

The invention discloses a full-closed-loop radar signal level simulation system and method based on intelligent optimization. The system comprises a simulation scenario configuration module, a radar signal generation module, a target and environment model module, a radar signal processing module, a data processing and tracking module, a performance evaluation module and a closed-loop control engine. The method comprises the steps that firstly, a simulation scenario configuration module initializes a simulation scenario; then a radar signal generation module generates a radar emission signal, and a target and environment model module performs modeling to generate a synthetic echo; then the radar signal processing module receives the echo signal and extracts a target trace point, and the data processing and tracking module processes the target trace point to form a target track; and finally, the performance evaluation module executes radar signal level simulation and outputs performance indexes, and a closed-loop control engine judges whether acceptance conditions are met or not and outputs optimal parameters and performance reports. According to the invention, intelligent full-closed-loop automatic simulation is realized, and the precision and flexibility of radar simulation are improved.

Description

Technical Field

[0001] This invention relates to the field of radar simulation and digital signal processing technology, and in particular to a fully closed-loop radar signal level simulation system and method based on intelligent optimization. Background Technology

[0002] Radar simulation is a technique that simulates radar signal waveforms, environmental interactions, and signal processing to test complex electromagnetic environments. Its core lies in high-precision modeling. The design and performance verification of radar systems heavily rely on simulation technology. Traditional radar simulation schemes mainly suffer from the following limitations:

[0003] 1. System-level open-loop simulation: Most simulation platforms focus on system-level and behavioral-level simulation, using simple signal-to-noise ratio models and detection probability formulas, failing to delve into the signal level. This type of simulation is an "open-loop" process, that is, setting parameters, running the simulation, and viewing the results, but it cannot automatically and intelligently adjust parameters in reverse to seek the optimal solution based on the results.

[0004] 2. Signal-level simulation: To achieve high-fidelity signal-level simulation, traditionally it is necessary to rely on hardware devices such as dedicated processors and high-speed AD / DA conversion cards, which is costly, has a long development cycle, and results in a rigid system.

[0005] 3. Closed-loop simulation: Existing closed-loop simulation technologies mostly rely on human experience to adjust parameters. They can only provide simple rule-based feedback for single parameters and lack intelligent parameter optimization capabilities. They cannot perform efficient and global automated optimization in multi-dimensional and complex parameter spaces. Summary of the Invention

[0006] The purpose of this invention is to provide a fully closed-loop radar signal-level simulation system and method based on intelligent optimization that can take into account high precision, high flexibility, and high intelligence, so as to realize intelligent fully closed-loop automated simulation, efficiently search for the optimal parameter combination in a multi-dimensional parameter space, achieve the unity of signal-level simulation accuracy and software flexibility, and improve the sufficiency and reliability of simulation verification.

[0007] The technical solution to achieve the purpose of this invention is: a fully closed-loop radar signal-level simulation system based on intelligent optimization, including a simulation scenario configuration module, a radar signal generation module, a target and environment model module, a radar signal processing module, a data processing and tracking module, a performance evaluation module, and a closed-loop control engine;

[0008] The simulation scenario configuration module is used to set radar parameters, target trajectory, environmental characteristics, and simulation process;

[0009] The radar signal generation module is used to generate radar transmission signals according to the configuration of the simulation scenario configuration module;

[0010] The target and environment model module is used to model the target scattering characteristics, electromagnetic propagation environment and interference, and generate synthetic echoes.

[0011] The radar signal processing module is used to receive echo signals containing target, environment and interference information, and to perform signal processing to extract target traces.

[0012] The data processing and tracking module is used to process the dots to form a target track;

[0013] The performance evaluation module is used to sequentially perform radar signal-level simulation and output performance indicators;

[0014] The closed-loop control engine is used to automatically search in the radar parameter space based on multiple evaluation indicators output by the evaluation module, through multiple simulation iterations, to find the radar parameter combination that optimizes the overall performance of the system, and then feeds back the parameter combination to the simulation scenario configuration module.

[0015] Furthermore, the closed-loop control engine has a built-in global optimization objective function for the overall performance of the radar system and is equipped with an iterative optimization algorithm.

