Construction method and system of high-frequency sensor simulation antenna
Through the combination of machine learning and electromagnetic field simulation, multi-dimensional model data of high-frequency sensors are processed, virtual radiation elements are generated and adaptive optimization is carried out, which solves the problems of insufficient simulation accuracy and incomplete robustness evaluation, and realizes that high-frequency sensor antennas are complex High precision and high stability construction in the environment.
Patent Information
- Application Number
- CN202410975233.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the simulation design of high-frequency sensor antennas, the simulation accuracy is insufficient and the robustness evaluation is incomplete, making it difficult to meet high reliability and stability requirements under complex electromagnetic environments and non-ideal conditions.
The machine learning model is used to process the multi-dimensional model data of high-frequency sensors, generate virtual radiation elements, and tune it through electromagnetic field distribution spectrum and evaluation model, combine random noise and extreme stress testing to generate environmental adaptability prediction indicators, and realize adaptive adjustment parameters. optimization.
Improve simulation accuracy and robustness evaluation, ensure high performance and long-term stability of the antenna in complex environments, and enhance the practicality and reliability of the design.
Smart Images

Figure CN118917190A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of simulated antennas, and in particular to a construction method and system for a high-frequency sensor simulated antenna. Background Art
[0002] With the rapid development of wireless communication technology, high-frequency sensors are increasingly used in civil and military fields. These sensors are often used in critical applications such as signal acquisition, radar systems, and navigation equipment. The quality of their performance directly affects the accuracy and stability of the entire system. Therefore, the design and simulation of high-frequency sensor antennas have become particularly important. In the high-frequency range, the propagation and interaction of electromagnetic waves become complex and highly nonlinear, requiring sensors to maintain high performance and high reliability under various environmental conditions. When it comes to simulation design, accurately estimating the performance of the antenna in the real working environment is of decisive significance to ensure the reliable operation of the equipment.
[0003] Among the related technical means, traditional simulation software is used to simulate the electromagnetic field and adjust the antenna parameters. Through these software, the antenna model is visually constructed and the theoretical data of electromagnetic wave propagation is instantly obtained. However, this technical means is often limited to an idealized simulation environment and is insufficient to simulate the complex electromagnetic environment and unpredictable interference factors in the real world.
[0004] For the above technical solutions, although traditional simulation software can simulate and predict antenna performance to a certain extent, there are large deviations and instability problems in actual complex electromagnetic environments and non-ideal working conditions. In addition, traditional methods are relatively weak in evaluating the nonlinear functions and environmental adaptability of antennas, and lack effective robustness considerations, so that the final antenna design may not meet the high reliability and stability requirements of actual applications. Summary of the invention
[0005] In order to improve the problems of insufficient simulation accuracy and incomplete robustness evaluation during the simulation process, the present application provides a method and system for constructing a high-frequency sensor simulation antenna.
[0006] The present invention provides a method for constructing a high-frequency sensor simulation antenna, comprising: obtaining multi-dimensional model data of the high-frequency sensor, inputting the multi-dimensional model data into a preset machine learning model to obtain multiple types of virtual radiation elements, sorting the multiple types of virtual radiation elements to obtain the radiation structure of the high-frequency sensor; performing a joint analysis on the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, performing a tuning process on the high-frequency sensor according to the electromagnetic field distribution spectrum to obtain the working parameters of the high-frequency sensor; inputting the working parameters of the high-frequency sensor into a preset evaluation model to output a stability index, inputting the stability index into a preset performance model to output a performance attenuation index number, perform trend analysis and fluctuation limit on the performance attenuation index, and generate an environmental adaptability prediction index; obtain the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and perform random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptability model; input the environmental adaptability prediction index into the comprehensive environmental adaptability model, output an enhanced robust index, perform real-time performance feedback on the enhanced robust index, and obtain an adaptive adjustment parameter; optimize the working parameters of the high-frequency sensor according to the adaptive adjustment parameter, adjust the high-frequency sensor according to the optimized working parameters of the high-frequency sensor, and complete the construction of the simulated antenna of the high-frequency sensor.
[0007] As a preferred solution, the steps of obtaining multidimensional model data of the high-frequency sensor, inputting the multidimensional model data into a preset machine learning model, obtaining multiple types of virtual radiating elements, sorting the multiple types of virtual radiating elements, and obtaining the radiation structure of the high-frequency sensor include: presetting multiple sensor nodes in the operating environment of the high-frequency sensor, collecting electromagnetic field strength, frequency distribution and waveform characteristics according to each of the sensor nodes, and using the electromagnetic field strength, the frequency distribution and the waveform characteristics as multidimensional model data; preprocessing the multidimensional model data, inputting the preprocessed multidimensional model data into a preset machine learning model, and obtaining multiple types of virtual radiating elements; wherein the virtual radiating elements include radiation efficiency, working bandwidth and resistance to environmental interference; sorting the various types of virtual radiating elements according to the radiation efficiency, the working bandwidth and the resistance to environmental interference, combining and optimizing the sorted virtual radiating elements to obtain the radiation structure with the best comprehensive performance, and using the radiation structure with the best comprehensive performance as the radiation structure of the high-frequency sensor.