[0016] Furthermore, the global objective optimization function is a function that optimizes the tracking accuracy index. Stability indicators Detection power index Resource efficiency indicators The scalar objective function F obtained after weighted fusion;

[0017] The tracking accuracy index The stability index is the root mean square error of the target position. The detection power index represents the target failure rate. The resource efficiency index is used to calculate the average discovery probability. This represents the average transmit power.

[0018] The evaluation indicators are normalized, dimensions are eliminated, and they are standardized to a form where smaller values ​​are considered better:

[0019] ,in For reference accuracy;

[0020] ,in The ratio is 0 to 1;

[0021] ,in The probability of discovery is converted into the probability of non-discovery.

[0022] ,in Maximum permissible power;

[0023] By using weighted summation, a scalar objective function F is constructed:

[0024]

[0025] in, , , , These are the accuracy weighting coefficient, stability weighting coefficient, discovery probability weighting coefficient, and resource efficiency weighting coefficient, respectively, and they satisfy the following conditions: The weighting coefficients are preset or dynamically configured based on the priorities set in the simulation. When the radar is operating in precision tracking mode, the weighting coefficients are adjusted to ensure accuracy. and stability Assign a higher weight; when the radar is operating in long-range surveillance mode, assign a higher probability of detection. Assign higher weights; when the radar operates in low-power mode, prioritize resource efficiency. Assign higher weight.

[0026] Furthermore, the iterative optimization algorithm is one of a genetic algorithm, a particle swarm optimization algorithm, or a Bayesian optimization algorithm, used to achieve automatic search of the radar parameter space.

[0027] Furthermore, the radar parameter space includes radar transmission waveform, signal bandwidth, pulse repetition frequency, transmission power, and signal processing algorithm threshold.

[0028] Furthermore, the closed-loop control engine determines whether the optimization process has converged based on the following criteria:

[0029] Criterion 1 is the stability criterion for the objective function: Monitoring the change of the local optimization objective function F in consecutive iterations, if it satisfies the following condition after K consecutive iterations...

[0030]

[0031] or

[0032]

[0033] in and If the preset small positive threshold is used, it is determined that the objective function has stabilized and the system has converged;

[0034] Criterion 2 is the parameter vector stability criterion: monitoring the historical optimal parameter vector. If the key parameters representing the core working mode of the radar remain unchanged for multiple consecutive iterations, and the range of change of numerical parameters is lower than the set threshold of their value space, then the parameter space is considered to have been fully explored and convergence is determined.

[0035] Criterion 3 is the maximum iteration count criterion: when the number of iterations reaches a preset upper limit. If the total computation time exceeds the budget, force a convergence check and output the current optimal solution;

[0036] Criterion 4 is the performance compliance criterion: if the performance evaluation result of a certain iteration has met the preset system design target threshold. If the condition is met, then convergence is determined.

[0037] The closed-loop control engine comprehensively utilizes the above judgment criteria and makes decisions using the logic of "criterion 1 OR criterion 2 OR criterion 3 OR criterion 4" to achieve intelligent convergence judgment that balances optimization accuracy and computational efficiency.

[0038] A fully closed-loop radar signal level simulation method based on intelligent optimization, the method being based on the aforementioned fully closed-loop radar signal level simulation system based on intelligent optimization, includes the following steps:

[0039] S1. The simulation scenario configuration module initializes the simulation scenario, sets radar parameters, target trajectory, environmental characteristics, and simulation process;

[0040] S2. The radar signal generation module generates radar transmission signals according to the configuration of the simulation scenario configuration module.

[0041] S3, the target and environment model module, models the target scattering characteristics, electromagnetic propagation environment and interference, and generates synthetic echoes;

[0042] S4. The radar signal processing module receives echo signals containing target, environment and interference information, and performs signal processing to extract target traces.

[0043] S5, the data processing and tracking module processes the points and forms the target track;

[0044] S6. The performance evaluation module sequentially performs radar signal-level simulation and outputs performance indicators.

[0045] S7. The closed-loop control engine determines whether the acceptance conditions are met. If so, it outputs the optimal parameters and performance report; otherwise, it performs intelligent optimization, generates a new radar parameter set, and feeds it back to the simulation scenario configuration module for the next simulation iteration.