[0008] As a preferred solution, the steps of jointly analyzing the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, tuning the high-frequency sensor according to the electromagnetic field distribution spectrum, and obtaining the working parameters of the high-frequency sensor include: importing the radiation structure of the high-frequency sensor into a simulation platform, and presetting simulation environment parameters in the simulation platform; simulating in the simulation platform based on the radiation structure of the high-frequency sensor and the simulation environment parameters to obtain initial simulation results, and generating an electromagnetic field distribution spectrum according to the initial simulation results; evaluating the radiation performance of the high-frequency sensor under different frequencies and environments according to the data of the electromagnetic field distribution spectrum to obtain evaluation results; tuning the radiation structure and simulation environment parameters of the high-frequency sensor based on the evaluation results, simulating the radiation structure and simulation environment parameters of the tuned high-frequency sensor again to obtain target simulation results, extracting features from the target simulation results to obtain key working parameters, and using the key working parameters as the working parameters of the high-frequency sensor.
[0009] As a preferred scheme, the step of performing trend analysis and fluctuation limitation on the performance decay index to generate an environmental adaptability prediction index includes: performing trend analysis on the performance decay index to obtain a performance change trend curve; wherein the trend analysis identifies the performance degradation trend through time series prediction; performing fluctuation limitation on the performance decay index to obtain a performance stability interval; wherein the fluctuation limitation determines a control threshold of performance fluctuation through a statistical control chart; and generating an environmental adaptability prediction index based on the performance change trend curve and the performance stability interval.
[0010] As a preferred solution, the steps of obtaining the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and performing random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model include: collecting data on the noise of the simulation environment according to actual environmental measurements, performing statistical analysis on the collected noise, and obtaining a random noise distribution; conducting a preliminary evaluation on the impact of changes in environmental variables and working conditions on the performance of the high-frequency sensor, obtaining the weights of the impact of various factors on the performance, and using the weights of the impact of various factors on the performance as the parameter set under non-ideal working conditions; performing Monte Carlo simulation on the random noise distribution and the parameter set under the non-ideal working conditions to obtain performance impact; performing extreme stress test on the random noise distribution and the parameter set under the non-ideal working conditions according to preset extreme working conditions to obtain test results; wherein the extreme working conditions are the working conditions of the high-frequency sensor exposed to harsh environmental conditions; inputting the performance impact and the test results into a preset environmental adaptability evaluation model, outputting a performance fluctuation range and a prediction result; and generating a comprehensive environmental adaptation model according to the performance fluctuation range and the prediction result.
[0011] As a preferred scheme, the steps of inputting the environmental adaptability prediction index into the comprehensive environmental adaptability model, outputting an enhanced robust index, performing real-time performance feedback on the enhanced robust index, and obtaining an adaptive adjustment parameter include: integrating and optimizing the environmental adaptability prediction index through data fusion technology to obtain an optimized environmental adaptability prediction index; inputting the optimized environmental adaptability prediction index into the comprehensive environmental adaptability model to output an enhanced robust index; performing real-time performance feedback on the enhanced robust index based on a predictive control or adaptive control algorithm to obtain an adjustment parameter optimized for the current environmental conditions; evaluating and verifying the adjustment parameter to obtain a verified adaptive parameter, and using the verified adaptive parameter as an adaptive adjustment parameter.
[0012] The present application also provides a system for constructing a high-frequency sensor simulation antenna, including: an acquisition module, used to acquire multi-dimensional model data of the high-frequency sensor, input the multi-dimensional model data into a preset machine learning model, obtain multiple types of virtual radiation elements, sort the multiple types of virtual radiation elements, and obtain the radiation structure of the high-frequency sensor; an analysis module, used to jointly analyze the high-frequency sensor based on the radiation structure of the high-frequency sensor, generate an electromagnetic field distribution spectrum, tune the high-frequency sensor according to the electromagnetic field distribution spectrum, and obtain the working parameters of the high-frequency sensor; a generation module, used to input the working parameters of the high-frequency sensor into a preset evaluation model, output a stability index, input the stability index into a preset performance model, and output a performance attenuation index. An index is provided for performing trend analysis and fluctuation limitation on the performance attenuation index to generate an environmental adaptability prediction index; a test module is provided to obtain the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and to perform random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptability model; a feedback module is provided to input the environmental adaptability prediction index into the comprehensive environmental adaptability model, output an enhanced robust index, perform real-time performance feedback on the enhanced robust index, and obtain an adaptive adjustment parameter; an optimization module is provided to optimize the working parameters of the high-frequency sensor according to the adaptive adjustment parameter, adjust the high-frequency sensor according to the optimized working parameters of the high-frequency sensor, and complete the construction of the simulated antenna of the high-frequency sensor.
[0013] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method for constructing a high-frequency sensor simulation antenna described in any one of the above is implemented.
[0014] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the method for constructing a high-frequency sensor simulation antenna as described in any one of the above.
[0015] Compared with the prior art, the present application has the following beneficial effects: high simulation accuracy and comprehensive robustness evaluation. By collecting detailed multi-dimensional model data of sensors and applying machine learning models, the configuration of radiation elements is efficiently generated and optimized, ensuring that the antenna design process responds quickly and adapts to design change requirements. Combined with electromagnetic field simulation analysis, the precise control of antenna working parameters is improved, and the prediction accuracy of antenna performance is enhanced. The introduction of evaluation models and performance models allows the evaluation of the stability and anti-interference ability of antennas in various environments, ensuring the long-term robustness of antenna performance. By simulating random noise and non-ideal working conditions in real environments, the model can predict the adaptability of antennas in a variety of complex environments, and generate environmental adaptability prediction indicators based on this, thereby further enhancing the practical application value of the simulation model. The determination and implementation of adaptive adjustment parameters provide real-time optimization of antenna performance, realizing the high-precision and high-stability construction of simulated antennas, greatly improving the practicality and reliability of antenna design, and improving the problems of insufficient simulation accuracy and incomplete robustness evaluation in the simulation process. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0017] The structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.
[0018] Figure 1 It is a flow chart of a method for constructing a high-frequency sensor simulation antenna provided by an embodiment of the present invention; Figure 2 is a schematic block diagram of the structure of a system for constructing a high-frequency sensor simulation antenna provided by an embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.
[0019] Description of reference numerals: 10. Construction system of high-frequency sensor simulation antenna; 11. Acquisition module; 12. Analysis module; 13. Generation module; 14. Testing module; 15. Feedback module; 16. Optimization module; 20. Electronic device; 21. Memory; 22. Processor. DETAILED DESCRIPTION
[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0022] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0023] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0024] The technical solution of the present invention is further described below with reference to the accompanying drawings and through specific implementation methods.
[0025] Embodiment 1: like Figure 1 As shown, the method for constructing a high-frequency sensor simulation antenna provided in an embodiment of the present application includes steps S100 to S600.
[0026] Step S100, obtaining multidimensional model data of the high-frequency sensor, inputting the multidimensional model data into a preset machine learning model, obtaining multiple types of virtual radiation elements, sorting the multiple types of virtual radiation elements, and obtaining the radiation structure of the high-frequency sensor.
[0027] In this step, the geometric data of the sensor is obtained using 3D modeling software or CAD tools and converted into a format suitable for processing by machine learning algorithms. Specifically, deep learning algorithms such as convolutional neural networks (CNNs) can be used to identify and classify different radiation element characteristics, and recommend the optimal radiation structure arrangement based on this.
[0028] For example, by analyzing how different parts of a sensor affect signal frequency and radiation direction, a machine learning model can predict the radiation performance of each component and rank them by efficiency.
[0029] Step S200: jointly analyzing the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, tuning the high-frequency sensor according to the electromagnetic field distribution spectrum to obtain working parameters of the high-frequency sensor.
[0030] In this step, electromagnetic simulation software such as ANSYS HFSS is used to perform full-wave simulation analysis of the high-frequency sensor to obtain accurate electromagnetic field distribution; specifically, the geometric dimensions and material properties of the sensor are adjusted through parameter scanning and optimization tools to achieve the desired resonant frequency and frequency band characteristics.
[0031] For example, the tuning process includes adjusting the antenna's length, width, feed line location, or spacing of radiating elements to optimize S-parameters and radiation patterns.
[0032] Step S300: input the working parameters of the high-frequency sensor into a preset evaluation model, output a stability index, input the stability index into a preset performance model, output a performance attenuation index, perform trend analysis and fluctuation limit on the performance attenuation index, and generate an environmental adaptability prediction index.
[0033] In this step, the operating parameters are calculated using the finite element method (FEM) and input into the evaluation model to evaluate their stability under different operating conditions. Specifically, Monte Carlo simulation or other statistical analysis methods are used to predict and quantify the performance fluctuations of the antenna under various interferences.