[0046] Furthermore, the intelligent optimization in S7 is based on a genetic algorithm, specifically including the following steps:

[0047] Step 1, Population Initialization: Randomly generate an initial population containing N individuals. Each individual represents a set of radar parameter schemes, which are represented by chromosome encoding. The encoded genes include waveform type, signal bandwidth, pulse repetition frequency, transmission power, and detection threshold.

[0048] Step 2, Fitness Evaluation Cycle: For each individual in the current population, perform the following operations:

[0049] Step 2.1: Decode the chromosome to obtain the specific radar parameter set;

[0050] Step 2.2: Load the parameter set into the simulation scenario configuration module;

[0051] Step 2.3: Run a complete radar signal-level simulation process once;

[0052] Step 2.4: Based on the performance evaluation results, calculate the global optimization objective function value F;

[0053] Step 2.5: According to the formula Fitness = Calculate the fitness of this individual;

[0054] Step 3, Convergence judgment: Record the fitness and parameter set of the best individual in the current population. If any of the following conditions are met, exit the optimization loop and execute step 6.

[0055] (1) The optimal fitness is below the threshold for multiple consecutive generations ;

[0056] (2) The preset maximum number of iterations has been reached;

[0057] (3) The optimal fitness has exceeded the preset performance threshold;

[0058] Step 4, Genetic Operations: If convergence is not achieved, perform the following operations to generate a new generation of the population:

[0059] Step 4.1: Selection: Based on the roulette wheel selection method, select the best parent individuals from the current population;

[0060] Step 4.2, Crossover: Cross over the selected parent individuals with probability. Perform a simulated binary crossover operation to generate a new individual;

[0061] Step 4.3, Mutation: Individuals in the new population are subjected to probabilistic mutations. Perform a polynomial mutation operation to introduce random perturbations;

[0062] Step 5, Iteration Loop: Use the newly generated population as the current population, and return to Step 2 to continue execution;

[0063] Step 6: Output the optimal solution: Decode the optimal individual recorded during the optimization process into the final combination of radar parameters, and output it to the simulation scenario configuration module to complete the optimization process.

[0064] A mobile terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the intelligent optimization-based full closed-loop radar signal level simulation method.

[0065] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the intelligent optimization-based full closed-loop radar signal level simulation method.

[0066] Compared with the prior art, the present invention has the following significant advantages: (1) It realizes intelligent closed-loop automated simulation, which can efficiently search for the optimal parameter combination in the multi-dimensional parameter space; (2) It achieves the unity of signal-level simulation accuracy and software flexibility; (3) It improves the sufficiency and reliability of simulation verification through asymmetric optimization strategy and in-depth utilization of signal-level intermediate data. Attached Figure Description

[0067] Figure 1 This is a structural block diagram of a fully closed-loop radar signal level simulation system based on intelligent optimization according to the present invention.

[0068] Figure 2 This is a flowchart illustrating a fully closed-loop radar signal level simulation method based on intelligent optimization according to the present invention.

[0069] Figure 3 This is a flowchart comparing the method of this invention with the traditional open-loop simulation method. Detailed Implementation

[0070] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0071] like Figure 1 As shown, the present invention provides a fully closed-loop radar signal-level simulation system based on intelligent optimization, including a simulation scenario configuration module, a radar signal generation module, a target and environment model module, a radar signal processing module, a data processing and tracking module, a performance evaluation module, and a closed-loop control engine.

[0072] The simulation scenario configuration module is used to set radar parameters, target trajectory, environmental characteristics, and simulation process;

[0073] The radar signal generation module is used to generate radar transmission signals according to the configuration of the simulation scenario configuration module;

[0074] The target and environment model module is used to perform high-precision modeling of target scattering characteristics, electromagnetic propagation environment and interference, and generate synthetic echo signals.

[0075] The radar signal processing module is used to receive echo signals containing target, environment and interference information, and to perform signal processing to extract target traces.

[0076] The data processing and tracking module is used to process the dots to form a target track;

[0077] The performance evaluation module is used to sequentially perform radar signal-level simulation and output performance indicators;

[0078] The closed-loop control engine is used to automatically search in the radar parameter space based on multiple evaluation indicators output by the evaluation module, through multiple simulation iterations, to find the radar parameter combination that optimizes the overall performance of the system, and then feeds back the parameter combination to the simulation scenario configuration module.

[0079] As a specific example, the closed-loop control engine has a built-in global optimization objective function that relates to the overall performance of the radar system, and is configured with an iterative optimization algorithm.

[0080] The closed-loop control engine can be configured with iterative optimization algorithms such as the previous algorithm and particle swarm optimization algorithm. Through multiple simulation iterations, it gradually approaches the optimal solution and finally outputs the optimal radar parameter combination and system performance report.

[0081] The design method of the global optimization function built into the closed-loop control engine adopts the principle of "multi-objective fusion and weight allocation", which integrates multiple competing performance indicators into a single scalar value F. The optimization process is the process of minimizing F.

[0082] The closed-loop control engine is the intelligent core of the entire system. It adopts an asymmetric optimization strategy, such as setting a more stringent convergence threshold for the false alarm rate index than for the tracking accuracy index. At the same time, the closed-loop control engine uses intermediate data from the radar signal processing module, such as the signal-to-noise ratio profile after pulse compression, to adjust the objective function.

[0083] As a specific example, the global objective optimization function is a function that optimizes the tracking accuracy index. Stability indicators Detection power index Resource efficiency indicators The scalar objective function F obtained after weighted fusion;

[0084] The tracking accuracy index The stability index is the root mean square error of the target position. The detection power index represents the target failure rate. The resource efficiency index is used to calculate the average discovery probability. The average transmit power is used as the metric. These evaluation metrics are normalized to eliminate dimensions and uniformly represent a form where smaller values ​​are considered better.

[0085] ,in For reference accuracy, such as 10 meters;

[0086] ,in The ratio is 0 to 1;

[0087] ,in The probability of discovery is converted into the probability of non-discovery.

[0088] ,in Maximum permissible power;

[0089] By using weighted summation, a scalar objective function F is constructed:

[0090]

[0091] in, , , , These are the accuracy weighting coefficient, stability weighting coefficient, discovery probability weighting coefficient, and resource efficiency weighting coefficient, respectively, and they satisfy the following conditions: The weighting coefficients are preset or dynamically configured based on the priorities set in the simulation. When the radar is operating in precision tracking mode, the weighting coefficients are adjusted to ensure accuracy. and stability Assign higher weights, example configuration is as follows When the radar is operating in long-range surveillance mode, the probability of detection is... Assign higher weights, example configuration is as follows When the radar operates in low-power mode, it prioritizes resource efficiency. Assign higher weights, example configuration is as follows This method employs a configurable weight design that is relevant to the task scenario, which is a key feature of this invention for achieving intelligent and adaptive optimization.

[0092] As a specific example, the iterative optimization algorithm is one of the genetic algorithm, particle swarm optimization algorithm or Bayesian optimization algorithm, used to realize the automatic search of radar parameter space.

[0093] As a specific example, the radar parameter space includes at least the radar transmitted waveform, signal bandwidth, pulse repetition frequency, transmit power, and signal processing algorithm threshold.

[0094] As a specific example, the closed-loop control engine employs a comprehensive judgment based on optimization theory and statistical laws, intelligently deciding whether to terminate the iteration by monitoring the optimization process. The specific judgment includes one or more combinations of the following:

[0095] 1. Stability criterion of the objective function: Monitor the change of the objective function F in continuous iterations. If the stability criterion is satisfied after K consecutive iterations...

[0096]

[0097] or

[0098]

[0099] in and If the preset small positive threshold is used, it is determined that the objective function has stabilized and the system has converged;

[0100] 2. Parameter vector stability criterion: Monitor the historical optimal parameter vector. If the key parameters representing the core working mode of the radar remain unchanged for multiple consecutive iterations, and the range of change of numerical parameters is lower than the set threshold of their value space, then the parameter space is considered to have been fully explored and convergence is determined.