[0034] For example, by simulating working scenarios under different temperature, humidity, vibration and other conditions, indicators such as the antenna's working life cycle and failure rate can be estimated.
[0035] Step S400: Obtain random noise distribution of the simulation environment and a parameter set under non-ideal working conditions, and perform random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model.
[0036] In this step, variables encountered by sensors in real environments, such as electromagnetic interference, vibration, temperature changes, etc., are collected, and statistical models are established to evaluate the performance of sensors under such non-ideal conditions; specifically, the extreme working conditions of sensors are tested through designed experiments and accelerated life tests.
[0037] For example, Gaussian noise models are used to simulate random interference in electromagnetic fields, and fault tree analysis (FTA) and failure mode and effects analysis (FMEA) are used to evaluate the anti-interference capabilities of key components.
[0038] Step S500: input the environmental adaptability prediction index into the comprehensive environmental adaptability model, output the enhanced robust index, perform real-time performance feedback on the enhanced robust index, and obtain the adaptive adjustment parameter.
[0039] In this step, based on the above statistical analysis results, artificial intelligence or optimization algorithms are used to extract more accurate robustness standards; specifically, environmental adaptability prediction indicators will be updated in real time to guide the dynamic adjustment of sensor parameters.
[0040] For example, using evolutionary algorithms such as genetic algorithms or particle swarm optimization (PSO), the working parameters are continuously updated based on the performance feedback obtained.
[0041] Step S600: optimizing the working parameters of the high-frequency sensor according to the adaptive adjustment parameters, adjusting the high-frequency sensor according to the optimized working parameters of the high-frequency sensor, and completing the construction of the simulated antenna of the high-frequency sensor.
[0042] In this step, the optimized parameters are used to make final design modifications to the sensor; specifically, this includes modifying the dimensions of the antenna, selecting different materials, or adjusting the configuration of the matching network.
[0043] For example, sensors can be equipped with appropriate antenna gain control, directivity adjustment or spectrum selection functions depending on the environment and application requirements.
[0044] In the above embodiment, by collecting detailed multi-dimensional model data of the sensor and applying the machine learning model, the radiation element configuration is efficiently generated and optimized, ensuring that the antenna design process responds quickly and adapts to design change requirements; further, combined with electromagnetic field simulation analysis, the precise control of antenna operating parameters is improved, and the prediction accuracy of antenna performance is enhanced, and the introduction of evaluation models and performance models allows the evaluation of the stability and anti-interference ability of the antenna in various environments, ensuring the long-term robustness of the antenna performance; by simulating random noise and non-ideal working conditions in the real environment, the model can predict the adaptability of the antenna in a variety of complex environments, and generate environmental adaptability prediction indicators based on this, thereby further enhancing the practical application value of the simulation model; finally, through the determination and implementation of adaptive adjustment parameters, real-time optimization of antenna performance is provided, and high-precision and high-stability construction of simulated antennas is achieved, which greatly improves the practicality and reliability of antenna design, and improves the problems of insufficient simulation accuracy and incomplete robustness evaluation in the simulation process.
[0045] Embodiment 2: In step S100, multiple sensor nodes are preset in the operating environment of the high-frequency sensor, and the electromagnetic field strength, frequency distribution and waveform characteristics are collected according to each sensor node, and the electromagnetic field strength, frequency distribution and waveform characteristics are used as multidimensional model data; the multidimensional model data is preprocessed, and the preprocessed multidimensional model data is input into a preset machine learning model to obtain multiple types of virtual radiation elements; wherein the virtual radiation elements include radiation efficiency, working bandwidth and resistance to environmental interference; according to the radiation efficiency, working bandwidth and resistance to environmental interference, the various types of virtual radiation elements are sorted, and the sorted virtual radiation elements of various types are combined and optimized to obtain the radiation structure with the best comprehensive performance, and the radiation structure with the best comprehensive performance is used as the radiation structure of the high-frequency sensor.
[0046] By deploying multiple sensor nodes in the high-frequency sensor operating environment, the electromagnetic field strength, frequency distribution and waveform feature information collected by each node are used as elements to constitute the multidimensional model data; the multidimensional model data is preprocessed to improve the quality and relevance of the data, and then the preprocessed data is input into a pre-established machine learning model; the model can identify and generate various types of virtual radiation elements based on the input data, and sort them according to characteristics such as radiation efficiency, working bandwidth and resistance to environmental interference, and then combine these virtual radiation elements to optimize the radiation structure with the best comprehensive performance, and finally determine the radiation structure of the high-frequency sensor; use advanced data preprocessing techniques such as normalization, denoising and feature selection; specifically, analyze the frequency domain and time domain characteristics of the signal to remove redundant information and strengthen the important features of model training.