[0101] 3. Maximum number of iterations criterion: When the number of iterations reaches the preset upper limit. If the total computation time exceeds the budget, force a convergence check and output the current optimal solution;

[0102] 4. Performance Compliance Criteria: If the performance evaluation results of a certain iteration have met the preset system design threshold... If the condition is met, then convergence is determined.

[0103] The closed-loop control engine comprehensively utilizes the above judgment criteria and adopts the logic of "criterion 1 OR criterion 2 OR criterion 3 OR criterion 4" to make decisions, thereby achieving intelligent convergence judgment that balances optimization accuracy and computational efficiency.

[0104] The key technical solution of the present invention is as follows: the closed-loop control engine adopts an asymmetric optimization strategy, sets differentiated optimization priorities and convergence thresholds for different performance indicators; and during the optimization process, at least in part, the global optimization objective function is constructed or adjusted based on intermediate data from the radar signal processing module.

[0105] like Figure 2 As shown, a fully closed-loop radar signal-level simulation method based on intelligent optimization demonstrates the closed-loop logic of simulation-evaluation-optimization, including the following steps:

[0106] S1. The simulation scenario configuration module initializes the simulation scenario, sets radar parameters, target trajectory, environmental characteristics, and simulation process;

[0107] S2. The radar signal generation module generates radar transmission signals according to the configuration of the simulation scenario configuration module.

[0108] S3, the target and environment model module, performs high-precision modeling of target scattering characteristics, electromagnetic propagation environment and interference, and generates synthetic echoes;

[0109] S4. The radar signal processing module receives echo signals containing target, environment and interference information, and performs signal processing to extract target traces.

[0110] S5, the data processing and tracking module processes the points and forms the target track;

[0111] S6. The performance evaluation module sequentially performs radar signal-level simulation and outputs performance indicators.

[0112] S7. The closed-loop control engine determines whether the acceptance conditions are met. If so, it outputs the optimal parameters and performance report; otherwise, it performs intelligent optimization, generates a new radar parameter set, and feeds it back to the simulation scenario configuration module for the next simulation iteration.

[0113] As a specific example, the intelligent optimization in the closed-loop control engine in step S7 is based on a genetic algorithm and includes the following steps:

[0114] Step 1, Population Initialization: Randomly generate an initial population containing N individuals. Each individual represents a set of radar parameter schemes, which are represented by chromosome encoding. The encoded genes include waveform type, signal bandwidth, pulse repetition frequency, transmission power, and detection threshold.

[0115] Step 2, Fitness Evaluation Cycle: For each individual in the current population, perform the following operations:

[0116] Step 2.1: Decode the chromosome to obtain the specific radar parameter set;

[0117] Step 2.2: Load the parameter set into the simulation scenario configuration module;

[0118] Step 2.3: Run a complete radar signal-level simulation process once;

[0119] Step 2.4: Based on the performance evaluation results, calculate the global optimization objective function value F;

[0120] Step 2.5: According to the formula Fitness = Calculate the fitness of this individual;

[0121] Step 3, Convergence judgment: Record the fitness and parameter set of the best individual in the current population. If any of the following conditions are met, exit the optimization loop and execute step 6.

[0122] (1) The optimal fitness is below the threshold for multiple consecutive generations ;

[0123] (2) The preset maximum number of iterations has been reached;

[0124] (3) The optimal fitness has exceeded the preset performance threshold;

[0125] Step 4, Genetic Operations: If convergence is not achieved, perform the following operations to generate a new generation of the population:

[0126] Step 4.1: Selection: Based on the roulette wheel selection method, select the best parent individuals from the current population;

[0127] Step 4.2, Crossover: Cross over the selected parent individuals with probability. Perform a simulated binary crossover operation to generate a new individual;

[0128] Step 4.3, Mutation: Individuals in the new population are subjected to probabilistic mutations. Perform a polynomial mutation operation to introduce random perturbations;

[0129] Step 5, Iteration Loop: Use the newly generated population as the current population, and return to Step 2 to continue execution;

[0130] Step 6: Output the optimal solution: Decode the optimal individual recorded during the optimization process into the final combination of radar parameters, and output it to the simulation scenario configuration module to complete the optimization process.

[0131] Optimization example: Assume that in the initial random population, the parameters of an individual are...

[0132]

[0133] After simulation evaluation, the fitness was 0.6. After multiple generations of genetic optimization, the final optimal solution may be: Its fitness improved to 0.92, indicating that the system automatically found a parameter combination that significantly outperformed the initial settings in a specific scenario. This intelligent parameter design method demonstrates the deep coupling of optimization algorithms with radar simulation, realizing a shift from "manual parameter testing" to "automatic optimization."

[0134] Figure 3This is a flowchart comparing the method of this invention with the traditional open-loop simulation method. It can be seen that the method of this invention achieves intelligent, fully closed-loop automated simulation, which can efficiently search for the optimal parameter combination in the multi-dimensional parameter space, without relying on human experience to adjust parameters, reducing the impact of personal factors on the simulation process, and improving the sufficiency and reliability of simulation verification.

[0135] The present invention also provides a mobile terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent optimization-based full closed-loop radar signal level simulation method described above.

[0136] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps in the intelligent optimization-based full closed-loop radar signal level simulation method.

[0137] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent optimization based full closed loop radar signal level simulation system, characterized in that, The simulation scenario configuration module, the radar signal generation module, the target and environment model module, the radar signal processing module, the data processing and tracking module, the performance evaluation module, and the closed-loop control engine are included. The simulation scenario configuration module is configured to set radar parameters, target trajectories, environmental characteristics, and simulation processes. The radar signal generation module is configured to generate radar transmission signals according to the configuration of the simulation scenario configuration module. The target and environment model module is configured to model target scattering characteristics, electromagnetic propagation environments, and interference to generate synthetic echoes. The radar signal processing module is configured to receive echo signals containing target, environmental, and interference information, and perform signal processing to extract target point tracks. The data processing and tracking module is configured to process point tracks to form target trajectories. The performance evaluation module is configured to sequentially perform radar signal level simulation and output performance indicators. The closed-loop control engine is configured to automatically search for radar parameter combinations that optimize the overall performance of the system by iteratively simulating and searching in the radar parameter space based on multiple evaluation indicators output by the evaluation module, and feeds back the parameter combinations to the simulation scenario configuration module.

2. The smart optimization based full closed loop radar signal level simulation system of claim 1, wherein, The closed-loop control engine has a global optimization objective function related to the overall performance of the associated radar system and is configured with an iterative optimization algorithm.

3. The smart optimization based full closed loop radar signal level simulation system of claim 2, wherein, The global target optimization function is a scalar target function F obtained by weighted fusion of a tracking accuracy index , a stability index , a detection power index , and a resource efficiency index ​ the tracking accuracy indicator is the root mean square error for the target position, the stability indicator is the target loss rate, the detection power indicator is the average discovery probability, the resource efficiency indicator is the average transmit power; The evaluation indicators are normalized to eliminate dimensions and unified into a form where smaller values are better: wherein is the reference accuracy; wherein is a ratio of 0 to 1; wherein is the discovery probability, converted to the non-discovery probability; wherein is the maximum allowed power; A scalar objective function F is constructed by weighted summation: ； wherein, , , , are precision weight coefficient, stability weight coefficient, discovery probability weight coefficient, resource efficiency weight coefficient respectively, and satisfy , the weight coefficient is preset or dynamically configured according to the priority of the simulation plan, when the radar works in the precision tracking mode, higher weights are given to precision and stability ; when the radar works in the long-range warning mode, higher weights are given to discovery probability ; when the radar works in the low-power mode, higher weights are given to resource efficiency .

4. The smart optimization based full closed loop radar signal level simulation system of claim 2, wherein, The iterative optimization algorithm is one of a genetic algorithm, a particle swarm algorithm, or a Bayesian optimization algorithm, which is used to automatically search the radar parameter space.

5. The smart-optimization-based full-closed-loop radar signal level simulation system of claim 1, wherein, The radar parameter space includes radar transmission waveforms, signal bandwidth, pulse repetition frequency, transmission power, and signal processing algorithm thresholds.