[0047] For example, methods such as Fourier transform can be used to analyze waveform features, and then methods such as principal component analysis (PCA) or autoencoders can be applied to reduce dimensionality and extract key features.
[0048] In step S200, the radiation structure of the high-frequency sensor is imported into the simulation platform, and the simulation environment parameters are preset in the simulation platform; simulation is performed in the simulation platform based on the radiation structure and simulation environment parameters of the high-frequency sensor to obtain initial simulation results, and an electromagnetic field distribution spectrum is generated according to the initial simulation results; the radiation performance of the high-frequency sensor under different frequencies and environments is evaluated according to the data of the electromagnetic field distribution spectrum to obtain evaluation results; the radiation structure and simulation environment parameters of the high-frequency sensor are tuned based on the evaluation results, and the radiation structure and simulation environment parameters of the tuned high-frequency sensor are simulated again to obtain target simulation results, feature extraction is performed on the target simulation results to obtain key working parameters, and the key working parameters are used as working parameters of the high-frequency sensor.
[0049] Detailed electromagnetic simulations are performed using advanced simulation software such as CST Studio Suite or ANSYS HFSS; specifically, the parametric modeling and optimization tools in these software are used to iteratively improve the antenna design and simulation conditions.
[0050] For example, the optimization modules of simulation software, such as genetic algorithms or particle swarm optimization (PSO), can be used to automatically adjust the antenna dimensions and simulation settings to achieve the expected performance indicators.
[0051] In step S300, a trend analysis is performed on the performance decay index to obtain a performance change trend curve; wherein the trend analysis identifies the performance degradation trend through time series prediction; the performance decay index is subjected to fluctuation restriction to obtain a performance stability interval; wherein the fluctuation restriction determines the control threshold of the performance fluctuation through a statistical control chart; and an environmental adaptability prediction index is generated according to the performance change trend curve and the performance stability interval.
[0052] By using ARIMA, neural network or other time series prediction models to analyze performance data, pattern recognition and prediction of long-term performance decay data can be performed to visualize performance change trends; at the same time, the statistical control chart method is used to set upper and lower control limits of performance stability, that is, fluctuation limits, to ensure that performance is within an acceptable range; finally, the trend line and stability interval are combined to generate a prediction indicator that reflects the adaptability of the sensor under various environmental conditions. Specifically, statistical methods running on historical data are used to set the limits of performance fluctuations.
[0053] For example, by analyzing historical performance data and using control chart technology to identify abnormal performance changes, data support can be provided for maintaining system stability.
[0054] In step S400, data is collected on the noise of the simulation environment according to the actual environment measurement, and the collected noise is statistically analyzed to obtain the random noise distribution; a preliminary evaluation is performed on the impact of changes in environmental variables and working conditions on the performance of the high-frequency sensor, and the weights of the impact of various factors on the performance are obtained, and the weights of the impact of various factors on the performance are used as the parameter set under non-ideal working conditions; Monte Carlo simulation is performed on the random noise distribution and the parameter set under non-ideal working conditions to obtain the performance impact; extreme stress testing is performed on the random noise distribution and the parameter set under non-ideal working conditions according to preset extreme working conditions to obtain test results; wherein the extreme working conditions are the working conditions of the high-frequency sensor exposed to harsh environmental conditions; the performance impact and the test results are input into a preset environmental adaptability evaluation model, and the performance fluctuation range and prediction results are output; a comprehensive environmental adaptability model is generated according to the performance fluctuation range and the prediction results.
[0055] Environmental noise data is collected through a sensor network in an actual environment, and statistical analysis is performed on these data to obtain the distribution characteristics of the noise; the impact of changing environmental variables and working conditions on performance is evaluated to determine the weight of the impact and form a parameter set under non-ideal working conditions; then, a large number of random experiments are conducted on these parameter sets using the Monte Carlo method to predict the impact on performance; and stress tests are performed based on set extreme conditions to test the performance of sensors in extreme environments; finally, these data are input into an environmental adaptability evaluation model to define the performance fluctuation range and obtain more robust prediction results, and a comprehensive environmental adaptation model is established based on this; specifically, Monte Carlo simulation is used to simulate and test various random factors such as temperature fluctuations and electromagnetic interference.
[0056] For example, it is possible to simulate scenarios where sensors are exposed to severe cold, high heat, high humidity, or electromagnetic pollution, and record the corresponding performance degradation for subsequent model training and verification.
[0057] In step S500, the environmental adaptability prediction index is integrated and optimized by data fusion technology to obtain the optimized environmental adaptability prediction index; the optimized environmental adaptability prediction index is input into the comprehensive environmental adaptability model to output the enhanced robust index; the enhanced robust index is given real-time performance feedback based on the predictive control or adaptive control algorithm to obtain the adjustment parameters optimized for the current environmental conditions; the adjustment parameters are evaluated and verified to obtain the verified adaptive parameters, and the verified adaptive parameters are used as the adaptive adjustment parameters.
[0058] By adopting data fusion technology, such as sensor fusion or decision-level fusion, the environmental adaptability prediction indicators obtained from different sources are integrated to improve their accuracy and reliability; these optimized prediction indicators are input into the comprehensive environmental adaptation model that has been tested and verified, so as to obtain enhanced robust indicators that can be used to face current environmental conditions; at the same time, predictive control and adaptive control algorithms are used for real-time performance analysis and feedback, and sensor adjustment parameters are optimized according to the results; and these adjustment parameters are actually tested to verify their effectiveness, and the final adaptive adjustment parameters are obtained for reference in practical applications; data from multiple sensors and information sources are combined to increase the dimension of prediction and improve the accuracy of the results; specifically, fuzzy logic, Kalman filtering and other methods are used to optimize the data fusion process.
[0059] For example, the data from temperature sensors, humidity sensors, and electromagnetic sensors can be comprehensively considered and integrated through weighted averaging or neural networks to ultimately obtain indicators that better represent the actual environmental conditions and adjust the antenna's operating parameters accordingly.
[0060] In this embodiment, by collecting sensor data in the actual environment and combining machine learning and simulation technology, the performance prediction and adaptability of the high-frequency sensor antenna in different environments are improved, and then its design and tuning working parameters are optimized to achieve better robustness and real-time adaptability.
[0061] Embodiment 3: like Figure 2 As shown, the present application also provides a system 10 for constructing a high-frequency sensor simulation antenna, which includes an acquisition module 11, an analysis module 12, a generation module 13, a test module 14, a feedback module 15 and an optimization module 16.
[0062] The acquisition module 11 is mainly used to acquire multi-dimensional model data of the high-frequency sensor, input the multi-dimensional model data into a preset machine learning model, obtain multiple types of virtual radiation elements, sort the multiple types of virtual radiation elements, and obtain the radiation structure of the high-frequency sensor; The analysis module 12 is mainly used to perform joint analysis on the high-frequency sensor based on the radiation structure of the high-frequency sensor, generate an electromagnetic field distribution spectrum, perform tuning processing on the high-frequency sensor according to the electromagnetic field distribution spectrum, and obtain the working parameters of the high-frequency sensor; The generation module 13 is mainly used to input the working parameters of the high-frequency sensor into a preset evaluation model, output a stability index, input the stability index into a preset performance model, output a performance attenuation index, perform trend analysis and fluctuation limit on the performance attenuation index, and generate an environmental adaptability prediction index; The test module 14 is mainly used to obtain the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and to perform random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model; The feedback module 15 is mainly used to input the environmental adaptability prediction index into the comprehensive environmental adaptability model, output the enhanced robust index, and perform real-time performance feedback on the enhanced robust index to obtain the adaptive adjustment parameter; The optimization module 16 is mainly used to optimize the working parameters of the high-frequency sensor according to the adaptive adjustment parameters, adjust the high-frequency sensor according to the optimized working parameters of the high-frequency sensor, and complete the construction of the simulation antenna of the high-frequency sensor.
[0063] In this embodiment, a systematic construction of a high-frequency sensor simulation antenna is achieved by integrating multiple specialized modules. The acquisition module 11 is responsible for collecting key data and analyzing these data using machine learning technology to construct the radiation characteristics of the sensor. The analysis module 12 allows for an in-depth understanding of the radiation structure of the sensor and generates a complex electromagnetic field distribution to guide further tuning. The generation module 13 combines the operating parameters obtained by the analysis with a predetermined performance model to predict the stability and performance degradation of the sensor and output environmental adaptability indicators. The test module 14 performs random simulation and extreme value testing on noise and potential non-ideal conditions in simulation and real environments to construct a comprehensive adaptability model. The feedback module 15 uses the obtained prediction indicators to perform real-time performance monitoring and output adaptive adjustment parameters to optimize sensor performance. The optimization module 16 is responsible for parameter optimization based on feedback to ensure that the final design of the sensor can meet the expected performance requirements.
[0064] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned high-frequency sensor simulation antenna construction method embodiment, and will not be repeated here.
[0065] Embodiment 4: like Figure 3 As shown, the present application also provides an electronic device 20, including a memory 21 and a processor 22, the memory 21 stores a computer program that can be run on the processor 22, and when the processor 22 executes the computer program, the method for constructing the high-frequency sensor simulation antenna in Example 1 is implemented.