6. The smart-optimization-based full-closed-loop radar signal level simulation system of claim 1, wherein, The closed-loop control engine determines whether the optimization process converges based on the following condition criteria: Criterion 1 is the target function stability criterion: monitor the changes in the local optimization objective function F in consecutive iterations, and if consecutive K iterations satisfy ； or ； wherein and is a preset small positive number threshold, it is judged that the objective function is stable and the system converges. Criterion 2 is the parameter vector stability criterion: monitor the change of the history optimal parameter vector If the key parameters representing the core working mode of the radar remain unchanged for several consecutive iterations, and the change range of numerical parameters is lower than the set threshold of their value space, it is considered that the parameter space has been fully explored, and convergence is judged. Criterion 3 is the maximum iteration number criterion: when the iteration number reaches the preset upper limit or the total computation time exceeds the budget, the convergence is forced to be judged, and the current optimal solution is output Criterion 4 is a performance criterion: if the performance evaluation result of a certain iteration has met the preset system design index threshold convergence is determined. The closed-loop control engine uses the above criteria to make decisions using the "Criterion 1 OR Criterion 2 OR Criterion 3 OR Criterion 4" logic to achieve intelligent convergence judgment that balances optimization accuracy and computational efficiency.

7. A smart optimization-based full closed loop radar signal level simulation method, characterized in that, The method is based on the intelligent optimization-based full-closed-loop radar signal level simulation system of any one of claims 1-6, comprising the following steps: S1, the simulation scenario configuration module initializes the simulation scenario, sets the radar parameters, target trajectories, environmental characteristics, and simulation processes; S2, the radar signal generation module generates radar transmission signals according to the configuration of the simulation scenario configuration module; S3, the target and environment model module models target scattering characteristics, electromagnetic propagation environments, and interference to generate synthetic echoes; S4, the radar signal processing module receives echo signals containing target, environmental, and interference information, and performs signal processing to extract target point tracks; S5, the data processing and tracking module processes point tracks to form target trajectories; S6, the performance evaluation module sequentially performs radar signal level simulation and outputs performance indicators; S7, the closed-loop control engine determines whether the acceptance condition is met, yes, output the optimal parameters and performance report, otherwise, intelligent optimization is performed, a new radar parameter set is generated, and is fed back to the simulation scenario configuration module for next simulation iteration.

8. The smart optimization based full closed loop radar signal level simulation method of claim 7, wherein, The intelligent optimization in S7 is realized based on a genetic algorithm, and specifically includes the following steps: Step 1, population initialization: an initial population containing N individuals is randomly generated, each individual represents a radar parameter scheme, which is represented by chromosome coding, and the coding genes include waveform type, signal bandwidth, pulse repetition frequency, transmit power and detection threshold; Step 2, fitness evaluation cycle: for each individual in the current population, the following operations are performed: Step 2.1, decode the chromosome to obtain a specific radar parameter set; Step 2.2, load the parameter set into the simulation scenario configuration module; Step 2.3, run a complete radar signal level simulation process; Step 2.4, according to the performance evaluation result, calculate the global optimization objective function value F; Step 2.5: According to the formula Fitness = Calculate the fitness of this individual; Step 3, convergence judgment: record the fitness and parameter set of the optimal individual in the current population, if any of the following conditions is met, exit the optimization loop and execute step 6; (1) Optimal fitness continues for multiple generations below a threshold ; (2) the maximum preset iteration number has been reached; (3) the optimal fitness has exceeded the preset performance threshold; Step 4, genetic operation: if not converged, the following operations are performed to generate a new population: Step 4.1, selection: based on roulette selection method, select parent individuals from the current population; Step 4.2, Crossover: Selected parent individuals are crossed over with a probability of 0.9 Perform a simulated binary crossover operation to produce new individuals; Step 4.3, Mutation: Individuals in the new population are mutated with probability A polynomial mutation operation is performed, introducing random perturbations; Step 5, iteration cycle: take the newly generated population as the current population and return to step 2 for continuous execution; Step 6, output the optimal solution: decode the optimal individual recorded in the optimization process into the final radar parameter combination, and output it to the simulation scenario configuration module to complete the optimization process.

9. A mobile terminal comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the full closed-loop radar signal level simulation method based on intelligent optimization in claim 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the steps in the full closed-loop radar signal level simulation method based on intelligent optimization in claim 8.

Images