[0066] In this embodiment, by storing the simulation antenna construction method in Embodiment 1 in the form of a computer program in the memory 21, the program can be executed by the processor 22 on the electronic device 20. Such a configuration facilitates the deployment and operation of the construction method on different electronic devices 20, and realizes efficient calculation of the algorithm and accurate simulation of the model. During the execution of the program by the processor 22, each step is automatically implemented in sequence, from data acquisition to the final antenna parameter optimization, ensuring the consistency and reliability of the simulation process, while improving the design efficiency.
[0067] Embodiment 5: The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the processor executes the construction method and system method of the high-frequency sensor simulation antenna as in Example 1.
[0068] In this embodiment, by encoding the method in Embodiment 1 into a computer program and storing it on a computer-readable storage medium, the method can be easily implemented on different computing platforms. When the computer program is read and executed by the processor, the processor follows the steps described in Embodiment 1 to complete the construction process of the high-frequency sensor simulation antenna. Such an implementation provides antenna designers with a high degree of flexibility, enabling them to execute these complex simulation and optimization algorithms on computing devices with various hardware configurations, thereby optimizing the design and testing process.
[0069] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for constructing a high-frequency sensor simulation antenna, characterized in that: include: Acquire multidimensional model data of the high-frequency sensor, input the multidimensional model data into a preset machine learning model to obtain multiple types of virtual radiation elements, sort the multiple types of virtual radiation elements, and obtain the radiation structure of the high-frequency sensor; Performing joint analysis on the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, performing tuning processing on the high-frequency sensor according to the electromagnetic field distribution spectrum to obtain working parameters of the high-frequency sensor; Inputting the working parameters of the high-frequency sensor into a preset evaluation model to output a stability index, inputting the stability index into a preset performance model to output a performance decay index, performing trend analysis and fluctuation limitation on the performance decay index, and generating an environmental adaptability prediction index; Obtaining random noise distribution of a simulation environment and a parameter set under non-ideal working conditions, and performing random process simulation and extreme stress testing on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model; Inputting the environmental adaptability prediction index into the comprehensive environmental adaptability model, outputting an enhanced robust index, performing real-time performance feedback on the enhanced robust index, and obtaining an adaptive adjustment parameter; The working parameters of the high-frequency sensor are optimized according to the adaptive adjustment parameters, and the high-frequency sensor is adjusted according to the optimized working parameters of the high-frequency sensor to complete the construction of the simulated antenna of the high-frequency sensor.
2. The method for constructing a high-frequency sensor simulation antenna according to claim 1, characterized in that: The step of obtaining multi-dimensional model data of the high-frequency sensor, inputting the multi-dimensional model data into a preset machine learning model, obtaining multiple types of virtual radiation elements, and sorting the multiple types of virtual radiation elements to obtain the radiation structure of the high-frequency sensor includes: A plurality of sensor nodes are preset in the operating environment of the high-frequency sensor, and electromagnetic field strength, frequency distribution and waveform characteristics are collected according to each of the sensor nodes, and the electromagnetic field strength, frequency distribution and waveform characteristics are used as multi-dimensional model data; Preprocessing the multidimensional model data, inputting the preprocessed multidimensional model data into a preset machine learning model to obtain multiple types of virtual radiation elements; wherein the virtual radiation elements include radiation efficiency, working bandwidth, and resistance to environmental interference; According to the radiation efficiency, the working bandwidth and the resistance to environmental interference, various types of virtual radiation elements are sorted, and the sorted virtual radiation elements of various types are combined and optimized to obtain a radiation structure with the best comprehensive performance, and the radiation structure with the best comprehensive performance is used as the radiation structure of the high-frequency sensor.
3. The method for constructing a high-frequency sensor simulation antenna according to claim 1, characterized in that: The step of jointly analyzing the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, tuning the high-frequency sensor according to the electromagnetic field distribution spectrum to obtain the working parameters of the high-frequency sensor includes: Importing the radiation structure of the high-frequency sensor into a simulation platform, and presetting simulation environment parameters in the simulation platform; Performing simulation in the simulation platform based on the radiation structure of the high-frequency sensor and the simulation environment parameters to obtain an initial simulation result, and generating an electromagnetic field distribution spectrum according to the initial simulation result; Evaluate the radiation performance of the high-frequency sensor under different frequencies and environments according to the data of the electromagnetic field distribution spectrum to obtain an evaluation result; Based on the evaluation result, the radiation structure and simulation environment parameters of the high-frequency sensor are tuned, the radiation structure and simulation environment parameters of the tuned high-frequency sensor are simulated again to obtain target simulation results, feature extraction is performed on the target simulation results to obtain key working parameters, and the key working parameters are used as the working parameters of the high-frequency sensor.
4. The method for constructing a high-frequency sensor simulation antenna according to claim 1, characterized in that: The step of performing trend analysis and fluctuation limitation on the performance decay index to generate an environmental adaptability prediction index comprises: Performing trend analysis on the performance decay index to obtain a performance change trend curve; wherein the trend analysis identifies the performance degradation trend through time series prediction; Limiting the fluctuation of the performance attenuation index to obtain a performance stability interval; wherein the fluctuation limit determines a control threshold of the performance fluctuation through a statistical control chart; An environmental adaptability prediction index is generated according to the performance change trend curve and the performance stability interval.
5. The method for constructing a high-frequency sensor simulation antenna according to claim 1, characterized in that: The step of obtaining the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and performing random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model includes: According to the actual environment measurement, the noise data of the simulation environment is collected, and the collected noise is statistically analyzed to obtain the random noise distribution; A preliminary evaluation is performed on the impact of changes in environmental variables and working conditions on the performance of the high-frequency sensor, and the weights of the impact of various factors on the performance are obtained, and the weights of the impact of various factors on the performance are used as a parameter set under non-ideal working conditions; Performing Monte Carlo simulation on the random noise distribution and the parameter set under the non-ideal working condition to obtain performance impact; Performing extreme stress tests on the random noise distribution and the parameter set under the non-ideal working conditions according to preset extreme working conditions to obtain test results; wherein the extreme working conditions are working conditions of the high-frequency sensor exposed to harsh environmental conditions; Input the performance impact and the test results into a preset environmental adaptability evaluation model, and output the performance fluctuation range and prediction results; A comprehensive environmental adaptation model is generated according to the performance fluctuation range and the prediction result.
6. The method for constructing a high-frequency sensor simulation antenna according to claim 1, characterized in that: The step of inputting the environmental adaptability prediction index into the comprehensive environmental adaptability model, outputting an enhanced robust index, performing real-time performance feedback on the enhanced robust index, and obtaining an adaptive adjustment parameter includes: The environmental adaptability prediction index is integrated and optimized by using data fusion technology to obtain an optimized environmental adaptability prediction index; Inputting the optimized environmental adaptability prediction index into the comprehensive environmental adaptability model to output an enhanced robust index; Based on the predictive control or adaptive control algorithm, real-time performance feedback is performed on the enhanced robust indicator to obtain adjustment parameters optimized for the current environmental conditions; The adjustment parameters are evaluated and verified to obtain verified adaptive parameters, and the verified adaptive parameters are used as adaptive adjustment parameters.
7. A system for constructing a high-frequency sensor simulation antenna, characterized in that: include: an acquisition module, used to acquire multi-dimensional model data of the high-frequency sensor, input the multi-dimensional model data into a preset machine learning model, obtain multiple types of virtual radiation elements, sort the multiple types of virtual radiation elements, and obtain the radiation structure of the high-frequency sensor; An analysis module, configured to jointly analyze the high-frequency sensor based on the radiation structure of the high-frequency sensor to generate an electromagnetic field distribution spectrum, perform tuning processing on the high-frequency sensor according to the electromagnetic field distribution spectrum, and obtain working parameters of the high-frequency sensor; A generation module, used for inputting the working parameters of the high-frequency sensor into a preset evaluation model, outputting a stability index, inputting the stability index into a preset performance model, outputting a performance attenuation index, performing trend analysis and fluctuation limitation on the performance attenuation index, and generating an environmental adaptability prediction index; A test module, used to obtain the random noise distribution of the simulation environment and the parameter set under non-ideal working conditions, and perform random process simulation and extreme stress test on the random noise distribution and the parameter set to generate a comprehensive environmental adaptation model; A feedback module, used for inputting the environmental adaptability prediction index into the comprehensive environmental adaptability model, outputting an enhanced robust index, performing real-time performance feedback on the enhanced robust index, and obtaining an adaptive adjustment parameter; The optimization module is used to optimize the working parameters of the high-frequency sensor according to the adaptive adjustment parameters, adjust the high-frequency sensor according to the optimized working parameters of the high-frequency sensor, and complete the construction of the simulated antenna of the high-frequency sensor.
8. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the method for constructing a high-frequency sensor simulation antenna according to any one of claims 1 to 6 is implemented.
9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the processor is enabled to execute the method for constructing a high-frequency sensor simulation antenna according to any one of claims 1 to 6.
Citation Information
Cited By
Radio astronomical electromagnetic environment simulation and construction method and system and computer equipment
CN119337644A
Epoxy resin insulation part curing degree simulation system
CN121093788A
An epoxy resin insulation component cure level simulation system
CN121093788B
PC5 antenna performance enhancement method and system based on AI large model
CN121480317A
PC5 antenna performance enhancement method and system based on ai large model
CN121480317B
